{"meta":{"query_hash":"122d1dfedb94","filters":{"venue":"Bioinformatics"},"cohort_total":946,"direct_labels_cover":0,"predictions_cover":946,"exported":946,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/122d1dfedb94","api":"https://metacan.xera.ac/api/v1/cohort?venue=Bioinformatics"},"results":[{"id":"W1793459287","doi":"10.1093/bioinformatics/btv420","title":"CEMAsuite: open source degenerate PCR primer design","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Molecular Biology Techniques and Applications","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Division of Chemical, Bioengineering, Environmental, and Transport Systems; Egg Farmers of Canada; Louisiana State University; National Science Foundation","keywords":"Primer (cosmetics); Suite; Computer science; Source code; Computational biology; Sequence (biology); Coding (social sciences); Multiple sequence alignment; Sequence alignment; Biology; Genetics; Programming language; Gene; Peptide sequence; Mathematics; Statistics","score_opus":0.053797628234244284,"score_gpt":0.2991767766964953,"score_spread":0.245379148462251,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1793459287","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018085347,0.00023964646,0.9680201,0.00025146958,0.00007267569,0.0007640636,0.000017143635,0.000060144062,0.012489415],"genre_scores_gemma":[0.21718235,0.00017048966,0.76972157,0.003882776,0.00025317294,0.00033856023,0.00074119266,0.00006781312,0.007642065],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991888,0.000046219728,0.00026748885,0.0001705779,0.000098357305,0.00022854636],"domain_scores_gemma":[0.9990727,0.000005500533,0.00011964834,0.0005234089,0.00012233199,0.00015644645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003916969,0.00015048154,0.00012914943,0.000030459101,0.00008675206,0.00007647564,0.00054806826,0.00018141694,0.0000112774505],"category_scores_gemma":[0.0000680546,0.00013111824,0.00004785932,0.00010036422,0.00007031711,0.000008674944,0.00044469352,0.0000684703,0.00009341099],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023850136,0.0002908313,0.0012348851,0.000046305755,0.00021035034,0.0000041555145,0.00052462384,0.001561588,0.30896842,0.005384481,0.6369715,0.044564363],"study_design_scores_gemma":[0.0005405368,0.00032378355,0.000042730288,0.000007297758,0.000019744011,0.000037900783,0.00010043974,0.003860206,0.3317857,0.00028990023,0.6626909,0.0003008826],"about_ca_topic_score_codex":0.000015301988,"about_ca_topic_score_gemma":0.000003048017,"teacher_disagreement_score":0.19909701,"about_ca_system_score_codex":0.000014825608,"about_ca_system_score_gemma":0.00016171258,"threshold_uncertainty_score":0.53468466},"labels":[],"label_agreement":null},{"id":"W1889881724","doi":"10.1093/bioinformatics/btv385","title":"Hyperscape: visualization for complex biological networks","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Hospital for Sick Children","funders":"Centre National de la Recherche Scientifique; Heart and Stroke Foundation of Canada","keywords":"Visualization; Computer science; Biological network; Computational biology; Artificial intelligence; Biology","score_opus":0.052094076985176846,"score_gpt":0.2850710021989206,"score_spread":0.23297692521374377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1889881724","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01484594,0.00029542192,0.9774065,0.000090237976,0.0004524963,0.0005662659,0.000045745015,0.000048089376,0.0062493104],"genre_scores_gemma":[0.8916976,0.00022967922,0.09952688,0.002973327,0.0011389952,0.00008016846,0.003825445,0.000045206925,0.00048270114],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990241,0.000017041222,0.00041252928,0.00012439351,0.0001071763,0.00031473892],"domain_scores_gemma":[0.99922067,0.00001595555,0.00015913213,0.0002656842,0.00016480907,0.0001737314],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036008202,0.00017070731,0.00016769844,0.00003603502,0.00009225105,0.000057676953,0.00020999178,0.00024780197,0.000008484121],"category_scores_gemma":[0.000090400514,0.00014329226,0.00009532573,0.00009252307,0.00007350851,0.000009866975,0.00011317139,0.000054945784,0.000024274219],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00086031796,0.00030347885,0.0033106927,0.00021497058,0.0003523187,0.000001437269,0.0014212759,0.028490428,0.0055562677,0.022348786,0.85322285,0.08391717],"study_design_scores_gemma":[0.0013561766,0.000622461,0.00021651742,0.000008847348,0.000018284527,0.000021198424,0.00055605517,0.6542165,0.00039031246,0.0004552814,0.3417849,0.00035343278],"about_ca_topic_score_codex":0.0000014672196,"about_ca_topic_score_gemma":0.0000029881069,"teacher_disagreement_score":0.8778796,"about_ca_system_score_codex":0.00001980917,"about_ca_system_score_gemma":0.00006533364,"threshold_uncertainty_score":0.5843289},"labels":[],"label_agreement":null},{"id":"W1891158457","doi":"10.1093/bioinformatics/btv615","title":"funtooNorm: an R package for normalization of DNA methylation data when there are multiple cell or tissue types","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Epigenetics and DNA Methylation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Child and Family Research Institute; University of British Columbia; Douglas Mental Health University Institute; McGill University; Centre Intégré Universitaire de Santé et de Services Sociaux du Saguenay–Lac-Saint-Jean; Université de Sherbrooke; McGill University Health Centre; Canadian Institute for Advanced Research; Jewish General Hospital","funders":"Canadian Institutes of Health Research","keywords":"Normalization (sociology); DNA methylation; DNA; Computer science; Computational biology; Methylation; R package; Biology; Genetics; Programming language; Gene; Gene expression","score_opus":0.07610816683406356,"score_gpt":0.31027202298495143,"score_spread":0.23416385615088786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1891158457","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5025077,0.0013019246,0.49213803,0.00005231133,0.00028117505,0.00082194625,0.000836246,0.000027622647,0.0020330802],"genre_scores_gemma":[0.9248309,0.00016115751,0.06868464,0.000047955065,0.00017780662,0.000012954091,0.0056133308,0.000025908948,0.0004453284],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99917,0.000034671102,0.00036122045,0.00014728465,0.00014543092,0.00014137234],"domain_scores_gemma":[0.9986495,0.000025087447,0.00032360217,0.0006478971,0.00026597746,0.000087929846],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041562505,0.00012173752,0.00013966484,0.00004368885,0.00004611093,0.000031566513,0.00028095997,0.00015286088,0.000010070187],"category_scores_gemma":[0.0003026333,0.00010020091,0.000024992345,0.00006578734,0.000027661265,0.000044689274,0.000116391304,0.000029300812,0.0000068357954],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012135037,0.0006292457,0.020418309,0.0014738344,0.00018571827,0.0000013622365,0.006117299,0.0039713467,0.85255235,0.00024613822,0.011940854,0.101250045],"study_design_scores_gemma":[0.0011513971,0.00074762356,0.00097338145,0.000016564962,0.00005164324,8.0509597e-7,0.00090974855,0.042892642,0.87311804,0.00021692671,0.07967701,0.0002441918],"about_ca_topic_score_codex":0.000019460005,"about_ca_topic_score_gemma":0.00019030676,"teacher_disagreement_score":0.4234534,"about_ca_system_score_codex":0.000010541571,"about_ca_system_score_gemma":0.00009739661,"threshold_uncertainty_score":0.40860745},"labels":[],"label_agreement":null},{"id":"W1905939051","doi":"10.1093/bioinformatics/btv277","title":"<i>pez</i>: phylogenetics for the environmental sciences","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Evolution and Paleontology Studies","field":"Earth and Planetary Sciences","cited_by":192,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Scarborough Hospital; McMaster University; University of Toronto; McGill University; Université du Québec à Montréal","funders":"","keywords":"R package; License; Phylogenetic tree; Computer science; MIT License; Open source; The Internet; Data science; Phylogenetics; World Wide Web; Software; Biology; Programming language; Operating system","score_opus":0.059458433312916684,"score_gpt":0.24322307357551956,"score_spread":0.18376464026260286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1905939051","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38109267,0.043356378,0.042241957,0.009848174,0.0074599762,0.002967995,0.0014590467,0.00030842022,0.5112654],"genre_scores_gemma":[0.98206425,0.00024598898,0.016032249,0.0011883822,0.0001142725,0.0000028177865,0.000026984402,0.0000011554199,0.00032389737],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99945676,0.000011655526,0.00014268434,0.000054685133,0.00015641199,0.00017782915],"domain_scores_gemma":[0.9995958,0.00019362394,0.00005543747,0.000086430424,0.000010309721,0.000058378188],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003261718,0.00006730613,0.00006678841,0.000020560976,0.00034366624,0.00003083155,0.00018884055,0.000030305458,0.000071641145],"category_scores_gemma":[0.000046709978,0.00003817546,0.00003167157,0.000060696613,0.0003789035,0.0000842989,0.000010085801,0.000035964134,0.00021569712],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018972903,0.0000101404485,0.91897875,0.00001199308,0.000032320215,3.1371027e-7,0.0019800204,0.0029075877,0.0000014381864,0.00048059883,0.037194293,0.038383562],"study_design_scores_gemma":[0.00048570117,0.0003364147,0.39458698,0.0000035283128,0.00003308981,0.000018637713,0.0066988096,0.25121936,0.000026156189,0.00060949626,0.34580308,0.0001787128],"about_ca_topic_score_codex":0.000027576654,"about_ca_topic_score_gemma":0.00091064157,"teacher_disagreement_score":0.6009716,"about_ca_system_score_codex":0.0000023022528,"about_ca_system_score_gemma":0.00003332689,"threshold_uncertainty_score":0.2772422},"labels":[],"label_agreement":null},{"id":"W1970806484","doi":"10.1093/bioinformatics/btv107","title":"The GPMDB REST interface","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"University of Manitoba","keywords":"Rest (music); Computer science; Interface (matter); Documentation; File Transfer Protocol; MIT License; Representational state transfer; Service (business); Software; Database; World Wide Web; Programming language; The Internet; Operating system; Web service","score_opus":0.027811404180778206,"score_gpt":0.2976196948278157,"score_spread":0.2698082906470375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1970806484","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032391015,0.00041750068,0.35500357,0.0022114296,0.00013798069,0.00032491112,0.000045956673,0.0007220011,0.60874563],"genre_scores_gemma":[0.44681415,0.00036629662,0.5361993,0.00035414784,0.00025151164,0.000235932,0.000042250584,0.00004476674,0.01569166],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99954706,0.0000015771304,0.00019021897,0.000041594245,0.000094402145,0.00012512208],"domain_scores_gemma":[0.9994113,0.00003355691,0.00008596214,0.00035007362,0.000052925487,0.000066194894],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009916246,0.00006334664,0.000049066562,0.0000072586427,0.00011361517,0.000050942977,0.00024828556,0.000044411958,0.00001359582],"category_scores_gemma":[0.0000658936,0.00004230764,0.000021714848,0.000051127656,0.00005467067,0.000086978966,0.00008625177,0.00010665244,0.00013781173],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016555781,0.00019756182,0.0011104014,0.00035086035,0.00010629645,0.0000032246173,0.0071351724,0.0008567663,0.0218839,0.26479197,0.3814041,0.3219942],"study_design_scores_gemma":[0.00013956902,0.0000111994195,0.0000033266754,0.00001556669,0.00000407874,0.000008422898,0.0010166859,0.010783333,0.07509027,0.00846879,0.9043495,0.000109255336],"about_ca_topic_score_codex":0.0000035981398,"about_ca_topic_score_gemma":0.0000026036992,"teacher_disagreement_score":0.593054,"about_ca_system_score_codex":0.000043449025,"about_ca_system_score_gemma":0.0000315289,"threshold_uncertainty_score":0.1771337},"labels":[],"label_agreement":null},{"id":"W1971987634","doi":"10.1093/bioinformatics/bts219","title":"SEQuel: improving the accuracy of genome assemblies","year":2012,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":70,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Center for Research Resources; Natural Sciences and Engineering Research Council of Canada; University of California, San Diego; National Institutes of Health; National Science Foundation","keywords":"Contig; De Bruijn graph; Sequence assembly; De Bruijn sequence; Indel; Hybrid genome assembly; Substitution (logic); Computer science; Genome; Reference genome; Computational biology; Error detection and correction; Algorithm; Graph; Biology; Genetics; Theoretical computer science; Gene; Mathematics; Combinatorics; Programming language","score_opus":0.019702669294599684,"score_gpt":0.24813360594177075,"score_spread":0.22843093664717107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1971987634","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99159104,0.0027864585,0.0013424812,0.000054526503,0.00020024713,0.00016871489,0.00002779479,0.0000032904359,0.0038254666],"genre_scores_gemma":[0.9953571,0.00031334843,0.0038378143,0.00018044446,0.00018813903,0.000008412433,0.000015662767,0.000008920547,0.00009014598],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99939966,0.0000130127755,0.0002382762,0.00005085565,0.000084285246,0.00021388681],"domain_scores_gemma":[0.99941945,0.000027347392,0.00016049371,0.0002935776,0.00005849958,0.00004063531],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023020995,0.00009712323,0.00009677803,0.000018994708,0.00008261952,0.000014118075,0.00018744677,0.000056066066,0.0000046508744],"category_scores_gemma":[0.00012175247,0.00006440775,0.00006413547,0.000050020877,0.000070943155,0.0000025430083,0.00019304926,0.000039800154,0.000010152867],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018487695,0.00004648648,0.011572747,0.00012957111,0.0001436853,7.862256e-8,0.002362885,0.00009989002,0.9738049,0.0008109384,0.0010525098,0.009957837],"study_design_scores_gemma":[0.0010039795,0.00053192064,0.16956113,0.000021989326,0.00016590324,0.000058400074,0.0075560655,0.0014747516,0.5068873,0.00017131839,0.31169212,0.0008750913],"about_ca_topic_score_codex":0.0000071926593,"about_ca_topic_score_gemma":0.0000021803414,"teacher_disagreement_score":0.46691754,"about_ca_system_score_codex":0.000005518394,"about_ca_system_score_gemma":0.000034933673,"threshold_uncertainty_score":0.26264718},"labels":[],"label_agreement":null},{"id":"W1976496804","doi":"10.1093/bioinformatics/btv163","title":"Learning chromatin states with factorized information criteria","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Genetics; Ministry of Education, Culture, Sports, Science and Technology; Japan Society for the Promotion of Science; University of Tokyo; Waseda University; Research Organization of Information and Systems","keywords":"Chromatin; Computer science; Computational biology; Nucleosome; Epigenome; Epigenetics; Genome; Bayesian probability; ChIP-sequencing; Epigenomics; Biology; Genetics; Artificial intelligence; DNA methylation; DNA; Gene","score_opus":0.008461581363955289,"score_gpt":0.22402182272729004,"score_spread":0.21556024136333476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1976496804","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9665634,0.000030620464,0.027812809,0.000053323525,0.00013600361,0.0001902948,0.000032400083,0.000045793928,0.005135326],"genre_scores_gemma":[0.95951855,0.00005127519,0.038415648,0.00021938063,0.00007680808,0.000014182172,0.0014489187,0.000018363531,0.00023684099],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991912,0.00001988343,0.00031945863,0.00007538156,0.00017899805,0.00021508163],"domain_scores_gemma":[0.99927586,0.000006148069,0.00019552605,0.00021790418,0.00017510078,0.00012946171],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018645961,0.00015670202,0.0001300229,0.000048117374,0.0000720648,0.00012485794,0.00015045566,0.00009761018,0.000011525158],"category_scores_gemma":[0.00007778732,0.000127344,0.000033283,0.000078289675,0.000042619566,0.00003753077,0.00008555193,0.000081340564,0.00007417781],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0048246123,0.0010741885,0.07162241,0.004168984,0.0024472154,0.000034167588,0.13346688,0.15356019,0.20474282,0.0039388873,0.23024955,0.18987007],"study_design_scores_gemma":[0.0077657346,0.004890173,0.0036410645,0.000109454704,0.00008706413,0.00018699288,0.02209219,0.4592757,0.027869727,0.00038644747,0.47192731,0.0017681392],"about_ca_topic_score_codex":0.000011557806,"about_ca_topic_score_gemma":0.0000069991424,"teacher_disagreement_score":0.3057155,"about_ca_system_score_codex":0.000030286235,"about_ca_system_score_gemma":0.00012481987,"threshold_uncertainty_score":0.5192938},"labels":[],"label_agreement":null},{"id":"W1978377575","doi":"10.1093/bioinformatics/btp280","title":"ISMB/ECCB 2009 Stockholm","year":2009,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Library science","score_opus":0.016323508100717782,"score_gpt":0.28009558421644304,"score_spread":0.2637720761157253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978377575","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5676994,0.0030267069,0.12126128,0.0069914795,0.0022870488,0.0030025197,0.00049938157,0.0004272403,0.29480496],"genre_scores_gemma":[0.9049805,0.002219274,0.07156744,0.009527089,0.0012754288,0.00002407549,0.00096076453,0.000050297585,0.0093951505],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99799514,0.000024761457,0.0006106192,0.00018892136,0.000547101,0.000633442],"domain_scores_gemma":[0.99868816,0.000014400355,0.00014672286,0.0006164885,0.00017797676,0.00035626997],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041056925,0.00025538928,0.00021875792,0.00012765724,0.00014716997,0.00010052516,0.00051971193,0.00030145972,0.0000681159],"category_scores_gemma":[0.0002804043,0.0002142138,0.0001492016,0.00019799235,0.00016140261,0.000017068269,0.00014800616,0.00019228707,0.00043114604],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021691676,0.00044528692,0.0006450715,0.00022942128,0.00013184655,0.000010783142,0.0010676702,0.00008190564,0.04421017,0.00083781715,0.3783195,0.5738036],"study_design_scores_gemma":[0.0024661066,0.0035939552,0.008620336,0.000078360004,0.00004909557,0.00010039795,0.0012796463,0.017878076,0.056971557,0.0008825177,0.90683776,0.0012422082],"about_ca_topic_score_codex":0.0000048177735,"about_ca_topic_score_gemma":0.0000061272326,"teacher_disagreement_score":0.5725614,"about_ca_system_score_codex":0.000023696593,"about_ca_system_score_gemma":0.00016708314,"threshold_uncertainty_score":0.8735385},"labels":[],"label_agreement":null},{"id":"W1981576666","doi":"10.1093/bioinformatics/btm223","title":"Efficient parameter estimation for RNA secondary structure prediction","year":2007,"lang":"en","type":"article","venue":"Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":248,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institutes of Health; National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Computer science; Energy minimization; Energy (signal processing); Algorithm; Constraint (computer-aided design); Minification; Estimation theory; Mathematical optimization; Mathematics; Statistics","score_opus":0.008428418146540894,"score_gpt":0.23505822218269098,"score_spread":0.2266298040361501,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981576666","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3750791,0.00004986288,0.6236344,0.000017621729,0.00025000764,0.00033740583,0.00010637357,0.00001654752,0.00050872815],"genre_scores_gemma":[0.7919404,0.0000047541134,0.20730405,0.00018893697,0.00014468467,0.000013643248,0.00028511244,0.000012554041,0.00010586845],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993363,0.00000734258,0.00026635922,0.00009830904,0.00010621117,0.00018545214],"domain_scores_gemma":[0.9995603,0.000024702927,0.000108346925,0.0001956617,0.00005628636,0.000054726795],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002761393,0.00010491567,0.00008023062,0.000042207837,0.00008428206,0.000024729889,0.000086719,0.00016381129,0.000018598865],"category_scores_gemma":[0.00011763632,0.000091148795,0.000061877305,0.000041038318,0.000021918937,0.0000039604215,0.000025064835,0.000042619897,0.000006459477],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022330054,0.00004043245,0.000072751776,0.00021598084,0.00006605282,4.8276536e-7,0.0003276848,0.0036146764,0.6576829,0.00066372927,0.0022514386,0.33484057],"study_design_scores_gemma":[0.00048827805,0.00030363593,0.0004797923,0.000016387596,0.000022204515,0.000013687378,0.00011101916,0.07284417,0.9157421,0.00062971545,0.009178474,0.00017056325],"about_ca_topic_score_codex":6.9908674e-7,"about_ca_topic_score_gemma":0.0000018132605,"teacher_disagreement_score":0.41686133,"about_ca_system_score_codex":0.00001306428,"about_ca_system_score_gemma":0.00003308382,"threshold_uncertainty_score":0.371694},"labels":[],"label_agreement":null},{"id":"W1993204833","doi":"10.1093/bioinformatics/btr342","title":"genBlastG: using BLAST searches to build homologous gene models","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":121,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Michael Smith Health Research BC; Simon Fraser University; University of British Columbia; BC Cancer Agency","funders":"","keywords":"Homologous chromosome; Computer science; Computational biology; Homologous recombination; Gene; Genetics; Biology","score_opus":0.0691356794700421,"score_gpt":0.2522758472029456,"score_spread":0.1831401677329035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993204833","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9503835,0.00042858653,0.043728948,0.000017607683,0.00015237606,0.00023939407,0.000055611486,0.000008379256,0.0049855933],"genre_scores_gemma":[0.81108963,0.00019670172,0.18803857,0.00036073654,0.00012075665,0.000011996422,0.000014730921,0.000023003975,0.00014383734],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99906325,0.000015621052,0.00028014518,0.00017272892,0.00011620954,0.0003520492],"domain_scores_gemma":[0.99930394,0.0000052280643,0.00007165746,0.0003748531,0.00010163965,0.00014266251],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013972819,0.00018153203,0.00015751645,0.00006533188,0.00011879125,0.000021578759,0.00025633126,0.000111619054,0.000010444086],"category_scores_gemma":[0.000024073888,0.00016850882,0.000078183904,0.00009203702,0.000073043215,0.0000024439403,0.00034095912,0.000056517245,0.000037586182],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018856989,0.00018370092,0.0028280723,0.000107100124,0.00041378962,0.000009488333,0.007065039,0.009176714,0.9663984,0.00051157223,0.0030091987,0.010108307],"study_design_scores_gemma":[0.0008899849,0.0012429093,0.0032421807,0.00003526893,0.00009233897,0.00016215895,0.0015873105,0.031409282,0.94690037,0.0012839686,0.012032245,0.0011219713],"about_ca_topic_score_codex":0.00004262737,"about_ca_topic_score_gemma":0.000016753154,"teacher_disagreement_score":0.14430963,"about_ca_system_score_codex":0.000016880713,"about_ca_system_score_gemma":0.000073389674,"threshold_uncertainty_score":0.687159},"labels":[],"label_agreement":null},{"id":"W1993730176","doi":"10.1093/bioinformatics/18.12.1633","title":"Statistical analysis of high-density oligonucleotidearrays: a multiplicative noise model","year":2002,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":86,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre hospitalier de l'Université Laval","funders":"National Institute of Allergy and Infectious Diseases; Center for AIDS Research, University of Washington","keywords":"Multiplicative function; Computer science; Statistical analysis; Noise (video); Multiplicative noise; Statistical model; Oligonucleotide; Algorithm; Computational biology; Statistical physics; Statistics; Mathematics; Artificial intelligence; Biology; Genetics; Telecommunications; Physics; Gene","score_opus":0.02114399827825491,"score_gpt":0.25410128395502685,"score_spread":0.23295728567677193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993730176","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.547205,0.00006409983,0.449157,0.00009356598,0.00004150123,0.00015737057,0.00019437198,0.00001739963,0.0030696935],"genre_scores_gemma":[0.96364856,0.00011833642,0.035554722,0.00016502912,0.00001773381,0.000011079082,0.0001765676,0.0000072655116,0.00030071888],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992358,0.000018709175,0.00031798484,0.00014040267,0.00015448345,0.00013259481],"domain_scores_gemma":[0.99919766,0.000011293233,0.00017332983,0.00041577185,0.00012006226,0.00008190542],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000076779535,0.00010308235,0.00018398538,0.00011549449,0.00004419192,0.000011684458,0.00014240622,0.000091171656,0.00006645782],"category_scores_gemma":[0.000071962546,0.000092407754,0.0000887061,0.00027169407,0.00007879518,0.0000057708994,0.000060873706,0.000047937112,0.000022026721],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032719265,0.0010099405,0.011123273,0.0002681998,0.0027690826,0.0000017091687,0.004664186,0.067576066,0.7542075,0.01344789,0.07909044,0.06551454],"study_design_scores_gemma":[0.000492792,0.000093314986,0.021615634,0.000007743719,0.00032477375,0.0000011261359,0.00021060044,0.9091877,0.066111535,0.00012132822,0.0016111995,0.0002222637],"about_ca_topic_score_codex":0.000014136624,"about_ca_topic_score_gemma":0.000009890646,"teacher_disagreement_score":0.8416116,"about_ca_system_score_codex":0.000012504276,"about_ca_system_score_gemma":0.000019118756,"threshold_uncertainty_score":0.3768279},"labels":[],"label_agreement":null},{"id":"W2000519643","doi":"10.1093/bioinformatics/btm024","title":"A simulation test bed for hypotheses of genome evolution","year":2007,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Australian Research Council; Genome Atlantic","keywords":"Computer science; Component (thermodynamics); Genetic algorithm; Genome; Software; Horizontal gene transfer; Data mining; Biology; Evolutionary biology; Gene; Genetics","score_opus":0.017961718638179174,"score_gpt":0.26076676186649106,"score_spread":0.2428050432283119,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2000519643","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32428864,0.00018221818,0.67365974,0.000012004193,0.00007545482,0.00050880335,0.00007373741,0.000013979246,0.001185402],"genre_scores_gemma":[0.95733315,0.000010521539,0.042206753,0.000027217658,0.000105936866,0.0000065715735,0.00013821358,0.000010570391,0.00016109418],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993731,0.0000033083759,0.00029073935,0.00006908108,0.00009918738,0.00016459741],"domain_scores_gemma":[0.99944645,0.00006383203,0.00014349124,0.00017280676,0.00013702881,0.000036404872],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027203336,0.000080512655,0.00008654838,0.00006214818,0.000041335978,0.0000073846654,0.00008951061,0.0000839397,0.0000054028587],"category_scores_gemma":[0.0002914949,0.00007722672,0.00006106464,0.0000725975,0.000031862764,0.0000056394374,0.000031305102,0.000019040612,0.000007063867],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015404045,0.00021009623,0.005620487,0.00043935017,0.0001129391,3.0456752e-7,0.00063037773,0.014113206,0.96426326,0.00026914635,0.00019205238,0.013994734],"study_design_scores_gemma":[0.0063503888,0.0044798553,0.10395439,0.00008676223,0.00023866502,0.0000134020975,0.0027911747,0.34465697,0.4198433,0.0011028493,0.114975415,0.0015068236],"about_ca_topic_score_codex":0.0000019094666,"about_ca_topic_score_gemma":0.000004404438,"teacher_disagreement_score":0.6330445,"about_ca_system_score_codex":0.000020943484,"about_ca_system_score_gemma":0.000029302524,"threshold_uncertainty_score":0.31492144},"labels":[],"label_agreement":null},{"id":"W2002295829","doi":"10.1093/bioinformatics/btv003","title":"Clonality inference in multiple tumor samples using phylogeny","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":284,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; BC Cancer Agency","funders":"BC Cancer Agency; Natural Sciences and Engineering Research Council of Canada; Genome Canada","keywords":"Phylogenetics; Biology; Phylogenetic tree; Inference; In silico; Computational biology; Evolutionary biology; Computer science; Genetics; Gene; Artificial intelligence","score_opus":0.06875968615801234,"score_gpt":0.2941810204304562,"score_spread":0.22542133427244385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2002295829","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9892208,0.00026277924,0.009418479,0.0000184533,0.00018138788,0.00014182452,0.00009682961,0.0000076212,0.0006518382],"genre_scores_gemma":[0.97557133,0.000050541126,0.023733547,0.00039326158,0.00012111982,0.00000623668,0.00010087969,0.0000098330165,0.000013234391],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992504,0.000015273858,0.00029684106,0.00011292135,0.00011157657,0.0002129803],"domain_scores_gemma":[0.9993956,0.000042333206,0.00009808326,0.00026291294,0.00008718728,0.00011386336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020671243,0.000116864045,0.00012612165,0.00004154367,0.00003223499,0.000033559274,0.00015407709,0.00007173029,0.00000377754],"category_scores_gemma":[0.0008424057,0.000116069445,0.000040320218,0.000087244676,0.000057418416,0.000006628168,0.00014994874,0.000059283044,0.0000134507645],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047706315,0.0004908425,0.8190572,0.0003091586,0.000108784196,0.00002446019,0.0024888397,0.03898191,0.11548246,0.0020234855,0.006789144,0.013766651],"study_design_scores_gemma":[0.010877373,0.0012917365,0.112272955,0.00020363987,0.00009388896,0.00011250563,0.004730361,0.40726376,0.1809683,0.0034692085,0.2758317,0.002884587],"about_ca_topic_score_codex":0.00023259682,"about_ca_topic_score_gemma":0.00035024658,"teacher_disagreement_score":0.70678425,"about_ca_system_score_codex":0.000049555885,"about_ca_system_score_gemma":0.00028746182,"threshold_uncertainty_score":0.47331747},"labels":[],"label_agreement":null},{"id":"W2012328875","doi":"10.1093/bioinformatics/btu714","title":"Characterization of structural variants with single molecule and hybrid sequencing approaches","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":63,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Human Genome Research Institute; Natural Sciences and Engineering Research Council of Canada; Burroughs Wellcome Fund; National Institutes of Health; National Science Foundation","keywords":"DNA sequencing; Structural variation; Genome; Computational biology; Illumina dye sequencing; Biology; Sequence assembly; Software; Hybrid genome assembly; Computer science; Reference genome; Genetics; DNA; Gene","score_opus":0.017511604946140517,"score_gpt":0.18655111901378327,"score_spread":0.16903951406764275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012328875","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98838377,0.000041131174,0.010534372,0.000013094399,0.000026097057,0.000083511586,0.00001937819,0.0000019879587,0.0008966775],"genre_scores_gemma":[0.9909147,0.000016575354,0.008896063,0.000047677764,0.000035031564,0.000002451692,0.000060727034,0.0000072572316,0.000019499685],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99961513,0.00000982595,0.00014641933,0.00007762871,0.000055052722,0.00009595325],"domain_scores_gemma":[0.99969864,0.0000037159198,0.000106220905,0.00012840272,0.000035347537,0.00002769757],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000059025315,0.00008359598,0.00009615084,0.00001841157,0.000041244326,0.000014223309,0.000052631887,0.000029438688,7.760555e-7],"category_scores_gemma":[0.000015159548,0.000065905544,0.000014462221,0.000025488609,0.000057587084,0.0000019189984,0.000052073206,0.000018900073,3.7059039e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016477336,0.0000050731123,0.0018028034,0.00005933872,0.00003329114,9.929852e-8,0.00025732862,0.00004741747,0.9944126,0.00016552473,0.000004092214,0.0031959324],"study_design_scores_gemma":[0.00053136214,0.0005964594,0.024315028,0.000021677484,0.000032404787,0.000044043863,0.00024818804,0.01902815,0.954295,0.00007455211,0.0005733888,0.00023974429],"about_ca_topic_score_codex":0.0000025486868,"about_ca_topic_score_gemma":0.0000022216102,"teacher_disagreement_score":0.04011762,"about_ca_system_score_codex":0.0000042687943,"about_ca_system_score_gemma":0.000017650511,"threshold_uncertainty_score":0.26875502},"labels":[],"label_agreement":null},{"id":"W2016928406","doi":"10.1093/bioinformatics/bth451","title":"Discovering patterns to extract protein–protein interactions from full texts","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":238,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Recall rate; Scientific literature; Matching (statistics); Information retrieval; Natural language processing; Artificial intelligence; Data mining; Biology","score_opus":0.015499909559941955,"score_gpt":0.267165727324153,"score_spread":0.25166581776421104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016928406","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82602096,0.000055970915,0.17235482,0.00042211424,0.00014886922,0.00025455776,0.00009902176,0.00004210442,0.00060158246],"genre_scores_gemma":[0.93986446,0.000008328059,0.059128102,0.00029174815,0.00021322188,0.00005623933,0.00014560012,0.000015006492,0.00027729594],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991258,0.000011013201,0.00029473606,0.00016667141,0.00014689517,0.00025492776],"domain_scores_gemma":[0.9993973,0.0000076722445,0.00008920826,0.00033522604,0.000031565538,0.00013902869],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007094621,0.00015893117,0.00013085117,0.000047099948,0.000081892686,0.00006033304,0.0002226249,0.00012383277,0.000036590565],"category_scores_gemma":[0.00014512084,0.00013441476,0.000074034826,0.00007302662,0.000045518078,0.000012222305,0.0001621443,0.00012385353,0.00014481338],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016345413,0.00021254252,0.0006073937,0.00010915837,0.00012622542,0.000012259564,0.0014789822,0.00023553774,0.7448636,0.00014298304,0.0010775778,0.25097027],"study_design_scores_gemma":[0.001987702,0.0014880485,0.005996979,0.00079283764,0.00004076964,0.00004732921,0.0025740068,0.00049063424,0.7400716,0.0010902515,0.24427053,0.0011493018],"about_ca_topic_score_codex":0.00010964915,"about_ca_topic_score_gemma":0.00017273542,"teacher_disagreement_score":0.24982098,"about_ca_system_score_codex":0.00003216602,"about_ca_system_score_gemma":0.000060856877,"threshold_uncertainty_score":0.54812753},"labels":[],"label_agreement":null},{"id":"W2022441134","doi":"10.1093/bioinformatics/btg182","title":"Class prediction and discovery using gene microarray andproteomics mass spectroscopy data: curses, caveats, cautions","year":2003,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":332,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; National Research Council Institute for Biodiagnostics","funders":"","keywords":"Computer science; Curse of dimensionality; Artificial intelligence; Pattern recognition (psychology); Feature (linguistics); Relevance (law); Data mining; Microarray analysis techniques; Identification (biology); Outlier; Machine learning; Biology; Gene","score_opus":0.02672686303689213,"score_gpt":0.270721456698394,"score_spread":0.24399459366150184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2022441134","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47864565,0.0012991177,0.51621956,0.00011732283,0.00069322094,0.00046992523,0.0005660174,0.000031671912,0.001957531],"genre_scores_gemma":[0.80099237,0.0027667275,0.19230276,0.0003542175,0.0003685787,0.000027569817,0.002315417,0.00004316487,0.0008292151],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99915487,0.000032531814,0.00027429173,0.00022885996,0.000114292176,0.00019517454],"domain_scores_gemma":[0.99912477,0.0000037839607,0.00013516049,0.0006108661,0.00004454256,0.000080900245],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016133995,0.00014272393,0.00010809563,0.00005231334,0.0001624988,0.000098886085,0.0001493769,0.00013809612,0.0000046951486],"category_scores_gemma":[0.000038517814,0.00013321004,0.00002862935,0.00009610545,0.000074034215,0.000047501435,0.000072513794,0.00008040398,0.0000031337481],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017349754,0.00002247456,0.0018061078,0.000028002838,0.000024525498,2.497175e-7,0.000045072375,0.00010733465,0.9937503,0.00037529424,0.0036498432,0.00017346287],"study_design_scores_gemma":[0.0007975999,0.000113584654,0.0010289594,0.000032280484,0.00006597338,0.0000646655,0.00043233545,0.014677413,0.8888269,0.000139671,0.09350351,0.00031708935],"about_ca_topic_score_codex":0.0000053495837,"about_ca_topic_score_gemma":0.0000053969584,"teacher_disagreement_score":0.3239168,"about_ca_system_score_codex":0.000033833316,"about_ca_system_score_gemma":0.00016476147,"threshold_uncertainty_score":0.5432148},"labels":[],"label_agreement":null},{"id":"W2029921227","doi":"10.1093/bioinformatics/btl648","title":"DataBiNS: a BioMoby-based data-mining workflow for biological pathways and non-synonymous SNPs","year":2007,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Paul's Hospital; University of British Columbia","funders":"Genome Canada","keywords":"Workflow; Computer science; Identifier; Web service; Workflow management system; World Wide Web; XML; Data mining; Information retrieval; Database; Programming language","score_opus":0.07184932710687342,"score_gpt":0.306166776981287,"score_spread":0.2343174498744136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029921227","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41840068,0.0009360207,0.5779365,0.00020518953,0.00037411193,0.0005173905,0.0007530632,0.00009664725,0.0007804653],"genre_scores_gemma":[0.504224,0.00013377075,0.49158305,0.00097004994,0.0002849182,0.000021282287,0.0027212417,0.000019899144,0.000041759326],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99867594,0.000013871095,0.00042852506,0.00030522933,0.00013012427,0.00044633384],"domain_scores_gemma":[0.99884844,0.0001345476,0.00014136037,0.00066070835,0.00005471096,0.00016023904],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00093227957,0.000205092,0.00022112236,0.00006942625,0.00015499933,0.000049821472,0.00045878376,0.00034437448,0.000004743601],"category_scores_gemma":[0.0005858237,0.00015654108,0.000052897318,0.00011435136,0.0002824858,0.0000101377,0.00035339812,0.00008494097,0.0000068973172],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004567797,0.00019186351,0.00510911,0.00029861397,0.00012219339,0.0000130588,0.00040710223,0.0000068094073,0.028541528,0.000087263645,0.024308586,0.9404571],"study_design_scores_gemma":[0.006610956,0.00393552,0.009534497,0.00025436122,0.00013447598,0.000113529284,0.004008765,0.06904561,0.05148867,0.00019755917,0.8528715,0.0018045703],"about_ca_topic_score_codex":0.0000038360113,"about_ca_topic_score_gemma":0.000017798688,"teacher_disagreement_score":0.9386525,"about_ca_system_score_codex":0.000009310189,"about_ca_system_score_gemma":0.00008907555,"threshold_uncertainty_score":0.638356},"labels":[],"label_agreement":null},{"id":"W2040481795","doi":"10.1093/bioinformatics/btu673","title":"FuncPatch: a web server for the fast Bayesian inference of conserved functional patches in protein 3D structures","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Inference; Computer science; Web server; Bayesian probability; Computational biology; Bayesian inference; Artificial intelligence; Biology; The Internet; World Wide Web","score_opus":0.018036198505034032,"score_gpt":0.22551523590222008,"score_spread":0.20747903739718604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2040481795","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.981699,0.00022433844,0.016951837,0.00013932679,0.000108243665,0.00048561694,0.00007547343,0.0000026497014,0.0003135028],"genre_scores_gemma":[0.99363196,0.0000373187,0.00592719,0.00015597633,0.00007280456,0.00006434736,0.00003349233,0.000008152236,0.00006874652],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9993305,0.000019789766,0.00030180885,0.000097058946,0.00009078304,0.00016003131],"domain_scores_gemma":[0.9994426,0.00006151494,0.0001347559,0.00024553374,0.000088494504,0.000027126029],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002119045,0.00012166955,0.00013921903,0.000026520793,0.00006574927,0.000015906026,0.0001529009,0.000085559266,0.000007752899],"category_scores_gemma":[0.00014277037,0.000084358806,0.00006432309,0.00005336794,0.000092758346,0.0000015653012,0.0000903149,0.000046607933,0.0000011948435],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010352957,0.00024446333,0.16139987,0.0016267044,0.0007412545,4.6230005e-7,0.0033879655,0.008438265,0.72750825,0.011269505,0.003794527,0.08055346],"study_design_scores_gemma":[0.007991111,0.002425645,0.40273914,0.00019256536,0.00017692104,0.0000146378,0.004416594,0.18282245,0.30056518,0.0067947996,0.090293154,0.0015678053],"about_ca_topic_score_codex":0.000023718954,"about_ca_topic_score_gemma":0.00031999638,"teacher_disagreement_score":0.42694306,"about_ca_system_score_codex":0.0000055000523,"about_ca_system_score_gemma":0.00008520214,"threshold_uncertainty_score":0.34400523},"labels":[],"label_agreement":null},{"id":"W2042280132","doi":"10.1093/bioinformatics/18.11.1538","title":"AcePrimer: automation of PCR primer design based on genestructure","year":2002,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetics, Aging, and Longevity in Model Organisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency","funders":"BC Cancer Agency; Genome Canada","keywords":"Primer (cosmetics); Perl; Caenorhabditis elegans; Genetics; Biology; Computational biology; In silico PCR; genomic DNA; Variants of PCR; Computer science; Polymerase chain reaction; Gene; Programming language; Multiplex polymerase chain reaction","score_opus":0.019623065265681378,"score_gpt":0.2214974692156349,"score_spread":0.2018744039499535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2042280132","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3580771,0.00038161236,0.6358312,0.00022586693,0.0004107126,0.0006620643,0.00005042899,0.00006384026,0.004297195],"genre_scores_gemma":[0.86035335,0.00007580668,0.1386145,0.0005377251,0.000085501306,0.0000060300968,0.000076458746,0.00002009682,0.00023054695],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990992,0.00003678717,0.00032509823,0.00013346213,0.00021514088,0.00019030565],"domain_scores_gemma":[0.99918044,0.000013820982,0.00018365626,0.00047072372,0.00008508043,0.00006629166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013713984,0.00016770665,0.0001472432,0.000066960514,0.000059277325,0.000018997302,0.00020289636,0.00018340813,0.00012365448],"category_scores_gemma":[0.00005926909,0.00015312296,0.00007678467,0.00007912104,0.00006752428,0.0000058432342,0.00003914314,0.00006775761,0.00007351773],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001922417,0.00066886185,0.004299051,0.00072609365,0.00026758565,0.00000393809,0.0051169903,0.2022808,0.6517793,0.0003851174,0.06763142,0.06664861],"study_design_scores_gemma":[0.00067751476,0.0005058237,0.0017680284,0.00002070928,0.00003953104,0.000007626774,0.000059871236,0.40271837,0.58645695,0.000050427025,0.0073985825,0.00029656672],"about_ca_topic_score_codex":0.0000025221063,"about_ca_topic_score_gemma":6.5129876e-7,"teacher_disagreement_score":0.50227624,"about_ca_system_score_codex":0.000012749526,"about_ca_system_score_gemma":0.000032558677,"threshold_uncertainty_score":0.6244173},"labels":[],"label_agreement":null},{"id":"W2042555832","doi":"10.1093/bioinformatics/bth247","title":"An interactive triple-helical collagen builder","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Collagen: Extraction and Characterization","field":"Materials Science","cited_by":104,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University of Alberta","funders":"","keywords":"Documentation; Computer science; Parsing; Terminal (telecommunication); Programming language; Algorithm","score_opus":0.014075450458584472,"score_gpt":0.2734084892093066,"score_spread":0.2593330387507221,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2042555832","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94715667,0.000006676814,0.0457248,0.00035357315,0.0010275806,0.00032844883,0.000052954358,0.00024927445,0.0051000477],"genre_scores_gemma":[0.9850446,0.000010472903,0.01360598,0.0007930754,0.00015454236,0.000017058488,0.00006491583,0.000013383251,0.0002959761],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990278,0.00002501068,0.00037330194,0.00012189863,0.00024424974,0.00020774758],"domain_scores_gemma":[0.9993032,0.000020083009,0.00017068276,0.00026251044,0.000107311134,0.00013617858],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00016740315,0.00012658784,0.00013841662,0.00008309077,0.00014554677,0.0002220843,0.00019157544,0.00008655975,0.00093177456],"category_scores_gemma":[0.000057541954,0.00011266619,0.0000426423,0.00018950649,0.00004445677,0.001130762,0.000035498593,0.00005321171,0.001336535],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018019369,0.0003957751,0.00008917543,0.00005992402,0.000014184485,0.000010074119,0.007963213,0.00064706354,0.97728133,0.002756772,0.0016217573,0.00898055],"study_design_scores_gemma":[0.004486585,0.0008073768,0.012135811,0.00011602564,0.00006943784,0.00022257278,0.007088137,0.021387467,0.86074656,0.0010289003,0.090759926,0.0011511999],"about_ca_topic_score_codex":0.00001532727,"about_ca_topic_score_gemma":0.000016370617,"teacher_disagreement_score":0.116534755,"about_ca_system_score_codex":0.00012665043,"about_ca_system_score_gemma":0.0001166858,"threshold_uncertainty_score":0.9999815},"labels":[],"label_agreement":null},{"id":"W2048796447","doi":"10.1093/bioinformatics/btl043","title":"Comparison of <i>P-RnaPredict</i> and <i>mfold</i>—algorithms for RNA secondary structure prediction","year":2006,"lang":"en","type":"article","venue":"Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":55,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Simon Fraser University","keywords":"RNA; Computer science; Algorithm; Computational biology; Biology; Genetics; Gene","score_opus":0.01121468157371556,"score_gpt":0.2478205323499416,"score_spread":0.23660585077622606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2048796447","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8357732,0.0015587592,0.15693761,0.00006551558,0.00048670665,0.0008447773,0.0016585118,0.0000388396,0.0026360438],"genre_scores_gemma":[0.94396275,0.000052530053,0.054971714,0.00007824805,0.000253609,0.000017960198,0.0004969536,0.000016611151,0.00014961127],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999197,0.0000123898035,0.00040113396,0.00011389631,0.000119295364,0.00015625876],"domain_scores_gemma":[0.99947834,0.000016050486,0.00020134143,0.00019068277,0.00007068672,0.00004290978],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000116034345,0.00013023031,0.00018278601,0.00003613856,0.00007492688,0.00002052466,0.000101728234,0.00018783876,0.000008527268],"category_scores_gemma":[0.000024222589,0.00011687099,0.00005943607,0.000041538005,0.00005697444,0.000010547928,0.000045085155,0.00005064044,5.890097e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009642898,0.00005086428,0.0023906766,0.0003635292,0.000054367356,1.438709e-7,0.0001617189,0.000120456134,0.9412424,0.0005287863,0.01023059,0.04476005],"study_design_scores_gemma":[0.0006937305,0.00046728825,0.000849508,0.000024146253,0.000038165163,0.000009220925,0.00015976622,0.0062790127,0.96251154,0.000724565,0.028089091,0.00015397723],"about_ca_topic_score_codex":0.000006075793,"about_ca_topic_score_gemma":0.0000061471164,"teacher_disagreement_score":0.10818954,"about_ca_system_score_codex":0.0000054838692,"about_ca_system_score_gemma":0.000040196173,"threshold_uncertainty_score":0.4765861},"labels":[],"label_agreement":null},{"id":"W2059736685","doi":"10.1093/bioinformatics/btq393","title":"Inferring cancer subnetwork markers using density-constrained biclustering","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":54,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Subnetwork; Computer science; Cancer; Computational biology; Software; Breast cancer; Biclustering; Artificial intelligence; Biology; Cluster analysis; Genetics","score_opus":0.011435322409209905,"score_gpt":0.2502772924467948,"score_spread":0.2388419700375849,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2059736685","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98939544,0.000100676596,0.0075560897,0.000046014244,0.0009944215,0.00014965475,0.00003068634,0.00001901471,0.0017080121],"genre_scores_gemma":[0.9682577,0.00017725196,0.03038147,0.00045421856,0.0005925467,0.0000081473545,0.00004327453,0.000024243756,0.00006110286],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99919885,0.000006554503,0.0002742764,0.00013236934,0.000096648575,0.00029128144],"domain_scores_gemma":[0.99937326,0.000017564766,0.00011762385,0.0003029382,0.000073016956,0.000115612864],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014709604,0.00015494897,0.0001339911,0.00004738081,0.0001229415,0.00007150168,0.0001551589,0.00015182816,0.000027929367],"category_scores_gemma":[0.00008579198,0.00016000566,0.00007074529,0.00008446931,0.00008218749,0.000008671629,0.00018053898,0.00014287964,0.0000072464936],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021235332,0.000058964728,0.048415605,0.00021729949,0.00021748715,0.000009535717,0.00044181405,0.007606959,0.89867485,0.0006983624,0.0033289567,0.040117793],"study_design_scores_gemma":[0.0042414824,0.00057413644,0.023358671,0.00027551266,0.00029971995,0.00037325008,0.0010674077,0.5711684,0.21381322,0.00029015925,0.18161573,0.0029222777],"about_ca_topic_score_codex":0.00008669629,"about_ca_topic_score_gemma":0.0005448711,"teacher_disagreement_score":0.68486166,"about_ca_system_score_codex":0.000023135757,"about_ca_system_score_gemma":0.00017060894,"threshold_uncertainty_score":0.6524842},"labels":[],"label_agreement":null},{"id":"W2076448238","doi":"10.1093/bioinformatics/btu759","title":"Local statistics allow quantification of cell-to-cell variability from high-throughput microscope images","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Cell; Protein subcellular localization prediction; Microscope; Subcellular localization; Microscopy; Biology; Computational biology; Cell biology; Cytoplasm; Pathology; Genetics; Gene; Medicine","score_opus":0.005301778245642983,"score_gpt":0.23982888409499534,"score_spread":0.23452710584935235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2076448238","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10727264,0.000026530259,0.8905114,0.0000323004,0.000040613264,0.00019892093,0.00021120977,0.00002497254,0.0016814312],"genre_scores_gemma":[0.6322484,0.000072510775,0.36632454,0.00019104886,0.000035079454,0.0000076025135,0.00092427555,0.000015107345,0.00018142289],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986715,0.0000775611,0.0006092274,0.00024778495,0.00018881663,0.00020513496],"domain_scores_gemma":[0.99840045,0.0000668046,0.00029523135,0.0008993709,0.0002478551,0.000090286696],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045583624,0.00018672388,0.00025969849,0.000055059427,0.000049894665,0.00004176259,0.00032859287,0.00021212782,0.00003719258],"category_scores_gemma":[0.0001844778,0.00018239567,0.00007813795,0.00012084533,0.00013958795,0.000012552473,0.00017550215,0.00010196996,0.00007189905],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026642223,0.00013982796,0.0003684173,0.00011569431,0.000024768966,1.9375943e-7,0.00010027626,0.00014518676,0.9739932,0.00007413069,0.021722196,0.0032894863],"study_design_scores_gemma":[0.00025067123,0.00018072814,0.00080733054,0.000009816402,0.00006261945,3.763699e-7,0.000066973174,0.0060904655,0.98082286,0.0001876764,0.011312164,0.00020830416],"about_ca_topic_score_codex":0.0001975084,"about_ca_topic_score_gemma":0.000021418064,"teacher_disagreement_score":0.5249758,"about_ca_system_score_codex":0.000022555181,"about_ca_system_score_gemma":0.00006120232,"threshold_uncertainty_score":0.743788},"labels":[],"label_agreement":null},{"id":"W2095681424","doi":"10.1093/bioinformatics/btu276","title":"Detecting independent and recurrent copy number aberrations using interval graphs","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Human Genome Research Institute; Natural Sciences and Engineering Research Council of Canada; Burroughs Wellcome Fund; National Institutes of Health; National Science Foundation","keywords":"Heuristics; Computer science; Algorithm","score_opus":0.014584606739911712,"score_gpt":0.2643972812608552,"score_spread":0.2498126745209435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2095681424","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9645869,0.000105052706,0.032620553,0.000027711654,0.00034863706,0.00011490552,0.00001898749,0.00001019014,0.0021670754],"genre_scores_gemma":[0.98395026,0.00015048064,0.015451758,0.00024149523,0.00012362137,0.0000050371827,0.000038899812,0.000011545417,0.000026875216],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994042,0.0000139190015,0.00023888481,0.00010647262,0.00008109345,0.00015545248],"domain_scores_gemma":[0.99956584,0.000019315989,0.00010285227,0.00018010882,0.0000550866,0.00007682616],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015162291,0.000106368156,0.000095669704,0.000028717242,0.00010945176,0.00006524101,0.00007790775,0.00008474048,0.000009425691],"category_scores_gemma":[0.00012444936,0.000105443396,0.000043975393,0.00004749782,0.000042569005,0.0000067518836,0.00012367465,0.00006949941,0.000009312148],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000507065,0.00058313034,0.22603479,0.0011751789,0.00078380585,0.0000062107233,0.007952098,0.003749402,0.18740849,0.020472696,0.022536123,0.528791],"study_design_scores_gemma":[0.007429621,0.0025841426,0.01911071,0.00047781708,0.00046930608,0.00068406767,0.0043704608,0.417457,0.21817826,0.0048590368,0.32076743,0.0036121216],"about_ca_topic_score_codex":0.000019199902,"about_ca_topic_score_gemma":0.00007111612,"teacher_disagreement_score":0.5251789,"about_ca_system_score_codex":0.000016290838,"about_ca_system_score_gemma":0.00003802067,"threshold_uncertainty_score":0.42998567},"labels":[],"label_agreement":null},{"id":"W2095885244","doi":"10.1093/bioinformatics/bth439","title":"Primer Design and Marker Clustering for Multiplex SNP-IT Primer Extension Genotyping Assay using Statistical Modeling","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill Genome Centre","funders":"","keywords":"Primer (cosmetics); Genotyping; Cluster analysis; Primer extension; Multiplex; SNP genotyping; SNP; Computer science; Statistical model; Computational biology; Biology; Genetics; Single-nucleotide polymorphism; Genotype; Artificial intelligence; Chemistry; Gene","score_opus":0.06619816459178136,"score_gpt":0.3131831912085179,"score_spread":0.24698502661673655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2095885244","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1403633,0.00015316097,0.8588537,0.000076324905,0.0000925804,0.00038607276,0.00001748433,0.0000106119005,0.00004677568],"genre_scores_gemma":[0.34663972,0.00006378619,0.65278924,0.00031853165,0.00006410503,0.000012537095,0.00007445056,0.000016960113,0.000020685195],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988874,0.00005216915,0.0004433677,0.00019925549,0.0000853367,0.0003324698],"domain_scores_gemma":[0.99938273,0.00007487763,0.00013647781,0.00019890623,0.00011851131,0.00008851151],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00075486524,0.00016364621,0.00019850775,0.00004293955,0.00019033713,0.000028744786,0.00007874691,0.00020669795,0.0000036793986],"category_scores_gemma":[0.00048712568,0.00015305195,0.000050802406,0.000038110826,0.00004666268,0.000010167668,0.00011564855,0.00006842056,0.0000035404807],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020998606,0.000070106245,0.0015550916,0.00018400422,0.00018618284,0.0000012433488,0.00058563147,0.8891153,0.09397383,0.00024269681,0.00064092077,0.013235019],"study_design_scores_gemma":[0.0007619502,0.00010163571,0.0008263823,0.000028722798,0.00004552904,0.000020263496,0.0001910835,0.9957367,0.0011484182,0.00027438608,0.0006493702,0.0002155552],"about_ca_topic_score_codex":0.000027415674,"about_ca_topic_score_gemma":0.00000745554,"teacher_disagreement_score":0.20627642,"about_ca_system_score_codex":0.000040923434,"about_ca_system_score_gemma":0.00010313235,"threshold_uncertainty_score":0.62412775},"labels":[],"label_agreement":null},{"id":"W2096066492","doi":"10.1093/bioinformatics/btu485","title":"Monte Carlo algorithms for Brownian phylogenetic models","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Agence Nationale de la Recherche","keywords":"Monte Carlo method; Markov chain Monte Carlo; Discretization; Algorithm; Statistical physics; Computer science; Brownian motion; Hybrid Monte Carlo; Mathematics; Mathematical optimization; Physics; Statistics; Mathematical analysis","score_opus":0.021551032029976158,"score_gpt":0.2363251618297108,"score_spread":0.21477412979973465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096066492","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76852065,0.0026417817,0.21546623,0.00024602027,0.00094518164,0.0011871604,0.00028784826,0.000028204391,0.010676901],"genre_scores_gemma":[0.92413276,0.00023775066,0.074265316,0.00048586057,0.0003119928,0.00006823388,0.000029949822,0.000028479304,0.00043962573],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99909335,0.000014021574,0.0003003786,0.00017803293,0.000100699035,0.00031352587],"domain_scores_gemma":[0.9992988,0.000018360719,0.00010232627,0.00037448434,0.00011472419,0.00009129421],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017294429,0.00018700161,0.00017903677,0.00003576983,0.00012753732,0.000032978543,0.00022070327,0.0001217216,0.0000015891959],"category_scores_gemma":[0.000047063626,0.00017094858,0.00012289525,0.000044943914,0.000060156508,0.0000015905298,0.00011060469,0.00003827354,0.000009031403],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003837194,0.00046134496,0.0054565542,0.0012058223,0.00153265,0.0000016664711,0.0050960435,0.13831942,0.21455802,0.008106168,0.043270715,0.5816079],"study_design_scores_gemma":[0.0022152164,0.0012432871,0.0019610769,0.000022638698,0.00010016397,0.000016484242,0.0004019543,0.64597934,0.021097464,0.002321401,0.32372934,0.00091165677],"about_ca_topic_score_codex":0.000007963293,"about_ca_topic_score_gemma":0.000013803221,"teacher_disagreement_score":0.5806962,"about_ca_system_score_codex":0.0000093961435,"about_ca_system_score_gemma":0.000035864054,"threshold_uncertainty_score":0.6971081},"labels":[],"label_agreement":null},{"id":"W2096265658","doi":"10.1093/bioinformatics/btm552","title":"Identification of linked regions using high-density SNP genotype data in linkage analysis","year":2007,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; University of Hong Kong; City University of Hong Kong","keywords":"Identification (biology); Linkage (software); SNP; Genotype; Genetics; Computational biology; Biology; SNP array; Genetic linkage; Computer science; Single-nucleotide polymorphism; Gene","score_opus":0.04586778108750514,"score_gpt":0.3173606241963624,"score_spread":0.27149284310885724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096265658","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7713513,0.00006719915,0.22825037,0.000039488485,0.000067499976,0.00008568064,0.000050453764,0.0000042420647,0.00008376428],"genre_scores_gemma":[0.96698695,0.0001021934,0.031770848,0.00007188282,0.000055421882,7.246627e-7,0.0009491072,0.000005536852,0.000057308378],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988018,0.000039728046,0.0007193424,0.00015195813,0.000098667544,0.00018845648],"domain_scores_gemma":[0.99861544,0.00003546729,0.0004083994,0.0007843889,0.00011455494,0.00004174746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013622968,0.0000854649,0.00020805391,0.00017529936,0.000049708597,0.00000831493,0.00027691474,0.0001978292,0.000004637626],"category_scores_gemma":[0.00035874904,0.00008573616,0.00006127312,0.000378308,0.000052947897,0.000008238023,0.00018204008,0.00006689316,0.000006235162],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000101858925,0.0003226417,0.6034825,0.00016670396,0.0012968228,0.000003895347,0.001065221,0.010299214,0.37212676,0.0008883085,0.0014953348,0.008750761],"study_design_scores_gemma":[0.00034994533,0.00004905031,0.9088185,0.000007086495,0.00029378914,0.0000032902228,0.0003947506,0.08122628,0.007906584,0.00017959681,0.00057830836,0.00019285266],"about_ca_topic_score_codex":0.00021593586,"about_ca_topic_score_gemma":0.0006977694,"teacher_disagreement_score":0.36422017,"about_ca_system_score_codex":0.000023344717,"about_ca_system_score_gemma":0.00005670197,"threshold_uncertainty_score":0.34962192},"labels":[],"label_agreement":null},{"id":"W2096349828","doi":"10.1093/bioinformatics/bth033","title":"GelScape: a web-based server for interactively annotating, manipulating, comparing and archiving 1D and 2D gel images","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Annotation; Java applet; Java; Software; Automatic image annotation; Image warping; Web server; Image retrieval; Image (mathematics); Web page; World Wide Web; Database; The Internet; Operating system; Artificial intelligence","score_opus":0.022021752804720185,"score_gpt":0.28336869555760646,"score_spread":0.2613469427528863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096349828","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75645,0.000033892524,0.24041626,0.00009255258,0.000008306825,0.00026686088,0.000050208448,0.00015286892,0.0025290383],"genre_scores_gemma":[0.5853851,0.000012750437,0.41436958,0.00006500636,0.000018845147,0.00007584312,0.000028226486,0.000013989195,0.00003066579],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99929935,0.0000021599003,0.00030297306,0.00013016243,0.00007383777,0.00019152292],"domain_scores_gemma":[0.9994218,0.000088485576,0.00021713265,0.00016749132,0.00003903349,0.00006606923],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000075009295,0.00014848309,0.00015881225,0.000042526273,0.00018331794,0.00009496799,0.000098906865,0.000050877297,0.000005346615],"category_scores_gemma":[0.00004867464,0.00014752122,0.00003553585,0.00004219308,0.00006018284,0.0002370181,0.00009285861,0.00013881137,0.0000014308293],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049530336,0.0007969223,0.10986986,0.017771415,0.0003781859,0.000009268321,0.014281399,0.012579598,0.55189276,0.057310767,0.001317685,0.23329686],"study_design_scores_gemma":[0.003903452,0.000108652435,0.003656544,0.0010435566,0.000078697914,0.000047552585,0.0013781204,0.6014606,0.3686568,0.015092132,0.0036594183,0.00091448263],"about_ca_topic_score_codex":0.000015195786,"about_ca_topic_score_gemma":0.000008296045,"teacher_disagreement_score":0.588881,"about_ca_system_score_codex":0.000042060576,"about_ca_system_score_gemma":0.000029269055,"threshold_uncertainty_score":0.60157406},"labels":[],"label_agreement":null},{"id":"W2096482937","doi":"10.1093/bioinformatics/btv321","title":"ABC: a tool to identify SNVs causing allele-specific transcription factor binding from ChIP-Seq experiments","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network; University of Toronto; Ontario Institute for Cancer Research","funders":"National Cancer Institute; Canadian Institutes of Health Research","keywords":"Perl; Computational biology; Computer science; Biology; SNP; False positive paradox; Chromatin; Genetics; Transcription factor; Single-nucleotide polymorphism; Gene; Artificial intelligence; Programming language","score_opus":0.039393317429218665,"score_gpt":0.2816686085563228,"score_spread":0.24227529112710414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096482937","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97453594,0.00019492552,0.023656141,0.000044859604,0.0005186244,0.000286834,0.00019632559,0.000027752825,0.00053858804],"genre_scores_gemma":[0.9656095,0.000088866465,0.03271219,0.00023141254,0.00022875247,0.000018106546,0.0008973336,0.00003498875,0.000178865],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987532,0.000018522538,0.00045956648,0.00021323953,0.00024282125,0.0003126358],"domain_scores_gemma":[0.9991743,0.0000045553747,0.00013420245,0.0004047789,0.00008370774,0.00019845346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012467205,0.00022323233,0.00018227208,0.000074282114,0.00010227946,0.00016450298,0.00021323793,0.00017501572,0.000030519634],"category_scores_gemma":[0.000027756498,0.00022473585,0.000093520095,0.000094585426,0.000027130553,0.000022418362,0.00011813459,0.00008113384,0.00014096683],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005627383,0.000050678966,0.00039130024,0.000020958769,0.0000623634,0.0000025810612,0.0033463277,0.0002481857,0.98873097,0.000037892605,0.0037960936,0.0032563724],"study_design_scores_gemma":[0.0057708155,0.0010475194,0.011160467,0.00017073426,0.00009347039,0.000054669614,0.011156189,0.028366836,0.7168056,0.0003472096,0.22231789,0.0027086297],"about_ca_topic_score_codex":0.000021517324,"about_ca_topic_score_gemma":0.000014090618,"teacher_disagreement_score":0.27192542,"about_ca_system_score_codex":0.00008785385,"about_ca_system_score_gemma":0.00007086464,"threshold_uncertainty_score":0.9164462},"labels":[],"label_agreement":null},{"id":"W2096529831","doi":"10.1093/bioinformatics/btv159","title":"A novel motif-discovery algorithm to identify co-regulatory motifs in large transcription factor and microRNA co-regulatory networks in human","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computational biology; Gene regulatory network; microRNA; Biological network; Biology; Motif (music); Gene; Transcription factor; Robustness (evolution); DNA binding site; Regulation of gene expression; Systems biology; Computer science; Genetics; Gene expression; Promoter","score_opus":0.017958116469330213,"score_gpt":0.2728153177653513,"score_spread":0.2548572012960211,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096529831","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87059116,0.0004891573,0.1272326,0.000040732048,0.0002861322,0.0006125378,0.00026983817,0.000022091452,0.00045572358],"genre_scores_gemma":[0.9909681,0.000062578474,0.0072251344,0.0006408171,0.00020748502,0.000025881709,0.00061000226,0.000040151976,0.00021985955],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979018,0.00003648477,0.0009063495,0.0002780574,0.00026191826,0.0006154211],"domain_scores_gemma":[0.9989579,0.000010703023,0.0002041991,0.00046552572,0.00006736332,0.00029436385],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00069182285,0.00034879157,0.00037349906,0.00024353093,0.000087170294,0.00016135578,0.0002864197,0.00043895235,0.000006759214],"category_scores_gemma":[0.000020429576,0.00035751995,0.000096495096,0.00019614316,0.00010171565,0.000084348816,0.00013585578,0.0002735184,0.000018036557],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012126347,0.0022818786,0.07833872,0.0015810467,0.00072460517,0.000052169355,0.031090982,0.03858155,0.661944,0.0017180202,0.06320008,0.11927435],"study_design_scores_gemma":[0.020781655,0.0013947849,0.44363868,0.000648735,0.00009992512,0.00020187421,0.0063729873,0.44679704,0.030622412,0.00037621852,0.045175474,0.003890197],"about_ca_topic_score_codex":0.0000425218,"about_ca_topic_score_gemma":0.00022324629,"teacher_disagreement_score":0.63132155,"about_ca_system_score_codex":0.00011697622,"about_ca_system_score_gemma":0.00011510648,"threshold_uncertainty_score":0.9998877},"labels":[],"label_agreement":null},{"id":"W2096589119","doi":"10.1093/bioinformatics/btt452","title":"The BioPAX Validator","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Cancer Institute; National Human Genome Research Institute; National Institutes of Health","keywords":"Validator; Computer science; Programming language; Service (business); Consistency (knowledge bases); Java; World Wide Web; Information retrieval; Software engineering; Artificial intelligence","score_opus":0.007486780389627012,"score_gpt":0.2108091162860064,"score_spread":0.20332233589637938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096589119","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6470738,0.004371859,0.10691003,0.0056022247,0.004395925,0.0039869426,0.00011115557,0.00026764776,0.2272804],"genre_scores_gemma":[0.9622296,0.0010276122,0.02406407,0.003506585,0.0008929382,0.00015233603,0.00024772526,0.000053817083,0.007825282],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99910796,0.000012431924,0.0003587625,0.000078169905,0.00012488164,0.00031781563],"domain_scores_gemma":[0.99919194,0.000018158618,0.00012536749,0.00047931875,0.000083992025,0.00010120616],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002032474,0.00013637856,0.00008516506,0.00001819053,0.00026006412,0.00019274825,0.00034073158,0.000115684365,0.00003741154],"category_scores_gemma":[0.000040847062,0.000086135624,0.000077643715,0.000070475595,0.000106166844,0.000011609486,0.00016094229,0.0000836703,0.00070427527],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003079641,0.000047931877,0.0008558053,0.00007495402,0.00018441424,5.053893e-7,0.00042704807,0.00011302375,0.009830173,0.0067499247,0.74015355,0.24153186],"study_design_scores_gemma":[0.00047562722,0.00018258719,0.0010751893,0.000011876409,0.0000147388355,0.000030280562,0.0007523683,0.020765666,0.0063286633,0.0013645076,0.96860725,0.00039122096],"about_ca_topic_score_codex":0.000008125642,"about_ca_topic_score_gemma":0.000005578599,"teacher_disagreement_score":0.31515583,"about_ca_system_score_codex":0.000009024925,"about_ca_system_score_gemma":0.000047146492,"threshold_uncertainty_score":0.9052268},"labels":[],"label_agreement":null},{"id":"W2097185378","doi":"10.1093/bioinformatics/btr392","title":"MetATT: a web-based metabolomics tool for analyzing time-series and two-factor datasets","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":73,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Institute for Nanotechnology; University of Alberta","funders":"Genome Alberta; Alberta Innovates","keywords":"Principal component analysis; Computer science; Metabolomics; Visualization; Data mining; Multivariate statistics; Time series; Session (web analytics); Identification (biology); Series (stratigraphy); Bioinformatics; Machine learning; Artificial intelligence; Biology","score_opus":0.018311101628872624,"score_gpt":0.24747668004217865,"score_spread":0.22916557841330604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2097185378","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92716545,0.0041190498,0.0575817,0.00020454219,0.00051955425,0.0014556719,0.0065630376,0.000098239536,0.0022927262],"genre_scores_gemma":[0.31464985,0.0017056811,0.6790772,0.00095803186,0.00032279128,0.0001445074,0.002479534,0.000076284276,0.0005860844],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990397,0.000018849178,0.00035899985,0.00020113288,0.00008897473,0.00029231407],"domain_scores_gemma":[0.9992766,0.000024108698,0.00017316485,0.00037535818,0.00007352289,0.000077257224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025221417,0.00022066811,0.0003023588,0.000093695315,0.00013646192,0.000046648463,0.00017378581,0.00008665216,0.000035167166],"category_scores_gemma":[0.0001787194,0.00018670222,0.000107044776,0.00009531919,0.00010377671,0.000023243592,0.00014149302,0.000054346205,0.000011600024],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0034090728,0.0007456147,0.018916536,0.0016551816,0.005107567,0.000010314303,0.0018053766,0.00006438144,0.80438435,0.016071696,0.0731578,0.07467211],"study_design_scores_gemma":[0.0052722925,0.0013766228,0.0034921905,0.000026377693,0.00069462956,0.000028011007,0.00027912017,0.010876927,0.44297007,0.0004609878,0.53312564,0.0013971158],"about_ca_topic_score_codex":0.0000039570778,"about_ca_topic_score_gemma":0.000011427348,"teacher_disagreement_score":0.62149554,"about_ca_system_score_codex":0.0000071871177,"about_ca_system_score_gemma":0.000066352375,"threshold_uncertainty_score":0.76134956},"labels":[],"label_agreement":null},{"id":"W2097392849","doi":"10.1093/bioinformatics/btt624","title":"Flexible analysis of RNA-seq data using mixed effects models","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":95,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"NIHR Cambridge Biomedical Research Centre; Biotechnology and Biological Sciences Research Council; Cancer Research UK","keywords":"Computer science; Expression (computer science); Bayesian probability; RNA-Seq; Data mining; Selection (genetic algorithm); Computational biology; Gene expression; Biology; Artificial intelligence; Gene; Genetics; Transcriptome","score_opus":0.05719972929131283,"score_gpt":0.2979505318125822,"score_spread":0.24075080252126935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2097392849","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47868273,0.00037754886,0.5163044,0.00003950484,0.00018645823,0.00030916667,0.00007061787,0.000019383804,0.004010196],"genre_scores_gemma":[0.9636896,0.000096861135,0.03515166,0.00012834684,0.000034801906,0.00000988895,0.0006700653,0.000008610343,0.00021012593],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99930334,0.000020026322,0.00028256958,0.00013115109,0.00013598758,0.0001269542],"domain_scores_gemma":[0.99880606,0.000008170441,0.00018033433,0.00085256103,0.00009454942,0.00005829633],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000107183434,0.00009116829,0.00015443513,0.00012700284,0.00003668322,0.000025520134,0.000330043,0.00009182809,0.000022806576],"category_scores_gemma":[0.000034785007,0.00007820645,0.000065733686,0.00032075524,0.000033798646,0.000025062101,0.00019716259,0.000031821517,0.000008982162],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019287818,0.00007398115,0.00057976355,0.00018160464,0.0006812063,1.14429916e-7,0.00018817295,0.015055347,0.94441444,0.00043245198,0.015369878,0.02300377],"study_design_scores_gemma":[0.00022403762,0.000036763195,0.0011630815,0.000014672942,0.00024392115,6.2011367e-7,0.00013334637,0.7528822,0.24349539,0.000103041486,0.0015747265,0.00012822985],"about_ca_topic_score_codex":0.000039000213,"about_ca_topic_score_gemma":0.0000033526583,"teacher_disagreement_score":0.7378268,"about_ca_system_score_codex":0.000008677441,"about_ca_system_score_gemma":0.000049981176,"threshold_uncertainty_score":0.31891665},"labels":[],"label_agreement":null},{"id":"W2097508475","doi":"10.1093/bioinformatics/btt138","title":"Cytoscape App Store","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":192,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Institute of General Medical Sciences; National Institutes of Health","keywords":"App store; Computer science; World Wide Web; Software; Open source; Data science; Visualization; Information retrieval; Data mining; Operating system","score_opus":0.006885813618096346,"score_gpt":0.20567563890478122,"score_spread":0.19878982528668487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2097508475","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.64012694,0.0014085463,0.12727383,0.0009120995,0.0015896276,0.0020848003,0.000084846324,0.00025321805,0.22626607],"genre_scores_gemma":[0.9444188,0.00024017191,0.047037624,0.002894783,0.00060549,0.000078108984,0.0004206038,0.000045885423,0.004258576],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99905086,0.000009142834,0.0003733256,0.00010646292,0.00013445901,0.00032573976],"domain_scores_gemma":[0.9992124,0.000006643867,0.000128749,0.0004308397,0.00008403481,0.0001373708],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000115973744,0.00017359732,0.00013307083,0.000040788225,0.00009479157,0.00008673879,0.00026127728,0.00018167314,0.00015679428],"category_scores_gemma":[0.00002228194,0.00014861621,0.00008895949,0.00007877955,0.00006500901,0.000016522543,0.00015196555,0.00009754183,0.0009435632],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003654893,0.00011298777,0.0016016915,0.00022572899,0.00020775627,0.0000012924141,0.0009568108,0.00042369845,0.023091218,0.002554131,0.7716411,0.19914703],"study_design_scores_gemma":[0.0017260002,0.00062470976,0.004032073,0.000048167563,0.00004535132,0.000100411635,0.0016479322,0.07615909,0.012096069,0.0015789953,0.90062547,0.0013157141],"about_ca_topic_score_codex":0.0000092281425,"about_ca_topic_score_gemma":0.0000042164556,"teacher_disagreement_score":0.3042918,"about_ca_system_score_codex":0.00001232221,"about_ca_system_score_gemma":0.000049374314,"threshold_uncertainty_score":0.9998343},"labels":[],"label_agreement":null},{"id":"W2097706952","doi":"10.1093/bioinformatics/bth903","title":"Analysis of domain correlations in yeast protein complexes","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; Mount Sinai Hospital","funders":"Canadian Institutes of Health Research; Genome Canada","keywords":"Computational biology; Biology; Saccharomyces cerevisiae; Ribosome; Protein domain; RNA-binding protein; Domain (mathematical analysis); RNA; Protein–protein interaction; Genetics; Yeast; Gene","score_opus":0.008864431876002487,"score_gpt":0.2266656028947092,"score_spread":0.2178011710187067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2097706952","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90882593,0.00008793933,0.08546771,0.000064276195,0.000049730086,0.00030209287,0.000096775286,0.000008427006,0.0050971406],"genre_scores_gemma":[0.9738095,0.000015100853,0.025644304,0.00008447909,0.000023876808,0.0000105953795,0.00034080903,0.000006573243,0.00006480448],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991302,0.000009616518,0.00050380465,0.000075383774,0.00010869819,0.00017232035],"domain_scores_gemma":[0.9994393,0.0000040471655,0.00018513972,0.00027893126,0.000044621876,0.00004797087],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017435351,0.000105863764,0.00019866822,0.00019763847,0.00003544835,0.000014494724,0.00015102456,0.000115299685,0.000013192489],"category_scores_gemma":[0.000017401697,0.00009939144,0.00011398291,0.0004727748,0.000074037256,0.000008070473,0.000069844566,0.00006930589,0.000011351659],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005115404,0.0014524104,0.05342182,0.0008491144,0.004945286,0.000009696759,0.01776471,0.59491843,0.17264278,0.123256885,0.0025930724,0.027634269],"study_design_scores_gemma":[0.024153242,0.0032837847,0.29195818,0.000971031,0.0024253053,0.00008292217,0.019828577,0.44803163,0.09777903,0.031832334,0.07403787,0.0056160884],"about_ca_topic_score_codex":0.000028946552,"about_ca_topic_score_gemma":0.0002386737,"teacher_disagreement_score":0.23853637,"about_ca_system_score_codex":0.000021145814,"about_ca_system_score_gemma":0.00007105106,"threshold_uncertainty_score":0.40530652},"labels":[],"label_agreement":null},{"id":"W2097828850","doi":"10.1093/bioinformatics/btp010","title":"Profiling model T-cell metagenomes with short reads","year":2009,"lang":"en","type":"article","venue":"Bioinformatics","topic":"T-cell and B-cell Immunology","field":"Immunology and Microbiology","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; BC Cancer Agency","funders":"Genome British Columbia; Michael Smith Health Research BC; Genome Canada","keywords":"T-cell receptor; Computational biology; Biology; Profiling (computer programming); Genetics; T cell; Algorithm; Computer science; Immune system","score_opus":0.017203179056754572,"score_gpt":0.22348327644139065,"score_spread":0.2062800973846361,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2097828850","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8261604,0.0039094007,0.025623823,0.0004486051,0.0005431341,0.00095191,0.00006198112,0.0006125463,0.1416882],"genre_scores_gemma":[0.9614736,0.00014305879,0.026308406,0.0005439964,0.000017517234,0.000011102937,0.00019030781,0.000016381096,0.011295658],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99881005,0.000030099296,0.00044072996,0.00017027778,0.00005034896,0.0004984887],"domain_scores_gemma":[0.99931955,0.00003257424,0.000119254604,0.00042438623,0.00007426768,0.000029980458],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016877877,0.00025851605,0.00034112565,0.00012971011,0.00020107273,0.000027130833,0.00030653912,0.00027547334,0.00007164976],"category_scores_gemma":[0.00001042445,0.00018482255,0.0000829346,0.00014648534,0.00015240585,0.00022441601,0.00005294332,0.0003206161,0.00064623286],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000118943084,0.00019078332,0.0002330019,0.000039609702,0.00010486129,0.000004755379,0.000865982,0.0004021943,0.9871416,0.0013794973,0.0022324026,0.0072863707],"study_design_scores_gemma":[0.001443942,0.000849828,0.00006991375,0.0000257546,0.0001488741,0.00015398645,0.00086162315,0.0041157096,0.97935116,0.000262891,0.012171124,0.0005451753],"about_ca_topic_score_codex":0.000003691654,"about_ca_topic_score_gemma":0.0000024337066,"teacher_disagreement_score":0.13531317,"about_ca_system_score_codex":0.0000313891,"about_ca_system_score_gemma":0.00010119451,"threshold_uncertainty_score":0.83062315},"labels":[],"label_agreement":null},{"id":"W2098429327","doi":"10.1093/bioinformatics/btn524","title":"The Burkholderia Genome Database: facilitating flexible queries and comparative analyses","year":2008,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Cystic Fibrosis Research Advances","field":"Medicine","cited_by":252,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Canadian Institutes of Health Research; Cystic Fibrosis Foundation Therapeutics; Michael Smith Health Research BC; Cystic Fibrosis Foundation","keywords":"Computer science; Burkholderia; Genome; Database; Computational biology; World Wide Web; Biology; Genetics; Gene; Bacteria","score_opus":0.180599334328155,"score_gpt":0.4012624785675375,"score_spread":0.2206631442393825,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098429327","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9517671,0.009707972,0.016078532,0.00061639864,0.00012113391,0.0011619446,0.00033019052,0.00020916855,0.02000757],"genre_scores_gemma":[0.8140205,0.002219437,0.18040067,0.00019545823,0.000092136775,0.000047417034,0.00023893728,0.000013363892,0.0027720544],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99891776,0.000018770408,0.00034180237,0.00009250831,0.0003565008,0.00027267562],"domain_scores_gemma":[0.9988597,0.00049663475,0.000089447276,0.00029263826,0.0001257819,0.00013581829],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002007116,0.00012329905,0.00023952486,0.000066965986,0.0005073318,0.00005459501,0.0000949033,0.000024925397,0.000024347495],"category_scores_gemma":[0.0004994933,0.000074758216,0.000036138044,0.0002119179,0.00057685986,0.00033860505,0.00010718718,0.00013776132,0.000056123048],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004400852,0.0007121501,0.024013447,0.008176594,0.002852483,0.00022268751,0.18812135,0.0012806115,0.59524,0.016017273,0.10094274,0.058019813],"study_design_scores_gemma":[0.0052064434,0.0022076336,0.09270226,0.0005615965,0.00022414397,0.0014677988,0.1102979,0.11592909,0.052344758,0.00035336742,0.6175893,0.0011157283],"about_ca_topic_score_codex":0.0000284917,"about_ca_topic_score_gemma":0.000012316823,"teacher_disagreement_score":0.54289526,"about_ca_system_score_codex":0.00003569856,"about_ca_system_score_gemma":0.000112042784,"threshold_uncertainty_score":0.39020374},"labels":[],"label_agreement":null},{"id":"W2098566726","doi":"10.1093/bioinformatics/bth124","title":"Evaluation and optimization of clustering in gene expression data analysis","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Cluster analysis; Computer science; Partition (number theory); Identification (biology); Data mining; Stability (learning theory); Cluster (spacecraft); Expression (computer science); Gene; Computational biology; Consensus clustering; Artificial intelligence; Pattern recognition (psychology); Machine learning; Biology; Genetics; Correlation clustering; Mathematics; CURE data clustering algorithm","score_opus":0.0391304351557178,"score_gpt":0.3075528175625202,"score_spread":0.2684223824068024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098566726","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17341971,0.00032067276,0.8256227,0.000038773003,0.00003945328,0.0001692521,0.000018214088,0.0000041807248,0.00036705247],"genre_scores_gemma":[0.9037711,0.00026330136,0.0952856,0.00002400519,0.000015300315,0.000006902768,0.00062418135,0.0000035716266,0.00000605403],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994125,0.000021688964,0.00022900049,0.000114574264,0.00016216755,0.000060083286],"domain_scores_gemma":[0.99939746,0.00000223433,0.00012062302,0.0003828333,0.000073278876,0.00002359029],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003915292,0.000053134183,0.00007583406,0.000116210154,0.000019706886,0.000010658113,0.000112584334,0.00006089274,0.000006348683],"category_scores_gemma":[0.00007037519,0.000048896054,0.000015466281,0.00020311061,0.000017907427,0.000015061879,0.00012141295,0.000020744792,3.5779755e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021512567,0.000029927542,0.0011725602,0.00002768264,0.000036669284,5.2878182e-8,0.00022790606,0.8226481,0.16990913,0.0000073565107,0.000047391626,0.0058717015],"study_design_scores_gemma":[0.0008925916,0.00004251485,0.0035276911,0.000027966493,0.00011646789,0.0000013248296,0.00023411502,0.8249481,0.16993877,0.000031901447,0.0001386064,0.000099986144],"about_ca_topic_score_codex":0.00000762728,"about_ca_topic_score_gemma":0.000036472047,"teacher_disagreement_score":0.7303514,"about_ca_system_score_codex":0.000015243108,"about_ca_system_score_gemma":0.000059735514,"threshold_uncertainty_score":0.19939233},"labels":[],"label_agreement":null},{"id":"W2099377894","doi":"10.1093/bioinformatics/bts053","title":"JointSNVMix: a probabilistic model for accurate detection of somatic mutations in normal/tumour paired next-generation sequencing data","year":2012,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":175,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia; BC Cancer Agency","funders":"Canadian Institutes of Health Research; Michael Smith Health Research BC","keywords":"Somatic cell; DNA sequencing; Computational biology; Probabilistic logic; Computer science; Genetics; Biology; Artificial intelligence; Gene","score_opus":0.1153016910058751,"score_gpt":0.28669141719358626,"score_spread":0.17138972618771114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099377894","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62654054,0.00017538437,0.3721442,0.000033730106,0.00016876614,0.00057293527,0.0002816398,0.000008973617,0.00007381314],"genre_scores_gemma":[0.9640478,0.00006344961,0.034434363,0.000069704365,0.0001455067,0.00006723549,0.001134487,0.000015246344,0.000022242284],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990316,0.000016266966,0.00050979014,0.00011678752,0.00009093881,0.00023462734],"domain_scores_gemma":[0.9991806,0.000038286344,0.00023280646,0.0004029541,0.00008267429,0.00006264492],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037553176,0.00012038213,0.00014228834,0.00007085869,0.000062132196,0.000032081596,0.00017470004,0.00009625095,0.0000017115623],"category_scores_gemma":[0.0005317164,0.00012204246,0.000043229895,0.00008348932,0.000032971133,0.00006130994,0.000109574496,0.000045465957,0.000003141185],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058078684,0.00013510311,0.00047590665,0.0006013881,0.000046010162,1.6804616e-7,0.002511745,0.09065896,0.89656657,0.00024512643,0.00060812297,0.00809283],"study_design_scores_gemma":[0.0004254118,0.0000711639,0.00015035037,0.000019773024,0.000036569316,0.000005268166,0.00029410582,0.9327474,0.0657937,0.00015840247,0.0001561729,0.00014165066],"about_ca_topic_score_codex":0.000027380922,"about_ca_topic_score_gemma":0.00041473247,"teacher_disagreement_score":0.84208846,"about_ca_system_score_codex":0.00006641131,"about_ca_system_score_gemma":0.0002183612,"threshold_uncertainty_score":0.49767473},"labels":[],"label_agreement":null},{"id":"W2099432911","doi":"10.1093/bioinformatics/btm487","title":"MDQC: a new quality assessment method for microarrays based on quality control reports","year":2007,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vancouver Coastal Health Research Institute; University of British Columbia; Vancouver Coastal Health; Providence Health Care","funders":"","keywords":"Mahalanobis distance; Computer science; Quality (philosophy); Data mining; Bioconductor; Outlier; Quality assurance; Data quality; Process (computing); Multivariate statistics; Control (management); Quality Score; Artificial intelligence; Metric (unit); Machine learning; Engineering","score_opus":0.044256724069191226,"score_gpt":0.394229669492128,"score_spread":0.3499729454229368,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099432911","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0042185443,0.000035138848,0.9879209,0.00046749457,0.00034173077,0.0005260179,0.000045071945,0.000024981278,0.0064201513],"genre_scores_gemma":[0.53126526,0.000008547359,0.46260127,0.0043785116,0.00029023847,0.00005420725,0.00045318776,0.000021570304,0.000927233],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984133,0.00007390164,0.00077479205,0.00023133343,0.00024777005,0.00025886702],"domain_scores_gemma":[0.9984621,0.00009857086,0.0004971571,0.00063597766,0.00014184095,0.00016436065],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024154482,0.00016269943,0.00020249106,0.000059556885,0.00009492638,0.0000372923,0.00012785636,0.0001833204,0.000018302253],"category_scores_gemma":[0.00030601217,0.00014200443,0.00016392989,0.000081888524,0.00002419837,0.000005930581,0.000021583859,0.00007779655,0.000004329242],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006815993,0.00021312124,0.0017714202,0.00016588194,0.00006132287,0.00000106665,0.00014582822,0.00046591111,0.84634626,0.0011505472,0.053835627,0.09516142],"study_design_scores_gemma":[0.004956823,0.0007454027,0.030627597,0.000060407616,0.000061217455,0.000011323686,0.0005841984,0.018190851,0.51118684,0.000556557,0.4322549,0.00076385686],"about_ca_topic_score_codex":0.000021671727,"about_ca_topic_score_gemma":0.000017077267,"teacher_disagreement_score":0.5270467,"about_ca_system_score_codex":0.000051465817,"about_ca_system_score_gemma":0.00029592318,"threshold_uncertainty_score":0.57907724},"labels":[],"label_agreement":null},{"id":"W2099999454","doi":"10.1093/bioinformatics/btv143","title":"Probing the binding affinity of amyloids to reduce toxicity of oligomers in diabetes","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Alzheimer's disease research and treatments","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University","funders":"Canadian Institutes of Health Research; McGill University","keywords":"Amylin; Amyloid (mycology); Amyloid fibril; Chemistry; Membrane; Toxicity; Amyloid disease; Fibril; Biophysics; Biochemistry; Insulin; Biology; Amyloid β; Medicine; Islet","score_opus":0.056556154752666836,"score_gpt":0.32062946861408237,"score_spread":0.2640733138614155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099999454","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9962571,0.00018737945,0.0000120801,0.00019029703,0.000029223153,0.00049070764,0.000026066702,0.000010577202,0.0027965547],"genre_scores_gemma":[0.99789333,0.000014165981,0.0019859807,0.000047839243,0.000013031229,0.00001542897,0.00001291104,0.0000059090416,0.0000113972965],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99902344,0.000023946963,0.0003310774,0.00005306271,0.00034312703,0.0002253578],"domain_scores_gemma":[0.9992871,0.00006381167,0.00010239153,0.00022324985,0.00010937799,0.00021402654],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039026863,0.000082571896,0.0002164827,0.00015328162,0.000022764902,0.000007093476,0.00010255892,0.000036094967,0.000007887157],"category_scores_gemma":[0.00024479444,0.00005212418,0.000049090148,0.0003923288,0.000079914185,0.00010452721,0.0000745717,0.00008148969,0.000030537984],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015858485,0.0033342638,0.88777804,0.003588769,0.0062432145,0.000033973593,0.04191873,0.00045445087,0.014084118,0.00091886055,0.006174539,0.033885162],"study_design_scores_gemma":[0.008907388,0.0033409237,0.13658041,0.0018980642,0.0006307134,0.000012897759,0.026342867,0.009307299,0.81182593,0.00028589653,0.00036356796,0.0005040429],"about_ca_topic_score_codex":0.000023397439,"about_ca_topic_score_gemma":0.0000049568284,"teacher_disagreement_score":0.79774183,"about_ca_system_score_codex":0.000078565594,"about_ca_system_score_gemma":0.00025295568,"threshold_uncertainty_score":0.21255623},"labels":[],"label_agreement":null},{"id":"W2100033550","doi":"10.1093/bioinformatics/16.12.1105","title":"Saturated BLAST: an automated multiple intermediate sequence search used to detect distant homology","year":2000,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":65,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Institute of General Medical Sciences; National Institutes of Health","keywords":"Perl; Computer science; False positive paradox; Sequence (biology); Sequence database; Cluster analysis; Parsing; Data mining; Multiple sequence alignment; Sequence alignment; Artificial intelligence; Programming language; Biology; Peptide sequence; Gene; Genetics","score_opus":0.014202928386738112,"score_gpt":0.279582879899132,"score_spread":0.2653799515123939,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100033550","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9931053,0.00003059206,0.0056751734,0.000038649643,0.00012475195,0.00037091612,0.00014188005,0.00015637686,0.00035638473],"genre_scores_gemma":[0.9826291,0.00003231741,0.016078627,0.00040339696,0.00007598588,0.000019487157,0.0005696116,0.000023302406,0.00016814955],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987733,0.00006681287,0.0003542796,0.00022666292,0.00015860789,0.00042033108],"domain_scores_gemma":[0.9991076,0.000016252745,0.00005898823,0.0005122616,0.0000850799,0.00021981944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017122104,0.00021250983,0.00018469192,0.0000671594,0.00011826792,0.000059756258,0.0003541002,0.00022565389,0.000051528044],"category_scores_gemma":[0.00008441553,0.00018415594,0.000056929905,0.00019134898,0.00011208023,0.000017799326,0.000100264915,0.00015981376,0.00011638538],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008557592,0.000076466866,0.0014523865,0.0001443411,0.00013702744,0.000044667486,0.002826795,0.0050778724,0.8476109,0.00004650148,0.0014640912,0.1402632],"study_design_scores_gemma":[0.002579388,0.0030224258,0.010012196,0.00007285538,0.000045874465,0.00029172865,0.00055095326,0.5909132,0.3675125,0.00016638209,0.023447555,0.0013849741],"about_ca_topic_score_codex":0.0000365224,"about_ca_topic_score_gemma":0.00020340637,"teacher_disagreement_score":0.5858353,"about_ca_system_score_codex":0.000033738437,"about_ca_system_score_gemma":0.00010627964,"threshold_uncertainty_score":0.75096613},"labels":[],"label_agreement":null},{"id":"W2100148038","doi":"10.1093/bioinformatics/btt151","title":"FishingCNV: a graphical software package for detecting rare copy number variations in exome-sequencing data","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomic variations and chromosomal abnormalities","field":"Biochemistry, Genetics and Molecular Biology","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University and Génome Québec Innovation Centre","funders":"Canadian Institutes of Health Research","keywords":"Computer science; Software; Scripting language; Java; Copy-number variation; Graphical user interface; Pipeline (software); Exome sequencing; Exome; Data mining; Programming language; Mutation; Biology; Genetics; Gene; Genome","score_opus":0.025449746610317375,"score_gpt":0.25206958009952374,"score_spread":0.22661983348920636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100148038","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7620128,0.000057953974,0.23493254,0.00023481558,0.00023876173,0.00082367996,0.00064231915,0.000050908937,0.0010062178],"genre_scores_gemma":[0.8806634,0.000022030705,0.11741779,0.00025386916,0.00012591235,0.000095842595,0.001258255,0.00001776663,0.00014516553],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998986,0.000022126422,0.00042386452,0.00018039625,0.000098424614,0.00028919263],"domain_scores_gemma":[0.9990624,0.000055709184,0.00013477149,0.00057678885,0.00010397442,0.000066357024],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023846429,0.00014073848,0.00013849488,0.0000508485,0.00015534229,0.00012626962,0.00036914268,0.00015815179,0.00007032258],"category_scores_gemma":[0.00044775172,0.00013542314,0.00005519925,0.00012520821,0.000031843505,0.000059591657,0.00024339583,0.0000963093,0.000039819908],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039347805,0.0009200326,0.68383884,0.0040812725,0.00129848,0.000021069174,0.025558393,0.001726119,0.07506352,0.0148325525,0.11823856,0.07402768],"study_design_scores_gemma":[0.02223654,0.0023771552,0.16657181,0.0012121561,0.000703144,0.0010694596,0.064371094,0.36431336,0.16900648,0.033488166,0.16463582,0.010014794],"about_ca_topic_score_codex":0.0001191321,"about_ca_topic_score_gemma":0.00014589539,"teacher_disagreement_score":0.51726705,"about_ca_system_score_codex":0.000034255507,"about_ca_system_score_gemma":0.00012758114,"threshold_uncertainty_score":0.55223954},"labels":[],"label_agreement":null},{"id":"W2100266218","doi":"10.1093/bioinformatics/btu849","title":"An automatic tool to analyze and cluster macromolecular conformations based on self-organizing maps","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Nautical Research Society","funders":"","keywords":"Computer science; Cluster (spacecraft); Data mining; Artificial intelligence; Programming language","score_opus":0.006141447108255647,"score_gpt":0.2239100227889064,"score_spread":0.21776857568065075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100266218","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047625873,0.0000015708198,0.9484666,0.0012726154,0.00006250649,0.00033649395,0.000005992989,0.00032492192,0.0019034107],"genre_scores_gemma":[0.6052635,0.0000013490636,0.38774014,0.0069038603,0.000031898027,0.000022392933,0.000016561595,0.000008027182,0.000012323766],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990807,0.00002865034,0.0003312944,0.0001301169,0.00020853619,0.00022068305],"domain_scores_gemma":[0.99896026,0.000080896345,0.0000982574,0.00064024894,0.000057567147,0.00016277848],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026142198,0.00013348329,0.00012810723,0.00012210206,0.00021881542,0.00037927652,0.0004398401,0.00004524123,0.0000051796846],"category_scores_gemma":[0.00002531635,0.000115233684,0.000029187106,0.00038796142,0.00001531107,0.00054672745,0.00009646341,0.000079662525,0.00012601404],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011703373,0.0005730466,0.0006238653,0.00065260456,0.000084990716,0.00000639307,0.011667939,0.07043731,0.0011643129,0.3514364,0.024283322,0.5390581],"study_design_scores_gemma":[0.00020725915,0.00011410843,0.0005278579,0.000022407168,0.000008032874,0.0000081391645,0.000024307523,0.9911662,0.00032407625,0.00034291143,0.007081507,0.00017322932],"about_ca_topic_score_codex":0.0000024296583,"about_ca_topic_score_gemma":0.0000018952549,"teacher_disagreement_score":0.92072886,"about_ca_system_score_codex":0.00002275788,"about_ca_system_score_gemma":0.000027387598,"threshold_uncertainty_score":0.4699093},"labels":[],"label_agreement":null},{"id":"W2100922775","doi":"10.1093/bioinformatics/btv157","title":"Test set bias affects reproducibility of gene signatures","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":123,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; University Health Network; Montreal Clinical Research Institute","funders":"National Institute of General Medical Sciences; National Cancer Institute; National Center for Advancing Translational Sciences; BC Cancer Agency","keywords":"Normalization (sociology); Computer science; Data set; Data mining; Set (abstract data type); Test set; Reproducibility; Sample size determination; Population; Test data; Statistics; Pattern recognition (psychology); Artificial intelligence; Mathematics; Medicine","score_opus":0.0516341996318329,"score_gpt":0.29076790735133456,"score_spread":0.23913370771950165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100922775","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9791114,0.001098194,0.005213644,0.00026534192,0.0004636536,0.00041692948,0.00008845135,0.000037883743,0.013304501],"genre_scores_gemma":[0.99330336,0.000038993072,0.0058189295,0.00016109544,0.00010448083,0.000008967813,0.00015267455,0.000007732556,0.00040377525],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99924815,0.000027765775,0.00023196776,0.00021838596,0.00016170811,0.000112016685],"domain_scores_gemma":[0.99858755,0.000012752055,0.00017463062,0.0009924986,0.00014342315,0.000089145484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061046024,0.00009075185,0.00010442624,0.000036034853,0.000022404749,0.0000114740415,0.00015340338,0.00011254057,0.0000055577443],"category_scores_gemma":[0.0011626373,0.000074552794,0.000048029084,0.000107353175,0.00005217228,0.0000055373907,0.00006061255,0.000047288722,0.000010538792],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000072279945,0.00010886315,0.008653097,0.00011037987,0.000023457287,3.680587e-7,0.0005649742,0.00026034215,0.85563755,0.00006320964,0.12877865,0.005726838],"study_design_scores_gemma":[0.0003932392,0.00025667067,0.0036875028,0.000011475286,0.000009390277,0.000003911169,0.00028962648,0.0007315241,0.9509135,0.000052928022,0.043528043,0.00012219834],"about_ca_topic_score_codex":0.0000031345924,"about_ca_topic_score_gemma":0.0000024467492,"teacher_disagreement_score":0.095275946,"about_ca_system_score_codex":0.00001196205,"about_ca_system_score_gemma":0.00013052739,"threshold_uncertainty_score":0.30401748},"labels":[],"label_agreement":null},{"id":"W2101347991","doi":"10.1093/bioinformatics/btm585","title":"Choosing BLAST options for better detection of orthologs as reciprocal best hits","year":2007,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":535,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reciprocal; Genome; Matching (statistics); Computational biology; Computer science; Gene; Biology; Genetics; Mathematics; Statistics","score_opus":0.014556145587829139,"score_gpt":0.2589700547250416,"score_spread":0.24441390913721245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2101347991","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93821514,0.00024393367,0.059417322,0.00004071429,0.00019463067,0.00022201288,0.000030645497,0.000003368922,0.0016322192],"genre_scores_gemma":[0.97185695,0.0001119771,0.027521066,0.00016258513,0.0001595189,0.000012112073,0.000031819574,0.000011039354,0.00013290667],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99938446,0.0000048743073,0.0002712277,0.00009079371,0.00006392631,0.0001847418],"domain_scores_gemma":[0.99955666,0.000018255281,0.00012312272,0.00015697538,0.00010310128,0.000041879906],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020446494,0.00009772973,0.00010575038,0.000045814682,0.0000928249,0.00000968786,0.000078625264,0.00011277982,0.0000017724235],"category_scores_gemma":[0.00006589921,0.00009186391,0.000077004705,0.000055770888,0.00006214493,0.0000015555985,0.000056332974,0.000037839764,0.0000072223656],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010110932,0.000055022552,0.0019837776,0.00008442614,0.00008364423,2.9902012e-7,0.00028568733,0.000070761416,0.9264577,0.00012376883,0.00026036426,0.070493445],"study_design_scores_gemma":[0.00071080466,0.00096703944,0.0080453195,0.000022296015,0.000057572233,0.000029275148,0.00073627837,0.00051579386,0.9321695,0.00016146695,0.056329627,0.00025500118],"about_ca_topic_score_codex":0.0000042467886,"about_ca_topic_score_gemma":0.000031770734,"teacher_disagreement_score":0.07023844,"about_ca_system_score_codex":0.000009004282,"about_ca_system_score_gemma":0.000024110204,"threshold_uncertainty_score":0.37461016},"labels":[],"label_agreement":null},{"id":"W2101456936","doi":"10.1093/bioinformatics/btn645","title":"Predicting the binding preference of transcription factors to individual DNA <i>k</i>-mers","year":2008,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Howard Hughes Medical Institute","keywords":"Inference; Computational biology; Biology; Transcription factor; DNA; DNA sequencing; DNA binding site; Preference; Gene; Genetics; Mechanism (biology); Computer science; Gene expression; Artificial intelligence; Mathematics; Promoter","score_opus":0.028418969096521675,"score_gpt":0.21702661677774326,"score_spread":0.1886076476812216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2101456936","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9966033,0.000029154873,0.002135507,0.000027489978,0.0001273626,0.00019061593,0.00012665096,0.000009681033,0.0007502077],"genre_scores_gemma":[0.9965827,0.00008104159,0.0029565278,0.00008399079,0.000036043304,0.000005739427,0.00015037884,0.000010001986,0.00009359184],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992467,0.000013656097,0.0003101575,0.000088088615,0.00016679533,0.00017456732],"domain_scores_gemma":[0.9995186,0.000011594423,0.00013473167,0.00022971329,0.000046968467,0.00005841684],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013052399,0.00011418168,0.00010262025,0.000040282466,0.00013886465,0.00001515004,0.00026683562,0.00008497406,0.000004182077],"category_scores_gemma":[0.000042255877,0.00008340712,0.00006547379,0.0000968688,0.0000628833,0.0000071734285,0.00007737221,0.00006413823,0.0000048388456],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056917106,0.00009973968,0.1028965,0.0002223791,0.00021553754,7.913409e-7,0.021722231,0.0020209244,0.8681486,0.0002057196,0.0017554022,0.0026552633],"study_design_scores_gemma":[0.001467276,0.0014599457,0.16553043,0.00013197231,0.00015405673,0.00008649082,0.013506605,0.014836903,0.79227483,0.00005113617,0.009498826,0.0010015483],"about_ca_topic_score_codex":0.000010243123,"about_ca_topic_score_gemma":0.000012181385,"teacher_disagreement_score":0.07587378,"about_ca_system_score_codex":0.000010190862,"about_ca_system_score_gemma":0.000059055346,"threshold_uncertainty_score":0.34012434},"labels":[],"label_agreement":null},{"id":"W2101497394","doi":"10.1093/bioinformatics/bts226","title":"Towards 3D structure prediction of large RNA molecules: an integer programming framework to insert local 3D motifs in RNA secondary structure","year":2012,"lang":"en","type":"article","venue":"Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Montréal; McGill University","funders":"National Institute of General Medical Sciences; Nepal Academy of Science and Technology","keywords":"RNA; Insert (composites); Nucleic acid structure; Nucleic acid secondary structure; Protein secondary structure; Computational biology; Computer science; Integer programming; Structural motif; Algorithm; Biology; Genetics; Engineering; Structural engineering; Gene; Biochemistry","score_opus":0.008293551987385947,"score_gpt":0.24386110810428036,"score_spread":0.2355675561168944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2101497394","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6893634,0.00028199793,0.3087615,0.000026196156,0.00045067634,0.0005042092,0.0002833503,0.000024482599,0.00030420255],"genre_scores_gemma":[0.8468746,0.00001817517,0.15223017,0.00035159884,0.00020335734,0.00001619638,0.00026379782,0.000027895254,0.000014226809],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998459,0.00006384285,0.00053848285,0.0001881093,0.0002647395,0.00048586316],"domain_scores_gemma":[0.99901855,0.000009530363,0.00018642556,0.00048104522,0.000092740476,0.00021171864],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002785979,0.00026474852,0.00026542213,0.00012474679,0.00006246496,0.00003501519,0.0002959553,0.0005446238,0.00009938461],"category_scores_gemma":[0.00013400696,0.00023040104,0.00007203684,0.0002025988,0.000051782306,0.00005037453,0.00015525428,0.00027364527,0.0000048541024],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028752515,0.00026494171,0.0022428045,0.0006582084,0.00014994708,0.0000029420953,0.009188877,0.0007684073,0.4795349,0.0013120411,0.00038908378,0.5052003],"study_design_scores_gemma":[0.0006998836,0.00088271644,0.0031608476,0.00022417627,0.000044621993,0.00003155824,0.0026307243,0.0051650465,0.97005,0.00050148374,0.016065251,0.0005437172],"about_ca_topic_score_codex":0.000017603687,"about_ca_topic_score_gemma":0.00003173812,"teacher_disagreement_score":0.5046566,"about_ca_system_score_codex":0.00003985303,"about_ca_system_score_gemma":0.00011003953,"threshold_uncertainty_score":0.9395482},"labels":[],"label_agreement":null},{"id":"W2101763464","doi":"10.1093/bioinformatics/bts072","title":"The identification of short linear motif-mediated interfaces within the human interactome","year":2012,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":72,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; University of Toronto; Mount Sinai Hospital","funders":"","keywords":"Interactome; Motif (music); Identification (biology); Computer science; Computational biology; Biology; Genetics; Gene; Ecology","score_opus":0.014387946493191764,"score_gpt":0.2640914391990048,"score_spread":0.24970349270581305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2101763464","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98795176,0.0006122329,0.007972377,0.00014919374,0.0007674096,0.00037311375,0.000038582017,0.000016436823,0.0021188986],"genre_scores_gemma":[0.99855596,0.00009218497,0.0005708435,0.00016640004,0.0001776912,0.000011928146,0.00013820856,0.0000113718825,0.00027538615],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987085,0.000028910647,0.0008175595,0.000058776102,0.00015336995,0.00023291404],"domain_scores_gemma":[0.9989532,0.0000422232,0.0003634551,0.00048990455,0.00009357496,0.000057628167],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009460085,0.00013067469,0.00010892866,0.000025616991,0.00022047099,0.000054741027,0.00042499608,0.00009602784,0.0000036977954],"category_scores_gemma":[0.000105866246,0.00007266288,0.00006981165,0.00009004677,0.00018492117,0.000021778216,0.00017745845,0.00013658252,0.00003351178],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023923325,0.0004869735,0.022521414,0.00058579387,0.0012925154,4.1199183e-7,0.026072958,0.0019311995,0.8332724,0.010177078,0.054374028,0.049046014],"study_design_scores_gemma":[0.0012119055,0.0006633772,0.01780897,0.00014546771,0.00022615987,0.00007411512,0.016276179,0.14605966,0.67087585,0.0007037518,0.14469224,0.0012623256],"about_ca_topic_score_codex":0.000003827504,"about_ca_topic_score_gemma":0.0000112020125,"teacher_disagreement_score":0.16239654,"about_ca_system_score_codex":0.000011282357,"about_ca_system_score_gemma":0.000026165111,"threshold_uncertainty_score":0.2963106},"labels":[],"label_agreement":null},{"id":"W2101793150","doi":"10.1093/bioinformatics/btn208","title":"Cytoscape ESP: simple search of complex biological networks","year":2008,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"U.S. National Library of Medicine; National Institute on Drug Abuse; National Institutes of Health; Genome Canada; Ontario Genomics; Israel Science Foundation; National Institute of General Medical Sciences; Ontario Genomics Institute","keywords":"Plug-in; Computer science; Biological network; Visualization; Software; Simple (philosophy); Syntax; Data mining; Information retrieval; Theoretical computer science; Programming language; Computational biology; Artificial intelligence; Biology","score_opus":0.03854118255699446,"score_gpt":0.25912986841015606,"score_spread":0.2205886858531616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2101793150","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82995456,0.00048882794,0.15554744,0.00006413086,0.00020688068,0.00048031102,0.00009492616,0.000045649955,0.013117286],"genre_scores_gemma":[0.9841359,0.0005849829,0.01388993,0.00044905482,0.00020003784,0.000006199511,0.00057625334,0.000016082133,0.00014154379],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986187,0.000029618828,0.00063264027,0.00013556077,0.00017736873,0.00040610813],"domain_scores_gemma":[0.99908066,0.000024799003,0.00018727349,0.00045354138,0.00011865226,0.00013506706],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025317044,0.00020005656,0.00027241817,0.000054951735,0.00015041362,0.000015000436,0.00034840003,0.0002753988,0.00006816085],"category_scores_gemma":[0.00003007547,0.00016597788,0.00014970839,0.00015449822,0.00028965547,0.000008663825,0.00026678076,0.00014385406,0.000033174594],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017885714,0.0015011909,0.10921177,0.0010692683,0.0016094551,0.000047564547,0.0054042963,0.08372515,0.14052126,0.009761403,0.4809951,0.16436496],"study_design_scores_gemma":[0.003927999,0.0027265954,0.037180208,0.000057123783,0.000058492024,0.00056345447,0.0012649815,0.69826037,0.024452614,0.00035002278,0.22936325,0.0017949138],"about_ca_topic_score_codex":0.000009012248,"about_ca_topic_score_gemma":0.000004375758,"teacher_disagreement_score":0.6145352,"about_ca_system_score_codex":0.000011483946,"about_ca_system_score_gemma":0.000077084056,"threshold_uncertainty_score":0.67683816},"labels":[],"label_agreement":null},{"id":"W2101963711","doi":"10.1093/bioinformatics/18.suppl_1.s303","title":"Multiple genome rearrangement: a general approach via the evolutionary genome graph","year":2002,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Genome; Phylogenetic tree; Graph; Set (abstract data type); Computer science; Theoretical computer science; Biology; Computational biology; Evolutionary biology; Gene; Genetics","score_opus":0.015668192281693593,"score_gpt":0.2004549549426579,"score_spread":0.1847867626609643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2101963711","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6182411,0.019350193,0.2629491,0.0012480028,0.0010874228,0.004996834,0.000572151,0.00032929968,0.09122593],"genre_scores_gemma":[0.8457707,0.0024233605,0.13786817,0.0015346202,0.0014868893,0.00032377985,0.00206393,0.00012049107,0.008408065],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99851626,0.000045707126,0.00041068226,0.00023959135,0.00031924603,0.00046851605],"domain_scores_gemma":[0.99892074,0.00000874833,0.00015182457,0.00071512896,0.00008722072,0.00011635698],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022799533,0.000257473,0.00016711756,0.00009071006,0.0002704993,0.000056521763,0.00050044205,0.00014831129,0.00012372533],"category_scores_gemma":[0.000026258605,0.00019629255,0.0001696185,0.00023015622,0.00014512481,0.0000157088,0.00023450468,0.00013199457,0.00025069172],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002384051,0.002118013,0.008471968,0.0010066184,0.0026499133,0.000022418339,0.011049992,0.015744483,0.8510019,0.0007810065,0.068036094,0.038879193],"study_design_scores_gemma":[0.003172499,0.0006342842,0.026548844,0.000011818769,0.0001654095,0.00022930674,0.0010005381,0.23859705,0.0015672529,0.00018653665,0.7264309,0.0014555819],"about_ca_topic_score_codex":0.000010069083,"about_ca_topic_score_gemma":0.0000029145185,"teacher_disagreement_score":0.8494346,"about_ca_system_score_codex":0.000038317663,"about_ca_system_score_gemma":0.00001734444,"threshold_uncertainty_score":0.8004578},"labels":[],"label_agreement":null},{"id":"W2102039892","doi":"10.1093/bioinformatics/btn163","title":"Biomolecular network motif counting and discovery by color coding","year":2008,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":218,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Color-coding; Computer science; Combinatorics; Bounded function; Mathematics; Biology; Theoretical computer science","score_opus":0.007867447708500175,"score_gpt":0.2044838500234672,"score_spread":0.19661640231496702,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102039892","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7403194,0.0026724483,0.24777783,0.00016323714,0.00048774236,0.0005082071,0.000109548615,0.00005663652,0.007904944],"genre_scores_gemma":[0.979406,0.0014843998,0.016051523,0.0014192641,0.00033346217,0.000013149975,0.00040504878,0.000033674798,0.00085347745],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99881774,0.000015240435,0.00043904153,0.0001560436,0.00015574896,0.00041617182],"domain_scores_gemma":[0.9993392,0.000017038961,0.00019380936,0.00028632733,0.000048543003,0.00011504416],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002304244,0.00021450459,0.00019757135,0.000029336152,0.00031254397,0.0001156688,0.00017290251,0.00019180284,0.00000484361],"category_scores_gemma":[0.00003205046,0.00019921476,0.00007009466,0.000109841676,0.00017447429,0.000030775933,0.00020952435,0.00010971623,0.000015943539],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003379367,0.00024957102,0.020148037,0.0008112446,0.00084333395,0.000039494906,0.0026420734,0.0030268065,0.14253268,0.0080466885,0.796629,0.024693124],"study_design_scores_gemma":[0.0043595503,0.0011736021,0.0025049408,0.0002277443,0.00016036694,0.0010297882,0.0012643879,0.24675699,0.028243937,0.0005749067,0.7109486,0.0027551753],"about_ca_topic_score_codex":0.0000071412824,"about_ca_topic_score_gemma":0.000002739672,"teacher_disagreement_score":0.24373017,"about_ca_system_score_codex":0.000014937559,"about_ca_system_score_gemma":0.00005748391,"threshold_uncertainty_score":0.8123742},"labels":[],"label_agreement":null},{"id":"W2102057828","doi":"10.1093/bioinformatics/btm032","title":"NetMatch: a Cytoscape plugin for searching biological networks","year":2007,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":83,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Ministero dell’Istruzione, dell’Università e della Ricerca","keywords":"Plug-in; Computer science; Biological network; Software; Data mining; Computational biology; Programming language; Biology","score_opus":0.021569911012977377,"score_gpt":0.26628448893634754,"score_spread":0.24471457792337017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102057828","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07752203,0.0003548479,0.91529214,0.00007875937,0.00039435652,0.0006093186,0.0000338982,0.000048261638,0.005666354],"genre_scores_gemma":[0.88336873,0.00026349985,0.11209038,0.0018973133,0.0011545265,0.00003554031,0.0007177661,0.00004355902,0.0004286983],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983498,0.0000143401585,0.00062510284,0.00017633142,0.00013483295,0.0006996297],"domain_scores_gemma":[0.99906677,0.00007299917,0.00019300527,0.00037946753,0.00008969935,0.0001980438],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011174813,0.0002369132,0.00021693128,0.00006848539,0.00019978869,0.00007504722,0.0003311432,0.00035319047,0.000011986714],"category_scores_gemma":[0.000083396604,0.00019860959,0.00017637656,0.0001229581,0.00010338069,0.000011470704,0.00018889128,0.0001707549,0.000022778962],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002668321,0.0005221537,0.007533985,0.000777549,0.000928506,0.000015226369,0.0031515085,0.019642826,0.035252906,0.024789952,0.15785675,0.7468603],"study_design_scores_gemma":[0.0036068927,0.0017726345,0.0027588087,0.00008678801,0.00006188521,0.00014422064,0.0018181775,0.4540203,0.008898874,0.0014963117,0.523721,0.001614132],"about_ca_topic_score_codex":0.0000030299375,"about_ca_topic_score_gemma":0.000015175313,"teacher_disagreement_score":0.8058467,"about_ca_system_score_codex":0.000022410348,"about_ca_system_score_gemma":0.000054731405,"threshold_uncertainty_score":0.80990636},"labels":[],"label_agreement":null},{"id":"W2102089979","doi":"10.1093/bioinformatics/btu453","title":"Effects of small particle numbers on long-term behaviour in discrete biochemical systems","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Microtubule and mitosis dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Deutsche Forschungsgemeinschaft","keywords":"Markup language; Computer science; Term (time); Theoretical computer science; Extension (predicate logic); Systems biology; Computational biology; Biology; XML; Programming language; World Wide Web; Physics","score_opus":0.005476390262512516,"score_gpt":0.22310761737710239,"score_spread":0.21763122711458988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102089979","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99446833,0.0001250643,0.0046046223,0.000010916518,0.0001200121,0.00026260238,0.000010152159,0.000009104822,0.000389189],"genre_scores_gemma":[0.9987503,0.00006104697,0.0008413289,0.00008945285,0.000052930965,0.00001913774,0.00007986354,0.000014102639,0.000091806854],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99917626,0.000032204865,0.0003453298,0.00012419804,0.00009686738,0.00022514389],"domain_scores_gemma":[0.99946916,0.000024798714,0.000120793375,0.0002822749,0.000029795918,0.000073170086],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013436902,0.00013742856,0.00017461613,0.0000337641,0.00001949667,0.000017808165,0.00016483305,0.00015606654,0.0000011705749],"category_scores_gemma":[0.000068589776,0.00012232414,0.00007002107,0.00006590698,0.00005334649,0.00000426944,0.0000716229,0.00007519122,0.000013615782],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016867547,0.000405228,0.15946355,0.0015169102,0.00007453189,0.0000050846743,0.00036381255,0.0002630293,0.8336154,0.0013159319,0.00082144793,0.0019863693],"study_design_scores_gemma":[0.001655927,0.0005990006,0.042858154,0.00026874265,0.00004718494,0.00001316601,0.00007505685,0.0076992456,0.9460918,0.000009505181,0.00031765844,0.00036461093],"about_ca_topic_score_codex":0.000027716498,"about_ca_topic_score_gemma":0.000023550914,"teacher_disagreement_score":0.11660541,"about_ca_system_score_codex":0.000014630258,"about_ca_system_score_gemma":0.000020212245,"threshold_uncertainty_score":0.49882337},"labels":[],"label_agreement":null},{"id":"W2102610257","doi":"10.1093/bioinformatics/bts272","title":"BreakFusion: targeted assembly-based identification of gene fusions in whole transcriptome paired-end sequencing data","year":2012,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"National Cancer Institute; National Human Genome Research Institute; BC Cancer Agency","keywords":"Scalability; Computational biology; Sequence assembly; Computer science; Transcriptome; Software; Genome; Identification (biology); DNA sequencing; R package; Data mining; Gene; Biology; Genetics; Gene expression; Database; Computational science","score_opus":0.0369776133322311,"score_gpt":0.2615952537368206,"score_spread":0.22461764040458948,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102610257","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99078345,0.0012853554,0.0066056624,0.00010753963,0.00023963732,0.00021446444,0.00046257087,0.0000052477426,0.0002960958],"genre_scores_gemma":[0.9880911,0.00009910757,0.01063152,0.000109986715,0.00008186507,0.000009716304,0.00092077156,0.000012297554,0.000043623433],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99890697,0.00003020825,0.0005313655,0.00013562402,0.00014435808,0.0002514834],"domain_scores_gemma":[0.9990107,0.0000140427865,0.00018451881,0.0006546871,0.00006771961,0.0000683642],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004875652,0.00013108633,0.00015922869,0.00007595758,0.00006737304,0.000013588687,0.00031530065,0.00010795241,0.000008397601],"category_scores_gemma":[0.00006528596,0.00012451493,0.00004959613,0.00014424913,0.00005627379,0.0000081153885,0.00012122569,0.000053924716,0.0000097152715],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012972367,0.00005625802,0.004525201,0.000059705417,0.000023693443,1.9891198e-7,0.00052950456,0.0002299899,0.9922549,0.00001547269,0.0005445337,0.0017475404],"study_design_scores_gemma":[0.0010519432,0.00013107875,0.07735978,0.000040625615,0.0000685406,0.000010615824,0.0015575872,0.025756285,0.8747885,0.000020329191,0.018780027,0.00043467138],"about_ca_topic_score_codex":0.000029460976,"about_ca_topic_score_gemma":0.000032533728,"teacher_disagreement_score":0.11746641,"about_ca_system_score_codex":0.000020619902,"about_ca_system_score_gemma":0.00010825251,"threshold_uncertainty_score":0.5077571},"labels":[],"label_agreement":null},{"id":"W2102803266","doi":"10.1093/bioinformatics/19.2.234","title":"A naive Bayes model to predict coupling between seventransmembrane domain receptors and G-proteins","year":2003,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"AstraZeneca (Canada)","funders":"","keywords":"G protein-coupled receptor; Computational biology; Protein sequencing; Bayesian probability; Transmembrane domain; Bayes' theorem; Computer science; Coupling (piping); Biology; Artificial intelligence; Bioinformatics; Machine learning; Peptide sequence; Genetics; Receptor; Gene","score_opus":0.009458093025253722,"score_gpt":0.24074601573063606,"score_spread":0.23128792270538234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102803266","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6277033,0.00009885011,0.36576155,0.00014462018,0.00011162338,0.00064679724,0.00006628614,0.000058555597,0.005408431],"genre_scores_gemma":[0.6745535,0.00011361017,0.32398358,0.00049786887,0.00010648291,0.00003606398,0.00019699399,0.000045244462,0.00046662154],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99858254,0.000026173277,0.00053699105,0.00018916825,0.00025676537,0.00040836798],"domain_scores_gemma":[0.9991028,0.000025808917,0.00015474945,0.0003810752,0.000073116025,0.00026246638],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000501222,0.00026884553,0.0002453655,0.00009573963,0.00017009402,0.00006984505,0.00021377465,0.00022268853,0.000016889146],"category_scores_gemma":[0.00025709646,0.0002503296,0.00007321784,0.00014668083,0.00007832525,0.000020230744,0.000105887564,0.00018621367,0.000031509902],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013028372,0.00077365374,0.18576461,0.008429826,0.0028235377,0.000018411438,0.055137996,0.48412466,0.11602529,0.025880694,0.054735724,0.06498275],"study_design_scores_gemma":[0.0050346334,0.0028327038,0.002140855,0.00044694886,0.00023610737,0.00013531551,0.0035998821,0.6761442,0.086351044,0.0016157134,0.21842583,0.0030368126],"about_ca_topic_score_codex":0.0000039907072,"about_ca_topic_score_gemma":0.000004817766,"teacher_disagreement_score":0.19201949,"about_ca_system_score_codex":0.000024159763,"about_ca_system_score_gemma":0.00010524393,"threshold_uncertainty_score":0.9999949},"labels":[],"label_agreement":null},{"id":"W2103006829","doi":"10.1093/bioinformatics/btq122","title":"LOTUS, a new domain associated with small RNA pathways in the germline","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Chromosomal and Genetic Variations","field":"Agricultural and Biological Sciences","cited_by":79,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Multidisciplinary University Research Initiative; Institute of Cancer Research; Université Pierre et Marie Curie; Institut National Du Cancer; Centre National de la Recherche Scientifique","keywords":"Piwi-interacting RNA; Biology; Germline; Argonaute; Genetics; Germ plasm; Lotus japonicus; Lotus; RasiRNA; RNA interference; RNA-binding protein; Germ cell; RNA; Computational biology; Cell biology; Gene; Embryo; Mutant; Botany","score_opus":0.02410917086021114,"score_gpt":0.19432815445272086,"score_spread":0.17021898359250973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103006829","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9942996,0.000008123548,0.00003615387,0.0020953903,0.000078221405,0.00018071952,0.000034370172,0.00003099554,0.0032364395],"genre_scores_gemma":[0.9944575,0.0000054874977,0.004377321,0.0006715391,0.0001692051,0.000008708038,0.000113313305,6.248476e-7,0.00019631146],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99938786,0.000019606347,0.00019787862,0.000063844294,0.00014781361,0.0001829937],"domain_scores_gemma":[0.99962246,0.0001447349,0.00008639083,0.00006205506,0.000026892738,0.00005748318],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022513008,0.00008774591,0.00008655539,0.000007736115,0.00010992536,0.00007041587,0.00023799573,0.00007508963,0.00013280762],"category_scores_gemma":[0.00006595105,0.000023844408,0.000033476943,0.00031919352,0.000029820727,0.000059992537,0.000028064413,0.0001567654,0.00003675302],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011475926,0.0016864521,0.049741827,0.000045203025,0.00013635466,0.00005275447,0.03328378,0.00009859147,0.2971673,0.038374525,0.01082517,0.5684733],"study_design_scores_gemma":[0.00092464103,0.0005504637,0.9436628,0.000047693302,0.000024115387,0.000040590035,0.0022501796,0.0021874823,0.00075553224,0.0073529505,0.041779518,0.0004240307],"about_ca_topic_score_codex":0.00014177435,"about_ca_topic_score_gemma":0.0129951,"teacher_disagreement_score":0.89392096,"about_ca_system_score_codex":0.0000075522485,"about_ca_system_score_gemma":0.000023576464,"threshold_uncertainty_score":0.7251571},"labels":[],"label_agreement":null},{"id":"W2103145565","doi":"10.1093/bioinformatics/btt308","title":"Identification of deleterious synonymous variants in human genomes","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":91,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"","keywords":"Biology; Identification (biology); Genome; In silico; Genetics; Computational biology; Genomics; Prioritization; Mutation; Human genome; 1000 Genomes Project; Single-nucleotide polymorphism; Gene; Genotype","score_opus":0.006778232057257463,"score_gpt":0.2260188908531121,"score_spread":0.21924065879585464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103145565","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9982492,0.00023324964,0.00057751895,0.000013208498,0.00004980342,0.0001841612,0.00002251732,0.0000041595877,0.0006661893],"genre_scores_gemma":[0.998896,0.00010518107,0.00066044607,0.000060478218,0.000023657047,0.000015356649,0.000097938144,0.0000071949426,0.0001337709],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993795,0.000008987597,0.00035950923,0.00007270813,0.0000606019,0.00011869691],"domain_scores_gemma":[0.9995458,0.0000026096648,0.00013316353,0.00022317882,0.00005787276,0.000037361],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000691941,0.00007187679,0.000087208464,0.00005349939,0.000027768343,0.000023570423,0.00013363553,0.00006247761,0.000020024307],"category_scores_gemma":[0.000018300963,0.000066903034,0.00003944182,0.000048642964,0.000032196473,0.00000690992,0.0000540865,0.000022711129,0.000027058903],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008835675,0.00011352662,0.004225999,0.00017072987,0.00003422086,0.0000018197716,0.00039557475,0.00013730199,0.98374283,0.00021150307,0.0010781843,0.009879496],"study_design_scores_gemma":[0.0036487323,0.0010584779,0.36851588,0.00012899404,0.00009467005,0.00011714822,0.003373107,0.02185319,0.5896655,0.0021820003,0.007733431,0.0016288948],"about_ca_topic_score_codex":0.000030457159,"about_ca_topic_score_gemma":0.000008469939,"teacher_disagreement_score":0.39407733,"about_ca_system_score_codex":0.000007740326,"about_ca_system_score_gemma":0.00002973719,"threshold_uncertainty_score":0.27282265},"labels":[],"label_agreement":null},{"id":"W2103173634","doi":"10.1093/bioinformatics/btl497","title":"Cell++—simulating biochemical pathways","year":2006,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":55,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Hospital for Sick Children","keywords":"Computer science; Computational biology; Biology","score_opus":0.007429909915520843,"score_gpt":0.20236138685553787,"score_spread":0.19493147694001703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103173634","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9760568,0.0007981959,0.011893315,0.000019930223,0.000079603284,0.0001057301,0.000011829677,0.000037776656,0.010996831],"genre_scores_gemma":[0.9833036,0.00001640642,0.0153595405,0.00010740385,0.00035445398,0.0000050061044,0.000284661,0.000018753415,0.0005501716],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99904585,0.0000144286805,0.0003549279,0.00014709788,0.00016243663,0.00027524354],"domain_scores_gemma":[0.9993628,0.000007886086,0.00013051853,0.00037395695,0.00005877712,0.000066013374],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011808752,0.00015710044,0.00013250494,0.000045009972,0.00008515285,0.00003338723,0.00016883,0.00015532094,0.000018291716],"category_scores_gemma":[0.000017041719,0.00014942304,0.00013490955,0.00013778303,0.000048235856,0.000004376698,0.00010936033,0.000058318743,0.000060728413],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034534627,0.00019003177,0.012175158,0.0001654038,0.0000965807,0.0000044774415,0.00011989215,0.034028582,0.80246115,0.00038629016,0.14607711,0.004260782],"study_design_scores_gemma":[0.0011696144,0.00017684494,0.0026325595,0.00002324248,0.00010762881,0.000025026427,0.00029335238,0.14739135,0.78162324,0.00032314367,0.065322824,0.0009111813],"about_ca_topic_score_codex":0.0000061347105,"about_ca_topic_score_gemma":0.0000022874624,"teacher_disagreement_score":0.11336276,"about_ca_system_score_codex":0.000014898462,"about_ca_system_score_gemma":0.000042107786,"threshold_uncertainty_score":0.6093295},"labels":[],"label_agreement":null},{"id":"W2103365019","doi":"10.1093/bioinformatics/btq271","title":"SLIMS—a user-friendly sample operations and inventory management system for genotyping labs","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Canadian Institutes of Health Research","keywords":"Computer science; User Friendly; Database; Java; Personalization; Interface (matter); Sample (material); Documentation; Source code; World Wide Web; User interface; Operating system","score_opus":0.013319885421856857,"score_gpt":0.2546115274215406,"score_spread":0.24129164199968373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103365019","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.541639,0.00044568532,0.45221147,0.00032628493,0.0012220308,0.0009045449,0.00020846412,0.00013561253,0.0029069688],"genre_scores_gemma":[0.34669983,0.0000920573,0.65161633,0.00032458987,0.00025404306,0.0001113562,0.0002942488,0.00001947661,0.00058806373],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99941814,0.000007582313,0.00021184888,0.00011242837,0.000072749324,0.0001772814],"domain_scores_gemma":[0.9995982,0.00001681138,0.000042427408,0.00022317469,0.0000445695,0.00007479484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019159376,0.00009721658,0.00009525115,0.000036454607,0.00015393112,0.000047697686,0.0001276993,0.00013537843,0.0000032971416],"category_scores_gemma":[0.000099132325,0.00008296433,0.00003672489,0.000039399994,0.0000842195,0.000005413552,0.000111510315,0.00006234247,0.0000057747707],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033437318,0.0003440556,0.00840813,0.0078099263,0.0011420044,0.000009159414,0.0036731448,0.00019638026,0.14462616,0.096653685,0.107705906,0.6290971],"study_design_scores_gemma":[0.0009997841,0.00029222216,0.00077186554,0.00004876973,0.00005504663,0.000023267325,0.0028543225,0.012710469,0.010291271,0.00004670446,0.97158927,0.00031702084],"about_ca_topic_score_codex":0.0000074359987,"about_ca_topic_score_gemma":0.00005586723,"teacher_disagreement_score":0.8638834,"about_ca_system_score_codex":0.0000072475113,"about_ca_system_score_gemma":0.000025602676,"threshold_uncertainty_score":0.3383187},"labels":[],"label_agreement":null},{"id":"W2103991913","doi":"10.1093/bioinformatics/btg030","title":"<i>K</i>-ary clustering with optimal leaf ordering for gene expression data","year":2003,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":118,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University","funders":"Leverhulme Trust; Florida State University; Natural Sciences and Engineering Research Council of Canada; Burroughs Wellcome Fund","keywords":"Cluster analysis; Hierarchical clustering; Computer science; Tree (set theory); Binary tree; Pairwise comparison; Hierarchical clustering of networks; Single-linkage clustering; Robustness (evolution); CURE data clustering algorithm; Data mining; Algorithm; Nearest-neighbor chain algorithm; Correlation clustering; Canopy clustering algorithm; Tree structure; Mathematics; Artificial intelligence; Gene; Biology; Combinatorics; Genetics","score_opus":0.055061850156336696,"score_gpt":0.306350724116407,"score_spread":0.2512888739600703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103991913","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007065247,0.00006439203,0.997188,0.000059173693,0.00017200684,0.00037961258,0.000020383106,0.00018375654,0.0012261719],"genre_scores_gemma":[0.005356442,0.000023571485,0.9941798,0.00009599646,0.00004178732,0.000035050572,0.000029435345,0.000022119955,0.00021582785],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984377,0.000021745238,0.00032238153,0.00030717917,0.00039498022,0.0005159879],"domain_scores_gemma":[0.99793106,0.00011480147,0.00011957916,0.0015556351,0.00010276326,0.00017617413],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004352963,0.00018353196,0.00017630866,0.00010250155,0.0002421556,0.0002511642,0.0015856228,0.000059369202,0.000004228434],"category_scores_gemma":[0.0001802609,0.00014998717,0.000025372663,0.00028300018,0.0000460651,0.0020031044,0.0011331387,0.00014614065,0.000017214143],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033431657,0.00042140874,0.00024060217,0.0027860897,0.00022671043,0.00012384942,0.01016453,0.45759565,0.023364475,0.0051362063,0.0069696447,0.49263653],"study_design_scores_gemma":[0.0007020261,0.00014003713,0.0000068202535,0.00006884495,0.0000034306888,0.00010088073,0.00016140928,0.96436507,0.016518569,0.000049077582,0.017634094,0.00024976765],"about_ca_topic_score_codex":0.0000020007562,"about_ca_topic_score_gemma":0.0000019404933,"teacher_disagreement_score":0.5067694,"about_ca_system_score_codex":0.000051568015,"about_ca_system_score_gemma":0.00015298178,"threshold_uncertainty_score":0.6116299},"labels":[],"label_agreement":null},{"id":"W2104040212","doi":"10.1093/bioinformatics/btg139","title":"GeneComber: combining outputs of gene prediction programs for improved results","year":2003,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of British Columbia Hospital","funders":"","keywords":"Computer science; Interface (matter); Perl; Software; Frame (networking); User interface; Relational database management system; Web application; Database; Information retrieval; Relational database; Data mining; Interoperability; Application programming interface; Programming language; World Wide Web; Operating system","score_opus":0.013806031331283376,"score_gpt":0.22770177500039665,"score_spread":0.21389574366911326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104040212","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.120615736,0.0011734961,0.8373688,0.00015667023,0.0021394412,0.0037420834,0.0012431601,0.00011275733,0.033447858],"genre_scores_gemma":[0.6903929,0.00020796574,0.30536723,0.00029809435,0.00021601754,0.00009666361,0.0026108075,0.0000469116,0.0007633824],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986758,0.000015490406,0.00077603175,0.00013501642,0.00009372863,0.0003038924],"domain_scores_gemma":[0.9989499,0.000016173342,0.00038278068,0.00039940185,0.0001615033,0.000090227615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048201563,0.00017320136,0.00020235915,0.00004476293,0.00008494517,0.00003111382,0.00016135622,0.00021658104,0.000001822285],"category_scores_gemma":[0.00010523766,0.00016016202,0.0001342714,0.00008542251,0.00006304511,0.000011192434,0.00004052182,0.00006791808,0.000003642386],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028880243,0.001669669,0.003337261,0.0026874486,0.0020988795,0.0000013912644,0.007204034,0.0028510436,0.31641954,0.021025306,0.11299842,0.526819],"study_design_scores_gemma":[0.010966383,0.0035251807,0.00034139917,0.00011370925,0.00016980915,0.00006591217,0.0012253051,0.14249308,0.24783145,0.0011994217,0.59104013,0.0010282242],"about_ca_topic_score_codex":0.000002220018,"about_ca_topic_score_gemma":0.0000046508926,"teacher_disagreement_score":0.5697772,"about_ca_system_score_codex":0.000014216892,"about_ca_system_score_gemma":0.000094728966,"threshold_uncertainty_score":0.65312177},"labels":[],"label_agreement":null},{"id":"W2104342875","doi":"10.1093/bioinformatics/btm114","title":"A fast and flexible approach to oligonucleotide probe design for genomes and gene families","year":2007,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University Health Network","funders":"Canadian Institutes of Health Research; National Natural Science Foundation of China","keywords":"Genome; Oligonucleotide; Flexibility (engineering); Computer science; Selection (genetic algorithm); Software; Computational biology; Biology; Gene; DNA sequencing; Gene family; Metagenomics; Data mining; Genetics; Artificial intelligence","score_opus":0.026061594489059897,"score_gpt":0.25945074660245515,"score_spread":0.23338915211339525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104342875","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.050914094,0.00056539587,0.94513166,0.000056623372,0.000044397013,0.00059591455,0.000016608708,0.0000172397,0.0026580493],"genre_scores_gemma":[0.24439487,0.00057829195,0.7530827,0.0007431365,0.000128809,0.00009759864,0.00009851092,0.000021828642,0.00085426326],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994239,0.0000066459165,0.00018908379,0.00013839861,0.00006516307,0.00017678409],"domain_scores_gemma":[0.9996152,0.0000088123215,0.00005678983,0.00016119894,0.000050492945,0.00010750701],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002447837,0.0001026464,0.000088447836,0.00006603926,0.00008489802,0.00003883573,0.00007362691,0.0000760552,5.993662e-7],"category_scores_gemma":[0.000026030202,0.00008890363,0.00002056676,0.00006702193,0.0000395615,0.000006712046,0.000063155196,0.000024117182,0.0000022374968],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033656548,0.00008293906,0.000650551,0.0003402414,0.000056595174,2.2900372e-7,0.0025434867,0.0003841436,0.8015122,0.0010073268,0.010579987,0.18250573],"study_design_scores_gemma":[0.001419323,0.00066110067,0.0063862824,0.000026086176,0.00003745906,0.000034987155,0.0037558253,0.009918317,0.7859944,0.00020325866,0.19100627,0.0005566579],"about_ca_topic_score_codex":0.0000012767823,"about_ca_topic_score_gemma":0.0000010916808,"teacher_disagreement_score":0.19348077,"about_ca_system_score_codex":0.000007652825,"about_ca_system_score_gemma":0.000030470575,"threshold_uncertainty_score":0.3625385},"labels":[],"label_agreement":null},{"id":"W2104398544","doi":"10.1093/bioinformatics/btp368","title":"PhyloBayes 3: a Bayesian software package for phylogenetic reconstruction and molecular dating","year":2009,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1351,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Université de Montréal; Agence Nationale de la Recherche","keywords":"Phylogenetic tree; Bayesian probability; Variety (cybernetics); Molecular clock; Probabilistic logic; Computer science; Software; Software package; Computational biology; Phylogenetics; Parametric statistics; Evolutionary biology; Biology; Data mining; Artificial intelligence; Genetics; Mathematics; Statistics; Programming language; Gene","score_opus":0.00846319551486009,"score_gpt":0.2270831567231505,"score_spread":0.21861996120829041,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104398544","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82788485,0.0014514455,0.16884555,0.0001409481,0.00016810853,0.0004883913,0.00009432004,0.000013786231,0.0009126104],"genre_scores_gemma":[0.8406689,0.00023954526,0.15835992,0.00049738464,0.00010790018,0.000018235616,0.000058703994,0.000013355096,0.00003606186],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992264,0.000011794816,0.0002699596,0.00018126272,0.00007057888,0.00023999796],"domain_scores_gemma":[0.9994782,0.000013582466,0.00011804954,0.00024492803,0.000072882234,0.000072340714],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010716475,0.00017054446,0.00015282279,0.000038858885,0.0001384132,0.00004581942,0.000106071086,0.00010460477,0.0000024734304],"category_scores_gemma":[0.00010710544,0.00016476958,0.00006925699,0.000050985574,0.00005688396,0.0000023143434,0.00005344352,0.00003908982,0.0000014376297],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054862016,0.000036699752,0.003244672,0.00012721539,0.00011070199,9.3346847e-7,0.00029862893,0.00006501803,0.6279398,0.00041784954,0.0011370048,0.36656663],"study_design_scores_gemma":[0.006247352,0.0056012305,0.04042868,0.0002273219,0.00039835135,0.00047555036,0.0029100375,0.016470652,0.8599095,0.015597506,0.04867041,0.0030634364],"about_ca_topic_score_codex":0.0000012489767,"about_ca_topic_score_gemma":0.0000024580067,"teacher_disagreement_score":0.3635032,"about_ca_system_score_codex":0.0000075784396,"about_ca_system_score_gemma":0.000030518106,"threshold_uncertainty_score":0.6719108},"labels":[],"label_agreement":null},{"id":"W2104474107","doi":"10.1093/bioinformatics/17.2.198","title":"COMBOSA3D: combining sequence alignments with three-dimensional structures","year":2001,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Documentation; Sequence (biology); Computer science; Source code; Code (set theory); Sequence alignment; Multiple sequence alignment; Scheme (mathematics); Information retrieval; Data mining; Programming language; Peptide sequence; Biology; Mathematics; Genetics; Set (abstract data type)","score_opus":0.020790341318182227,"score_gpt":0.24309067341316407,"score_spread":0.22230033209498185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104474107","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9954845,0.00024248274,0.0013844412,0.000059606635,0.00011148359,0.00014399082,0.000025925772,0.0000066256757,0.0025409549],"genre_scores_gemma":[0.98441255,0.00006710137,0.0147981085,0.00046597735,0.000060156486,0.000007645166,0.00006871896,0.000013004227,0.00010672775],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99928635,0.00000793445,0.00019721595,0.00012632756,0.00015764742,0.00022454263],"domain_scores_gemma":[0.99952453,0.000007990048,0.00009411954,0.000245293,0.0000617213,0.000066353816],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006653201,0.0001532139,0.0001234497,0.000024051611,0.0001296337,0.000026025196,0.00014997862,0.00006788311,0.000011906709],"category_scores_gemma":[0.000010785965,0.000117814634,0.00003540839,0.00005787053,0.00009443076,0.0000017754336,0.00011739015,0.000049376235,0.000011782174],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009721427,0.0003570169,0.46490774,0.0002431355,0.0018043938,0.00006509969,0.0017436076,0.014491577,0.45258918,0.0066775316,0.016671516,0.039477058],"study_design_scores_gemma":[0.016039876,0.0083077485,0.37073663,0.00032839068,0.0004964116,0.0021338824,0.0029550768,0.045667842,0.18876646,0.009399847,0.34937182,0.0057960344],"about_ca_topic_score_codex":0.000015090443,"about_ca_topic_score_gemma":0.00003814938,"teacher_disagreement_score":0.33270028,"about_ca_system_score_codex":0.000009451252,"about_ca_system_score_gemma":0.00004780836,"threshold_uncertainty_score":0.48043415},"labels":[],"label_agreement":null},{"id":"W2104502840","doi":"10.1093/bioinformatics/btu808","title":"Kablammo: an interactive, web-based BLAST results visualizer","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":92,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates; Alberta Innovates - Health Solutions","keywords":"Computer science; MIT License; Visualization; License; Source code; Web application; Code (set theory); Interactive visualization; Sequence (biology); Software; World Wide Web; Programming language; Data mining; Biology; Operating system; Set (abstract data type); Genetics","score_opus":0.010736696061096446,"score_gpt":0.2563567379274806,"score_spread":0.24562004186638414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104502840","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97111833,0.0000665893,0.0056372555,0.00016337463,0.00035107363,0.00020226435,0.000109267145,0.000020827249,0.022330998],"genre_scores_gemma":[0.99009675,0.000035756573,0.008423384,0.00072587637,0.00020607372,0.000011274169,0.00017146608,0.000018815756,0.0003105979],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991089,0.00003909652,0.00033442906,0.00017243419,0.000112358786,0.00023274508],"domain_scores_gemma":[0.99920785,0.000024104715,0.00014298227,0.00042659984,0.00010040034,0.00009808461],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023603595,0.00016955895,0.00014404106,0.000045561057,0.00009572107,0.000045452525,0.00020045208,0.00010274318,0.0000071942827],"category_scores_gemma":[0.00013088569,0.00014956592,0.00007043912,0.00005705174,0.000070079695,0.0000026486648,0.00009603676,0.00005931688,0.00004659344],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020008546,0.00077624293,0.006707342,0.00031212653,0.0004939291,0.0000031800585,0.0024057867,0.004181461,0.8386565,0.0014093244,0.071867846,0.07118545],"study_design_scores_gemma":[0.0032407714,0.0014996746,0.005816473,0.000027319642,0.000036774316,0.000008158995,0.0003924303,0.07408588,0.101256676,0.00008413303,0.81296915,0.00058257504],"about_ca_topic_score_codex":0.0000068322,"about_ca_topic_score_gemma":0.000035680678,"teacher_disagreement_score":0.7411013,"about_ca_system_score_codex":0.000009684645,"about_ca_system_score_gemma":0.000056519846,"threshold_uncertainty_score":0.60991216},"labels":[],"label_agreement":null},{"id":"W2104873783","doi":"10.1093/bioinformatics/btm475","title":"PFRES: protein fold classification by using evolutionary information and predicted secondary structure","year":2007,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":122,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Protein tertiary structure; Protein secondary structure; Computer science; Pseudo amino acid composition; Similarity (geometry); Classifier (UML); Pattern recognition (psychology); Protein Data Bank (RCSB PDB); Fold (higher-order function); Protein superfamily; Protein structure prediction; Representation (politics); Feature vector; Structural Classification of Proteins database; Protein structure; Sequence (biology); Structural alignment; Data mining; Algorithm; Artificial intelligence; Sequence alignment; Biology; Peptide sequence; Amino acid; Genetics","score_opus":0.006359821080226958,"score_gpt":0.23383970742686902,"score_spread":0.22747988634664207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104873783","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9147561,0.00023667625,0.07972391,0.000071910064,0.00016151206,0.00072799844,0.00045017037,0.00008083306,0.0037908962],"genre_scores_gemma":[0.90902483,0.000041729636,0.086719796,0.00051792833,0.00013633909,0.00000827685,0.0033725423,0.000023091447,0.00015544954],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985908,0.00002300433,0.0006936755,0.00011064344,0.00027511528,0.00030673883],"domain_scores_gemma":[0.99900067,0.000014203073,0.00038309474,0.00032061312,0.00015251765,0.00012889368],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029440536,0.00021520966,0.00013775687,0.00012890613,0.00019547003,0.00008329767,0.00017862114,0.0003191696,0.000025299367],"category_scores_gemma":[0.00019808361,0.00020498339,0.00004076739,0.00015942566,0.00011676046,0.000115627736,0.00013101615,0.00023452385,0.000008141166],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008285359,0.00020210126,0.032331817,0.00331084,0.0004787053,0.0000025794357,0.0054949974,0.00082391256,0.57222074,0.0027627198,0.108060375,0.27348268],"study_design_scores_gemma":[0.0030431466,0.0007773762,0.027494166,0.0001712224,0.000087549444,0.0002722591,0.0030118127,0.49539155,0.048070304,0.00023467267,0.42006275,0.0013831853],"about_ca_topic_score_codex":0.000012874647,"about_ca_topic_score_gemma":0.0000066785124,"teacher_disagreement_score":0.52415043,"about_ca_system_score_codex":0.000051655887,"about_ca_system_score_gemma":0.00013148399,"threshold_uncertainty_score":0.835898},"labels":[],"label_agreement":null},{"id":"W2105091000","doi":"10.1093/bioinformatics/btn295","title":"Poisson adjacency distributions in genome comparison: multichromosomal, circular, signed and unsigned cases","year":2008,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Poisson distribution; Phylogenetic tree; Mathematics; Statistics; Limiting; Adjacency list; Similarity (geometry); Chromosome; Probability distribution; Genome; Adjacency matrix; Poisson regression; Biology; Combinatorics; Genetics; Computer science; Artificial intelligence; Population","score_opus":0.02415182833651396,"score_gpt":0.2510118703173962,"score_spread":0.22686004198088222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105091000","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99145263,0.0016033344,0.0057685943,0.00006701178,0.00006704829,0.0003866092,0.000101018944,0.000024586696,0.0005291412],"genre_scores_gemma":[0.9898266,0.00044166934,0.008889754,0.00005265719,0.000055759552,0.00002250957,0.00058791554,0.000015069866,0.00010806752],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99888843,0.000031428826,0.00042091386,0.00018325693,0.00015350894,0.00032244044],"domain_scores_gemma":[0.99938494,0.000017742577,0.00011241112,0.0002994123,0.00006532556,0.000120179015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000109082466,0.00019118964,0.00021895385,0.00007870338,0.00014675931,0.000024455094,0.00014318862,0.00014028345,0.000022061604],"category_scores_gemma":[0.00009231289,0.00019120151,0.000056373032,0.00016743648,0.0001321588,0.000013825305,0.00012053358,0.00008272818,0.000030845757],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022308542,0.0014968622,0.14633138,0.00080057763,0.00042179556,0.00035854243,0.006770027,0.0007193899,0.8298768,0.00029393588,0.0047135917,0.007994058],"study_design_scores_gemma":[0.022062525,0.005872791,0.574461,0.0002794324,0.00040216377,0.0042199097,0.008711556,0.054082043,0.2030797,0.0002841307,0.120317414,0.0062273266],"about_ca_topic_score_codex":0.000021198899,"about_ca_topic_score_gemma":0.000021045187,"teacher_disagreement_score":0.6267971,"about_ca_system_score_codex":0.00003503863,"about_ca_system_score_gemma":0.00007470136,"threshold_uncertainty_score":0.7796971},"labels":[],"label_agreement":null},{"id":"W2105187843","doi":"10.1093/bioinformatics/btr288","title":"The role of indirect connections in gene networks in predicting function","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":81,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"National Institute of General Medical Sciences; Canadian Institutes of Health Research; National Institutes of Health; Michael Smith Health Research BC","keywords":"Computer science; Function (biology); Data mining; Code (set theory); Gene regulatory network; Source code; MATLAB; Algorithm; Theoretical computer science; Machine learning; Artificial intelligence; Gene; Gene expression; Programming language; Biology; Genetics","score_opus":0.009714114048023536,"score_gpt":0.1941080902456587,"score_spread":0.18439397619763517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105187843","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9516128,0.0020953505,0.016994389,0.000019560823,0.00055118144,0.0005311675,0.00001507785,0.000019708166,0.028160766],"genre_scores_gemma":[0.9977688,0.00035503597,0.0016684053,0.000048677433,0.00006463718,0.000017844155,0.00003566614,0.000008428719,0.0000324841],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999079,0.00002235684,0.0005233896,0.00007151764,0.000071292685,0.00023245167],"domain_scores_gemma":[0.999477,0.000022366627,0.00019144201,0.00023783605,0.00003659297,0.00003471758],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043204761,0.00010107178,0.00011617635,0.00006502733,0.00007107628,0.00001368153,0.00015526937,0.0001531531,0.000004799269],"category_scores_gemma":[0.00003740057,0.000079795995,0.000047831105,0.00017643323,0.00006157187,0.0000106606685,0.0000833914,0.00013260932,0.0000029657006],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012391127,0.00050481135,0.5326653,0.0001782662,0.00041319247,0.000003009997,0.012047607,0.023394454,0.009583268,0.009221008,0.0016716355,0.4090783],"study_design_scores_gemma":[0.0023835064,0.0009994899,0.116006255,0.00013698886,0.00005635515,0.000040259594,0.00962021,0.8104594,0.033650845,0.0034941344,0.022414373,0.00073821965],"about_ca_topic_score_codex":0.000048726142,"about_ca_topic_score_gemma":0.0003720533,"teacher_disagreement_score":0.7870649,"about_ca_system_score_codex":0.000015198734,"about_ca_system_score_gemma":0.00004182501,"threshold_uncertainty_score":0.32539862},"labels":[],"label_agreement":null},{"id":"W2106350001","doi":"10.1093/bioinformatics/bts350","title":"Identifying aberrant pathways through integrated analysis of knowledge in pharmacogenomics","year":2012,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"National Human Genome Research Institute; National Institutes of Health; European Commission","keywords":"Pharmacogenomics; Ontology; Disease; Drug repositioning; Identification (biology); Computational biology; Computer science; Drug discovery; Data science; Bioinformatics; Drug; Biology; Medicine; Pharmacology","score_opus":0.05877106970867121,"score_gpt":0.3227743530747683,"score_spread":0.26400328336609713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106350001","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9777607,0.0017252195,0.017522402,0.000014400011,0.00023150956,0.000078961675,0.000066605804,0.000015918855,0.0025843242],"genre_scores_gemma":[0.98501194,0.00021749172,0.014382368,0.00007055627,0.0000524065,0.0000061469436,0.00019600951,0.000007138209,0.000055949688],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991157,0.00003174055,0.000426995,0.00008313092,0.00008410645,0.0002583385],"domain_scores_gemma":[0.9995785,0.000018856244,0.00013996626,0.00016848682,0.000045363042,0.00004885336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032189526,0.000116369614,0.00024476735,0.00014752723,0.0000330761,0.000008712937,0.00017113175,0.00014876426,0.000017804125],"category_scores_gemma":[0.00005529249,0.00009604007,0.00012345395,0.000523662,0.00010093188,0.000009639918,0.00009981825,0.00008424648,0.000010784083],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002846939,0.0015044722,0.091858886,0.00089201535,0.0041517345,0.000004165803,0.05196844,0.00020689853,0.58802,0.0018544443,0.008950997,0.25030324],"study_design_scores_gemma":[0.0038235537,0.00043621854,0.087575965,0.00015074821,0.001986374,0.000020387386,0.024137285,0.046733394,0.56514674,0.00011952715,0.26832125,0.001548571],"about_ca_topic_score_codex":0.000015938074,"about_ca_topic_score_gemma":0.000019282796,"teacher_disagreement_score":0.25937024,"about_ca_system_score_codex":0.000018055107,"about_ca_system_score_gemma":0.00003787222,"threshold_uncertainty_score":0.39164004},"labels":[],"label_agreement":null},{"id":"W2106415954","doi":"10.1093/bioinformatics/bth257","title":"PUNS: transcriptomic- and genomic-<i>in silico</i> PCR for enhanced primer design","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Molecular Biology Techniques and Applications","field":"Biochemistry, Genetics and Molecular Biology","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"","keywords":"Primer (cosmetics); In silico; UniGene; Computational biology; In silico PCR; Polymerase chain reaction; DNA microarray; Biology; Genetics; Computer science; Genome; Multiplex polymerase chain reaction; Gene; Expressed sequence tag; Chemistry","score_opus":0.014534450628128975,"score_gpt":0.25213249264830595,"score_spread":0.23759804202017698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106415954","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24485283,0.0003033145,0.7533677,0.00018414676,0.000025205412,0.000788456,0.000026226175,0.000020826561,0.00043128637],"genre_scores_gemma":[0.70530456,0.0004735163,0.29275298,0.00090692576,0.000044171324,0.00028079,0.00013738469,0.00002068803,0.00007896737],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993238,0.000010417829,0.0002599231,0.00016264438,0.000036830173,0.00020642749],"domain_scores_gemma":[0.99961823,0.000007997882,0.00006406221,0.00022798496,0.0000308175,0.000050912033],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000149823,0.00013024555,0.00012426918,0.00003819876,0.000056168432,0.000015694879,0.00012822177,0.00016560151,0.0000016513969],"category_scores_gemma":[0.000020548909,0.00012271482,0.000054611086,0.0000507509,0.00006922832,0.0000049113637,0.000034000834,0.00005024474,0.000003646601],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048777805,0.000039255447,0.000034012995,0.000030735388,0.000016904629,1.6739455e-7,0.00013415722,0.00014499712,0.994403,0.0012957214,0.0003046382,0.0035475995],"study_design_scores_gemma":[0.0012058616,0.00029747665,0.0002566256,0.000014902819,0.000015320798,0.000011107099,0.00006792335,0.0004436666,0.9749707,0.0012645205,0.021223003,0.00022889026],"about_ca_topic_score_codex":0.000006452687,"about_ca_topic_score_gemma":0.0000123076625,"teacher_disagreement_score":0.4606147,"about_ca_system_score_codex":0.00001614223,"about_ca_system_score_gemma":0.00006019755,"threshold_uncertainty_score":0.50041646},"labels":[],"label_agreement":null},{"id":"W2106433904","doi":"10.1093/bioinformatics/btt659","title":"Fingerprinting protein structures effectively and efficiently","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; False positive paradox; Rendering (computer graphics); Algorithm; Protein structure; Similarity (geometry); Protein structure prediction; Local structure; Data structure; Artificial intelligence; Pattern recognition (psychology); Image (mathematics); Biology","score_opus":0.003844789569114486,"score_gpt":0.20698742703711143,"score_spread":0.20314263746799693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106433904","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98367834,0.00013702769,0.0132745495,0.00003374312,0.000053888918,0.0005199651,0.0000055301084,0.00002093738,0.0022760287],"genre_scores_gemma":[0.9702426,0.000008195977,0.029304033,0.00017082482,0.00006847468,0.00003330818,0.0000226807,0.000010940999,0.00013889922],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994076,0.000014161643,0.00017385752,0.000119776894,0.00009131673,0.00019331659],"domain_scores_gemma":[0.9995992,0.0000071657587,0.0000836246,0.00018913449,0.000056088506,0.00006478927],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007743004,0.00012973558,0.00009694865,0.000033133212,0.00008757478,0.00007280994,0.000105132814,0.00011288884,0.000010938622],"category_scores_gemma":[0.00009872778,0.00010533795,0.00003325899,0.000049209983,0.00006660219,0.000009736883,0.00013966675,0.000074724856,0.00001675806],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004686688,0.000032241383,0.004452295,0.00047160618,0.000112834554,0.0000015284318,0.00066593144,0.00019387927,0.8044953,0.004340563,0.0013960804,0.18379088],"study_design_scores_gemma":[0.0029251361,0.0013526566,0.11890198,0.00016695935,0.000063233965,0.00018693939,0.00091285974,0.052927487,0.79052716,0.010083349,0.02002063,0.0019315798],"about_ca_topic_score_codex":0.000015509026,"about_ca_topic_score_gemma":0.0000023259602,"teacher_disagreement_score":0.1818593,"about_ca_system_score_codex":0.000006340455,"about_ca_system_score_gemma":0.00002230912,"threshold_uncertainty_score":0.4295557},"labels":[],"label_agreement":null},{"id":"W2106532429","doi":"10.1093/bioinformatics/btm422","title":"Multiple spaced seeds for homology search","year":2007,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":67,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Homology (biology); Exponential function; Heuristic; Algorithm; Computer science; Time complexity; Mathematics; Sensitivity (control systems); Smith–Waterman algorithm; Artificial intelligence; Sequence alignment; Biology; Genetics; Amino acid; Gene; Peptide sequence","score_opus":0.018724202756338102,"score_gpt":0.27138495041828953,"score_spread":0.2526607476619514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106532429","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.58455735,0.0002038807,0.40855637,0.00015232226,0.00034803958,0.0008170143,0.000055441014,0.000038131348,0.005271468],"genre_scores_gemma":[0.8106944,0.00006873452,0.18527806,0.000379498,0.0004279371,0.00003055193,0.00052136095,0.000038201593,0.0025612544],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99910766,0.000008349244,0.00024940446,0.000117999145,0.00011667048,0.00039991725],"domain_scores_gemma":[0.9994282,0.000030490182,0.00005952685,0.00027683174,0.00011043742,0.000094511095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004911626,0.00012151825,0.00011208975,0.00007744926,0.00007788214,0.000018300598,0.0001724899,0.00015392802,0.000011404611],"category_scores_gemma":[0.00008624225,0.000115660216,0.00008173957,0.00008424645,0.000058810696,0.000004307614,0.00009369968,0.000055568773,0.000051391056],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00085182965,0.00042433987,0.033172533,0.0008618591,0.0006207796,0.000011827401,0.0029370084,0.00048000345,0.77379704,0.0012634855,0.033546027,0.1520333],"study_design_scores_gemma":[0.004769404,0.001582113,0.011483536,0.000017558863,0.000055573844,0.000075243086,0.0024110689,0.017145133,0.47027552,0.000106663596,0.49123478,0.000843395],"about_ca_topic_score_codex":0.0000053118533,"about_ca_topic_score_gemma":0.000026321617,"teacher_disagreement_score":0.45768875,"about_ca_system_score_codex":0.000018656088,"about_ca_system_score_gemma":0.000045933786,"threshold_uncertainty_score":0.4716487},"labels":[],"label_agreement":null},{"id":"W2106763642","doi":"10.1093/bioinformatics/17.4.385","title":"PhyloBLAST: facilitating phylogenetic analysis of BLAST results","year":2001,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Phylogenetic tree; Perl; Multiple sequence alignment; The Internet; Sequence (biology); Computer science; Sequence analysis; Sequence alignment; Biology; World Wide Web; Genetics; Peptide sequence","score_opus":0.014662420360273883,"score_gpt":0.24227252337551633,"score_spread":0.22761010301524245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106763642","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98941016,0.00039416616,0.002802379,0.000026259697,0.00007107986,0.00012163294,0.00024827858,0.0000042351926,0.00692182],"genre_scores_gemma":[0.99050057,0.00038428803,0.008579115,0.00008116185,0.00005348769,0.000006539658,0.00012679074,0.000009275038,0.0002587471],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9988477,0.000021253269,0.00056709844,0.00017046735,0.00015261321,0.0002408717],"domain_scores_gemma":[0.99911445,0.00003403643,0.000236547,0.00041644278,0.00013381007,0.00006470596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020011203,0.00016136734,0.0002669659,0.00014959941,0.000070250666,0.000014219551,0.00019442607,0.00008889386,0.0000085029515],"category_scores_gemma":[0.00013411418,0.00014898635,0.00019250212,0.00045746707,0.00009830936,0.0000010794117,0.0001303682,0.00004159742,0.000010100004],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00061027164,0.00029462783,0.07872314,0.00019564228,0.0065197493,0.000004458629,0.006141714,0.043309312,0.80261654,0.00021264885,0.0027073908,0.058664523],"study_design_scores_gemma":[0.006058787,0.0033073975,0.4974138,0.00008612365,0.0033652557,0.000045729306,0.011941411,0.13223858,0.15829958,0.00021888268,0.18457268,0.0024517567],"about_ca_topic_score_codex":0.000016385318,"about_ca_topic_score_gemma":0.000062174666,"teacher_disagreement_score":0.6443169,"about_ca_system_score_codex":0.000007913143,"about_ca_system_score_gemma":0.000034541266,"threshold_uncertainty_score":0.60754865},"labels":[],"label_agreement":null},{"id":"W2106808791","doi":"10.1093/bioinformatics/btn565","title":"Slider—maximum use of probability information for alignment of short sequence reads and SNP detection","year":2008,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; BC Cancer Agency","funders":"Michael Smith Health Research BC","keywords":"Computer science; Sequence (biology); Base (topology); Algorithm; SNP; Slider; Data mining; Mathematics; Genetics; Engineering; Single-nucleotide polymorphism","score_opus":0.06261196664988462,"score_gpt":0.25981289960732773,"score_spread":0.19720093295744312,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106808791","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97972786,0.00006408642,0.019559434,0.0000113061205,0.0000510814,0.00038260792,0.0000983673,0.0000020255957,0.00010325265],"genre_scores_gemma":[0.9706337,0.000368732,0.028874755,0.000035850728,0.00001328484,0.00002148147,0.000040463532,0.0000034530365,0.000008269975],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99936926,0.0000074637223,0.00038350193,0.000060498114,0.000081195154,0.00009808587],"domain_scores_gemma":[0.9994703,0.000016262778,0.00014298514,0.00017665424,0.00016540755,0.000028416536],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012148373,0.0000839212,0.00012650558,0.00002884994,0.000053305837,0.0000057747775,0.0000506488,0.000071216346,3.9865193e-7],"category_scores_gemma":[0.000096489326,0.00007556101,0.000045763492,0.000037312053,0.00011075574,0.000008359315,0.000058892765,0.000018110744,2.3720955e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003309174,0.000109599576,0.029867522,0.0012299184,0.00022531125,1.5564768e-7,0.0033069528,0.0009551921,0.9001717,0.00036643082,0.00063424016,0.06280207],"study_design_scores_gemma":[0.0005934885,0.0010400461,0.026096687,0.000023371493,0.00004647255,0.00002973987,0.0003411435,0.0050131977,0.9488408,0.0004507858,0.017273817,0.00025046282],"about_ca_topic_score_codex":0.000016066888,"about_ca_topic_score_gemma":0.000009081572,"teacher_disagreement_score":0.0625516,"about_ca_system_score_codex":0.000009601854,"about_ca_system_score_gemma":0.000037524183,"threshold_uncertainty_score":0.30812886},"labels":[],"label_agreement":null},{"id":"W2106848411","doi":"10.1093/bioinformatics/btt538","title":"Single assay-wide variance experimental (SAVE) design for high-throughput screening","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University and Génome Québec Innovation Centre","funders":"","keywords":"Replication (statistics); Computer science; Bayes' theorem; Variance (accounting); Throughput; Statistical hypothesis testing; False discovery rate; Design of experiments; Data mining; Statistics; Algorithm; Bayesian probability; Artificial intelligence; Mathematics; Biology","score_opus":0.019963986038961396,"score_gpt":0.26029553693097496,"score_spread":0.24033155089201355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106848411","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01374441,0.00017659801,0.9836994,0.000083220555,0.000035724526,0.00060091494,0.0000054785055,0.00006058796,0.0015936623],"genre_scores_gemma":[0.43267912,0.000020733232,0.5654512,0.0006845837,0.000105693856,0.00013834029,0.0001671238,0.000025078512,0.0007281289],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989902,0.000030993935,0.00036802772,0.00018479815,0.00013440775,0.00029157693],"domain_scores_gemma":[0.9991422,0.00004955202,0.00016948053,0.00043199817,0.00013283103,0.000073888],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025137173,0.00018475587,0.00017594092,0.00004825444,0.00010421127,0.00011549672,0.00024180433,0.00014300356,0.000053935175],"category_scores_gemma":[0.00017097416,0.00017679439,0.000108939945,0.00007988124,0.00006273903,0.000035887566,0.00012838523,0.000052679312,0.00004433851],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034935747,0.00014623339,0.00010863126,0.00004207819,0.00012662649,8.012749e-7,0.00017232512,0.00012645277,0.84875643,0.00013826217,0.13485004,0.015497214],"study_design_scores_gemma":[0.00037654696,0.0003546229,0.00005069226,0.000014474531,0.000025750722,0.000004933757,0.00019281812,0.014183351,0.96200484,0.00013921084,0.022391481,0.00026125825],"about_ca_topic_score_codex":0.0000339202,"about_ca_topic_score_gemma":0.0000020767739,"teacher_disagreement_score":0.41893473,"about_ca_system_score_codex":0.00002645594,"about_ca_system_score_gemma":0.00002999287,"threshold_uncertainty_score":0.7209466},"labels":[],"label_agreement":null},{"id":"W2106855819","doi":"10.1093/bioinformatics/17.6.487","title":"Uniform integration of genome mapping data using intersection graphs","year":2001,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Intersection (aeronautics); Computer science; Contig; Software; Clique; Linkage (software); Data mining; Graph; Set (abstract data type); Data set; Algorithm; Genome; Theoretical computer science; Artificial intelligence; Biology; Mathematics; Genetics; Combinatorics","score_opus":0.03211698764524208,"score_gpt":0.25416274389606996,"score_spread":0.2220457562508279,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106855819","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.799823,0.00004843497,0.19842838,0.000008627533,0.00011714512,0.00009643967,0.00004943899,0.00000720681,0.0014213406],"genre_scores_gemma":[0.949111,0.00022010086,0.049403965,0.00004879272,0.000052734922,0.0000011296332,0.0010984191,0.000011034641,0.000052820866],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993333,0.0000082577435,0.00034534172,0.000103228405,0.00008205879,0.00012781887],"domain_scores_gemma":[0.99919623,0.0000031158272,0.0001995766,0.0004974766,0.00007028421,0.000033318414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016896254,0.00009824262,0.00009968202,0.00007915257,0.000050832172,0.000021955118,0.00027530035,0.000089533205,0.0000074455584],"category_scores_gemma":[0.000028446108,0.00009369981,0.000041122516,0.00012427305,0.0000393311,0.000017468974,0.00020658133,0.000048830523,0.000003289557],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005108814,0.00008070256,0.0018329697,0.00015727048,0.00012986673,0.0000012069261,0.0010003941,0.0028660356,0.97588503,0.00072302134,0.00024640196,0.017026037],"study_design_scores_gemma":[0.00055890746,0.00020678077,0.002403742,0.000060134807,0.000040375133,0.00011840852,0.0035990889,0.9725983,0.010605217,0.000340321,0.009122504,0.00034623418],"about_ca_topic_score_codex":0.000024242598,"about_ca_topic_score_gemma":0.000039484203,"teacher_disagreement_score":0.9697322,"about_ca_system_score_codex":0.000022008106,"about_ca_system_score_gemma":0.00004488652,"threshold_uncertainty_score":0.38209674},"labels":[],"label_agreement":null},{"id":"W2107141268","doi":"10.1093/bioinformatics/btn381","title":"Multi-dimensional classification of biomedical text: Toward automated, practical provision of high-utility text to diverse users","year":2008,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":134,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Computer science; Categorization; Annotation; Sentence; Information retrieval; Task (project management); Variety (cybernetics); Artificial intelligence; Information extraction; Natural language processing; Focus (optics)","score_opus":0.05631967128910629,"score_gpt":0.3222240203340662,"score_spread":0.2659043490449599,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107141268","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97775584,0.000042069663,0.020929322,0.0005631018,0.00019298967,0.00026196492,0.00010353951,0.000065946675,0.0000852286],"genre_scores_gemma":[0.8155844,0.000026627762,0.18404311,0.000103946855,0.000029852594,0.0000063307866,0.00015147953,0.0000070487163,0.00004715193],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99854374,0.000047607336,0.000602001,0.00018832946,0.000397725,0.00022058962],"domain_scores_gemma":[0.998969,0.00005985909,0.00025923993,0.00034415143,0.00018911644,0.00017858895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029429267,0.00014795034,0.0002567589,0.000096039556,0.000066070155,0.0000049968417,0.00019202425,0.00031487562,0.000023735598],"category_scores_gemma":[0.0010193741,0.00011631675,0.00008715648,0.00019624732,0.0005531384,0.000010737838,0.00020804034,0.00010562084,0.000031550408],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017773821,0.0035180752,0.017679846,0.001177802,0.00038865887,0.000030619703,0.004495988,0.000114402384,0.67434675,0.00031049998,0.16969942,0.12646057],"study_design_scores_gemma":[0.006448968,0.0052807033,0.48960584,0.00031832018,0.0001778205,0.00031430298,0.0049037077,0.21255389,0.19623587,0.00004060416,0.082877055,0.0012429169],"about_ca_topic_score_codex":0.000036937054,"about_ca_topic_score_gemma":0.000004413275,"teacher_disagreement_score":0.47811088,"about_ca_system_score_codex":0.00001736057,"about_ca_system_score_gemma":0.00024370705,"threshold_uncertainty_score":0.47432593},"labels":[],"label_agreement":null},{"id":"W2107249189","doi":"10.1093/bioinformatics/btq430","title":"Cytoscape Web: an interactive web-based network browser","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":746,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Institutes of Health; National Institute of General Medical Sciences; Ontario Genomics Institute; Ontario Genomics; Genome Canada; University of Michigan; University of Toronto; Memorial Sloan-Kettering Cancer Center","keywords":"Computer science; JavaScript; World Wide Web; Web application; Web page; ActionScript; Visualization; Information retrieval; Data mining","score_opus":0.00650414083413331,"score_gpt":0.22936811716642294,"score_spread":0.22286397633228963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107249189","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92011815,0.00014206824,0.025379226,0.00039234216,0.0033663278,0.00086769706,0.00016296055,0.00020332981,0.049367893],"genre_scores_gemma":[0.951735,0.000036300855,0.043429445,0.002485919,0.0012031674,0.000027615524,0.0006026601,0.00004586436,0.00043399495],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99856836,0.000025909492,0.0005284565,0.00019226209,0.00018152765,0.00050351693],"domain_scores_gemma":[0.99859613,0.00002340388,0.000257682,0.00075197086,0.00012977759,0.00024103773],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003629441,0.00028535814,0.00021452225,0.000060425642,0.0001727416,0.00012872671,0.00044293815,0.00037172466,0.00012626214],"category_scores_gemma":[0.000044647386,0.00025720394,0.0001367136,0.00013859184,0.00012291041,0.000033648244,0.00015293984,0.00038405295,0.00014439297],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012809368,0.00086998305,0.009627581,0.0004659648,0.00064894476,0.000014969111,0.0015352456,0.01433536,0.35274807,0.005701444,0.48585615,0.12691537],"study_design_scores_gemma":[0.0018501928,0.0005408791,0.00072575355,0.000031749085,0.000044248987,0.000042530617,0.00023943676,0.45435438,0.008225552,0.00026867597,0.5329311,0.0007455387],"about_ca_topic_score_codex":0.0000038754997,"about_ca_topic_score_gemma":0.00017046327,"teacher_disagreement_score":0.440019,"about_ca_system_score_codex":0.0000128922,"about_ca_system_score_gemma":0.0002543734,"threshold_uncertainty_score":0.999988},"labels":[],"label_agreement":null},{"id":"W2107279733","doi":"10.1093/bioinformatics/btl415","title":"Nemo: an evolutionary and population genetics programming framework","year":2006,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Evolution and Genetic Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":196,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Computer science; Executable; Population; Coalescent theory; Variety (cybernetics); Genetic programming; Programming language; Flexibility (engineering); Context (archaeology); Theoretical computer science; Biology; Machine learning; Artificial intelligence; Genetics; Phylogenetics","score_opus":0.005687145129834929,"score_gpt":0.24141533977967328,"score_spread":0.23572819464983835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107279733","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88769835,0.0010171944,0.1097037,0.000070119335,0.00015847715,0.00025725007,0.000023369566,0.00005208321,0.001019485],"genre_scores_gemma":[0.719409,0.000091487236,0.27911797,0.00015102411,0.00022983397,0.000007629249,0.0007725717,0.000015094212,0.00020539894],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9992358,0.000018851602,0.00027092383,0.00013948741,0.00013198581,0.00020293001],"domain_scores_gemma":[0.99951154,0.0000056150225,0.00009103178,0.00025542817,0.000059337977,0.00007703961],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000090200505,0.00012711645,0.00008530019,0.00004247401,0.00012474546,0.000057741225,0.00009204807,0.00018738105,0.0000056206677],"category_scores_gemma":[0.000026816257,0.00012891076,0.000033994602,0.000079945705,0.00006421305,0.0000104716055,0.00006801028,0.00006628957,0.0000071487166],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020593744,0.00085042167,0.6181284,0.00053456664,0.00015017352,0.0000059037025,0.0008057597,0.027359057,0.015915686,0.040211856,0.013747659,0.28208455],"study_design_scores_gemma":[0.00096922903,0.00081936264,0.5726754,0.00004807247,0.00006543921,0.00013103477,0.0005415883,0.3195554,0.00076258293,0.0067536277,0.09667239,0.0010058642],"about_ca_topic_score_codex":0.000031522897,"about_ca_topic_score_gemma":0.00003572256,"teacher_disagreement_score":0.29219633,"about_ca_system_score_codex":0.000014727736,"about_ca_system_score_gemma":0.000031064363,"threshold_uncertainty_score":0.5256828},"labels":[],"label_agreement":null},{"id":"W2107320771","doi":"10.1093/bioinformatics/bts457","title":"ANGES: reconstructing ANcestral GEnomeS maps","year":2012,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":70,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Agence Nationale de la Recherche","keywords":"Genome; Extant taxon; Python (programming language); Merge (version control); Biology; Suite; Evolutionary biology; Computer science; Computational biology; Genetics; Geography; Archaeology; Programming language; Information retrieval","score_opus":0.02167448892732243,"score_gpt":0.24648847665906595,"score_spread":0.22481398773174352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107320771","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9695575,0.0028059792,0.0020805846,0.0000518197,0.0010061684,0.0002515994,0.000049395534,0.000046126934,0.02415079],"genre_scores_gemma":[0.88197595,0.0005656312,0.11486829,0.00022727533,0.0012309676,0.00001972032,0.00030334885,0.00003241757,0.0007763773],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991887,0.000012334109,0.00023062107,0.00008120059,0.000108887936,0.0003782248],"domain_scores_gemma":[0.9995021,0.000006941365,0.00010471783,0.00023937388,0.000033626988,0.00011322001],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001921272,0.00012718397,0.000099702556,0.000042477113,0.00006831459,0.000028261078,0.00014165211,0.000092792696,0.00003815902],"category_scores_gemma":[0.000034633686,0.00011881371,0.000059163984,0.00007196906,0.000050864463,0.000017255325,0.00008119176,0.000058088386,0.00012180725],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005293127,0.00021300964,0.53749114,0.00052971335,0.00042827745,0.0000025294435,0.003917962,0.00006469828,0.06897915,0.00073694915,0.024045268,0.36353835],"study_design_scores_gemma":[0.0016416346,0.00042240226,0.025497872,0.000050144557,0.00008903991,0.00027952596,0.006046236,0.0011071891,0.07515888,0.00012426535,0.888227,0.0013558011],"about_ca_topic_score_codex":0.0000017000716,"about_ca_topic_score_gemma":0.0000013163514,"teacher_disagreement_score":0.86418176,"about_ca_system_score_codex":0.000015119486,"about_ca_system_score_gemma":0.000027181526,"threshold_uncertainty_score":0.48450825},"labels":[],"label_agreement":null},{"id":"W2107414458","doi":"10.1093/bioinformatics/btv136","title":"EpIC: a rational pipeline for epitope immunogenicity characterization","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"vaccines and immunoinformatics approaches","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Immunogenicity; Epitope; Computational biology; Peptide vaccine; Computer science; Peptide; Epitope mapping; Pipeline (software); Biology; Virology; Antibody; Immunology; Biochemistry; Programming language","score_opus":0.029183676362852008,"score_gpt":0.2518450514789635,"score_spread":0.2226613751161115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107414458","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34197402,0.00030561158,0.6524161,0.00045347895,0.00061327126,0.001010282,0.00028193794,0.00004760915,0.0028976947],"genre_scores_gemma":[0.8731411,0.00033369818,0.10294334,0.0018555169,0.0012069225,0.00022591688,0.01697227,0.0000670806,0.0032541289],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99909693,0.000011120135,0.00046138337,0.00009243426,0.00013518569,0.00020293455],"domain_scores_gemma":[0.99917734,0.000007879896,0.00019387573,0.00027768704,0.00025760345,0.000085643886],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003196927,0.00014618122,0.00013902952,0.000041225027,0.000085088934,0.00006404938,0.000182224,0.00011849884,0.000008448387],"category_scores_gemma":[0.00018202284,0.00012880421,0.00008859655,0.00007337831,0.00002426959,0.000030895855,0.00009007158,0.00004518278,0.000031999727],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0029467372,0.0009961342,0.005303638,0.0011628076,0.00077410677,0.0000012873497,0.0068288324,0.002048368,0.53390986,0.012719847,0.15889446,0.27441394],"study_design_scores_gemma":[0.0043341806,0.00068955537,0.0014054859,0.00002725081,0.00006167849,0.00005892209,0.0009372819,0.31747895,0.09114886,0.00036373647,0.5827698,0.0007242547],"about_ca_topic_score_codex":0.00000182668,"about_ca_topic_score_gemma":0.0000015657857,"teacher_disagreement_score":0.54947275,"about_ca_system_score_codex":0.000019389307,"about_ca_system_score_gemma":0.00014339919,"threshold_uncertainty_score":0.5252483},"labels":[],"label_agreement":null},{"id":"W2107861779","doi":"10.1093/bioinformatics/btp253","title":"Fluctuation AnaLysis CalculatOR: a web tool for the determination of mutation rate using Luria–Delbrück fluctuation analysis","year":2009,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Evolution and Genetic Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":405,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University","funders":"U.S. Public Health Service; National Institutes of Health","keywords":"Calculator; Java applet; Computer science; Java; Estimator; Mutation testing; Mutation; Programming language; Operating system; Statistics; Biology; Genetics; Mathematics; Gene","score_opus":0.011083137509752405,"score_gpt":0.2770608778069041,"score_spread":0.26597774029715165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107861779","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35080922,0.00005045005,0.64869434,0.000051887855,0.00003619142,0.00026984478,0.00004410876,0.000007541415,0.00003642281],"genre_scores_gemma":[0.95213234,0.0000520616,0.04645224,0.00015054575,0.00005424802,0.000010764796,0.0010679162,0.000006309922,0.000073586525],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989177,0.00004373068,0.0005496259,0.00013896794,0.00019900802,0.00015097074],"domain_scores_gemma":[0.9988232,0.000039931223,0.00040841108,0.00033779937,0.00035844086,0.000032174103],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005235405,0.00013300007,0.00020142764,0.0002794639,0.0001334536,0.000041091473,0.00012949838,0.00013231553,0.0000090582935],"category_scores_gemma":[0.00020186679,0.00010960548,0.00030247783,0.0008590017,0.00004068618,0.000020446609,0.000019713965,0.000035415633,0.0000015666669],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002418628,0.00019088647,0.0033722832,0.00011954042,0.0036146143,3.4676637e-7,0.0014443183,0.65777224,0.25724196,0.0009831503,0.00025019926,0.07476856],"study_design_scores_gemma":[0.0003760441,0.0001068868,0.017197613,0.0000033801318,0.0026845732,0.000001264858,0.00013701519,0.9709963,0.0081342645,0.00011233097,0.000115002185,0.00013532746],"about_ca_topic_score_codex":0.000009562947,"about_ca_topic_score_gemma":0.00007914092,"teacher_disagreement_score":0.6022421,"about_ca_system_score_codex":0.00003843494,"about_ca_system_score_gemma":0.00008620449,"threshold_uncertainty_score":0.44695815},"labels":[],"label_agreement":null},{"id":"W2107867384","doi":"10.1093/bioinformatics/btg106","title":"Inference of transcriptional regulation relationshipsfrom gene expression data","year":2003,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":77,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"False positive paradox; Inference; Event (particle physics); Gene; Computer science; Computational biology; Data mining; Microarray analysis techniques; Microarray; Biology; Gene expression; Genetics; Artificial intelligence","score_opus":0.039213382559552604,"score_gpt":0.261241824872769,"score_spread":0.2220284423132164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107867384","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09367532,0.00050701265,0.8926851,0.000041085357,0.00029698547,0.0002892681,0.00026151008,0.000017320055,0.0122263925],"genre_scores_gemma":[0.82672745,0.00010818874,0.17101122,0.000070488124,0.000056937697,0.000003863481,0.0017927405,0.00000953377,0.00021959952],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990693,0.000029329252,0.00048126705,0.000116393516,0.00016055284,0.00014316547],"domain_scores_gemma":[0.9989308,0.000019704696,0.00021191432,0.00069938996,0.00008124391,0.00005693088],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034583415,0.000111676505,0.00011230406,0.000042614098,0.000075548676,0.00001918777,0.00026970013,0.00015721623,0.00004490724],"category_scores_gemma":[0.000092819224,0.00010258663,0.00004157247,0.00008522946,0.00006045084,0.000029520821,0.00008030369,0.000074519216,0.000013860659],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018852593,0.00028874588,0.010172317,0.00042255677,0.00020167258,6.4339787e-7,0.0016023255,0.00870312,0.85740113,0.07756407,0.02638328,0.017071636],"study_design_scores_gemma":[0.0036124135,0.00053311395,0.018170405,0.00023027913,0.00014325665,0.00007139087,0.0009886564,0.12077962,0.46287626,0.011694176,0.37950164,0.0013987824],"about_ca_topic_score_codex":0.0000013710667,"about_ca_topic_score_gemma":0.0000034216587,"teacher_disagreement_score":0.7330521,"about_ca_system_score_codex":0.000007346649,"about_ca_system_score_gemma":0.000099412464,"threshold_uncertainty_score":0.41833615},"labels":[],"label_agreement":null},{"id":"W2108016183","doi":"10.1093/bioinformatics/bti189","title":"Finding differentially expressed genes for pattern generation","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Gene; Computational biology; Biology; Genetics; Computer science","score_opus":0.03261465458513153,"score_gpt":0.27135140593004875,"score_spread":0.23873675134491723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2108016183","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29304358,0.00013113632,0.70588404,0.000110603985,0.00031340143,0.00021597311,0.000025085226,0.000014360762,0.00026180377],"genre_scores_gemma":[0.9888851,0.00007318857,0.009483809,0.00022246923,0.000387366,0.0000866932,0.00057502213,0.000014272973,0.0002720547],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994444,0.000006703423,0.00020681914,0.00012084529,0.00007962229,0.00014156196],"domain_scores_gemma":[0.9995604,0.0000027269216,0.00010056835,0.00022565019,0.000060437498,0.000050225644],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000056841665,0.00009931904,0.000069617825,0.00003512043,0.000121960555,0.000061700266,0.00011755247,0.00009664644,0.0000101194055],"category_scores_gemma":[0.000024506411,0.00008939338,0.000060933937,0.000036998026,0.000023497465,0.000007731892,0.000026302056,0.000024360093,0.00000939812],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000069195607,0.000020055719,0.00020725458,0.000037854632,0.000012682065,6.010405e-8,0.0001888066,0.00048552922,0.9595825,0.00014588551,0.0026152816,0.036697134],"study_design_scores_gemma":[0.0009626503,0.00010912897,0.0005276435,0.000015814554,0.000012365751,0.0000017831044,0.000096646516,0.0033842619,0.958299,0.00011834452,0.036293563,0.00017878888],"about_ca_topic_score_codex":0.0000010804292,"about_ca_topic_score_gemma":0.0000048676225,"teacher_disagreement_score":0.6964002,"about_ca_system_score_codex":0.000012057066,"about_ca_system_score_gemma":0.00007785236,"threshold_uncertainty_score":0.36453563},"labels":[],"label_agreement":null},{"id":"W2108102223","doi":"10.1093/bioinformatics/bts695","title":"ChromoZoom: a flexible, fluid, web-based genome browser","year":2012,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; University of Toronto","funders":"National Human Genome Research Institute; National Heart, Lung, and Blood Institute; University of California, Santa Cruz","keywords":"Computer science; Scrolling; Zoom; Rendering (computer graphics); Source code; Web server; Genome browser; User interface; Server; Web application; Computer graphics (images); Operating system; World Wide Web; The Internet; Genome; Genomics","score_opus":0.015099627374970379,"score_gpt":0.232037945268106,"score_spread":0.2169383178931356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2108102223","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9716619,0.0038702616,0.0039477097,0.0001206747,0.0004967214,0.00032136863,0.000098020995,0.000025327254,0.019458018],"genre_scores_gemma":[0.98176944,0.00024658005,0.015800005,0.0009913266,0.00044313315,0.000026218822,0.00010844314,0.000025615453,0.0005892659],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99900967,0.000015797608,0.00029135708,0.000113519876,0.00013107996,0.00043859874],"domain_scores_gemma":[0.999293,0.000009204666,0.00009318977,0.00039061395,0.00006488034,0.00014910163],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019183355,0.00019257577,0.00015506067,0.000051623,0.00011202846,0.0000268981,0.00019467567,0.00012793235,0.00004374449],"category_scores_gemma":[0.000031738466,0.00017250927,0.00010581796,0.00009222777,0.00007124761,0.000002750399,0.00013234565,0.00005501786,0.00016947526],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008056045,0.00021695638,0.018087583,0.00019554829,0.00023775834,9.1621416e-7,0.0005831997,0.0004218977,0.9593514,0.00036418633,0.015396771,0.0050632204],"study_design_scores_gemma":[0.0013229277,0.00030861754,0.0219887,0.00001239015,0.00005820479,0.000022211974,0.00021682373,0.002368095,0.09107454,0.000023971075,0.88198435,0.0006191414],"about_ca_topic_score_codex":0.0000034116633,"about_ca_topic_score_gemma":0.000002823938,"teacher_disagreement_score":0.86827683,"about_ca_system_score_codex":0.000016880831,"about_ca_system_score_gemma":0.00008563991,"threshold_uncertainty_score":0.7034724},"labels":[],"label_agreement":null},{"id":"W2108125432","doi":"10.1093/bioinformatics/btq657","title":"A regression framework incorporating quantitative and negative interaction data improves quantitative prediction of PDZ domain–peptide interaction from primary sequence","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Hippo pathway signaling and YAP/TAZ","field":"Biochemistry, Genetics and Molecular Biology","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Western University","funders":"Canadian Institutes of Health Research; China Scholarship Council; National Natural Science Foundation of China","keywords":"PDZ domain; Context (archaeology); Sequence (biology); Computer science; Domain (mathematical analysis); Regression; Similarity (geometry); Construct (python library); Protein–protein interaction; Peptide; Computational biology; Data mining; Artificial intelligence; Biology; Mathematics; Statistics; Genetics","score_opus":0.0473592794905898,"score_gpt":0.3209091213810167,"score_spread":0.27354984189042686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2108125432","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9560249,0.00009696268,0.04176436,0.000051112398,0.00051792833,0.00023775474,0.00067514984,0.000025969324,0.0006058616],"genre_scores_gemma":[0.7130482,0.00006915698,0.2852304,0.000061504616,0.00010377758,0.000009103414,0.0014513497,0.000013968729,0.000012548253],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987487,0.00009372347,0.0005370257,0.00028822702,0.00018595054,0.00014636044],"domain_scores_gemma":[0.99824333,0.00027190478,0.0007083541,0.0005055852,0.00019725469,0.00007358404],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003674047,0.00019718267,0.00021831277,0.000083256484,0.00015180041,0.00005737027,0.00022536352,0.00024134993,0.000006513957],"category_scores_gemma":[0.0010974291,0.0001683708,0.00004250862,0.000119421085,0.00021287777,0.00014149098,0.0003237668,0.0004572401,0.000006484542],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026416482,0.000042118714,0.00043735094,0.00007856301,0.000072811104,8.3536287e-7,0.0035724859,0.000019267267,0.98879147,0.0005431358,0.00010153695,0.006076294],"study_design_scores_gemma":[0.0017267265,0.002835375,0.0045979023,0.0018037331,0.00017218072,0.00006133138,0.052292377,0.13517395,0.7850422,0.012090133,0.0032915813,0.0009124942],"about_ca_topic_score_codex":0.00011033405,"about_ca_topic_score_gemma":0.00006333562,"teacher_disagreement_score":0.24346603,"about_ca_system_score_codex":0.000020397829,"about_ca_system_score_gemma":0.00010831163,"threshold_uncertainty_score":0.68659616},"labels":[],"label_agreement":null},{"id":"W2108174382","doi":"10.1093/bioinformatics/btp456","title":"Modified variational Bayes EM estimation of hidden Markov tree model of cell lineages","year":2009,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; Mount Sinai Hospital","funders":"Engineering and Physical Sciences Research Council","keywords":"Lineage (genetic); Tree (set theory); Computer science; Bayes' theorem; Markov chain; Coalescent theory; Population; Markov model; Hidden Markov model; Bayesian probability; Algorithm; Expectation–maximization algorithm; Artificial intelligence; Biology; Mathematics; Machine learning; Statistics; Combinatorics; Phylogenetic tree; Maximum likelihood; Genetics","score_opus":0.014285339395681794,"score_gpt":0.22304628592734063,"score_spread":0.20876094653165883,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2108174382","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61445737,0.000064393935,0.38070434,0.000034603647,0.000058193284,0.00013287878,0.000088129236,0.00001029597,0.004449766],"genre_scores_gemma":[0.82645345,0.00004609367,0.17302842,0.00007359889,0.000030659245,0.0000014288828,0.00020816657,0.0000056595395,0.00015254524],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99922615,0.000010025516,0.00042646017,0.00007749336,0.00015130037,0.00010858273],"domain_scores_gemma":[0.9994552,0.000011179044,0.00020416838,0.00019320476,0.00009984462,0.00003640049],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001083912,0.00010685917,0.00014982521,0.000049418497,0.000026104586,0.000010325395,0.00013921279,0.00012906568,0.000004388775],"category_scores_gemma":[0.000036002504,0.00009968936,0.00008090156,0.00005653426,0.0000282716,0.000011123956,0.00001776237,0.0000422583,0.0000014225861],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024418984,0.00040602143,0.00015881415,0.00032250214,0.000055083074,2.153647e-7,0.0012166674,0.12016767,0.80937654,0.0009996394,0.0009815465,0.06607112],"study_design_scores_gemma":[0.0004539223,0.00018171757,0.00048726253,0.000012448546,0.000020109688,7.2652364e-7,0.00003986659,0.74249536,0.25590253,0.0002964981,0.000015627018,0.00009393325],"about_ca_topic_score_codex":0.00000316144,"about_ca_topic_score_gemma":0.0000027354486,"teacher_disagreement_score":0.6223277,"about_ca_system_score_codex":0.00000652752,"about_ca_system_score_gemma":0.000073955314,"threshold_uncertainty_score":0.4065214},"labels":[],"label_agreement":null},{"id":"W2108563376","doi":"10.1093/bioinformatics/btq639","title":"TE Displayer for post-genomic analysis of transposable elements","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Chromosomal and Genetic Variations","field":"Agricultural and Biological Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Transposable element; In silico; Computer science; Computational biology; Biology; Data mining; Artificial intelligence; Genome; Genetics; Gene","score_opus":0.012886655885956541,"score_gpt":0.22270072485348852,"score_spread":0.20981406896753196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2108563376","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99808955,0.000005268331,0.00006310225,0.00024908347,0.000082012826,0.00017324246,0.0009038807,0.000011860083,0.0004219715],"genre_scores_gemma":[0.99378514,0.000004054604,0.005477678,0.00011618432,0.000040392202,0.000010593068,0.00046774937,3.441815e-7,0.00009785923],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9994516,0.0000033172387,0.00027825657,0.000057209076,0.00008428744,0.00012538017],"domain_scores_gemma":[0.9996686,0.00006775007,0.00009929022,0.000047627396,0.0000723081,0.000044410437],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009249226,0.00006158303,0.00012694043,0.00001952804,0.00008272576,0.000017560285,0.00013469752,0.000048814385,0.0004586649],"category_scores_gemma":[0.000018486879,0.000023422035,0.00014089634,0.00028889044,0.000019063307,0.000060832383,0.00001383905,0.000033587323,0.000011915089],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040197825,0.00020070246,0.10745343,0.000044149958,0.00056110666,1.219022e-7,0.0010919722,0.0000887222,0.7917381,0.0034998483,0.00023051335,0.09505114],"study_design_scores_gemma":[0.0005411245,0.0005143488,0.78676754,0.000008493444,0.0011597268,0.0000016854725,0.00094310805,0.12412873,0.017105687,0.0005746328,0.06787249,0.00038245664],"about_ca_topic_score_codex":0.000030882708,"about_ca_topic_score_gemma":0.0022532567,"teacher_disagreement_score":0.7746324,"about_ca_system_score_codex":0.0000037242173,"about_ca_system_score_gemma":0.0000072184203,"threshold_uncertainty_score":0.5022059},"labels":[],"label_agreement":null},{"id":"W2108614159","doi":"10.1093/bioinformatics/btt001","title":"MaSC: mappability-sensitive cross-correlation for estimating mean fragment length of single-end short-read sequencing data","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Ontario Ministry of Economic Development and Innovation; Ministero dello Sviluppo Economico; Ottawa Hospital Research Institute","keywords":"Fragment (logic); Computer science; Perl; Subroutine; Cross-correlation; Algorithm; Correlation; Reliability (semiconductor); Software; Data mining; Statistics; Mathematics","score_opus":0.04575954669842852,"score_gpt":0.28354031649707506,"score_spread":0.23778076979864654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2108614159","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84275705,0.000111796886,0.15452754,0.000043254593,0.00026049302,0.0007083854,0.00030752705,0.0000069139232,0.0012770465],"genre_scores_gemma":[0.74598974,0.000015583351,0.25326756,0.000051380757,0.00010852094,0.00002105401,0.00048509528,0.000013699622,0.00004739806],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99884164,0.000016141614,0.0005467873,0.00021938376,0.00013565291,0.00024038485],"domain_scores_gemma":[0.9987923,0.00006235332,0.00020968376,0.00061742536,0.00026320518,0.00005505401],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032777048,0.00017154607,0.0002011318,0.000033348453,0.0001230237,0.00005261439,0.00023869326,0.00011542083,0.000008054347],"category_scores_gemma":[0.00022586415,0.0001583353,0.00006796199,0.000048282232,0.00012428183,0.000011167286,0.00031239036,0.00005175463,0.0000059506215],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010452352,0.00023375211,0.01018768,0.0010418777,0.0006538318,6.855046e-7,0.005650881,0.02354339,0.82607573,0.00033790822,0.0025719544,0.12959777],"study_design_scores_gemma":[0.0009030725,0.0008036752,0.0054021296,0.00009031556,0.000120525954,0.000016710328,0.0034971503,0.8379234,0.14676483,0.00051892025,0.0033277152,0.00063157344],"about_ca_topic_score_codex":0.000041386018,"about_ca_topic_score_gemma":0.000021826532,"teacher_disagreement_score":0.81438,"about_ca_system_score_codex":0.000036332614,"about_ca_system_score_gemma":0.00006687569,"threshold_uncertainty_score":0.6456726},"labels":[],"label_agreement":null},{"id":"W2108998942","doi":"10.1093/bioinformatics/btg1025","title":"Detection and validation of single gene inversions","year":2003,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":56,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Université de Montréal; Université du Québec à Montréal","funders":"","keywords":"Computer science; Computational biology; Gene; Genetics; Biology","score_opus":0.013892619292329735,"score_gpt":0.21265513003258144,"score_spread":0.1987625107402517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2108998942","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97751147,0.000096149946,0.01983516,0.000007009563,0.00006511732,0.000098325174,0.0000050888852,0.0000048880597,0.002376794],"genre_scores_gemma":[0.9829342,0.00007328147,0.016840253,0.000021160973,0.000013888159,0.000002282609,0.000025664209,0.0000044591343,0.00008481773],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99969417,0.000011089802,0.00012328284,0.000046444242,0.0000577304,0.00006729224],"domain_scores_gemma":[0.9997647,0.0000027845563,0.000062308,0.00010466533,0.000038289385,0.00002727064],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008328168,0.000047583297,0.00004588434,0.0000324911,0.000029056944,0.0000071941395,0.000028169461,0.0000499605,0.000006204891],"category_scores_gemma":[0.000046126414,0.000046526155,0.00001863956,0.00005026438,0.00002518628,0.0000045462475,0.000020219157,0.000015391981,0.000004523985],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000038000574,0.000019143032,0.00056977355,0.000029428382,0.000015518403,5.416691e-8,0.00010435769,0.000027288375,0.9960832,0.000026050515,0.00007189199,0.0030495182],"study_design_scores_gemma":[0.00023624685,0.0001334839,0.00026792087,0.0000028199045,0.000010389685,0.0000070694396,0.00015759781,0.00030052487,0.99165344,0.000033015684,0.00713889,0.00005861568],"about_ca_topic_score_codex":0.0000013016273,"about_ca_topic_score_gemma":0.0000011950714,"teacher_disagreement_score":0.007066998,"about_ca_system_score_codex":0.0000058330006,"about_ca_system_score_gemma":0.000011814172,"threshold_uncertainty_score":0.18972816},"labels":[],"label_agreement":null},{"id":"W2109028614","doi":"10.1093/bioinformatics/btp600","title":"Ancestors 1.0: a web server for ancestral sequence reconstruction","year":2009,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université du Québec à Montréal","funders":"","keywords":"Synteny; Inference; Computer science; Indel; Genome; Context (archaeology); Sequence (biology); Web server; Biology; Computational biology; Artificial intelligence; The Internet; Genetics; World Wide Web; Gene","score_opus":0.0301068154565614,"score_gpt":0.2728592275455003,"score_spread":0.24275241208893888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109028614","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98964804,0.00019181575,0.006592888,0.00020014854,0.00038922802,0.0004606845,0.000054220516,0.00003872082,0.0024242692],"genre_scores_gemma":[0.8978003,0.00025188076,0.100370035,0.00042902396,0.00035714576,0.000026086705,0.00019932367,0.000012573969,0.000553605],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993486,0.000006520721,0.00021825997,0.00011728109,0.00009080331,0.00021857134],"domain_scores_gemma":[0.99956954,0.0000032967878,0.00010304061,0.00020433548,0.00006210753,0.000057702287],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011882777,0.000113487644,0.00009410379,0.000035836845,0.00006397141,0.000029924277,0.0001312424,0.00009428737,0.000007934121],"category_scores_gemma":[0.000027920416,0.00010830413,0.000069010166,0.0000757665,0.00003874844,0.000016820983,0.000014757783,0.000038745955,0.000014586452],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017774166,0.00012776343,0.0053589796,0.00028822623,0.00012933998,0.0000021315307,0.00044507385,0.0004677919,0.30554318,0.0008804376,0.012458717,0.6741206],"study_design_scores_gemma":[0.009188114,0.007247868,0.021680757,0.00026833077,0.0002158845,0.0006045551,0.0018923783,0.092266336,0.33182508,0.004080085,0.5274303,0.003300289],"about_ca_topic_score_codex":9.874361e-7,"about_ca_topic_score_gemma":0.000004583802,"teacher_disagreement_score":0.67082036,"about_ca_system_score_codex":0.00002061712,"about_ca_system_score_gemma":0.0000713604,"threshold_uncertainty_score":0.4416514},"labels":[],"label_agreement":null},{"id":"W2109363750","doi":"10.1093/bioinformatics/btq315","title":"Count: evolutionary analysis of phylogenetic profiles with parsimony and likelihood","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":491,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Phylogenetic tree; Java; Phylogenetics; Computer science; Source code; Lineage (genetic); Maximum parsimony; Software; Biology; Gene; Programming language; Genetics; Clade","score_opus":0.005104281382279222,"score_gpt":0.203892047635604,"score_spread":0.19878776625332478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109363750","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99778926,0.0006121142,0.0003610679,0.000027708857,0.000045598597,0.00012815947,0.000105520434,0.0000024422316,0.0009281134],"genre_scores_gemma":[0.9834595,0.00027950483,0.016048199,0.00005868242,0.000038402235,0.000010676709,0.00006755625,0.00000771397,0.000029793973],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99939674,0.000007074947,0.00021822528,0.00011834395,0.00010507467,0.00015453332],"domain_scores_gemma":[0.999438,0.00001116682,0.00012235026,0.00026171067,0.0001102312,0.000056535886],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000084065105,0.000119285476,0.00017917022,0.00008312841,0.00006056953,0.000010862247,0.000100791,0.00008390852,0.00000702999],"category_scores_gemma":[0.000018280034,0.00009358575,0.00005407237,0.00017240271,0.00016388515,0.0000011358231,0.00008311307,0.00005128089,0.0000012965886],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000106353385,0.000120713805,0.49852973,0.00013763757,0.0024645044,8.9703553e-7,0.0007298901,0.00038026253,0.48932067,0.00048048503,0.00073140167,0.0069974707],"study_design_scores_gemma":[0.0008464389,0.00078818726,0.9205887,0.000013468522,0.0012280651,0.000020942918,0.0007108142,0.010250205,0.04963052,0.00014287591,0.01527398,0.00050580135],"about_ca_topic_score_codex":0.000010728339,"about_ca_topic_score_gemma":0.00009608135,"teacher_disagreement_score":0.43969014,"about_ca_system_score_codex":0.0000024184408,"about_ca_system_score_gemma":0.000053649317,"threshold_uncertainty_score":0.3816316},"labels":[],"label_agreement":null},{"id":"W2109550992","doi":"10.1093/bioinformatics/bth946","title":"Into the heart of darkness: large-scale clustering of human non-coding DNA","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":69,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Human genome; Biology; Genome; Computational biology; Conserved sequence; Cluster analysis; Genetics; Gene; Coding region; Computer science; Peptide sequence; Artificial intelligence","score_opus":0.009885294791323542,"score_gpt":0.24885973694188881,"score_spread":0.23897444215056526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109550992","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94103163,0.00012948114,0.0550522,0.00010536553,0.000115474366,0.00026935825,0.000013783683,0.000008159042,0.003274516],"genre_scores_gemma":[0.9797614,0.00004144003,0.019939885,0.00007199179,0.000057347173,0.000006231495,0.000042435815,0.000011133448,0.00006809169],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99925834,0.000008568634,0.00034747925,0.00007454331,0.00014438243,0.00016667391],"domain_scores_gemma":[0.9994085,0.0000043180185,0.0001508689,0.0003386747,0.00006562649,0.000032035285],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024606526,0.00009853231,0.00014349217,0.000039854855,0.000078396486,0.000010964941,0.000214727,0.000070948496,0.000007744926],"category_scores_gemma":[0.000015480025,0.0000758222,0.00008072639,0.00008777041,0.000075062606,0.0000070614115,0.00018907634,0.000048491827,0.0000065384656],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015847021,0.00009260131,0.00093697605,0.0004692294,0.000075673845,3.2190894e-7,0.007953673,0.0007837158,0.9880705,0.000116433606,0.0003058026,0.0011792384],"study_design_scores_gemma":[0.0015842088,0.00047684187,0.0032886255,0.00012888401,0.000042758908,0.000008969277,0.004928622,0.0038266538,0.9790202,0.00015482635,0.006267874,0.00027156714],"about_ca_topic_score_codex":0.000018302148,"about_ca_topic_score_gemma":0.000041017403,"teacher_disagreement_score":0.03872978,"about_ca_system_score_codex":0.000013090591,"about_ca_system_score_gemma":0.000036782534,"threshold_uncertainty_score":0.30919397},"labels":[],"label_agreement":null},{"id":"W2109614625","doi":"10.1093/bioinformatics/btt041","title":"AbCD: arbitrary coverage design for sequencing-based genetic studies","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"National Human Genome Research Institute; National Heart, Lung, and Blood Institute","keywords":"Computer science; Computational biology; Biology","score_opus":0.04451066268123887,"score_gpt":0.2829542883865914,"score_spread":0.23844362570535255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109614625","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39076903,0.00094566616,0.60600966,0.00030026434,0.00024863845,0.0010240042,0.0000392571,0.00003102944,0.00063245307],"genre_scores_gemma":[0.53886354,0.00025921423,0.45727488,0.0026269325,0.00017373404,0.00030171694,0.0001360748,0.000022735745,0.0003411714],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989604,0.00005130199,0.00042681154,0.00015224071,0.000082148516,0.00032712452],"domain_scores_gemma":[0.99912363,0.00012102396,0.0001872919,0.00028955637,0.00020275539,0.000075716605],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028084966,0.00016843788,0.00021680583,0.000043920965,0.00012564957,0.00002574172,0.00015754113,0.00016762699,0.000017501769],"category_scores_gemma":[0.00043436038,0.0001451377,0.00010791231,0.00005850131,0.000070735514,0.000006695987,0.00004721737,0.000051852403,0.00006378582],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024678127,0.00034779642,0.040748943,0.0015025419,0.0020793264,0.0000050629405,0.00236749,0.15186314,0.0854764,0.0008963373,0.6383219,0.07614428],"study_design_scores_gemma":[0.009104292,0.007827066,0.055642415,0.0001878157,0.00047490105,0.0000760557,0.0054764026,0.71515507,0.08094665,0.023009682,0.09860427,0.0034953638],"about_ca_topic_score_codex":0.000008596247,"about_ca_topic_score_gemma":0.0000031561267,"teacher_disagreement_score":0.56329197,"about_ca_system_score_codex":0.00004250674,"about_ca_system_score_gemma":0.00019955455,"threshold_uncertainty_score":0.5918544},"labels":[],"label_agreement":null},{"id":"W2109641307","doi":"10.1093/bioinformatics/18.6.894","title":"DMLE+: Bayesian linkage disequilibrium gene mapping","year":2002,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":137,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Institutes of Health; Canadian Institutes of Health Research; Killam Trusts; National Human Genome Research Institute; Fondation pour la Recherche Médicale","keywords":"Linkage disequilibrium; Bayesian probability; Linkage (software); Disequilibrium; Computational biology; Genetics; Computer science; Gene; Biology; Artificial intelligence; Haplotype; Allele; Medicine","score_opus":0.01966016657473886,"score_gpt":0.2320162652202325,"score_spread":0.21235609864549365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109641307","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82739663,0.0016565121,0.1194865,0.0016298436,0.00072779955,0.00046914385,0.000100777215,0.00009798523,0.048434794],"genre_scores_gemma":[0.9453633,0.00054367207,0.048687942,0.0012801851,0.00040485754,0.000017986262,0.0002302791,0.000023884308,0.0034479203],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989797,0.000035527406,0.00040269332,0.00014763465,0.00009776822,0.00033668734],"domain_scores_gemma":[0.9992978,0.000016318585,0.00015351604,0.00037336448,0.000051153816,0.000107826076],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019511934,0.00014743378,0.00016409859,0.00004957373,0.00010396123,0.000025280076,0.00019310831,0.000199106,0.000112920694],"category_scores_gemma":[0.00016122442,0.00013852687,0.000102616425,0.00010104476,0.000053604588,0.000006081109,0.00011702985,0.00007853182,0.00019066811],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048367823,0.0006386666,0.2102219,0.0004916049,0.00088069035,0.000020888432,0.0047339797,0.0020296266,0.12712206,0.0009582168,0.5554442,0.09740982],"study_design_scores_gemma":[0.002776301,0.00067086006,0.08115482,0.000050997805,0.00009084434,0.0001401872,0.0009547249,0.2864371,0.010658835,0.0005413462,0.61489314,0.001630812],"about_ca_topic_score_codex":0.0000035047387,"about_ca_topic_score_gemma":0.000002967927,"teacher_disagreement_score":0.28440747,"about_ca_system_score_codex":0.000016601733,"about_ca_system_score_gemma":0.000017802455,"threshold_uncertainty_score":0.56489617},"labels":[],"label_agreement":null},{"id":"W2109643429","doi":"10.1093/bioinformatics/bti040","title":"Stepwise detection of recombination breakpoints in sequence alignments","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute of Allergy and Infectious Diseases","keywords":"Breakpoint; Sequence (biology); Recombination; Genetics; Computer science; Computational biology; Biology; Algorithm; Gene; Chromosome","score_opus":0.01422088828083883,"score_gpt":0.23910917761121972,"score_spread":0.22488828933038088,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109643429","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9970974,0.00009607081,0.0017218783,0.000022993849,0.00010206367,0.00012607269,0.000011298037,0.0000016514341,0.0008206146],"genre_scores_gemma":[0.9970367,0.00020694737,0.0026523126,0.000042413565,0.0000139022095,0.0000070042342,0.00001457541,0.0000048174143,0.00002132279],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995093,0.0000075882745,0.00024010753,0.00006999563,0.00007194437,0.000101066384],"domain_scores_gemma":[0.9997031,0.0000029495275,0.00009868758,0.00013264312,0.000041687108,0.000020907764],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000103880695,0.00006890985,0.00007856102,0.000043159664,0.000021618947,0.0000050974086,0.0000731112,0.0000590177,9.3244654e-7],"category_scores_gemma":[0.000028287684,0.00006818057,0.000028872893,0.00006838025,0.000030517604,0.0000017602237,0.000046526806,0.000024864945,0.0000048753627],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028968587,0.000070048554,0.002786207,0.000055128763,0.000025546846,4.6321023e-7,0.00053567777,0.0008080691,0.9785921,0.00013442224,0.000013246911,0.016950153],"study_design_scores_gemma":[0.0015059218,0.00040297493,0.02939274,0.00003906672,0.0000102962185,0.000011402897,0.00042922364,0.0004870817,0.96504277,0.0014008469,0.0010859895,0.00019167365],"about_ca_topic_score_codex":0.000035570887,"about_ca_topic_score_gemma":0.000057712707,"teacher_disagreement_score":0.026606534,"about_ca_system_score_codex":0.000027147591,"about_ca_system_score_gemma":0.000030530293,"threshold_uncertainty_score":0.2780323},"labels":[],"label_agreement":null},{"id":"W2110019612","doi":"10.1093/bioinformatics/btp478","title":"Methods for labeling error detection in microarrays based on the effect of data perturbation on the regression model","year":2009,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of British Columbia","keywords":"Support vector machine; Computer science; Artificial intelligence; Pattern recognition (psychology); Algorithm; Regression; Data mining; DNA microarray; Source code; Mathematics; Statistics","score_opus":0.05680105849511773,"score_gpt":0.3634192508253875,"score_spread":0.30661819233026977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110019612","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13129021,0.00012840371,0.86340404,0.0025411951,0.00014918298,0.001187029,0.000040402767,0.00001445753,0.0012450671],"genre_scores_gemma":[0.9692321,0.000023681956,0.02954443,0.0008906884,0.00003750162,0.000047149446,0.00014767663,0.000007763649,0.00006902937],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993392,0.00012255862,0.00022259429,0.00012348988,0.00009607782,0.00009608559],"domain_scores_gemma":[0.9990089,0.0001478419,0.00016326252,0.00062666956,0.00003690571,0.000016437636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010329175,0.000098594326,0.00008549158,0.00004639134,0.00008838944,0.000015535534,0.00027402758,0.00009537557,0.0000017794445],"category_scores_gemma":[0.00042931398,0.00004897948,0.0000429061,0.000092776296,0.000020195166,0.00000808523,0.000026157571,0.00007519184,8.8699994e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040690758,0.000027213922,0.000009851535,0.00003666958,0.0000051703964,1.0657343e-8,0.000105042505,0.005984309,0.85752606,0.0001250397,0.0018544095,0.13391931],"study_design_scores_gemma":[0.00023539223,0.00028953917,0.000032064036,0.00003811812,0.00000571435,1.3015531e-7,0.000037106987,0.5381966,0.46000215,0.000066812354,0.001057968,0.00003837036],"about_ca_topic_score_codex":5.888787e-7,"about_ca_topic_score_gemma":0.0000015102469,"teacher_disagreement_score":0.8379419,"about_ca_system_score_codex":0.000016067606,"about_ca_system_score_gemma":0.000030871794,"threshold_uncertainty_score":0.19973253},"labels":[],"label_agreement":null},{"id":"W2110092182","doi":"10.1093/bioinformatics/bts349","title":"MolClass: a web portal to interrogate diverse small molecule screen datasets with different computational models","year":2012,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Institute for Research in Immunology and Cancer","funders":"Wellcome Trust","keywords":"Computer science; Software; Source code; Fingerprint (computing); Database; Web service; Python (programming language); Data mining; Cheminformatics; Function (biology); Open source; World Wide Web; Information retrieval; Bioinformatics; Programming language; Artificial intelligence; Biology","score_opus":0.046192672568302624,"score_gpt":0.2841637598046638,"score_spread":0.23797108723636118,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110092182","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.120405085,0.000013985018,0.8768753,0.0002073072,0.00016487301,0.00028664907,0.00031565595,0.000117682175,0.0016134649],"genre_scores_gemma":[0.53863865,0.000001150514,0.4601887,0.000752366,0.00003831915,0.000014257436,0.00033611694,0.000010751073,0.000019710658],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99831563,0.00006365338,0.0004074604,0.00019874405,0.0005735152,0.00044102073],"domain_scores_gemma":[0.9987616,0.00014409829,0.00016475574,0.0004677635,0.000099118464,0.00036267834],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029257403,0.00024524122,0.00021596457,0.00021133781,0.00011082806,0.00020199522,0.00079986657,0.0000449162,0.000014127902],"category_scores_gemma":[0.000028413937,0.00019628576,0.00006314792,0.00034214655,0.00004627085,0.0017516972,0.0008544303,0.00012826014,0.000116538424],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006874282,0.00041293353,0.0008393906,0.00009033597,0.00016081159,0.000022784752,0.006884948,0.8618406,0.000020693584,0.10844559,0.0072075063,0.014005676],"study_design_scores_gemma":[0.0004483704,0.000103802086,0.0016337505,0.000042182743,0.000015149869,0.00005353464,0.00019856497,0.99569523,0.00009688303,0.0010216677,0.00040061816,0.0002902604],"about_ca_topic_score_codex":0.0000136015,"about_ca_topic_score_gemma":0.000019986725,"teacher_disagreement_score":0.41823354,"about_ca_system_score_codex":0.00007471552,"about_ca_system_score_gemma":0.00012040306,"threshold_uncertainty_score":0.80043006},"labels":[],"label_agreement":null},{"id":"W2110628507","doi":"10.1093/bioinformatics/18.suppl_2.s54","title":"Common intervals and sorting by reversals: a marriage of necessity","year":2002,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Sorting; Computer science; Econometrics; Psychology; Algorithm; Mathematics","score_opus":0.014919944998585408,"score_gpt":0.23653411034470762,"score_spread":0.22161416534612222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110628507","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98983824,0.0020367869,0.00232028,0.00010949905,0.00006343333,0.00018720518,0.000049323105,0.000012957891,0.005382259],"genre_scores_gemma":[0.9893255,0.00089360046,0.008958167,0.00016774803,0.00003489896,0.0000041578637,0.000059750575,0.000010943117,0.0005451871],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993933,0.000017425216,0.00029312077,0.00007538983,0.00008922449,0.00013156801],"domain_scores_gemma":[0.999555,0.000007813128,0.00017391244,0.00018792451,0.000028030221,0.000047354504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001665944,0.000088505505,0.00013050526,0.000024330442,0.00003354035,0.000016256652,0.00010929099,0.00007290824,0.000038163947],"category_scores_gemma":[0.000046753958,0.00008264268,0.000037879923,0.000045210814,0.00005260525,0.000007419681,0.0001263516,0.000042209886,0.000009212468],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006026268,0.00035439586,0.046992,0.0016221332,0.00042519416,0.000003981964,0.0048598554,0.000020583953,0.49251232,0.000087366156,0.14793147,0.30513042],"study_design_scores_gemma":[0.006487629,0.0023918028,0.007108728,0.00064365164,0.00028367512,0.000106161875,0.0048326035,0.08319234,0.6569391,0.0004061601,0.23548834,0.0021198164],"about_ca_topic_score_codex":0.000007144971,"about_ca_topic_score_gemma":0.0000031133288,"teacher_disagreement_score":0.3030106,"about_ca_system_score_codex":0.0000052945907,"about_ca_system_score_gemma":0.0000037124598,"threshold_uncertainty_score":0.33700705},"labels":[],"label_agreement":null},{"id":"W2110783096","doi":"10.1093/bioinformatics/btq264","title":"GPCR-OKB: the G Protein Coupled Receptor Oligomer Knowledge Base","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Receptor Mechanisms and Signaling","field":"Biochemistry, Genetics and Molecular Biology","cited_by":75,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Institute for Research in Immunology and Cancer","funders":"National Institute on Drug Abuse; National Institute of Mental Health; National Institutes of Health; Norwegian Biodiversity Information Centre","keywords":"Oligomer; G protein-coupled receptor; Base (topology); Receptor; Computer science; Computational biology; Chemistry; Biology; Biochemistry; Mathematics; Polymer chemistry","score_opus":0.009851811084422688,"score_gpt":0.23317525974567035,"score_spread":0.22332344866124768,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110783096","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.980312,0.0002075492,0.011832143,0.00026362317,0.001024304,0.00068118476,0.000027551085,0.000045720404,0.0056059435],"genre_scores_gemma":[0.9667006,0.000060009545,0.027539833,0.00048803067,0.0008644742,0.00010696374,0.00016566766,0.000045032968,0.0040293857],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99905795,0.00002468814,0.00031645893,0.0001415063,0.00014637595,0.00031302983],"domain_scores_gemma":[0.99913055,0.000014150787,0.0001234543,0.00049654517,0.00011877322,0.00011655917],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004680068,0.00017853222,0.00012815122,0.000033196426,0.0001912156,0.00007151592,0.00033728385,0.00020058232,0.00046079556],"category_scores_gemma":[0.0001423094,0.000118651464,0.00010734956,0.000103553786,0.000084522886,0.0000093817325,0.00012642764,0.00022006953,0.00031324523],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017953016,0.000034980836,0.000022511678,0.00003033476,0.000023764116,2.1081503e-7,0.00024108904,0.000003820857,0.9918613,0.0009912571,0.0038726395,0.0029001497],"study_design_scores_gemma":[0.00042770285,0.00014595619,0.000025147061,0.000017689561,0.000013682467,0.000009893862,0.00031765274,0.00899888,0.71156347,0.00007799841,0.27813065,0.00027124965],"about_ca_topic_score_codex":0.0000071279965,"about_ca_topic_score_gemma":0.000025034204,"teacher_disagreement_score":0.28029782,"about_ca_system_score_codex":0.000007971031,"about_ca_system_score_gemma":0.000116162155,"threshold_uncertainty_score":0.50453883},"labels":[],"label_agreement":null},{"id":"W2110845299","doi":"10.1093/bioinformatics/btn226","title":"Malin: maximum likelihood analysis of intron evolution in eukaryotes","year":2008,"lang":"en","type":"article","venue":"Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Intron; Biology; Computational biology; Exon; Phylogenetic tree; Gene; Genetics","score_opus":0.009916707369705392,"score_gpt":0.22100113472890803,"score_spread":0.21108442735920263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110845299","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9546623,0.00036748304,0.043378115,0.000035528024,0.0000610489,0.00014241094,0.000025090681,0.000008515255,0.0013194606],"genre_scores_gemma":[0.98624337,0.00022460554,0.013277671,0.000055396984,0.000033387845,0.000008809961,0.00009460586,0.0000068528057,0.000055305816],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992042,0.000027070162,0.00036922607,0.0000954086,0.00013236896,0.00017169729],"domain_scores_gemma":[0.9994856,0.000010064074,0.00014330342,0.00026922446,0.00005071611,0.0000410965],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001874424,0.00010029527,0.00019806267,0.00020742304,0.00003329957,0.0000047002513,0.00013589414,0.00013113757,0.00002646938],"category_scores_gemma":[0.00006670532,0.00009277777,0.000118623255,0.00035676328,0.000043399228,0.000007390422,0.000052948322,0.000039139617,0.000011478581],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003580909,0.0004122988,0.14071307,0.00027310828,0.0013519552,0.000010081557,0.0016639406,0.0019711873,0.8202092,0.0012536534,0.0011919795,0.030591438],"study_design_scores_gemma":[0.0012629268,0.00074480876,0.15363398,0.000060467737,0.00042826656,0.000028210345,0.0007207846,0.019209715,0.8190685,0.0012481665,0.0029193885,0.0006747777],"about_ca_topic_score_codex":0.000032329946,"about_ca_topic_score_gemma":0.000037730297,"teacher_disagreement_score":0.031581014,"about_ca_system_score_codex":0.000016678669,"about_ca_system_score_gemma":0.000054920194,"threshold_uncertainty_score":0.37833676},"labels":[],"label_agreement":null},{"id":"W2111044311","doi":"10.1093/bioinformatics/bts593","title":"SCALCE: boosting sequence compression algorithms using locally consistent encoding","year":2012,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":158,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Human Genome Research Institute; Natural Sciences and Engineering Research Council of Canada; ExxonMobil Research and Engineering Company","keywords":"Boosting (machine learning); Encoding (memory); Computer science; Algorithm; Sequence (biology); Data compression; Compression (physics); Artificial intelligence","score_opus":0.08296651646590367,"score_gpt":0.3066863161757942,"score_spread":0.22371979970989056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111044311","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0067167077,0.00030342597,0.9895922,0.000043884524,0.000981133,0.00018497939,0.000013698077,0.00022552675,0.0019384457],"genre_scores_gemma":[0.19242942,0.000028016524,0.80694634,0.0003533696,0.00018263455,0.0000039682022,0.000016683094,0.0000107988935,0.000028774812],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99808526,0.000045116554,0.0005603871,0.00017747509,0.00052049826,0.0006112811],"domain_scores_gemma":[0.9985444,0.00011874906,0.0002989297,0.0006333629,0.000114833834,0.00028970282],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005529899,0.0002186725,0.00022466414,0.00011473981,0.00043137383,0.00028001398,0.0007810478,0.00010307531,0.0000126897785],"category_scores_gemma":[0.000075468,0.00017786253,0.00007204158,0.00030757123,0.00007516307,0.0029733675,0.0009538991,0.0001980353,0.00008781949],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017956114,0.00053252716,0.007545118,0.000794589,0.000111427384,0.00005260268,0.012898469,0.005487966,0.030120352,0.03243376,0.006466916,0.90353835],"study_design_scores_gemma":[0.00023209541,0.000026467664,0.0004018914,0.00026992348,0.000009116056,0.00014154849,0.00017635433,0.991502,0.002525733,0.00008464232,0.0043505477,0.00027966758],"about_ca_topic_score_codex":0.000025908057,"about_ca_topic_score_gemma":2.3619415e-7,"teacher_disagreement_score":0.98601407,"about_ca_system_score_codex":0.00010916622,"about_ca_system_score_gemma":0.00009455502,"threshold_uncertainty_score":0.7253024},"labels":[],"label_agreement":null},{"id":"W2111451842","doi":"10.1093/bioinformatics/btv284","title":"Identification of C2H2-ZF binding preferences from ChIP-seq data using RCADE","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Advanced Research; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Identification (biology); Chip; Computer science; Software; Data mining; Programming language; Telecommunications; Biology","score_opus":0.061321560761717665,"score_gpt":0.2850528448438939,"score_spread":0.22373128408217627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111451842","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9862954,0.00015896438,0.012277355,0.000014015589,0.00021885676,0.000108020315,0.00055077276,0.000008156586,0.0003684821],"genre_scores_gemma":[0.97324246,0.000078118064,0.024470452,0.000022773009,0.00009529431,0.0000015205972,0.002024169,0.000011485918,0.00005374261],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99908775,0.000017277765,0.00046205183,0.00014255934,0.00015629854,0.00013403248],"domain_scores_gemma":[0.9988065,0.000007798297,0.00034666323,0.0006896086,0.000080720594,0.000068739486],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027272772,0.00010693474,0.00012441918,0.00004074325,0.00004122849,0.000046480047,0.000512529,0.00011721574,0.000003965785],"category_scores_gemma":[0.00010688318,0.00010080912,0.00002871882,0.00007185039,0.000050261475,0.00001994011,0.00034149026,0.00004856432,0.000014001525],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043123095,0.000089916306,0.0073588197,0.00013486536,0.00016391966,4.943883e-7,0.0012945713,0.0016087586,0.9813094,0.00017526669,0.0019544146,0.0058664214],"study_design_scores_gemma":[0.001042569,0.00017098726,0.0027283956,0.0000728743,0.00012665485,0.000010846502,0.0035322907,0.73746043,0.24959676,0.0009075796,0.0037942596,0.0005563491],"about_ca_topic_score_codex":0.00003815602,"about_ca_topic_score_gemma":0.000018748276,"teacher_disagreement_score":0.7358517,"about_ca_system_score_codex":0.000016819036,"about_ca_system_score_gemma":0.00013702275,"threshold_uncertainty_score":0.41108766},"labels":[],"label_agreement":null},{"id":"W2111510868","doi":"10.1093/bioinformatics/btq200","title":"Model-based detection of alternative splicing signals","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"RNA Research and Splicing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Genome Canada; Ontario Genomics; Canadian Institute for Advanced Research; Ontario Genomics Institute; Ontario Innovation Trust","keywords":"Alternative splicing; RNA splicing; Exon; Computational biology; Probabilistic logic; Computer science; Proteome; Identification (biology); Exon skipping; Biology; Data mining; Gene; Bioinformatics; Artificial intelligence; Genetics; RNA","score_opus":0.016073067615979535,"score_gpt":0.2758594418579076,"score_spread":0.2597863742419281,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111510868","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8172516,0.000009853364,0.181617,0.000014785578,0.000052179686,0.00009416125,0.000008939371,0.000006061249,0.00094537984],"genre_scores_gemma":[0.9888182,0.000008529592,0.010832817,0.00008290196,0.000057591074,0.000005935821,0.000017798167,0.000007907081,0.00016828037],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994212,0.000008528245,0.00020159261,0.00007151746,0.00014228869,0.00015491704],"domain_scores_gemma":[0.9995018,0.000011133914,0.00009924191,0.00021438197,0.00010935586,0.00006406933],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019105381,0.00007584854,0.00008338561,0.00005732662,0.00004590872,0.000013727494,0.00013275532,0.00008315525,0.0000058036803],"category_scores_gemma":[0.000106954314,0.0000665273,0.00005571845,0.000058902016,0.000053078635,0.0000063614525,0.00004105934,0.000103964856,0.000006471886],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002787541,0.000013964216,0.00013324943,0.000031453754,0.000010781903,1.6468606e-7,0.000035859306,0.00386078,0.98906267,0.000038190523,0.000042514497,0.0067424946],"study_design_scores_gemma":[0.00016217917,0.000081896986,0.00005035856,0.0000051832944,0.000002444638,0.0000012207851,0.000023477218,0.41760308,0.58182317,0.000027024527,0.00017299225,0.00004697874],"about_ca_topic_score_codex":0.000019316467,"about_ca_topic_score_gemma":0.000043797074,"teacher_disagreement_score":0.4137423,"about_ca_system_score_codex":0.000005059331,"about_ca_system_score_gemma":0.000066573106,"threshold_uncertainty_score":0.27129045},"labels":[],"label_agreement":null},{"id":"W2111642038","doi":"10.1093/bioinformatics/btp415","title":"Statistical lower bounds on protein copy number from fluorescence expression images","year":2009,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomic variations and chromosomal abnormalities","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; Ottawa Hospital","funders":"Concordia University; Ottawa Hospital Research Institute; Natural Sciences and Engineering Research Council of Canada; McGill University","keywords":"Expression (computer science); Computer science; Noise (video); Estimator; Drosophila melanogaster; Computational biology; Segmentation; Algorithm; Pattern recognition (psychology); Biology; Gene; Artificial intelligence; Mathematics; Statistics; Genetics; Image (mathematics)","score_opus":0.006398281335425863,"score_gpt":0.23268936742304722,"score_spread":0.22629108608762136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111642038","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9651659,0.000037648035,0.018199831,0.0002009146,0.00019143934,0.00029454386,0.0004559436,0.000038614304,0.015415132],"genre_scores_gemma":[0.94701034,0.000018823348,0.05126803,0.00036570107,0.00016101803,0.000010618654,0.00040036044,0.0000085662505,0.0007565194],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992045,0.000020896112,0.00026572502,0.00013934473,0.0001593617,0.00021015249],"domain_scores_gemma":[0.9994698,0.000010770369,0.00008408454,0.00030398645,0.00005083355,0.000080521255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006397194,0.00014804404,0.000111809255,0.000016603564,0.000107927684,0.0000762582,0.00015682956,0.00011518027,0.00021034638],"category_scores_gemma":[0.0000492245,0.00012438829,0.000044431756,0.000035142515,0.000051336534,0.000012420556,0.00004679429,0.00007960134,0.00020472225],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00080545497,0.00079781783,0.005092422,0.000096908436,0.000090976966,0.000024477853,0.0010933738,0.00011324159,0.84973216,0.010634962,0.11077984,0.02073839],"study_design_scores_gemma":[0.00096085435,0.00088006863,0.010153993,0.00010343321,0.000019763087,0.000012945227,0.00034132754,0.0005086028,0.9498034,0.0018683927,0.034809433,0.00053779024],"about_ca_topic_score_codex":0.000010796374,"about_ca_topic_score_gemma":0.000001057164,"teacher_disagreement_score":0.10007125,"about_ca_system_score_codex":0.000016614538,"about_ca_system_score_gemma":0.0000547857,"threshold_uncertainty_score":0.5072407},"labels":[],"label_agreement":null},{"id":"W2111693807","doi":"10.1093/bioinformatics/btq266","title":"DETECT—a Density Estimation Tool for Enzyme ClassificaTion and its application to <i>Plasmodium falciparum</i>","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":60,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; Canada Research Chairs; Hospital for Sick Children; University of Toronto","funders":"Ontario Ministry of Research and Innovation; Canadian Institutes of Health Research","keywords":"Annotation; Ranking (information retrieval); Computer science; Computational biology; Probabilistic logic; Plasmodium falciparum; Sequence alignment; Genomics; Data mining; Biology; Machine learning; Artificial intelligence; Genetics; Gene; Peptide sequence; Genome; Malaria","score_opus":0.009605648486673174,"score_gpt":0.2615764797752238,"score_spread":0.25197083128855063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111693807","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54544723,0.000011851917,0.45270783,0.00024943732,0.00015756997,0.0009009774,0.00003795414,0.00004650729,0.00044064072],"genre_scores_gemma":[0.82245445,0.00001209703,0.17621197,0.0005539017,0.00011269434,0.00014734767,0.0003689548,0.000019216028,0.00011933843],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99900585,0.000012211973,0.00041831564,0.00017403002,0.00015247718,0.00023708574],"domain_scores_gemma":[0.9990544,0.000036086087,0.00021553918,0.0003922908,0.00018595016,0.00011573428],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039602388,0.00017825516,0.0001358307,0.000073766445,0.0001754456,0.00007203775,0.0001915618,0.00023411358,0.0000029963412],"category_scores_gemma":[0.0005878659,0.00017624082,0.000047951107,0.00009999645,0.000033758242,0.000028136406,0.000104380655,0.000142932,0.00006213477],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017409644,0.0000536362,0.0016031961,0.0004963477,0.000043482545,9.11305e-8,0.0006363132,0.0015737159,0.8977702,0.0051492644,0.0054730717,0.08702658],"study_design_scores_gemma":[0.0005214654,0.00022993838,0.004603269,0.000009821512,0.000029481462,0.000025481346,0.000051083316,0.7769703,0.16654465,0.00013806323,0.05052901,0.00034743795],"about_ca_topic_score_codex":0.0000022669806,"about_ca_topic_score_gemma":0.000022859975,"teacher_disagreement_score":0.7753966,"about_ca_system_score_codex":0.000014034719,"about_ca_system_score_gemma":0.000051031195,"threshold_uncertainty_score":0.7186892},"labels":[],"label_agreement":null},{"id":"W2111716459","doi":"10.1093/bioinformatics/btt611","title":"WaveCNV: allele-specific copy number alterations in primary tumors and xenograft models from next-generation sequencing","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomic variations and chromosomal abnormalities","field":"Biochemistry, Genetics and Molecular Biology","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research","funders":"Ontario Ministry of Research and Innovation","keywords":"Copy-number variation; Copy number analysis; Genome; Computational biology; DNA sequencing; Biology; Gene duplication; DNA microarray; Segmental duplication; Executable; Genetics; Comparative genomic hybridization; Computer science; Gene","score_opus":0.03453435057544929,"score_gpt":0.21140131668597067,"score_spread":0.17686696611052138,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111716459","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9849954,0.00020914851,0.010548552,0.00009026279,0.00006543566,0.0002605663,0.00005105019,0.000013642037,0.003765915],"genre_scores_gemma":[0.96542203,0.00031352034,0.032217663,0.00034120923,0.00016070233,0.000049527243,0.001246514,0.000013072162,0.00023574424],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99912727,0.000024582758,0.0004069402,0.000147426,0.00009819431,0.00019560622],"domain_scores_gemma":[0.99953806,0.000009540386,0.000094440664,0.00022133766,0.00007065849,0.000065964545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008139494,0.00014482527,0.00013286047,0.000040463197,0.00010968348,0.0001752585,0.0000940232,0.00010868616,0.00009013868],"category_scores_gemma":[0.000007395476,0.00013879065,0.000035109148,0.000060324117,0.00004126491,0.00008278443,0.00007653264,0.00007179374,0.00004865299],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000091645634,0.0003080813,0.02746397,0.0002967152,0.00027544438,0.000009597954,0.02358024,0.024565723,0.8494149,0.011242053,0.034546576,0.028205086],"study_design_scores_gemma":[0.0036823035,0.00037390707,0.017710688,0.00013837594,0.000059314498,0.00014143191,0.014456973,0.8235197,0.11700799,0.0058519365,0.0149679,0.0020894941],"about_ca_topic_score_codex":0.00027819068,"about_ca_topic_score_gemma":0.000095782845,"teacher_disagreement_score":0.79895395,"about_ca_system_score_codex":0.00005087806,"about_ca_system_score_gemma":0.000081291764,"threshold_uncertainty_score":0.56597185},"labels":[],"label_agreement":null},{"id":"W2112005039","doi":"10.1093/bioinformatics/btr629","title":"Feature-based classifiers for somatic mutation detection in tumour–normal paired sequencing data","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":154,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia; BC Cancer Agency","funders":"Canadian Institutes of Health Research; Michael Smith Health Research BC","keywords":"Computer science; Discriminative model; Artificial intelligence; Feature selection; Random forest; Machine learning; Ground truth; Genome; Support vector machine; Germline mutation; Cluster analysis; Computational biology; Mutation; Data mining; Biology; Genetics; Gene","score_opus":0.047249894469341115,"score_gpt":0.2508523294330022,"score_spread":0.20360243496366107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112005039","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5420939,0.00019105636,0.45431194,0.000117494055,0.0005868137,0.0009694942,0.00032867296,0.00003957863,0.0013611105],"genre_scores_gemma":[0.9498287,0.000025957017,0.048731092,0.00029233607,0.000097062984,0.000042327236,0.0009375253,0.00001814861,0.00002685076],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99926436,0.000014067814,0.0002606508,0.00015672446,0.00008413594,0.00022007462],"domain_scores_gemma":[0.9992932,0.000028988097,0.00015163531,0.00041047143,0.000057470133,0.00005820491],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026288317,0.00012529771,0.00011300301,0.00007801211,0.00006525665,0.000030697785,0.00022950032,0.00013663585,0.0000032107937],"category_scores_gemma":[0.00024968473,0.00012818686,0.000045497884,0.00008741774,0.000034252065,0.0000202557,0.000072521514,0.000063135936,0.0000048277493],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0031673608,0.00073277025,0.012088961,0.0038436723,0.00047283515,0.00005118383,0.008499238,0.010097534,0.6257664,0.0010909718,0.030136183,0.30405286],"study_design_scores_gemma":[0.0025940742,0.0006410272,0.0033724466,0.00007121773,0.00006974134,0.00002404146,0.001322941,0.5670371,0.4171394,0.00028536996,0.006924656,0.0005179844],"about_ca_topic_score_codex":0.000040350125,"about_ca_topic_score_gemma":0.0004359738,"teacher_disagreement_score":0.55693954,"about_ca_system_score_codex":0.000067921894,"about_ca_system_score_gemma":0.00022187673,"threshold_uncertainty_score":0.5227309},"labels":[],"label_agreement":null},{"id":"W2112034631","doi":"10.1093/bioinformatics/19.2.169","title":"Computational and experimental analysis reveals a novel Src family kinase in the C. elegans genome","year":2003,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetics, Aging, and Longevity in Model Organisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Biology; Proto-oncogene tyrosine-protein kinase Src; Gene; Genetics; Gene family; Open reading frame; Genome; Sequence analysis; Coding region; Phylogenetic tree; Myristoylation; Conserved sequence; Kinase; Computational biology; Peptide sequence; Phosphorylation","score_opus":0.013691928919307655,"score_gpt":0.24233260069530932,"score_spread":0.22864067177600167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112034631","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9487753,0.00059472263,0.04922694,0.00004758406,0.00003487378,0.00017229629,0.000031690233,0.0000052454798,0.0011113719],"genre_scores_gemma":[0.9750708,0.00003990975,0.02361337,0.0010477456,0.000025845147,0.0000092536775,0.00013034068,0.000007785413,0.000054962828],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9992123,0.00003659989,0.00027820148,0.0001313846,0.00015920182,0.00018228556],"domain_scores_gemma":[0.9995933,0.000014104778,0.00007596839,0.00023076036,0.000036181937,0.000049694467],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028528413,0.00012951657,0.00013664368,0.000081854894,0.00008057616,0.00005775742,0.00014702445,0.00007851614,0.0000075358184],"category_scores_gemma":[0.00002908586,0.00010540431,0.00006483468,0.00018248237,0.00007231675,0.0000069564403,0.000040779683,0.00006372233,0.0000053808944],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000973148,0.00146608,0.03661384,0.0002440169,0.0012915905,0.000017512095,0.047938075,0.117126636,0.7830043,0.0089444555,0.002487356,0.0007688679],"study_design_scores_gemma":[0.01378605,0.0027510093,0.46206564,0.00006573985,0.0016156277,0.00046364233,0.065043494,0.22358665,0.12951396,0.0023684988,0.094005115,0.0047345595],"about_ca_topic_score_codex":0.000013459009,"about_ca_topic_score_gemma":0.000014551777,"teacher_disagreement_score":0.6534903,"about_ca_system_score_codex":0.000012609458,"about_ca_system_score_gemma":0.000038272352,"threshold_uncertainty_score":0.4298263},"labels":[],"label_agreement":null},{"id":"W2112072385","doi":"10.1093/bioinformatics/btv006","title":"Integrating alignment-based and alignment-free sequence similarity measures for biological sequence classification","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"Government of Ontario; Ontario Institute for Cancer Research","keywords":"Weighting; Similarity (geometry); Sequence alignment; Sequence (biology); Classifier (UML); Multiple sequence alignment; Computer science; Artificial intelligence; Pattern recognition (psychology); Set (abstract data type); Metagenomics; Protein sequencing; Data mining; Computational biology; Biology; Genetics; Peptide sequence","score_opus":0.12212028373722353,"score_gpt":0.30315173594708955,"score_spread":0.18103145220986602,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112072385","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91554993,0.0009144553,0.07960206,0.00091764756,0.00026184635,0.00087181514,0.0004358057,0.00002298637,0.0014234715],"genre_scores_gemma":[0.9209817,0.00014926432,0.07797702,0.000568091,0.00007714245,0.000066351065,0.00014599744,0.000009595386,0.000024853001],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991094,0.000031059037,0.00030572034,0.00019355361,0.00013604626,0.00022422723],"domain_scores_gemma":[0.99920374,0.000033286608,0.00014541055,0.00033987433,0.00016280482,0.000114873976],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044383304,0.00016664392,0.00014882027,0.000025354553,0.000115638526,0.000046367677,0.00023213614,0.00013676313,7.2289635e-7],"category_scores_gemma":[0.00051486917,0.0001347883,0.000051292463,0.00004502321,0.00015596123,0.0000032164323,0.00013602924,0.000046992183,0.0000017177373],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022674799,0.000114194365,0.021907007,0.00015806429,0.00016096843,0.0000011277049,0.0010688471,0.0002446649,0.93619543,0.0051960554,0.009366571,0.025360309],"study_design_scores_gemma":[0.009736438,0.005538036,0.010499732,0.00016820623,0.00024735808,0.000072063034,0.013647109,0.1786659,0.49359107,0.01663537,0.2684072,0.002791515],"about_ca_topic_score_codex":0.000010813288,"about_ca_topic_score_gemma":0.000015733562,"teacher_disagreement_score":0.44260436,"about_ca_system_score_codex":0.000035299254,"about_ca_system_score_gemma":0.00011282289,"threshold_uncertainty_score":0.5496507},"labels":[],"label_agreement":null},{"id":"W2112491476","doi":"10.1093/bioinformatics/btp367","title":"<i>De novo</i> transcriptome assembly with ABySS","year":2009,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":410,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency","funders":"Genome British Columbia; Michael Smith Health Research BC; National Cancer Institute; Genome Canada","keywords":"Contig; Sequence assembly; Transcriptome; Genome; Computational biology; Java; Biology; De novo transcriptome assembly; Software; Computer science; Hybrid genome assembly; Source code; Shotgun sequencing; Reference genome; Perl; Genetics; Gene; Programming language; Gene expression","score_opus":0.009809137250629119,"score_gpt":0.24134644448210438,"score_spread":0.23153730723147525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112491476","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7296356,0.00046172168,0.1758008,0.0017215513,0.0002105132,0.00041963425,0.000023325949,0.00009854194,0.09162831],"genre_scores_gemma":[0.98830664,0.00008871114,0.008279017,0.002241423,0.000088103276,0.0000085219335,0.000058520927,0.000008194496,0.00092085946],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99943584,0.000009957727,0.00015925484,0.00009631336,0.00011956816,0.00017909343],"domain_scores_gemma":[0.9995604,0.000001801207,0.000063141386,0.0002550034,0.00004053687,0.000079107616],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008221749,0.00010090656,0.000075086784,0.000032860662,0.000052287356,0.00004040577,0.00013705701,0.00008603499,0.000009808737],"category_scores_gemma":[0.000008327382,0.00007901855,0.000038766055,0.00009264829,0.0000224046,0.0000075148223,0.000007712173,0.000051895357,0.000014964279],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013232707,0.000073642215,0.0003245116,0.000026206075,0.00001900716,0.0000013882513,0.00036247476,0.00010120885,0.955516,0.00063764333,0.014576945,0.02822868],"study_design_scores_gemma":[0.0016425438,0.0010372315,0.0077810003,0.000044616954,0.000030569754,0.000092933515,0.00044312468,0.001440564,0.4272533,0.00010872385,0.5596684,0.00045696643],"about_ca_topic_score_codex":5.8266306e-7,"about_ca_topic_score_gemma":0.0000010485873,"teacher_disagreement_score":0.54509145,"about_ca_system_score_codex":0.000012316782,"about_ca_system_score_gemma":0.00006871361,"threshold_uncertainty_score":0.32222828},"labels":[],"label_agreement":null},{"id":"W2112492259","doi":"10.1093/bioinformatics/btu172","title":"HyperModules: identifying clinically and phenotypically significant network modules with disease mutations for biomarker discovery","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Center for Research Resources; National Institute of General Medical Sciences; National Institutes of Health","keywords":"Personalized medicine; Biomarker discovery; Computational biology; Biomarker; Genomics; Disease; Phenotype; Computer science; Bioinformatics; Biology; Gene; Genetics; Medicine; Genome; Proteomics","score_opus":0.016452039156111462,"score_gpt":0.2520578626700897,"score_spread":0.23560582351397827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112492259","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11140632,0.00017187647,0.88670206,0.00016347307,0.00016579147,0.00054378744,0.00011357272,0.000026004198,0.0007070965],"genre_scores_gemma":[0.84637505,0.00015009136,0.1511424,0.0008783807,0.0003766562,0.00006709206,0.0007248399,0.000037110458,0.00024836836],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99862415,0.000026841952,0.00061458827,0.00021876555,0.00014247095,0.0003732028],"domain_scores_gemma":[0.9989158,0.00009234259,0.0002583046,0.00041109603,0.00010199756,0.00022046364],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044803135,0.00022683808,0.00022814111,0.000035486308,0.00023439103,0.00020221577,0.00019251107,0.00013047211,0.0000022575434],"category_scores_gemma":[0.00013139081,0.00017718921,0.00009975866,0.00007788357,0.0002025948,0.00003591803,0.00012191598,0.00008029548,0.0000057370576],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010048616,0.0010535797,0.044514894,0.0047200657,0.002767352,0.000009952755,0.002677451,0.055711843,0.01413935,0.11396137,0.054734904,0.69566065],"study_design_scores_gemma":[0.005011086,0.0015461759,0.038404863,0.0003538423,0.00047631204,0.000027940248,0.00067225605,0.8904512,0.00036308618,0.014993444,0.04593661,0.0017631847],"about_ca_topic_score_codex":0.0000017834183,"about_ca_topic_score_gemma":0.000008595463,"teacher_disagreement_score":0.8347394,"about_ca_system_score_codex":0.000009059995,"about_ca_system_score_gemma":0.00007394349,"threshold_uncertainty_score":0.72255665},"labels":[],"label_agreement":null},{"id":"W2112861424","doi":"10.1093/bioinformatics/btt744","title":"ALEA: a toolbox for allele-specific epigenomics analysis","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Epigenetics and DNA Methylation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; Simon Fraser University; University of British Columbia; BC Cancer Agency","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Genome British Columbia; Dermatology Foundation","keywords":"Epigenomics; Pipeline (software); Genome browser; Allele; Computational biology; Identification (biology); Biology; Computer science; Genetics; Genomics; Genome; Gene; DNA methylation; Gene expression; Programming language","score_opus":0.015137580687410666,"score_gpt":0.23971749601868483,"score_spread":0.22457991533127417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112861424","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5502935,0.0013598643,0.4426246,0.00014883766,0.00014941886,0.0007460342,0.00006927871,0.000023473944,0.0045849923],"genre_scores_gemma":[0.8508978,0.0012829804,0.14380032,0.0003359706,0.0003532845,0.00016278996,0.0016824648,0.000036668604,0.0014477143],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990919,0.000012710989,0.00038258382,0.00015639796,0.00010368114,0.00025267614],"domain_scores_gemma":[0.99918073,0.000020452142,0.00014276688,0.00039162024,0.00017225588,0.000092175105],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017222106,0.00014434833,0.00017368434,0.00009868571,0.00009404024,0.000081664475,0.0001734356,0.00014757691,0.00006114779],"category_scores_gemma":[0.00004596802,0.00013410165,0.00021009683,0.00017469481,0.000036336463,0.000009952475,0.000045048986,0.00004065583,0.00008073521],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002835933,0.00051595055,0.022263115,0.0004426989,0.004415421,0.000001268416,0.0026222162,0.01607798,0.5473033,0.0043352074,0.08772201,0.3140172],"study_design_scores_gemma":[0.0011742214,0.0005278317,0.015261393,0.0000057657885,0.00030369972,0.0000015465404,0.00057435554,0.051669985,0.12618694,0.0008415035,0.80266553,0.000787255],"about_ca_topic_score_codex":0.000010122054,"about_ca_topic_score_gemma":0.000015768705,"teacher_disagreement_score":0.7149435,"about_ca_system_score_codex":0.000015889384,"about_ca_system_score_gemma":0.00003226903,"threshold_uncertainty_score":0.5468506},"labels":[],"label_agreement":null},{"id":"W2112862832","doi":"10.1093/bioinformatics/btl414","title":"SANTA domain: a novel conserved protein module in <i>Eukaryota</i> with potential involvement in chromatin regulation","year":2006,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Genomics; University of Ottawa","funders":"","keywords":"Chromatin; Biology; Chromatin remodeling; Protein domain; Gene; Genome; Genetics; Conserved sequence; Computational biology; Lineage (genetic); Gene duplication; B3 domain; Phylogenetic tree; ChIA-PET; Transcription factor; DNA-binding domain; Peptide sequence","score_opus":0.004771413853950824,"score_gpt":0.18169389461563537,"score_spread":0.17692248076168454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112862832","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.990363,0.00005106645,0.00760096,0.0000569941,0.000025465786,0.000632937,0.00007067275,0.00001180942,0.0011870752],"genre_scores_gemma":[0.95404685,0.000007763663,0.044616554,0.00009949733,0.00004910536,0.000064586755,0.0009960856,0.000020162794,0.00009941497],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988257,0.000018783534,0.0005270651,0.00017431592,0.00017288476,0.00028124524],"domain_scores_gemma":[0.99941033,0.0000035397672,0.00019837283,0.00030408837,0.000044943212,0.00003874032],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018255941,0.00018670727,0.00017099992,0.00009201298,0.000043049826,0.000045185025,0.0001579247,0.00014021283,0.000011247871],"category_scores_gemma":[0.000008414522,0.00017264452,0.000040952706,0.0001599898,0.0000489756,0.000013980605,0.00009129494,0.000082319515,0.0000075453704],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022825484,0.0005484668,0.010012584,0.00036044643,0.00003421649,0.000012057009,0.00031257456,0.023268497,0.9627652,0.0009656596,0.001004289,0.0004877471],"study_design_scores_gemma":[0.01790651,0.0014448862,0.19785865,0.00080974365,0.00003659437,0.0001436202,0.0017427173,0.5489199,0.22176509,0.0028122414,0.004476742,0.0020832901],"about_ca_topic_score_codex":0.00015426517,"about_ca_topic_score_gemma":0.0011902832,"teacher_disagreement_score":0.7410001,"about_ca_system_score_codex":0.00006668641,"about_ca_system_score_gemma":0.00011539599,"threshold_uncertainty_score":0.7040239},"labels":[],"label_agreement":null},{"id":"W2112893969","doi":"10.1093/bioinformatics/btr303","title":"Sensitive and fast mapping of di-base encoded reads","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; Michael Smith Health Research BC; National Human Genome Research Institute; Howard Hughes Medical Institute","keywords":"Computer science; Sequence (biology); Genome; Software; Source code; Code (set theory); Computational biology; Biology; Genetics; Gene; Set (abstract data type)","score_opus":0.021789904438875348,"score_gpt":0.21008830602175843,"score_spread":0.18829840158288308,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112893969","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98700225,0.0001990222,0.003895288,0.000009962828,0.000057667792,0.00009447502,0.000037618905,0.0000023468574,0.008701353],"genre_scores_gemma":[0.9817572,0.0002797662,0.017777693,0.00007162449,0.000027738131,0.0000026815167,0.000013325263,0.0000061790633,0.00006379142],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99955314,0.00000888611,0.0001983833,0.00007682625,0.00004766409,0.00011507049],"domain_scores_gemma":[0.9996361,0.0000062170666,0.00009524553,0.00015722735,0.00006491718,0.00004026418],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008210172,0.00008949307,0.00011415995,0.000028486424,0.000037876533,0.0000044908948,0.00005539282,0.000057681114,0.0000020593607],"category_scores_gemma":[0.000024461215,0.00007935739,0.00003371934,0.000035105102,0.00009403869,9.192512e-7,0.000107927786,0.000025604562,0.0000025152565],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010272291,0.00008600405,0.018840035,0.0002480141,0.00029236835,0.0000033984456,0.015117991,0.00001688369,0.94166374,0.00085380505,0.00063823356,0.022136815],"study_design_scores_gemma":[0.00064112316,0.00043601365,0.04399751,0.000034439763,0.0000386649,0.000030121195,0.0052880007,0.0012919994,0.94500846,0.00016022866,0.0027504412,0.00032302673],"about_ca_topic_score_codex":0.000014478541,"about_ca_topic_score_gemma":0.000006440118,"teacher_disagreement_score":0.025157474,"about_ca_system_score_codex":0.0000025745824,"about_ca_system_score_gemma":0.00002068195,"threshold_uncertainty_score":0.32361007},"labels":[],"label_agreement":null},{"id":"W2113127959","doi":"10.1093/bioinformatics/btr461","title":"Reconstructing the architecture of the ancestral amniote genome","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Agence Nationale de la Recherche","keywords":"Amniote; Genome; Biology; Vertebrate; Evolutionary biology; Extant taxon; Phylogenomics; Genomics; Most recent common ancestor; Ancestor; Python (programming language); Context (archaeology); Phylogenetics; Genetics; Computer science; Gene; Paleontology; Clade; Geography","score_opus":0.020882426988871196,"score_gpt":0.20813427935761294,"score_spread":0.18725185236874176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113127959","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9815723,0.000196505,0.0030396702,0.00012707658,0.0003107304,0.00033966964,0.000029450986,0.000009965013,0.014374637],"genre_scores_gemma":[0.9688665,0.000059905353,0.030410886,0.00016194856,0.00013297984,0.0000069884163,0.000012979408,0.000012204802,0.00033558076],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994308,0.00002089208,0.00022240034,0.00006602241,0.00010130672,0.00015860212],"domain_scores_gemma":[0.9993692,0.000005010214,0.00016765686,0.00039754793,0.000035989066,0.00002460423],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014847715,0.00008972945,0.00007416779,0.000015760595,0.000080024074,0.000009351912,0.00037728605,0.000060562095,0.000020851572],"category_scores_gemma":[0.000031287556,0.0000430506,0.000083648956,0.000083165134,0.00015705348,0.0000031696711,0.00013891,0.00008654865,0.000006270373],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021708901,0.00024900152,0.099203736,0.0009224696,0.0011750163,0.0000032237706,0.03605448,0.00096220523,0.5490372,0.0016689246,0.0022290014,0.30827767],"study_design_scores_gemma":[0.0023743098,0.0009933835,0.16799033,0.0001422802,0.00025286226,0.00046530433,0.009625424,0.0031799208,0.6608431,0.0025581673,0.15016624,0.0014086845],"about_ca_topic_score_codex":0.000007501683,"about_ca_topic_score_gemma":0.0000065456175,"teacher_disagreement_score":0.30686897,"about_ca_system_score_codex":0.0000048059346,"about_ca_system_score_gemma":0.00003931464,"threshold_uncertainty_score":0.17555526},"labels":[],"label_agreement":null},{"id":"W2113154626","doi":"10.1093/bioinformatics/btt407","title":"RACER: Rapid and accurate correction of errors in reads","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":84,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Computer science; Software; Variety (cybernetics); Error detection and correction; DNA sequencing; Throughput; Data mining; Artificial intelligence; Algorithm; Programming language; Biology; Operating system","score_opus":0.010741544253993585,"score_gpt":0.22662187815072116,"score_spread":0.21588033389672756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113154626","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9958606,0.00048466396,0.00011962376,0.000042809254,0.00015420368,0.00014537605,0.000004695716,0.0000014266567,0.003186598],"genre_scores_gemma":[0.99659693,0.0009967413,0.0021451234,0.00006555958,0.00002167817,0.000010505887,0.000010740614,0.00000473154,0.00014798722],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9995802,0.000009010183,0.0002108012,0.00006127508,0.000039507977,0.00009921233],"domain_scores_gemma":[0.9997249,0.000007890846,0.0000813616,0.000117257514,0.000042983756,0.000025568668],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000075357144,0.00007012897,0.000094305986,0.000034401935,0.000020892541,0.000008709001,0.0000493396,0.00005984255,0.000008260519],"category_scores_gemma":[0.000035652767,0.00006141714,0.000020638963,0.000046372224,0.00004661886,0.00000182173,0.000062929284,0.000029056022,0.000005745735],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001020594,0.00012604763,0.07001358,0.00029028286,0.00016118976,7.3143724e-7,0.0038757273,0.0008734776,0.63561356,0.0001221429,0.017726652,0.27109453],"study_design_scores_gemma":[0.003031026,0.0015815191,0.5023945,0.000101766054,0.000054963148,0.00005306089,0.0073256507,0.05418189,0.36317047,0.00038337626,0.06672245,0.0009993104],"about_ca_topic_score_codex":0.000039484654,"about_ca_topic_score_gemma":0.000022308193,"teacher_disagreement_score":0.43238094,"about_ca_system_score_codex":0.0000037653267,"about_ca_system_score_gemma":0.000015896741,"threshold_uncertainty_score":0.2504518},"labels":[],"label_agreement":null},{"id":"W2113229776","doi":"10.1093/bioinformatics/btt527","title":"FPSAC: fast phylogenetic scaffolding of ancient contigs","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Yersinia bacterium, plague, ectoparasites research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Pacific Institute for the Mathematical Sciences; Simon Fraser University","funders":"","keywords":"Contig; Genome; Phylogenetic tree; Biology; Ancient DNA; Extant taxon; DNA sequencing; Clade; Whole genome sequencing; Evolutionary biology; Computational biology; Genetics; DNA; Gene","score_opus":0.011547503245307398,"score_gpt":0.25099856947682125,"score_spread":0.23945106623151385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113229776","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9947286,0.00017909943,0.0017204426,0.000040292955,0.00009950215,0.00034946934,0.00004327083,0.000011161999,0.0028281338],"genre_scores_gemma":[0.9930992,0.000067630324,0.0060110753,0.00018708971,0.000063921594,0.000021702046,0.00014995602,0.00001588706,0.000383503],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988574,0.000024725869,0.0003813398,0.00014265084,0.00023358146,0.00036032093],"domain_scores_gemma":[0.9990722,0.000015086994,0.00014764296,0.0004243856,0.00021106668,0.00012964284],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015858164,0.00014784493,0.00017746953,0.000088293426,0.00005396809,0.000048404218,0.00029090434,0.00012759218,0.00012450629],"category_scores_gemma":[0.00008364038,0.00013468575,0.000084756415,0.00014221274,0.00012536366,0.000012909247,0.000175005,0.00006447494,0.00020489158],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000133543035,0.000037593796,0.008564216,0.00008826308,0.000032478114,5.136428e-7,0.0001348545,0.000021934567,0.98167616,0.00001553759,0.0028460498,0.0065690167],"study_design_scores_gemma":[0.0008652986,0.0005148022,0.10573371,0.000050668266,0.000018916246,0.00004130228,0.00045386588,0.006758684,0.8643615,0.000009700547,0.02080544,0.0003860866],"about_ca_topic_score_codex":0.000017692204,"about_ca_topic_score_gemma":0.0000055237147,"teacher_disagreement_score":0.11731467,"about_ca_system_score_codex":0.000018526367,"about_ca_system_score_gemma":0.000080932325,"threshold_uncertainty_score":0.54923254},"labels":[],"label_agreement":null},{"id":"W2113432929","doi":"10.1093/bioinformatics/bth339","title":"A spline function approach for detecting differentially expressed genes in microarray data analysis","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; Mount Sinai Hospital","funders":"Networks of Centres of Excellence of Canada; Canadian Institutes of Health Research","keywords":"Bayes' theorem; Parametric statistics; Computer science; Microarray analysis techniques; Statistical hypothesis testing; Covariate; Nonparametric statistics; Bayes factor; Parametric model; Sample size determination; False discovery rate; Inference; Data mining; Bayesian probability; Statistics; Mathematics; Gene; Machine learning; Artificial intelligence; Biology; Genetics; Gene expression","score_opus":0.0336993615275709,"score_gpt":0.2709232451001219,"score_spread":0.23722388357255098,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113432929","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13153714,0.00019891869,0.867622,0.000034218167,0.00007571069,0.00024648817,0.000058205318,0.000013032643,0.00021425956],"genre_scores_gemma":[0.89203054,0.00009435231,0.1044507,0.00010446001,0.00012630233,0.00006009486,0.0030369926,0.00001243116,0.000084096864],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99916404,0.000012921078,0.00031996693,0.00024168642,0.00009619943,0.00016520251],"domain_scores_gemma":[0.99909776,0.0000050469826,0.00014470353,0.0006573828,0.00005154007,0.000043545617],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019124891,0.0001157596,0.00013927589,0.000141619,0.00006503213,0.000040931667,0.00027918452,0.000115834504,0.000003707215],"category_scores_gemma":[0.000047358164,0.00010392499,0.00007329731,0.0002623249,0.000019672521,0.000013424052,0.00011116488,0.00004609058,0.000001462716],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016300808,0.00011634877,0.0008691575,0.0001020269,0.00017521795,7.457159e-8,0.00015723871,0.007981665,0.9729033,0.000039213024,0.00032239422,0.017170321],"study_design_scores_gemma":[0.005571186,0.00037242816,0.008469848,0.000042056574,0.000686695,0.000004576128,0.0018387289,0.2116078,0.74514073,0.00023758874,0.025180966,0.0008474117],"about_ca_topic_score_codex":0.000009611928,"about_ca_topic_score_gemma":0.000047612204,"teacher_disagreement_score":0.7631713,"about_ca_system_score_codex":0.000018836592,"about_ca_system_score_gemma":0.00006275388,"threshold_uncertainty_score":0.42379382},"labels":[],"label_agreement":null},{"id":"W2113574907","doi":"10.1093/bioinformatics/btl238","title":"Integrating copy number polymorphisms into array CGH analysis using a robust HMM","year":2006,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomic variations and chromosomal abnormalities","field":"Biochemistry, Genetics and Molecular Biology","cited_by":184,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Michael Smith Health Research BC; Genome Canada","keywords":"Outlier; Hidden Markov model; Computer science; Comparative genomic hybridization; Segmentation; Pattern recognition (psychology); Copy-number variation; Benchmark (surveying); Artificial intelligence; Chromosome; Biology; Genome; Genetics; Gene","score_opus":0.00988208704385298,"score_gpt":0.22812102365176937,"score_spread":0.21823893660791638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113574907","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7809937,0.00008034229,0.20942041,0.000037670135,0.00011185191,0.00010092883,0.000040766066,0.000023305482,0.009190998],"genre_scores_gemma":[0.85663646,0.000009292891,0.14199737,0.000117509466,0.00019983867,0.000006237432,0.00039035894,0.000013115009,0.000629839],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998988,0.000022581595,0.00046161588,0.00014166786,0.00013595975,0.00025022548],"domain_scores_gemma":[0.99933404,0.000008392424,0.00019941428,0.00030628918,0.00009701778,0.00005487182],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013628993,0.00017941317,0.0001950873,0.00008607248,0.00019254479,0.0000950199,0.00016603923,0.00013581073,0.00010913083],"category_scores_gemma":[0.000020829078,0.00016224841,0.00017692888,0.00030583167,0.000059736944,0.000016687782,0.000068552865,0.00007022196,0.000035273126],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014099704,0.0005114478,0.49120963,0.00035576583,0.0030135063,0.000011880182,0.006500112,0.088859834,0.38318434,0.0141147785,0.008811699,0.0032860094],"study_design_scores_gemma":[0.0034966865,0.0005448238,0.019859148,0.00015285063,0.0030515147,0.0003555367,0.016884377,0.20620148,0.6898589,0.0023431233,0.053244956,0.0040065837],"about_ca_topic_score_codex":0.000582031,"about_ca_topic_score_gemma":0.00020896099,"teacher_disagreement_score":0.4713505,"about_ca_system_score_codex":0.000042987376,"about_ca_system_score_gemma":0.00008361126,"threshold_uncertainty_score":0.66162986},"labels":[],"label_agreement":null},{"id":"W2113595151","doi":"10.1093/bioinformatics/btq422","title":"Multiple gene expression profile alignment for microarray time-series data clustering","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Cluster analysis; Pairwise comparison; Data mining; Computer science; Similarity (geometry); Series (stratigraphy); Expression (computer science); Time series; Data set; Dimension (graph theory); Data point; Similarity measure; Pattern recognition (psychology); Artificial intelligence; Mathematics; Machine learning; Biology","score_opus":0.024812553836522346,"score_gpt":0.2374502952753484,"score_spread":0.21263774143882605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113595151","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003924562,0.000019579233,0.9939414,0.00016832423,0.00040834243,0.00033933308,0.0001280503,0.00013009629,0.0009402868],"genre_scores_gemma":[0.009152387,0.000004931259,0.98965275,0.00007586116,0.00012416435,0.000020988966,0.00023319894,0.000010793182,0.00072494114],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989146,0.0000073008773,0.0003964463,0.00021171416,0.00018378325,0.00028617444],"domain_scores_gemma":[0.9983899,0.00005578125,0.00020565327,0.0011976911,0.000064993044,0.00008598833],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035962576,0.00014169698,0.00017054273,0.000055983266,0.00025090337,0.00028104745,0.0012386085,0.00006784777,0.00004218896],"category_scores_gemma":[0.00009999998,0.000114090944,0.000057144072,0.00012068458,0.000035436326,0.0014764346,0.0010708185,0.000087341854,0.000083340645],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006656384,0.00015845588,0.0005394126,0.00041824314,0.00011549615,0.0000035813011,0.0054183607,0.0006769854,0.7337163,0.0012151091,0.04263605,0.21503545],"study_design_scores_gemma":[0.00022319169,0.000042370008,0.000028589826,0.000017189925,0.000008404515,0.000012178121,0.00008975784,0.8665406,0.084947996,0.00003134879,0.04789042,0.00016794218],"about_ca_topic_score_codex":0.0000053582153,"about_ca_topic_score_gemma":0.000015398587,"teacher_disagreement_score":0.8658636,"about_ca_system_score_codex":0.00001213091,"about_ca_system_score_gemma":0.00003661557,"threshold_uncertainty_score":0.46524936},"labels":[],"label_agreement":null},{"id":"W2113768712","doi":"10.1093/bioinformatics/btt591","title":"ORMAN: Optimal resolution of ambiguous RNA-Seq multimappings in the presence of novel isoforms","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"RNA-Seq; Focus (optics); Gene isoform; Resolution (logic); Computational biology; Computer science; RNA; Biology; Artificial intelligence; Genetics; Transcriptome; Gene; Physics; Gene expression","score_opus":0.016720026813189442,"score_gpt":0.23036194235701427,"score_spread":0.21364191554382483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113768712","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.994646,0.00022711737,0.0031206447,0.000089952315,0.0000511751,0.00029657743,0.000021694901,0.0000012771039,0.0015455275],"genre_scores_gemma":[0.9787655,0.00018062968,0.020842483,0.00009774315,0.000024660438,0.000020345784,0.000014772687,0.00000490937,0.000048990187],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999246,0.000009575401,0.00038476606,0.000072836665,0.00012307074,0.0001637614],"domain_scores_gemma":[0.99940723,0.000013796416,0.000187562,0.00026841328,0.00010301559,0.000019951141],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019500342,0.00009473821,0.00012978051,0.000037624366,0.00003271313,0.000009743253,0.00024819505,0.00007388749,0.0000033817148],"category_scores_gemma":[0.00007285839,0.00006465587,0.000054253134,0.000087165834,0.00011804791,0.000003809911,0.00012216397,0.000049455368,0.0000035032742],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007531698,0.0003461767,0.0031296392,0.00035789792,0.0001081426,3.1435704e-7,0.008262375,0.007534477,0.96008116,0.00044384704,0.00388452,0.015776133],"study_design_scores_gemma":[0.0048619662,0.0021686058,0.22146825,0.00020052909,0.000076130054,0.000054544194,0.015771367,0.30719352,0.4321257,0.00022634164,0.014865101,0.0009879449],"about_ca_topic_score_codex":0.00024397677,"about_ca_topic_score_gemma":0.000013782388,"teacher_disagreement_score":0.5279555,"about_ca_system_score_codex":0.0000052209457,"about_ca_system_score_gemma":0.000030129779,"threshold_uncertainty_score":0.26365897},"labels":[],"label_agreement":null},{"id":"W2113892406","doi":"10.1093/bioinformatics/btm491","title":"<i>CellLine</i>, a stochastic cell lineage simulator","year":2007,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Lineage (genetic); Computer science; Cellular differentiation; Cell fate determination; Bistability; Gene regulatory network; Biology; Gene; Biological system; Computational biology; Genetics; Physics; Gene expression","score_opus":0.0066561639445456245,"score_gpt":0.2249542220159751,"score_spread":0.21829805807142946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113892406","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5468209,0.0006047121,0.44865066,0.000017462628,0.00020925101,0.0002126097,0.000013403164,0.000042502408,0.0034284908],"genre_scores_gemma":[0.9849575,0.000028474848,0.012692756,0.00037365512,0.00044332363,0.0000029228524,0.00013446488,0.000028223103,0.0013386923],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99871933,0.000013554791,0.00047790242,0.00017200847,0.00021554442,0.00040166793],"domain_scores_gemma":[0.9989994,0.00002414759,0.00017229028,0.00051709486,0.0001023984,0.00018464187],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043720708,0.00020378028,0.0001772722,0.00008224772,0.000088625085,0.000028825489,0.00023467642,0.00018789784,0.000027683027],"category_scores_gemma":[0.000044742643,0.00019193922,0.00016485846,0.00020348406,0.000059261078,0.000005434195,0.00011565617,0.000090887974,0.00013879295],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005924909,0.00091046636,0.005771137,0.0006577333,0.00082462723,0.00003580624,0.0014578091,0.5142111,0.384041,0.0002761897,0.063205,0.028016645],"study_design_scores_gemma":[0.0027555756,0.00065382133,0.0011700267,0.00003938327,0.00031335844,0.000047096673,0.0007654967,0.32303372,0.49554664,0.000041427375,0.17408015,0.0015533029],"about_ca_topic_score_codex":0.000002058264,"about_ca_topic_score_gemma":0.000012334314,"teacher_disagreement_score":0.43813658,"about_ca_system_score_codex":0.000018542303,"about_ca_system_score_gemma":0.0000602341,"threshold_uncertainty_score":0.7827054},"labels":[],"label_agreement":null},{"id":"W2113944588","doi":"10.1093/bioinformatics/btn433","title":"Accurate sequence-based prediction of catalytic residues","year":2008,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":85,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Nankai University","keywords":"Support vector machine; Curse of dimensionality; Sequence (biology); Computer science; Classifier (UML); Protein structure prediction; Feature selection; Artificial intelligence; Biological system; Data mining; Pattern recognition (psychology); Protein structure; Chemistry; Biology; Biochemistry","score_opus":0.028211413451712894,"score_gpt":0.26240301861543913,"score_spread":0.23419160516372622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113944588","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9414378,0.00013054498,0.03953401,0.00011874831,0.000280164,0.00042889643,0.0002838111,0.00009670048,0.017689323],"genre_scores_gemma":[0.96783745,0.000103865386,0.03064948,0.00022774948,0.000080606056,0.000008977158,0.00070352136,0.000017023904,0.00037132244],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988642,0.000023092003,0.00055991084,0.000097117234,0.00024534567,0.0002103603],"domain_scores_gemma":[0.9989862,0.000020011092,0.00031939187,0.00046070665,0.00014049395,0.00007320621],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019658572,0.00015824579,0.00016399653,0.000087818706,0.00010616287,0.0000119935585,0.00024013115,0.0001505152,0.000014233796],"category_scores_gemma":[0.00025977654,0.00014218852,0.000085798245,0.00014473707,0.00018817182,0.000017796256,0.000072826384,0.00010845049,0.000036819267],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015773431,0.001232331,0.35383806,0.006312343,0.0011762168,0.00005293434,0.015072884,0.1254538,0.24290124,0.0025393637,0.21642981,0.033413667],"study_design_scores_gemma":[0.0030242193,0.0018482847,0.03851151,0.00020115066,0.000095033865,0.00030105584,0.00055232685,0.5443331,0.34532413,0.000052580865,0.064847514,0.00090905634],"about_ca_topic_score_codex":0.000013265272,"about_ca_topic_score_gemma":0.0000042860047,"teacher_disagreement_score":0.41887933,"about_ca_system_score_codex":0.000018647745,"about_ca_system_score_gemma":0.00020967619,"threshold_uncertainty_score":0.57982796},"labels":[],"label_agreement":null},{"id":"W2114013334","doi":"10.1093/bioinformatics/btr368","title":"SpEED: fast computation of sensitive spaced seeds","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":62,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Software; Computation; Speedup; Similarity (geometry); Source code; Sequence (biology); Code (set theory); Algorithm; Data mining; Artificial intelligence; Parallel computing; Programming language; Biology; Image (mathematics)","score_opus":0.019925179716295455,"score_gpt":0.22735844778708,"score_spread":0.20743326807078455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114013334","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9789874,0.0000690856,0.00844183,0.000011138924,0.0001162183,0.000115030234,0.000028222445,0.000003172979,0.012227934],"genre_scores_gemma":[0.9802018,0.000048997274,0.019547287,0.00006577969,0.00003870442,8.5468395e-7,0.000023941227,0.0000070443807,0.00006561507],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995433,0.000009368516,0.00020327033,0.00006642209,0.00006597663,0.00011163532],"domain_scores_gemma":[0.9996107,0.0000038682047,0.00012104085,0.00012297416,0.00010796278,0.000033460296],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000071942646,0.00008852278,0.0001073505,0.000030170515,0.00003130195,0.000004088416,0.00006149508,0.000059210877,0.0000029409691],"category_scores_gemma":[0.000015645404,0.00008116618,0.00005005251,0.000046895522,0.00006522941,8.908578e-7,0.00007513312,0.000024338744,0.0000111170975],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003013434,0.00025259302,0.022367146,0.00033008595,0.00070127146,0.0000038103335,0.019906417,0.00062032964,0.91840136,0.0014966184,0.0031378348,0.032481164],"study_design_scores_gemma":[0.0010341514,0.0008913135,0.09169219,0.000035183177,0.00007086632,0.000028424709,0.0034314857,0.005942949,0.8936295,0.0004131165,0.002377339,0.00045351248],"about_ca_topic_score_codex":0.000013752603,"about_ca_topic_score_gemma":0.00000652949,"teacher_disagreement_score":0.06932504,"about_ca_system_score_codex":0.0000039000874,"about_ca_system_score_gemma":0.000025178153,"threshold_uncertainty_score":0.33098608},"labels":[],"label_agreement":null},{"id":"W2114143739","doi":"10.1093/bioinformatics/18.3.484","title":"Assembly of fingerprint contigs: parallelized FPC","year":2002,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Biometric Identification and Security","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency","funders":"National Human Genome Research Institute; BC Cancer Agency","keywords":"Contig; Fingerprint (computing); Computer science; File Transfer Protocol; Artificial intelligence; Operating system; Biology; Genome; Genetics; The Internet","score_opus":0.039415668603740885,"score_gpt":0.24664642156911182,"score_spread":0.20723075296537094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114143739","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014819912,0.0001614375,0.9645546,0.0006613333,0.00043747417,0.0001817333,0.00001005548,0.0001505767,0.019022893],"genre_scores_gemma":[0.8092661,0.00028737928,0.18858883,0.0003464096,0.000026340462,0.000007612212,0.000008338612,0.0000045644347,0.0014644231],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991484,0.000017025342,0.00039609484,0.00007900167,0.00021881195,0.00014061708],"domain_scores_gemma":[0.9991358,0.00005142945,0.00019133932,0.0004610398,0.0000992139,0.00006117529],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001824661,0.00007540896,0.0001435086,0.00020310108,0.000045634166,0.0000940281,0.000520036,0.00005512792,0.00008141887],"category_scores_gemma":[0.00007735789,0.00006418308,0.00006845955,0.0006086896,0.00003402512,0.00036231743,0.00008421667,0.000045016088,0.00029723835],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004891725,0.0004389565,0.00040551118,0.00019228828,0.00006724302,0.00000318934,0.012827962,0.000015774089,0.0018746541,0.15809827,0.020965485,0.8051058],"study_design_scores_gemma":[0.00051175186,0.00006289815,0.0015792134,0.000012057159,0.0000044572416,0.0000068437807,0.00006610989,0.77158093,0.0036437295,0.00017905273,0.22219308,0.00015986327],"about_ca_topic_score_codex":0.0000091617585,"about_ca_topic_score_gemma":0.0000013691013,"teacher_disagreement_score":0.80494595,"about_ca_system_score_codex":0.000023049555,"about_ca_system_score_gemma":0.000018224198,"threshold_uncertainty_score":0.38204968},"labels":[],"label_agreement":null},{"id":"W2115480698","doi":"10.1093/bioinformatics/btn176","title":"A robust framework for detecting structural variations in a genome","year":2008,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":60,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Genome; Structural variation; Computational biology; Biology; Identification (biology); Genetics; Source code; Reference genome; 1000 Genomes Project; Population; Human genome; Probabilistic logic; Computer science; Gene; Single-nucleotide polymorphism; Genotype; Artificial intelligence","score_opus":0.0291062581705459,"score_gpt":0.24351418172296851,"score_spread":0.2144079235524226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115480698","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88866967,0.00028464125,0.11021316,0.000043143224,0.0001334512,0.00027250728,0.000043823937,0.0000043460177,0.00033526018],"genre_scores_gemma":[0.78102124,0.00008050663,0.21857126,0.00011300185,0.00011931038,0.00002927336,0.000025680056,0.0000089634805,0.000030768417],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9994048,0.0000068135673,0.0002394737,0.000098422606,0.00005154528,0.00019892736],"domain_scores_gemma":[0.9996417,0.000026301137,0.00007890413,0.00017018282,0.00004866913,0.000034213957],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007861357,0.00009930561,0.00010605013,0.000040727857,0.00015401159,0.000011656858,0.00010610173,0.00009746855,0.0000028456254],"category_scores_gemma":[0.00015401728,0.00009467267,0.000056131015,0.00007558091,0.00003377727,0.0000012546452,0.000064172535,0.000052646898,0.000002773658],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010101508,0.00044689662,0.25231358,0.0013557855,0.0016492911,0.000022647513,0.05909428,0.09434197,0.5038333,0.03664844,0.0022552395,0.047028437],"study_design_scores_gemma":[0.0077082887,0.0024629885,0.6866108,0.00012537229,0.0001576336,0.0004558385,0.0053541604,0.18228817,0.035252847,0.021847878,0.05430845,0.0034275632],"about_ca_topic_score_codex":0.000006924716,"about_ca_topic_score_gemma":0.00002264517,"teacher_disagreement_score":0.46858042,"about_ca_system_score_codex":0.000013485239,"about_ca_system_score_gemma":0.000048081914,"threshold_uncertainty_score":0.38606396},"labels":[],"label_agreement":null},{"id":"W2116062363","doi":"10.1093/bioinformatics/btp011","title":"SCARF: maximizing next-generation EST assemblies for evolutionary and population genomic analyses","year":2009,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Contig; License; Sequence assembly; Sequence (biology); Computer science; MIT License; Software; Genomics; Computational biology; Population; Biology; Programming language; Genome; Genetics; Operating system; Gene","score_opus":0.06561212450917692,"score_gpt":0.297059179803663,"score_spread":0.23144705529448606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116062363","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9920497,0.0022614545,0.0049249544,0.000121671845,0.00009869526,0.00022381198,0.000029131634,0.000005928159,0.000284684],"genre_scores_gemma":[0.96131486,0.00053620985,0.037306104,0.00022794974,0.0002424405,0.000010410763,0.00031554734,0.0000071908025,0.000039264316],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99942696,0.0000068559193,0.00023817527,0.00012129839,0.000060769697,0.00014596556],"domain_scores_gemma":[0.99964815,0.000008563943,0.000097875716,0.00014086938,0.00006567733,0.00003888044],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008529252,0.00011747795,0.000115529205,0.000051015573,0.00017965968,0.000056991867,0.00006168167,0.000077602475,8.5381686e-7],"category_scores_gemma":[0.000038392594,0.000110921326,0.000054532582,0.000042059637,0.000021695583,0.0000055048995,0.00003609808,0.000022500994,0.0000014576832],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003199258,0.000024210633,0.0033029178,0.000034677294,0.00006609403,1.14633394e-7,0.00017137933,0.001234931,0.9650282,0.00041607348,0.0017647207,0.027924674],"study_design_scores_gemma":[0.0025330523,0.0019164012,0.5970434,0.000043530425,0.00033452583,0.0000626648,0.0014929753,0.27027553,0.096843384,0.0027840887,0.02520081,0.0014696352],"about_ca_topic_score_codex":0.00000989458,"about_ca_topic_score_gemma":0.000012761414,"teacher_disagreement_score":0.8681848,"about_ca_system_score_codex":0.000014417889,"about_ca_system_score_gemma":0.000024709201,"threshold_uncertainty_score":0.45232403},"labels":[],"label_agreement":null},{"id":"W2116063068","doi":"10.1093/bioinformatics/btl379","title":"General framework for developing and evaluating database scoring algorithms using the TANDEM search engine","year":2006,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":218,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Cancer Institute; U.S. Public Health Service","keywords":"Computer science; Database search engine; Database; Function (biology); Software; Suite; Information retrieval; Matching (statistics); Source code; Data mining; Open source; Search engine; Programming language; Mathematics","score_opus":0.07749868424509176,"score_gpt":0.3742599619674528,"score_spread":0.29676127772236105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116063068","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.122488,0.00009035329,0.87674445,0.00008967546,0.000013701829,0.0002394128,0.000044018492,0.00007001711,0.00022039731],"genre_scores_gemma":[0.016250152,0.000037003658,0.98320556,0.000058118472,0.00024537562,0.00007579681,0.00006565972,0.000016988204,0.000045351957],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992484,0.0000034942714,0.00028731543,0.000100315636,0.00013603806,0.00022443816],"domain_scores_gemma":[0.9994182,0.00013739204,0.00010555148,0.00024137736,0.000071100934,0.000026350837],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000277617,0.00010896876,0.0000978251,0.000024088373,0.00037053536,0.00007627043,0.0001400074,0.000069036774,0.0000055062674],"category_scores_gemma":[0.000059890397,0.00008663064,0.000026828695,0.000100617406,0.000042328316,0.00014309832,0.000114846705,0.0001599326,7.135791e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038178332,0.00008434854,0.0030824726,0.002311271,0.00011241115,0.0000022590805,0.0015792178,0.020449692,0.2140604,0.47316444,0.0004128336,0.28470248],"study_design_scores_gemma":[0.00015681659,0.0000062840154,0.0000135175305,0.00013454437,0.000016068941,0.000011751868,0.00025052656,0.86234003,0.12632823,0.009746153,0.0008386869,0.00015741527],"about_ca_topic_score_codex":0.00002099189,"about_ca_topic_score_gemma":0.0000010795108,"teacher_disagreement_score":0.84189034,"about_ca_system_score_codex":0.00006909124,"about_ca_system_score_gemma":0.00005504313,"threshold_uncertainty_score":0.35326952},"labels":[],"label_agreement":null},{"id":"W2116887561","doi":"10.1093/bioinformatics/btl553","title":"Dependence network modeling for biomarker identification","year":2006,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Biomarker discovery; Biomarker; Identification (biology); Computational biology; Consistency (knowledge bases); Cancer; Cancer biomarkers; Microarray analysis techniques; Computer science; Microarray; Relevance (law); Data mining; Bioinformatics; Gene; Biology; Proteomics; Artificial intelligence; Genetics; Gene expression","score_opus":0.022975766169512985,"score_gpt":0.26833696639057386,"score_spread":0.24536120022106087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116887561","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038628384,0.0002956468,0.95798993,0.000091998525,0.00027290775,0.00026749627,0.000012900779,0.00002280633,0.0024179006],"genre_scores_gemma":[0.9793618,0.000048124,0.018786041,0.0001311423,0.0002842906,0.00007296285,0.00041627645,0.000011728774,0.00088767],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99933404,0.000008631125,0.00028539557,0.00011902439,0.000094905714,0.00015800147],"domain_scores_gemma":[0.99951077,0.00000453907,0.00011106658,0.0002484674,0.00009616632,0.00002900642],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017913252,0.000080812,0.000057670888,0.00002788231,0.00010516896,0.00004304253,0.00012404007,0.000092051545,0.0000042305696],"category_scores_gemma":[0.000023444156,0.00007622666,0.000054113218,0.0000784393,0.000015841677,0.000008463998,0.000028473356,0.000022245407,0.000012377163],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001723823,0.000090025234,0.0012954336,0.00016342396,0.00004467625,1.707838e-7,0.0000741279,0.0761092,0.70542806,0.005440546,0.17595606,0.035225924],"study_design_scores_gemma":[0.00054303015,0.00004761866,0.0013230785,0.000020673066,0.000020991172,0.0000047687886,0.00009600296,0.8604364,0.052156072,0.001954746,0.08312326,0.00027340022],"about_ca_topic_score_codex":0.00000428946,"about_ca_topic_score_gemma":0.000007759482,"teacher_disagreement_score":0.9407334,"about_ca_system_score_codex":0.000010862873,"about_ca_system_score_gemma":0.000038812428,"threshold_uncertainty_score":0.3108433},"labels":[],"label_agreement":null},{"id":"W2117368100","doi":"10.1093/bioinformatics/btm538","title":"GEIGER: investigating evolutionary radiations","year":2007,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Evolution and Paleontology Studies","field":"Earth and Planetary Sciences","cited_by":2550,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"","keywords":"Geiger counter; Computer science; Software; R package; Software package; Theoretical computer science; Programming language; Physics; Nuclear physics","score_opus":0.026116039978048948,"score_gpt":0.2387691718893873,"score_spread":0.21265313191133833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117368100","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23865573,0.0025202944,0.012795013,0.000995968,0.0012122974,0.00027259364,0.00009487422,0.00029628235,0.74315697],"genre_scores_gemma":[0.93188643,0.000062733314,0.066206954,0.0011665573,0.00014978973,4.4638534e-7,0.00011368785,0.0000015513555,0.000411852],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9992557,0.000012662759,0.00028295026,0.000057722922,0.00014815708,0.00024277063],"domain_scores_gemma":[0.9994856,0.00018340249,0.00008940721,0.00009664484,0.00003863142,0.00010628327],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003137391,0.00007661487,0.00008377733,0.000085389824,0.00032534386,0.000015584881,0.00009195752,0.000057448608,0.00033682946],"category_scores_gemma":[0.00013290838,0.000065256456,0.00003296402,0.00019772556,0.00013497654,0.00023314838,0.000006553413,0.000091269794,0.00074690755],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000022724473,0.0000034477887,0.97561145,0.000012070273,0.000011849733,0.0000012390963,0.00093662133,0.00022500305,8.779741e-7,0.00089382066,0.007617218,0.014684154],"study_design_scores_gemma":[0.0001064521,0.000023157669,0.9473146,0.0000060427783,0.0000063050884,0.00001674102,0.0011007175,0.029878434,0.000004366615,0.000470418,0.020977963,0.00009480044],"about_ca_topic_score_codex":0.0001285275,"about_ca_topic_score_gemma":0.0046459683,"teacher_disagreement_score":0.7427451,"about_ca_system_score_codex":0.0000056878694,"about_ca_system_score_gemma":0.00004014662,"threshold_uncertainty_score":0.96002346},"labels":[],"label_agreement":null},{"id":"W2117428399","doi":"10.1093/bioinformatics/btu665","title":"ExomeAI: detection of recurrent allelic imbalance in tumors using whole-exome sequencing data","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University and Génome Québec Innovation Centre","funders":"Canadian Institutes of Health Research; Diamond Blackfan Anemia Foundation","keywords":"Exome sequencing; Allele; Exome; Genetics; Computational biology; Computer science; Biology; Gene; Mutation","score_opus":0.032638080909792394,"score_gpt":0.26518746949311117,"score_spread":0.23254938858331878,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117428399","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98983866,0.0002806147,0.009358167,0.000009491836,0.00012118354,0.000109106564,0.00007082577,0.0000057484485,0.00020622014],"genre_scores_gemma":[0.99568444,0.00007772358,0.0038270932,0.000055539695,0.00006903094,0.0000021051453,0.00026320596,0.000009376158,0.000011502885],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992426,0.000021105854,0.00034278687,0.00013446853,0.000094574505,0.00016444805],"domain_scores_gemma":[0.99922913,0.00000669367,0.00016644382,0.000504342,0.000043867152,0.00004951792],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022621187,0.00010138779,0.00013109067,0.000062617226,0.000033387252,0.000015360321,0.00026231012,0.00006760229,0.0000015286397],"category_scores_gemma":[0.00010682815,0.00009625147,0.000034927365,0.00008657506,0.000036154855,0.000012271575,0.00019286737,0.000051044048,0.000004179728],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008816553,0.00009490112,0.0052980813,0.0004973975,0.00004611017,0.0000031833313,0.0004085926,0.0028897293,0.9628163,0.000052369734,0.00019010238,0.02761505],"study_design_scores_gemma":[0.0018147866,0.0006067551,0.019269459,0.00034381918,0.000060793725,0.0001072666,0.0014434585,0.811106,0.1382735,0.00016978984,0.025938332,0.0008660008],"about_ca_topic_score_codex":0.000027920027,"about_ca_topic_score_gemma":0.00005185553,"teacher_disagreement_score":0.8245428,"about_ca_system_score_codex":0.000026753632,"about_ca_system_score_gemma":0.00008079903,"threshold_uncertainty_score":0.39250207},"labels":[],"label_agreement":null},{"id":"W2117628101","doi":"10.1093/bioinformatics/btu807","title":"flowCL: ontology-based cell population labelling in flow cytometry","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institute of Allergy and Infectious Diseases; National Institute of General Medical Sciences","keywords":"Labelling; Flow cytometry; Computer science; Ontology; Population; Biology; Molecular biology; Medicine; Biochemistry","score_opus":0.009206576639586,"score_gpt":0.2153353101133954,"score_spread":0.20612873347380942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117628101","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84940946,0.00009329688,0.14722168,0.00004584828,0.0003206905,0.00014937184,0.000012113847,0.000028163824,0.002719367],"genre_scores_gemma":[0.9441681,0.000019784193,0.05476108,0.00052302773,0.00010600077,0.000005090234,0.00032871275,0.000016049284,0.0000721776],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999137,0.000033823053,0.00034514882,0.00013447631,0.00011172772,0.00023781304],"domain_scores_gemma":[0.99954516,0.000019410196,0.000085096704,0.0002535114,0.00003706811,0.00005975172],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024431548,0.00014224598,0.00015526055,0.0001082691,0.00005308414,0.000025974514,0.00014602054,0.00021127413,0.000009239987],"category_scores_gemma":[0.000058395024,0.00013932589,0.00006487688,0.00013443593,0.000026873937,0.0000074803124,0.000021485797,0.00010037639,0.000024556019],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005779026,0.00093341595,0.39283836,0.0014481617,0.00007043988,0.000006283305,0.0010465955,0.073545106,0.42672488,0.00037437107,0.0024732295,0.09996127],"study_design_scores_gemma":[0.00254561,0.00039624446,0.012715585,0.000055421762,0.000023295068,0.000004328758,0.00007487854,0.84852344,0.12135264,0.00009686603,0.013666693,0.00054497796],"about_ca_topic_score_codex":0.00004288116,"about_ca_topic_score_gemma":0.00012634243,"teacher_disagreement_score":0.77497834,"about_ca_system_score_codex":0.000020348843,"about_ca_system_score_gemma":0.000031390497,"threshold_uncertainty_score":0.5681545},"labels":[],"label_agreement":null},{"id":"W2117658386","doi":"10.1093/bioinformatics/bth010","title":"The Hera database and its use in the characterization of endoplasmic reticulum proteins","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Cellular transport and secretion","field":"Biochemistry, Genetics and Molecular Biology","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Canadian Institutes of Health Research; Genome Canada","keywords":"Endoplasmic reticulum; HERA; Transmembrane protein; Computational biology; Transmembrane domain; ER retention; Biology; Membrane protein; Chemistry; Cell biology; Biochemistry; Receptor; Gene; Membrane; Physics","score_opus":0.011676975472815937,"score_gpt":0.2055065723436951,"score_spread":0.19382959687087917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117658386","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99469775,0.00007443027,0.0046716356,0.00013212995,0.000030352505,0.00030313645,0.00003319104,0.000002465947,0.000054900083],"genre_scores_gemma":[0.997436,0.0006287242,0.0003696032,0.00008581816,0.000021235584,0.000011893136,0.0014186755,0.000004152463,0.00002389844],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999568,0.000014666474,0.00019135156,0.000051930754,0.00008607579,0.00008801616],"domain_scores_gemma":[0.9997054,0.0000064144765,0.000073348114,0.00016796909,0.00003163479,0.000015246791],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017201035,0.000060449325,0.00004894033,0.000015213179,0.000064617525,0.000027941938,0.00008834597,0.000047019214,9.0494297e-7],"category_scores_gemma":[0.000033539192,0.000036359965,0.000019828449,0.00005551445,0.000044552227,0.000015403963,0.000018267054,0.000047396312,0.000001370225],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035823778,0.000026746173,0.00092934474,0.000054762735,0.00000722765,0.000001043309,0.00060204853,0.000013894755,0.9968635,0.0011657582,0.000002596746,0.00029726268],"study_design_scores_gemma":[0.0013654603,0.00027900116,0.027614426,0.00008412485,0.000025464306,0.000038769704,0.0005376584,0.0027059682,0.9382303,0.000058681548,0.028843775,0.00021641137],"about_ca_topic_score_codex":0.000010168231,"about_ca_topic_score_gemma":0.00007570903,"teacher_disagreement_score":0.05863323,"about_ca_system_score_codex":0.0000031535435,"about_ca_system_score_gemma":0.000027526665,"threshold_uncertainty_score":0.14827164},"labels":[],"label_agreement":null},{"id":"W2117706019","doi":"10.1093/bioinformatics/btu793","title":"Adaptive settings for the nearest-neighbor particle tracking algorithm","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Target Tracking and Data Fusion in Sensor Networks","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Hôpital Maisonneuve-Rosemont","funders":"","keywords":"k-nearest neighbors algorithm; Computer science; Tracking (education); Algorithm; Set (abstract data type); Series (stratigraphy); Data set; License; Particle filter; Data mining; Artificial intelligence","score_opus":0.022137062114337126,"score_gpt":0.24040703049046752,"score_spread":0.21826996837613039,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117706019","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00025831556,0.00006843721,0.99687594,0.0011225804,0.0006106263,0.0002606468,0.000018821964,0.00022658723,0.00055804796],"genre_scores_gemma":[0.12479974,0.000021390711,0.87262404,0.0020281854,0.0003531997,0.000037619357,0.000011113244,0.000014508982,0.00011017872],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988388,0.000030949206,0.00034733483,0.00015403639,0.0002540667,0.00037482136],"domain_scores_gemma":[0.9980228,0.000985285,0.00016003287,0.0006207159,0.00012284344,0.000088351306],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067587144,0.00013555479,0.00013406061,0.000026477033,0.00045150626,0.0003834766,0.00084323133,0.00006460436,0.0000071001323],"category_scores_gemma":[0.00019473098,0.00008990729,0.000080880935,0.00022263317,0.00006143092,0.0006239789,0.00017609596,0.00013761777,0.000078971265],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004782188,0.000018399993,0.00003727461,0.00001603411,0.00001523028,4.522262e-7,0.0015508903,0.0012409121,0.000007208297,0.028614465,0.015585878,0.95290846],"study_design_scores_gemma":[0.00026238247,0.000080016376,0.000279708,0.000021248336,0.000009918692,0.0000086138525,0.00018892635,0.9096791,0.00035651703,0.0010215288,0.08795665,0.00013539044],"about_ca_topic_score_codex":0.0000065314434,"about_ca_topic_score_gemma":0.000001888085,"teacher_disagreement_score":0.9527731,"about_ca_system_score_codex":0.00001599919,"about_ca_system_score_gemma":0.000026315076,"threshold_uncertainty_score":0.36978737},"labels":[],"label_agreement":null},{"id":"W2117716708","doi":"10.1093/bioinformatics/btq152","title":"Detection and characterization of novel sequence insertions using paired-end next-generation sequencing","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomic variations and chromosomal abnormalities","field":"Biochemistry, Genetics and Molecular Biology","cited_by":130,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; BC Cancer Agency","funders":"Natural Sciences and Engineering Research Council of Canada; Genome British Columbia; National Institutes of Health; National Human Genome Research Institute; Michael Smith Health Research BC; Howard Hughes Medical Institute","keywords":"Structural variation; Sequence (biology); Genome; Reference genome; Computational biology; Pipeline (software); Biology; DNA sequencing; Whole genome sequencing; Genetics; Sequence assembly; Genomics; Alignment-free sequence analysis; Sequence analysis; Sequence alignment; Computer science; Gene; Peptide sequence","score_opus":0.05710006682181176,"score_gpt":0.23859978664029263,"score_spread":0.18149971981848087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117716708","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9515097,0.0000061753494,0.048087876,0.0000136195,0.00016455058,0.000094878356,0.00004956683,0.000008066761,0.00006557097],"genre_scores_gemma":[0.98479825,0.000023613582,0.014782956,0.000047487807,0.00012430175,0.000004775681,0.00018794328,0.0000068056847,0.000023879844],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995123,0.000007835162,0.00024865294,0.00007620354,0.00006436609,0.000090616726],"domain_scores_gemma":[0.9995865,0.000002996092,0.00014946733,0.00013559079,0.00009310879,0.00003233255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010283106,0.00007785624,0.000068088615,0.00004457328,0.00011772602,0.00003847592,0.000047268364,0.000099859295,0.000006268726],"category_scores_gemma":[0.000029886272,0.00007804217,0.000023626535,0.000062211555,0.00005067437,0.000038029553,0.000034824774,0.00005313477,6.814272e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000032073144,0.000010180222,0.000382842,0.000026709866,0.000008243175,4.0775436e-8,0.00026529934,0.00008100686,0.9967969,0.00017360308,7.64371e-7,0.0022511748],"study_design_scores_gemma":[0.00018652606,0.000058174028,0.0019354032,0.000008325694,0.000015762222,0.000049062714,0.00027238266,0.18662934,0.810419,0.000007926464,0.00030621057,0.000111872185],"about_ca_topic_score_codex":0.00004345273,"about_ca_topic_score_gemma":0.00009113123,"teacher_disagreement_score":0.18654834,"about_ca_system_score_codex":0.0000138970045,"about_ca_system_score_gemma":0.00008080017,"threshold_uncertainty_score":0.31824675},"labels":[],"label_agreement":null},{"id":"W2118070789","doi":"10.1093/bioinformatics/btl612","title":"Flexible empirical Bayes models for differential gene expression","year":2006,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":65,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Bayes' theorem; Inference; Bayesian probability; Bayesian inference; Bayes factor; Data mining; Sensitivity (control systems); Hierarchical database model; Artificial intelligence; Machine learning","score_opus":0.029594441859634186,"score_gpt":0.2868024409490328,"score_spread":0.2572079990893986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118070789","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.084537864,0.00017431332,0.91043013,0.00011964861,0.00023840507,0.00028510805,0.000051276103,0.000039115857,0.004124104],"genre_scores_gemma":[0.9516647,0.000057276793,0.044299886,0.00023572506,0.00049388263,0.00010562097,0.0008424364,0.000021627919,0.0022788607],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99923706,0.000011525787,0.0002763043,0.00015200999,0.00013168262,0.00019143449],"domain_scores_gemma":[0.99947923,0.0000066590687,0.00010453185,0.00028160395,0.00007227326,0.000055723754],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000057383622,0.00012378595,0.00010051264,0.000044768425,0.000103063736,0.000040005598,0.00014386927,0.0001452817,0.000016685066],"category_scores_gemma":[0.0000125019415,0.0001024104,0.00009084208,0.000051498144,0.000029253202,0.000010741441,0.00006186608,0.000035753976,0.000007923195],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009455975,0.0000742288,0.00018648083,0.000045214336,0.0000086328855,7.2075565e-8,0.00004989062,0.0010337647,0.8845334,0.00043066006,0.11082319,0.0027198896],"study_design_scores_gemma":[0.00071660784,0.00010124429,0.00037361673,0.000012761237,0.000011444511,0.0000027704393,0.00004958994,0.026118606,0.9030552,0.0012365679,0.0681284,0.0001931869],"about_ca_topic_score_codex":0.0000019387396,"about_ca_topic_score_gemma":0.0000013464795,"teacher_disagreement_score":0.8671268,"about_ca_system_score_codex":0.000012220116,"about_ca_system_score_gemma":0.000050917155,"threshold_uncertainty_score":0.4176175},"labels":[],"label_agreement":null},{"id":"W2118085282","doi":"10.1093/bioinformatics/btl126","title":"HTS-Corrector: software for the statistical analysis and correction of experimental high-throughput screening data","year":2006,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University and Génome Québec Innovation Centre; Université du Québec à Montréal","funders":"","keywords":"Computer science; Software; Throughput; Error detection and correction; Data mining; Raw data; Reliability engineering; Computer engineering; Algorithm; Operating system; Programming language","score_opus":0.03918408295329441,"score_gpt":0.3240491938539534,"score_spread":0.284865110900659,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118085282","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004306897,0.00012085844,0.99454707,0.000051608327,0.00048301416,0.00019232748,0.00018847312,0.000046951805,0.00006277592],"genre_scores_gemma":[0.19698536,0.0000031077827,0.802662,0.000045038214,0.000046362067,0.000008455607,0.0002264875,0.0000042578727,0.000018915318],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99898154,0.0000423719,0.0003781461,0.0001709723,0.000283427,0.0001435708],"domain_scores_gemma":[0.9972444,0.0019013364,0.00018448706,0.000547114,0.00009270454,0.00002992308],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004893305,0.000103607956,0.0001789878,0.0001084707,0.00015147643,0.00014005901,0.0005665407,0.00003191079,0.0000050897775],"category_scores_gemma":[0.00024982533,0.000078007375,0.00004104087,0.00052151544,0.00008347908,0.00069744786,0.00045004892,0.000055283712,0.0000014236606],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007575036,0.00020808956,0.005503549,0.000117770476,0.0006299311,0.0000015372909,0.0019311208,0.26129282,0.00008658557,0.048106838,0.021045446,0.6610006],"study_design_scores_gemma":[0.0001991156,0.00004368612,0.013798491,0.00000727545,0.0000949984,0.0000034704626,0.00014557084,0.98354894,0.0007786949,0.0005007727,0.0007835582,0.00009544253],"about_ca_topic_score_codex":0.00032278112,"about_ca_topic_score_gemma":0.000036966594,"teacher_disagreement_score":0.7222561,"about_ca_system_score_codex":0.000025625326,"about_ca_system_score_gemma":0.000057006404,"threshold_uncertainty_score":0.31810486},"labels":[],"label_agreement":null},{"id":"W2118087641","doi":"10.1093/bioinformatics/btl530","title":"sGAL: a computational method for finding surface exposed sites in proteins suitable for Cys-mediated cross-linking","year":2006,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Atom (system on chip); Surface (topology); Steric effects; Computer science; Protein Data Bank (RCSB PDB); Crystallography; Chemistry; Algorithm; Physics; Mathematics; Stereochemistry; Geometry","score_opus":0.0159941549849161,"score_gpt":0.2967423365172292,"score_spread":0.2807481815323131,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118087641","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3419599,0.00009712652,0.6563412,0.000029891913,0.000059675644,0.0010278024,0.00027448984,0.00002079182,0.00018911157],"genre_scores_gemma":[0.30432296,0.0000031637035,0.6919589,0.0001288868,0.00010633411,0.00009248787,0.0031721094,0.000022094995,0.00019304676],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99890006,0.000016875027,0.00045190036,0.000168191,0.00012099393,0.00034199725],"domain_scores_gemma":[0.99935067,0.00011876787,0.0001864113,0.00015531646,0.00015060898,0.00003824744],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042760605,0.0001664254,0.00018258863,0.00005856354,0.00012908611,0.00008570873,0.0001545045,0.00022155637,0.0000020441853],"category_scores_gemma":[0.00017688985,0.00016124433,0.000094899966,0.00011592522,0.00003535782,0.000019217887,0.000057129728,0.00007026073,0.0000018529903],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007860193,0.00021494062,0.027538046,0.0016628224,0.00014115845,0.000002579232,0.000826382,0.34083638,0.61539614,0.005979012,0.0023817557,0.004234747],"study_design_scores_gemma":[0.0033695465,0.00032660906,0.0020299093,0.00005080511,0.000018466844,0.0000108575105,0.00011517782,0.8748181,0.10611532,0.005732435,0.006945585,0.00046720137],"about_ca_topic_score_codex":0.000020048086,"about_ca_topic_score_gemma":0.00008175002,"teacher_disagreement_score":0.53398174,"about_ca_system_score_codex":0.000033360076,"about_ca_system_score_gemma":0.00011644323,"threshold_uncertainty_score":0.6575353},"labels":[],"label_agreement":null},{"id":"W2118290743","doi":"10.1093/bioinformatics/btp366","title":"Automated protein (re)sequencing with MS/MS and a homologous database yields almost full coverage and accuracy","year":2009,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bioinformatics Solutions (Canada); University of Waterloo; Western University","funders":"","keywords":"Protein sequencing; Sequence database; Sequence (biology); Proteomics; Protein methods; Computational biology; DNA sequencing; Tandem mass spectrometry; Database; Peptide sequence; Computer science; Sequence analysis; Mass spectrometry; Biology; Genetics; DNA; Chemistry; Gene; Chromatography","score_opus":0.014643112685008496,"score_gpt":0.26237445132770787,"score_spread":0.24773133864269936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118290743","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9282958,0.00012717785,0.060924,0.00027712103,0.0000045179136,0.0006016542,0.00018968475,0.0008000779,0.008779992],"genre_scores_gemma":[0.7100922,0.00019286311,0.28911775,0.00022867991,0.000024887097,0.00008467863,0.00013604548,0.000015995478,0.00010693849],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999206,0.0000037415805,0.00029370256,0.00015316221,0.000114755836,0.00022864566],"domain_scores_gemma":[0.99923223,0.000042317755,0.00019952114,0.00037835265,0.00004367085,0.00010391087],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007685454,0.00018444494,0.0001698124,0.000037615937,0.00017176158,0.000081544946,0.00013002372,0.00011610655,0.000035208737],"category_scores_gemma":[0.00005638319,0.00015370472,0.000016072483,0.00010683729,0.00007622374,0.0003843558,0.00007708712,0.00020665137,0.000004610388],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034510123,0.00024519136,0.00038865054,0.0018322807,0.00009797791,0.00010919099,0.0034421803,0.00019584033,0.8967405,0.009030868,0.002342966,0.08522924],"study_design_scores_gemma":[0.0024293822,0.0006854239,0.00021317758,0.001039384,0.000100906334,0.0010950937,0.0008758601,0.19548325,0.7821543,0.004673874,0.009737452,0.00151187],"about_ca_topic_score_codex":0.000030349707,"about_ca_topic_score_gemma":0.000008212865,"teacher_disagreement_score":0.22819376,"about_ca_system_score_codex":0.000050002032,"about_ca_system_score_gemma":0.00005686327,"threshold_uncertainty_score":0.6267897},"labels":[],"label_agreement":null},{"id":"W2118379383","doi":"10.1093/bioinformatics/btq204","title":"Estimating genome-wide IBD sharing from SNP data via an efficient hidden Markov model of LD with application to gene mapping","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Azrieli Foundation","keywords":"Linkage disequilibrium; Identity by descent; Locus (genetics); Genome-wide association study; Computer science; Genetic association; Multifactor dimensionality reduction; SNP; Genetics; Data mining; Computational biology; Biology; Single-nucleotide polymorphism; Allele; Haplotype; Gene; Genotype","score_opus":0.024204406816163513,"score_gpt":0.26412662976389323,"score_spread":0.23992222294772972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118379383","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5161032,0.000009562975,0.48338792,0.00004211818,0.00003450657,0.00015916527,0.00010674774,0.000008551062,0.00014824739],"genre_scores_gemma":[0.49800104,0.0000024946676,0.50059706,0.0001415318,0.00007158406,0.000012927492,0.0011495274,0.000010494699,0.000013347558],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988555,0.000013991045,0.00047670316,0.00028376278,0.00012945995,0.00024058967],"domain_scores_gemma":[0.99832135,0.000024080531,0.000302018,0.0011288804,0.00010805802,0.00011562982],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045775762,0.00014563728,0.0001969502,0.000054012165,0.000094301984,0.000021757334,0.00058766874,0.000151217,0.0000053121244],"category_scores_gemma":[0.00016172366,0.00013139631,0.000027329444,0.00009319207,0.000039556155,0.0000108308195,0.00043662856,0.000103135346,0.000010029396],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049418923,0.00012642166,0.044877723,0.000081090366,0.00014074717,3.140025e-7,0.0012329193,0.26323038,0.65563494,0.000030874886,0.00031837076,0.034276813],"study_design_scores_gemma":[0.00020098039,0.00006158082,0.013608863,0.00000790501,0.000023138913,0.00000244511,0.000121772646,0.98210526,0.0034343116,0.00006358567,0.00019620503,0.00017397363],"about_ca_topic_score_codex":0.000075881064,"about_ca_topic_score_gemma":0.00008992314,"teacher_disagreement_score":0.7188749,"about_ca_system_score_codex":0.000013886962,"about_ca_system_score_gemma":0.00006550399,"threshold_uncertainty_score":0.53581864},"labels":[],"label_agreement":null},{"id":"W2118446779","doi":"10.1093/bioinformatics/btg415","title":"Functional topology in a network of protein interactions","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":430,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computational biology; Computer science; Network analysis; Function (biology); Interaction network; Construct (python library); Mutation; Protein–protein interaction; Network model; Set (abstract data type); Biological network; Biology; Genetics; Artificial intelligence; Gene; Computer network","score_opus":0.010753722658915683,"score_gpt":0.22999407287449528,"score_spread":0.21924035021557958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118446779","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77430236,0.00042823452,0.20253305,0.00059180195,0.00076568394,0.000732676,0.000031178475,0.000023665034,0.020591317],"genre_scores_gemma":[0.9796134,0.000028550621,0.01955693,0.0002461252,0.00017791393,0.000021070256,0.00010254491,0.000008212296,0.00024525647],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991954,0.000009415361,0.00043869377,0.00007237679,0.00007542289,0.00020869011],"domain_scores_gemma":[0.9995437,0.0000060375496,0.00015228648,0.00020429926,0.000051454695,0.00004219421],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015105317,0.00010040558,0.00012835438,0.00004088399,0.000037062167,0.000009035948,0.00010725566,0.00010980964,0.000027851582],"category_scores_gemma":[0.000026517824,0.0000946753,0.00006208968,0.00012350414,0.00007157816,0.000009281924,0.0000817787,0.0001016985,0.00002287419],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017166006,0.001535763,0.014037749,0.0011938597,0.00078249094,0.000013835261,0.0049179033,0.4570121,0.10012803,0.25301427,0.039743163,0.12590426],"study_design_scores_gemma":[0.029624343,0.005891891,0.06539228,0.0017330052,0.00019934023,0.0008414533,0.005807293,0.05057667,0.16681243,0.18109562,0.48709095,0.00493473],"about_ca_topic_score_codex":0.000017565095,"about_ca_topic_score_gemma":0.00011039902,"teacher_disagreement_score":0.4473478,"about_ca_system_score_codex":0.000026623446,"about_ca_system_score_gemma":0.00011648987,"threshold_uncertainty_score":0.38607466},"labels":[],"label_agreement":null},{"id":"W2118584916","doi":"10.1093/bioinformatics/btp552","title":"Reproducing the manual annotation of multiple sequence alignments using a SVM classifier","year":2009,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Annotation; Classifier (UML); Support vector machine; Software; Artificial intelligence; Data mining; Sequence (biology); Machine learning; Multiple sequence alignment; Pattern recognition (psychology); Sequence alignment; Programming language; Peptide sequence","score_opus":0.040615098603383734,"score_gpt":0.2885442176537646,"score_spread":0.24792911905038084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118584916","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99630505,0.00020450559,0.002400953,0.00008584893,0.000088115536,0.00015316284,0.000020273144,0.0000020774457,0.00074003346],"genre_scores_gemma":[0.9875086,0.00007984317,0.012029471,0.00023279028,0.00006826596,0.0000020257635,0.000016494057,0.0000042045267,0.000058336973],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994061,0.000014241695,0.0002518834,0.000102556725,0.00009777274,0.00012742952],"domain_scores_gemma":[0.99945223,0.000009005249,0.00015037967,0.0003012996,0.00006649581,0.000020581778],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017430814,0.00008391252,0.00008379473,0.000017733324,0.0000865605,0.00001260326,0.000117967924,0.000047068846,0.0000010470446],"category_scores_gemma":[0.00007457557,0.00006161709,0.00004300397,0.000054838474,0.000051217554,0.000001883416,0.00004974176,0.000030525916,0.0000017473436],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002716736,0.000027344317,0.0031796393,0.000022875909,0.00004450769,3.048456e-7,0.0011371876,0.0014011207,0.98247886,0.00009443922,0.00042066895,0.011165875],"study_design_scores_gemma":[0.0013585036,0.0008270676,0.0826443,0.000077440964,0.000108203385,0.000052133444,0.0037368613,0.07169653,0.8213296,0.00067933614,0.016861022,0.000629022],"about_ca_topic_score_codex":0.000009570968,"about_ca_topic_score_gemma":0.0000029866878,"teacher_disagreement_score":0.16114928,"about_ca_system_score_codex":0.0000094711195,"about_ca_system_score_gemma":0.000031711686,"threshold_uncertainty_score":0.2512672},"labels":[],"label_agreement":null},{"id":"W2118596665","doi":"10.1093/bioinformatics/btk027","title":"ORegAnno: an open access database and curation system for literature-derived promoters, transcription factor binding sites and regulatory variation","year":2006,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":123,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"Genome British Columbia; Genome Canada","keywords":"Ensembl; Annotation; License; Database; Transcription factor; dbSNP; Computer science; DNA binding site; Promoter; World Wide Web; Computational biology; Biology; Gene; Bioinformatics; Genetics; Genomics; Genotype","score_opus":0.019126779821666915,"score_gpt":0.2672365525115915,"score_spread":0.2481097726899246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118596665","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96544605,0.00013405111,0.033051193,0.000027355105,0.00008032397,0.0006797954,0.0005077546,0.000016886615,0.000056604844],"genre_scores_gemma":[0.9741091,0.00005509414,0.020599062,0.000026753412,0.000093413735,0.000030395368,0.0050327815,0.000016267804,0.000037101883],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99933904,0.000019714931,0.0002726846,0.00017269835,0.00006689849,0.00012898447],"domain_scores_gemma":[0.99948704,0.0000061684677,0.00016991358,0.00020763933,0.00007861199,0.00005059822],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015911135,0.00013328408,0.00011504696,0.00005210027,0.00017399648,0.00076478993,0.00018845077,0.00012141192,7.68115e-7],"category_scores_gemma":[0.000013303139,0.00012375665,0.000018075993,0.000053588537,0.000027492106,0.00021031451,0.00011795106,0.000034972472,3.2160082e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053671127,0.000028027573,0.0005189415,0.0005749418,0.000019517378,2.692003e-7,0.0005310202,0.000033374,0.9958342,0.0010991707,0.000115533585,0.0011913475],"study_design_scores_gemma":[0.00576709,0.0013952283,0.06036907,0.0005403702,0.00020408112,0.0001136271,0.0014559868,0.54708683,0.37769115,0.00077575614,0.0030325123,0.001568295],"about_ca_topic_score_codex":0.000014258097,"about_ca_topic_score_gemma":0.000039599166,"teacher_disagreement_score":0.618143,"about_ca_system_score_codex":0.000023796625,"about_ca_system_score_gemma":0.00003444062,"threshold_uncertainty_score":0.7374887},"labels":[],"label_agreement":null},{"id":"W2118651376","doi":"10.1093/bioinformatics/bth240","title":"A practical and robust sequence search strategy for structural genomics target selection","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Medical Research Council","keywords":"Prioritization; Genome; Selection (genetic algorithm); Computer science; Sequence (biology); Structural genomics; Computational biology; Genomics; Software; Sequence alignment; Similarity (geometry); Data mining; Gene; Biology; Genetics; Artificial intelligence; Protein structure; Peptide sequence; Image (mathematics)","score_opus":0.051150241365374265,"score_gpt":0.31169337020729015,"score_spread":0.2605431288419159,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118651376","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68563855,0.00013310481,0.31254563,0.00031405227,0.000106180734,0.00074250664,0.00008419564,0.000026706983,0.00040908455],"genre_scores_gemma":[0.36357462,0.000119841025,0.6356838,0.00009836366,0.00016446329,0.0000203671,0.00023367196,0.00001821415,0.00008666187],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993015,0.000009045616,0.00019514996,0.00013658321,0.00010391567,0.00025381203],"domain_scores_gemma":[0.9996279,0.000006865988,0.00006122657,0.000121194156,0.000099105724,0.00008373069],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015056206,0.00012080024,0.00009471796,0.000035477402,0.00010959518,0.00006764845,0.000073795214,0.00011611818,0.000005476654],"category_scores_gemma":[0.000042096526,0.00011345636,0.00003613802,0.000059920265,0.00006190712,0.000017796305,0.000056039127,0.00007716635,0.0000059502836],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007675344,0.0002442474,0.0032792503,0.0016790207,0.00078591274,0.0000116872925,0.0033483994,0.23076154,0.6992347,0.014437673,0.0043105814,0.041139394],"study_design_scores_gemma":[0.008952244,0.0051363385,0.0032498983,0.000054901247,0.0001763581,0.0011494415,0.00484264,0.5515269,0.3859953,0.0045429124,0.032341223,0.0020318327],"about_ca_topic_score_codex":0.000007443544,"about_ca_topic_score_gemma":0.000010258528,"teacher_disagreement_score":0.32313818,"about_ca_system_score_codex":0.00004997875,"about_ca_system_score_gemma":0.00025920803,"threshold_uncertainty_score":0.4626616},"labels":[],"label_agreement":null},{"id":"W2118986663","doi":"10.1093/bioinformatics/btu581","title":"Human structural proteome-wide characterization of Cyclosporine A targets","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Signaling Pathways in Disease","field":"Biochemistry, Genetics and Molecular Biology","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Canadian Institutes of Health Research","keywords":"Computational biology; Proteome; Drug discovery; Cyclophilin; Surface plasmon resonance; Human proteome project; Biology; Docking (animal); Cyclophilin A; Biochemistry; Proteomics; Molecular biology; Medicine; Gene; Nanotechnology","score_opus":0.007432989959109125,"score_gpt":0.23173405607790284,"score_spread":0.22430106611879372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118986663","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99318117,0.000009446584,0.005722946,0.000021074211,0.00009328624,0.00019907657,0.000037906302,0.00001741715,0.0007177034],"genre_scores_gemma":[0.99576896,0.0000016645059,0.0034338178,0.00012970559,0.00009269688,0.000010902234,0.00045164346,0.0000124847,0.000098119344],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99932873,0.000017333321,0.00030370028,0.00008757825,0.00012669078,0.00013596639],"domain_scores_gemma":[0.9993526,0.0000036642284,0.00020926143,0.00029231535,0.00008134989,0.00006080528],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000115038834,0.00010743549,0.00011352893,0.000028408045,0.000048559785,0.0000118832595,0.00015370193,0.00007726922,0.000022370195],"category_scores_gemma":[0.00012594744,0.0000981654,0.000054481945,0.00005353913,0.00005247322,0.000007235014,0.00006929946,0.000038224433,0.0000072856838],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018642986,0.00001747366,0.0072001447,0.00011314046,0.000020305519,2.0501273e-7,0.00012260606,0.000026009478,0.99142057,0.0002243535,0.00015284537,0.00068368105],"study_design_scores_gemma":[0.0004952481,0.00026938837,0.044122685,0.000025801011,0.000014361702,0.0000029692317,0.000021102755,0.0012594652,0.94931144,0.00013883314,0.004141622,0.00019706736],"about_ca_topic_score_codex":0.0000015625154,"about_ca_topic_score_gemma":5.5163304e-7,"teacher_disagreement_score":0.042109136,"about_ca_system_score_codex":0.000006399622,"about_ca_system_score_gemma":0.000025356725,"threshold_uncertainty_score":0.40030688},"labels":[],"label_agreement":null},{"id":"W2119191448","doi":"10.1093/bioinformatics/btr217","title":"Sorting the nuclear proteome","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Australian Research Council; Canadian Institutes of Health Research","keywords":"Proteome; Computational biology; Nuclear protein; Biology; Nuclear transport; Sorting; Compartment (ship); Transcription factor; Computer science; Cell nucleus; Bioinformatics; Gene; Genetics","score_opus":0.012928176794443665,"score_gpt":0.20010404968187503,"score_spread":0.18717587288743137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119191448","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95271236,0.00004300844,0.002301596,0.000060223534,0.00012518212,0.0002528306,0.000007791502,0.000022385268,0.044474605],"genre_scores_gemma":[0.9745948,0.000037197453,0.024499632,0.00046640533,0.00008213027,0.000009401483,0.000020898437,0.000018277555,0.00027129048],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994774,0.000008641844,0.00021271082,0.00006765929,0.00006922134,0.00016437084],"domain_scores_gemma":[0.99950165,0.000002272392,0.00011313998,0.00031371723,0.00003202525,0.00003719902],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013862994,0.00008655925,0.00005901347,0.000012751599,0.00011834935,0.000025289279,0.00024728174,0.000067918314,0.000031257856],"category_scores_gemma":[0.000030457457,0.0000594247,0.000053555865,0.00003928611,0.00005488417,0.0000034558373,0.00013268826,0.000057745907,0.00007658701],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005432438,0.0010348966,0.021767512,0.0012504195,0.0013438102,0.000024144894,0.06443117,0.00061051175,0.6157956,0.076733366,0.06462279,0.1518425],"study_design_scores_gemma":[0.0040363823,0.0029922477,0.04962357,0.00015370795,0.00026071668,0.000576073,0.022266887,0.21720167,0.1850741,0.00803673,0.506053,0.003724963],"about_ca_topic_score_codex":0.000005776745,"about_ca_topic_score_gemma":0.0000044316316,"teacher_disagreement_score":0.44143015,"about_ca_system_score_codex":0.0000056381923,"about_ca_system_score_gemma":0.000024650077,"threshold_uncertainty_score":0.24232689},"labels":[],"label_agreement":null},{"id":"W2119610982","doi":"10.1093/bioinformatics/btn219","title":"quantiNemo: an individual-based program to simulate quantitative traits with explicit genetic architecture in a dynamic metapopulation","year":2008,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Evolution and Genetic Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":117,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Université de Lausanne; National Science Foundation","keywords":"Executable; Genetic architecture; Selection (genetic algorithm); Quantitative trait locus; Computer science; Population; Metapopulation; Source code; Computer program; Programming language; Artificial intelligence; Biological dispersal","score_opus":0.020357586103040764,"score_gpt":0.29393550746773456,"score_spread":0.2735779213646938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119610982","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8466296,0.00006321479,0.15229027,0.00008059398,0.000019771142,0.0007228975,0.000042339398,0.000041929194,0.0001093859],"genre_scores_gemma":[0.740526,0.000012135517,0.2585345,0.0003377393,0.000011958887,0.00005397653,0.0004345994,0.000023401584,0.000065690845],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99868464,0.000054010605,0.00041617878,0.00024731277,0.0002627082,0.00033513087],"domain_scores_gemma":[0.9992965,0.000010535819,0.00013451748,0.00030430921,0.00009579978,0.00015837203],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012859277,0.00023948301,0.00020435979,0.00020019284,0.0000920983,0.00003077722,0.00021270111,0.00014447956,0.000005651238],"category_scores_gemma":[0.000050728162,0.00020692217,0.000057744546,0.00035928146,0.00006817431,0.00001151489,0.00004378036,0.00011341137,0.000011929561],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00054499984,0.00060048833,0.012267145,0.00011131843,0.00008082919,0.000014803062,0.0036302067,0.93664104,0.009187012,0.00013591777,0.00016244546,0.036623802],"study_design_scores_gemma":[0.001806569,0.0031227968,0.22502917,0.000042849024,0.000035763034,0.000049115915,0.00041255887,0.76567304,0.000794866,0.000033886343,0.0024249975,0.0005744],"about_ca_topic_score_codex":0.000017022585,"about_ca_topic_score_gemma":0.0007955054,"teacher_disagreement_score":0.21276203,"about_ca_system_score_codex":0.000020757268,"about_ca_system_score_gemma":0.00013672537,"threshold_uncertainty_score":0.84380406},"labels":[],"label_agreement":null},{"id":"W2120173546","doi":"10.1093/bioinformatics/btl506","title":"Predicted function of the vaccinia virus G5R protein","year":2006,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Poxvirus research and outbreaks","field":"Immunology and Microbiology","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"National Center for Research Resources; Natural Sciences and Engineering Research Council of Canada; National Institute of Allergy and Infectious Diseases; University of California, San Francisco; U.S. Public Health Service; National Institutes of Health","keywords":"Vaccinia; Virology; Virus; Function (biology); Biology; Orthopoxvirus; Computational biology; Computer science; Genetics; Gene","score_opus":0.008804086629035637,"score_gpt":0.21386878367333337,"score_spread":0.20506469704429772,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120173546","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97850084,0.00038524801,0.00063546846,0.0001288921,0.00037422153,0.00060388906,0.00019749081,0.00007786704,0.01909609],"genre_scores_gemma":[0.9963295,0.000007291498,0.00016790039,0.000059891518,0.00002744313,0.00001647513,0.000079161546,0.0000058908954,0.0033064566],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999304,0.00004539332,0.00031172688,0.000053089632,0.000057390564,0.00022838156],"domain_scores_gemma":[0.99949825,0.000023850227,0.00013787042,0.0002640226,0.00006458572,0.0000113957685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013605985,0.00008417441,0.000113707356,0.000053174503,0.00011373781,0.000009027846,0.00020946456,0.00013969383,0.00025269412],"category_scores_gemma":[0.000063151216,0.00005171412,0.00006721684,0.00015615567,0.00010309787,0.000100540296,0.000087565386,0.0001700386,0.0003105446],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040556683,0.00017334324,0.0022382946,0.00013851008,0.00012282464,4.6644618e-7,0.00027457136,0.000011723936,0.9198422,0.0037897888,0.055909667,0.017093033],"study_design_scores_gemma":[0.0015891168,0.0003085195,0.08996739,0.000061903964,0.000035022385,0.000013295564,0.000119532895,0.00025497572,0.72396636,0.0006399216,0.18288471,0.00015923976],"about_ca_topic_score_codex":0.00016192698,"about_ca_topic_score_gemma":0.00004768029,"teacher_disagreement_score":0.19587584,"about_ca_system_score_codex":0.000018607368,"about_ca_system_score_gemma":0.00007276757,"threshold_uncertainty_score":0.3991526},"labels":[],"label_agreement":null},{"id":"W2120625059","doi":"10.1093/bioinformatics/btn246","title":"Estimating dynamic models for gene regulation networks","year":2008,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":53,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; National Science Foundation","keywords":"Ode; Gene regulatory network; Ordinary differential equation; Computer science; Smoothing; Systems biology; Biological network; Mathematical optimization; Process (computing); Algorithm; Theoretical computer science; Applied mathematics; Mathematics; Differential equation; Computational biology; Biology; Gene; Gene expression","score_opus":0.013247565527927451,"score_gpt":0.2320814970041585,"score_spread":0.21883393147623106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120625059","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16165663,0.000304023,0.837361,0.000019812498,0.00013255877,0.00022047391,0.000008816393,0.000025892574,0.00027080084],"genre_scores_gemma":[0.7173173,0.000069380614,0.2812428,0.00009427863,0.00021869481,0.000025706213,0.0006225068,0.0000220089,0.00038736497],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990759,0.000013545726,0.0003668857,0.00015457855,0.00012474596,0.00026437372],"domain_scores_gemma":[0.9992439,0.000011034143,0.00017874748,0.0003772599,0.00011566958,0.000073360185],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016057232,0.00015366811,0.00015774589,0.000049613547,0.0002136464,0.00001729955,0.00014839221,0.00015780838,0.0000037650475],"category_scores_gemma":[0.000027276647,0.00015264573,0.00014540831,0.00011611932,0.00005538366,0.000013045168,0.00006171224,0.00004229227,0.000004989488],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001869745,0.000012898189,0.00011183561,0.000022719125,0.00006302364,2.7554606e-7,0.00007431234,0.99065655,0.002679457,0.000044760876,0.0023631013,0.0039523654],"study_design_scores_gemma":[0.00030885002,0.00006413229,0.0002940096,0.0000071860204,0.000036442332,0.000032397395,0.000018514002,0.99602324,0.0018371253,0.00021605298,0.0009747797,0.00018729818],"about_ca_topic_score_codex":0.0000016189534,"about_ca_topic_score_gemma":0.000004436702,"teacher_disagreement_score":0.5561182,"about_ca_system_score_codex":0.000024235918,"about_ca_system_score_gemma":0.000047265716,"threshold_uncertainty_score":0.6224713},"labels":[],"label_agreement":null},{"id":"W2120688086","doi":"10.1093/bioinformatics/btq262","title":"Fast integration of heterogeneous data sources for predicting gene function with limited annotation","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":139,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Ontario Genomics; Ontario Genomics Institute; Genome Canada","keywords":"Overfitting; Computer science; Function (biology); Data mining; Annotation; Construct (python library); Source code; Artificial intelligence; Gene regulatory network; Machine learning; Association (psychology); Artificial neural network; Gene; Biology; Genetics","score_opus":0.015437980484894882,"score_gpt":0.2300689522546752,"score_spread":0.2146309717697803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120688086","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5899263,0.000040207666,0.40906143,0.000020597885,0.0002023511,0.00031973823,0.00019601216,0.000014841573,0.00021849983],"genre_scores_gemma":[0.91443104,0.000023200466,0.08094632,0.00010889669,0.0002518708,0.000017052347,0.004155602,0.000017077202,0.000048962997],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991874,0.0000068009062,0.00040223057,0.00012629322,0.00011436695,0.00016288372],"domain_scores_gemma":[0.9988984,0.00001754437,0.00033346872,0.0005254537,0.00017565559,0.000049510923],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024551927,0.0001317292,0.00012186586,0.000049665265,0.00009006976,0.000042042644,0.00023525293,0.0001575259,0.0000035045357],"category_scores_gemma":[0.000059359216,0.00010514032,0.000038174443,0.00007471204,0.0000617137,0.000028257766,0.000093188835,0.00009102338,0.0000018614875],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011726876,0.0001655958,0.0031131264,0.00047496738,0.00042990022,3.7743146e-7,0.0017786849,0.007778928,0.74957836,0.00047497381,0.0027801555,0.23225223],"study_design_scores_gemma":[0.0016438158,0.0015638177,0.0011616165,0.00005116799,0.0001557346,0.00005872201,0.0009292767,0.76506776,0.21578191,0.00012341709,0.013036671,0.00042610988],"about_ca_topic_score_codex":0.000004437634,"about_ca_topic_score_gemma":0.00009949333,"teacher_disagreement_score":0.7572888,"about_ca_system_score_codex":0.000004080532,"about_ca_system_score_gemma":0.000055435023,"threshold_uncertainty_score":0.4287498},"labels":[],"label_agreement":null},{"id":"W2120817193","doi":"10.1093/bioinformatics/bts273","title":"MicrobeDB: a locally maintainable database of microbial genomic sequences","year":2012,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Centre for Disease Control; Simon Fraser University; Dalhousie University","funders":"Canadian Institutes of Health Research","keywords":"Upload; Computer science; Parsing; Genome; Bacterial genome size; Key (lock); Database; Automation; Interface (matter); World Wide Web; Biology; Programming language; Genetics; Operating system","score_opus":0.01155662655029321,"score_gpt":0.22623209520254178,"score_spread":0.21467546865224857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120817193","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99263334,0.002129174,0.00281249,0.000030412268,0.00021368568,0.00018159962,0.00014707158,0.0000034068885,0.0018488154],"genre_scores_gemma":[0.9684742,0.00048141056,0.030337926,0.0002306328,0.00018182663,0.0000069539174,0.000092951115,0.0000130896315,0.00018097133],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99917746,0.000015248337,0.0003174975,0.00009040262,0.00007047172,0.00032892192],"domain_scores_gemma":[0.9994042,0.000008072482,0.00014283638,0.00029570365,0.00006898121,0.0000802068],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022326084,0.00013751429,0.0001495187,0.00003769477,0.00006469061,0.000012159996,0.00019849083,0.00007864047,0.000011947236],"category_scores_gemma":[0.00002978725,0.00012376657,0.00007226078,0.00005647391,0.00011951055,0.0000032359735,0.00023466231,0.000043006716,0.000025668534],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030503617,0.0000490307,0.004649238,0.00011429604,0.00006908812,2.9098658e-7,0.0003802643,0.00004744539,0.9910097,0.00034109424,0.0024880539,0.000820989],"study_design_scores_gemma":[0.001074272,0.00040302207,0.0075488794,0.0000498635,0.00009077328,0.00009441341,0.0018737869,0.00037511523,0.82999647,0.000082543345,0.1577809,0.0006299596],"about_ca_topic_score_codex":0.000028175391,"about_ca_topic_score_gemma":0.000009857248,"teacher_disagreement_score":0.16101323,"about_ca_system_score_codex":0.0000147663895,"about_ca_system_score_gemma":0.0000848853,"threshold_uncertainty_score":0.5047054},"labels":[],"label_agreement":null},{"id":"W2120905579","doi":"10.1093/bioinformatics/btv458","title":"NRGsuite: a PyMOL plugin to perform docking simulations in real time using FlexAID","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Protein Degradation and Inhibitors","field":"Biochemistry, Genetics and Molecular Biology","cited_by":96,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Plug-in; Computer science; Docking (animal); Software; Computer graphics (images); Computational science; Programming language","score_opus":0.03695817191731657,"score_gpt":0.29749589377417157,"score_spread":0.260537721856855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120905579","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9927596,0.00002007441,0.0019228512,0.000073188145,0.00010063676,0.000303453,0.000020177853,0.000023316567,0.004776718],"genre_scores_gemma":[0.9795445,0.0000058085543,0.019461183,0.00027837502,0.00016584911,0.00000709949,0.00015331086,0.000015443755,0.0003684018],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99915487,0.00001873273,0.00033522377,0.00010917645,0.00016712285,0.00021486507],"domain_scores_gemma":[0.99943227,0.000006698569,0.000081369406,0.00024638214,0.000088400404,0.00014488907],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022654924,0.00011918043,0.00011041372,0.00012131066,0.00005509726,0.000034757788,0.00013294633,0.0001098561,0.000024574476],"category_scores_gemma":[0.00017700094,0.00011602679,0.000036815472,0.00019531134,0.000022517874,0.00002278717,0.000113643684,0.00006190946,0.000088282344],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00054546964,0.0004163963,0.031940363,0.00022793406,0.0001341109,0.000013344145,0.0099633355,0.18532325,0.7089348,0.00072268763,0.027786547,0.03399179],"study_design_scores_gemma":[0.0019651097,0.00045244637,0.0016451165,0.00010765365,0.000019008958,0.000026371214,0.0006819736,0.8101121,0.12981352,0.00008607413,0.054367088,0.00072354055],"about_ca_topic_score_codex":0.000038674025,"about_ca_topic_score_gemma":0.000025618838,"teacher_disagreement_score":0.6247888,"about_ca_system_score_codex":0.00007262131,"about_ca_system_score_gemma":0.00015559755,"threshold_uncertainty_score":0.47314352},"labels":[],"label_agreement":null},{"id":"W2120942948","doi":"10.1093/bioinformatics/btv241","title":"Using kernelized partial canonical correlation analysis to study directly coupled side chains and allostery in small G proteins","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Allosteric regulation; Canonical correlation; Partial correlation; Side chain; Inference; Computer science; Correlation; Graph; Computational biology; Biological system; Chemistry; Physics; Theoretical computer science; Biology; Artificial intelligence; Mathematics; Biochemistry; Nuclear magnetic resonance","score_opus":0.03087710946533728,"score_gpt":0.28210783536686584,"score_spread":0.25123072590152856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120942948","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91380143,0.00005908083,0.085200116,0.000023498193,0.000055571734,0.0006942422,0.000011060418,0.000010862362,0.0001441288],"genre_scores_gemma":[0.9771571,0.000006069844,0.022506932,0.00013334038,0.000050978586,0.000026952246,0.00007401884,0.000009864713,0.000034725435],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99907297,0.00004930325,0.00037717042,0.000167152,0.00012957165,0.00020386082],"domain_scores_gemma":[0.99939954,0.000008948871,0.000108429485,0.00025377175,0.00007460839,0.00015468369],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032563406,0.00014464819,0.00022836124,0.00012248624,0.000041640404,0.00004173688,0.00010052752,0.00012541027,0.0000013630512],"category_scores_gemma":[0.00016835009,0.00013111826,0.00004768034,0.0002870501,0.000027256507,0.000008928984,0.00014977914,0.00007593697,0.0000019521362],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0034031777,0.0012314472,0.67164534,0.00018243422,0.0031919014,0.000087562614,0.023029204,0.1587542,0.11472374,0.00043831576,0.00009202993,0.023220623],"study_design_scores_gemma":[0.0029061919,0.00079244416,0.025167989,0.000015206942,0.0003522355,0.000016408076,0.0012230923,0.9646439,0.004113012,0.000047981324,0.00026253422,0.0004590099],"about_ca_topic_score_codex":0.00027643458,"about_ca_topic_score_gemma":0.0020327994,"teacher_disagreement_score":0.8058897,"about_ca_system_score_codex":0.000038558774,"about_ca_system_score_gemma":0.00012752615,"threshold_uncertainty_score":0.5346847},"labels":[],"label_agreement":null},{"id":"W2121166244","doi":"10.1093/bioinformatics/btt056","title":"Non-parametric Bayesian approach to post-translational modification refinement of predictions from tandem mass spectrometry","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Bayesian probability; Posttranslational modification; Tandem mass spectrometry; Computer science; Parametric statistics; Mass spectrometry; Tandem; Chemistry; Computational biology; Chromatography; Mathematics; Artificial intelligence; Statistics; Biology; Materials science","score_opus":0.014431690440249959,"score_gpt":0.2489121045829948,"score_spread":0.23448041414274484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121166244","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045492534,0.000014401785,0.92450964,0.00024031675,0.00001504989,0.00048496848,0.0003026056,0.00010370981,0.02883676],"genre_scores_gemma":[0.43261302,0.000012826583,0.5665203,0.000040987634,0.000034651803,0.00024107695,0.0004218598,0.000009865248,0.00010544722],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988789,0.000002581625,0.0005458862,0.00014604328,0.00025439053,0.00017218634],"domain_scores_gemma":[0.99902487,0.000040682124,0.00022004638,0.0004418144,0.00016641893,0.000106185274],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006012119,0.00013618024,0.00016061141,0.00017378604,0.00008710273,0.000034188884,0.00024263134,0.00011470913,0.00030730426],"category_scores_gemma":[0.000027106218,0.00013301354,0.00006638483,0.0004759906,0.000031320415,0.00019861115,0.00003228225,0.00013577528,0.000056130855],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006554389,0.0017622929,0.014792162,0.00088889594,0.0004076542,2.640217e-7,0.0031659591,0.018738614,0.8810237,0.040234115,0.009081755,0.029839013],"study_design_scores_gemma":[0.00075442577,0.000096456744,0.009678328,0.0000809327,0.00008501892,0.0000039961146,0.0013684304,0.7626164,0.20761369,0.014612166,0.0024770275,0.0006131175],"about_ca_topic_score_codex":0.000084295905,"about_ca_topic_score_gemma":8.5421186e-7,"teacher_disagreement_score":0.74387777,"about_ca_system_score_codex":0.00007315329,"about_ca_system_score_gemma":0.000040496358,"threshold_uncertainty_score":0.5424135},"labels":[],"label_agreement":null},{"id":"W2121305702","doi":"10.1093/bioinformatics/btp054","title":"Fast computation of neighbor seeds","year":2009,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; Western University","funders":"","keywords":"Computation; Heuristic; Computer science; Exponential function; Current (fluid); Class (philosophy); Algorithm; Exponential growth; Sensitivity (control systems); k-nearest neighbors algorithm; Polynomial; Time complexity; Artificial intelligence; Mathematics","score_opus":0.009562008365173272,"score_gpt":0.233085311769209,"score_spread":0.22352330340403573,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121305702","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9794504,0.00031726403,0.012831207,0.00009050243,0.00008978623,0.00010187468,0.00001793012,0.000003354501,0.007097697],"genre_scores_gemma":[0.98803234,0.00007803822,0.0115570305,0.00020220429,0.000052323754,9.292922e-7,0.000025810525,0.0000033815893,0.000047920752],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995824,0.0000051927314,0.00020126968,0.000052656687,0.00006281148,0.00009568347],"domain_scores_gemma":[0.99970645,0.0000029648409,0.00009054695,0.000111528076,0.00006175723,0.000026740032],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000054921606,0.00007091302,0.00008705633,0.000023516579,0.000029822175,0.0000070928836,0.000071719616,0.000048032554,0.0000015298345],"category_scores_gemma":[0.00001314017,0.00006380656,0.000042978223,0.00004647953,0.000027300994,6.8707953e-7,0.000027899401,0.000019455,0.0000048661877],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000109684035,0.00019814522,0.0067660585,0.00013961854,0.00017767036,7.5626224e-7,0.0020215032,0.003100126,0.8019889,0.0025532884,0.006572211,0.17637205],"study_design_scores_gemma":[0.0036822462,0.004567566,0.36782494,0.00009731605,0.00013664897,0.00004863556,0.002065224,0.03935541,0.53202456,0.0035005866,0.045377348,0.0013195451],"about_ca_topic_score_codex":0.0000016263931,"about_ca_topic_score_gemma":9.791488e-7,"teacher_disagreement_score":0.3610589,"about_ca_system_score_codex":0.0000031144957,"about_ca_system_score_gemma":0.000021193206,"threshold_uncertainty_score":0.2601956},"labels":[],"label_agreement":null},{"id":"W2121367512","doi":"10.1093/bioinformatics/btt529","title":"Ontology-aware classification of tissue and cell-type signals in gene expression profiles across platforms and technologies","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Human Genome Research Institute; National Institute of General Medical Sciences; Canadian Institute for Advanced Research; Princeton University; National Institutes of Health; National Science Foundation","keywords":"Preprocessor; Source code; Computational biology; Computer science; Gene expression; Gene ontology; Annotation; Gene; Data mining; Biology; Artificial intelligence; Genetics","score_opus":0.017833288188142147,"score_gpt":0.27234277418341923,"score_spread":0.25450948599527706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121367512","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99698234,0.0008446869,0.0014577996,0.00008805936,0.000040797426,0.00032787008,0.00001107157,0.000018924266,0.00022847106],"genre_scores_gemma":[0.99363244,0.0008962602,0.005209281,0.000023696408,0.000010428207,0.000049887105,0.00006882145,0.0000068216277,0.000102380065],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993295,0.000008614086,0.000295129,0.00014109311,0.00007935158,0.00014629573],"domain_scores_gemma":[0.99947256,0.000009060913,0.00017749635,0.00022862256,0.000079846315,0.000032408912],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009393316,0.000106045474,0.00012558747,0.000058607755,0.000046770052,0.000022464345,0.000106384236,0.00022818107,0.00000646007],"category_scores_gemma":[0.000038260878,0.00008296051,0.000012010329,0.000090911424,0.000119474505,0.000023304478,0.000114299844,0.00006117106,0.0000040746145],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017595441,0.000021057176,0.005865825,0.00009644767,0.0000029171458,7.9416274e-8,0.0003134697,0.0000045804713,0.9733233,0.000017867005,0.0006818676,0.019655032],"study_design_scores_gemma":[0.0003260222,0.00013751829,0.019189335,0.000030643318,0.00000272994,0.0000043116634,0.0033404718,0.0011441034,0.9745857,0.00016451506,0.00096224574,0.0001123946],"about_ca_topic_score_codex":0.000007966042,"about_ca_topic_score_gemma":0.0000049488362,"teacher_disagreement_score":0.019542636,"about_ca_system_score_codex":0.0000073717006,"about_ca_system_score_gemma":0.000023871595,"threshold_uncertainty_score":0.33830315},"labels":[],"label_agreement":null},{"id":"W2121621283","doi":"10.1093/bioinformatics/btg004","title":"IslandPath: aiding detection of genomic islands in prokaryotes","year":2003,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Salmonella and Campylobacter epidemiology","field":"Agricultural and Biological Sciences","cited_by":395,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; Simon Fraser University","funders":"","keywords":"Computational biology; Computer science; Biology","score_opus":0.023017004468561517,"score_gpt":0.21639375044336323,"score_spread":0.1933767459748017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121621283","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9958662,0.00008006264,0.00013073577,0.000030560856,0.0000948501,0.00009904461,0.0000069404914,0.00001679711,0.003674854],"genre_scores_gemma":[0.999447,0.00005077576,0.0003169454,0.00011641534,0.000027684737,0.0000043207456,0.000009647223,3.9103372e-7,0.000026852222],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9993343,0.000049397524,0.0003257166,0.00006675197,0.00005740537,0.0001664418],"domain_scores_gemma":[0.9996525,0.00014938899,0.00011584516,0.0000365194,0.000018446743,0.00002729183],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033161225,0.000073846604,0.0001515565,0.000018293258,0.000037913214,0.000008004106,0.0000801762,0.00008246986,0.000052431344],"category_scores_gemma":[0.000110087785,0.000028533981,0.00004416735,0.00015148116,0.000021995145,0.00008203793,0.000015853573,0.00006089543,0.000024479134],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034753295,0.000079440164,0.5085257,0.0000552092,0.000013661246,0.0000015550761,0.0013309361,0.00002113134,0.4237526,0.00064847776,0.0001683335,0.06536819],"study_design_scores_gemma":[0.00047350745,0.00051063753,0.9245027,0.000043215772,0.000013116902,0.00004294936,0.002234231,0.0040684333,0.05425024,0.0025204017,0.010991446,0.0003491479],"about_ca_topic_score_codex":0.000024868614,"about_ca_topic_score_gemma":0.00012757427,"teacher_disagreement_score":0.41597697,"about_ca_system_score_codex":0.00001837625,"about_ca_system_score_gemma":0.000006014713,"threshold_uncertainty_score":0.1163582},"labels":[],"label_agreement":null},{"id":"W2121628067","doi":"10.1093/bioinformatics/btt064","title":"Phylogenomic clustering for selecting non-redundant genomes for comparative genomics","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Genomics; Comparative genomics; Cluster analysis; Genome; Computational biology; Computer science; Biology; Evolutionary biology; Genetics; Artificial intelligence; Gene","score_opus":0.026802228151749517,"score_gpt":0.2642351388127584,"score_spread":0.23743291066100888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121628067","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9005025,0.0007195142,0.095146246,0.00007385595,0.00033896425,0.002109783,0.00015635927,0.000009098308,0.00094368664],"genre_scores_gemma":[0.82962847,0.0001638728,0.16858928,0.0002859045,0.00039623523,0.00046029876,0.00013741554,0.000034948884,0.0003035707],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99886394,0.0000075688317,0.0004326075,0.0002116826,0.00005747955,0.0004266968],"domain_scores_gemma":[0.9992052,0.000048871647,0.00020168311,0.00024995534,0.00021008735,0.00008421561],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015461388,0.00023531949,0.00027583865,0.00004827207,0.00028234022,0.000084191975,0.00022624827,0.00010916942,0.0000038976896],"category_scores_gemma":[0.000028564758,0.00022325834,0.00015838214,0.000045588476,0.000060469712,0.000003550531,0.00014468198,0.000045238874,0.000018428009],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007846057,0.0000400172,0.00044979205,0.00023591334,0.00033067187,4.411025e-8,0.0024429434,0.0025552337,0.97952336,0.00005651126,0.005031199,0.009255841],"study_design_scores_gemma":[0.004494088,0.0023228088,0.004587456,0.000041434472,0.00018620743,0.000033920605,0.0074352156,0.30807373,0.35164392,0.00088824274,0.31851146,0.0017815179],"about_ca_topic_score_codex":0.000010959053,"about_ca_topic_score_gemma":0.000026439337,"teacher_disagreement_score":0.62787944,"about_ca_system_score_codex":0.00004011163,"about_ca_system_score_gemma":0.00008988813,"threshold_uncertainty_score":0.9104211},"labels":[],"label_agreement":null},{"id":"W2121653135","doi":"10.1093/bioinformatics/btr472","title":"Conserved and differential gene interactions in dynamical biological systems","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Core Research for Evolutional Science and Technology; National Cancer Institute; U.S. Department of Agriculture; New Mexico State University; National Science Foundation","keywords":"Computational biology; Differential (mechanical device); Gene; Biology; Computer science; Genetics; Physics","score_opus":0.02893718377708309,"score_gpt":0.23776513239720018,"score_spread":0.20882794862011708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121653135","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9939089,0.00018819245,0.0050495765,0.00000894871,0.00013097326,0.00010582259,0.000010089133,0.000010546132,0.0005869942],"genre_scores_gemma":[0.9973057,0.000115061834,0.0023042937,0.0000305671,0.000053610183,0.0000115804005,0.000091988026,0.0000063505563,0.00008086642],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99932885,0.00003918079,0.0002926435,0.000119021955,0.000055187513,0.00016511316],"domain_scores_gemma":[0.99962497,0.000007770127,0.000075438875,0.00019323865,0.000028366292,0.00007019679],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000080240454,0.00011023259,0.00014690006,0.000058302183,0.000035808753,0.000018674202,0.000095086165,0.00009486022,0.000020798025],"category_scores_gemma":[0.000021616954,0.00009088919,0.000051870567,0.000068159,0.00008205989,0.000004712125,0.00010568084,0.00006413788,0.000009696395],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006054107,0.00082572084,0.5865868,0.00028222732,0.0009555919,0.000030454808,0.0019867094,0.000626844,0.39385313,0.0025184564,0.002844225,0.008884463],"study_design_scores_gemma":[0.0034089792,0.0008134348,0.50549865,0.000104217754,0.00020901993,0.0004198564,0.0023380395,0.43758157,0.03904913,0.0002046308,0.008815193,0.0015572632],"about_ca_topic_score_codex":0.000029977975,"about_ca_topic_score_gemma":0.00006112522,"teacher_disagreement_score":0.43695474,"about_ca_system_score_codex":0.000011830404,"about_ca_system_score_gemma":0.000017802377,"threshold_uncertainty_score":0.37063536},"labels":[],"label_agreement":null},{"id":"W2122062351","doi":"10.1093/bioinformatics/btr389","title":"BRISK—research-oriented storage kit for biology-related data","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Canadian Institutes of Health Research","keywords":"Computer science; Java; Documentation; Data sharing; Data management; Software; Data access; Web application; World Wide Web; Data science; Database; Operating system","score_opus":0.17065333150659484,"score_gpt":0.373670698899958,"score_spread":0.20301736739336318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122062351","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5179604,0.0051632156,0.42020246,0.0009003068,0.003580091,0.0029678736,0.003259313,0.00053497363,0.045431342],"genre_scores_gemma":[0.6732935,0.0006063657,0.3153401,0.00059526577,0.00044173218,0.000103524435,0.0067614526,0.00006664614,0.0027914403],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987908,0.00005047469,0.0003539219,0.00025024367,0.00012685264,0.0004277059],"domain_scores_gemma":[0.9986898,0.000048849848,0.00010414359,0.00089259923,0.00014480554,0.00011984646],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009133617,0.00013626537,0.0001572859,0.00008018361,0.00015171747,0.000016100623,0.0007248028,0.00034076333,0.00004004559],"category_scores_gemma":[0.00088325224,0.00011037452,0.000055651035,0.00015325306,0.00043549767,0.000008608839,0.0005378547,0.00015615555,0.00006480159],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00063776906,0.00068016106,0.004817649,0.00044973494,0.0007868667,0.000008948167,0.004158215,0.0000055797177,0.02144875,0.008691803,0.44796458,0.5103499],"study_design_scores_gemma":[0.0013336849,0.0011711925,0.0009854096,0.000033294997,0.00003554833,0.000014165953,0.0013333213,0.00962997,0.007841074,0.00089231983,0.976363,0.00036701185],"about_ca_topic_score_codex":0.000023641542,"about_ca_topic_score_gemma":0.000011535787,"teacher_disagreement_score":0.5283984,"about_ca_system_score_codex":0.0000107311735,"about_ca_system_score_gemma":0.00010158107,"threshold_uncertainty_score":0.45009425},"labels":[],"label_agreement":null},{"id":"W2122270525","doi":"10.1093/bioinformatics/16.5.425","title":"Prediction of genetic structure in eukaryotic DNA using reference point logistic regression and sequence alignment","year":2000,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Logistic regression; Sequence (biology); Computer science; Point (geometry); Computational biology; DNA; Statistics; Biology; Genetics; Mathematics; Geometry","score_opus":0.02673682026311662,"score_gpt":0.24565773206027303,"score_spread":0.2189209117971564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122270525","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9983652,0.00014779372,0.000976955,0.000008270881,0.000035992784,0.00013636395,0.00011333144,0.000004184467,0.00021187885],"genre_scores_gemma":[0.9800747,0.00041497799,0.019310797,0.00003696164,0.000018340126,0.00000156664,0.00010388042,0.000007828437,0.000030952557],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99926,0.000017615936,0.00036148066,0.00011867696,0.00009912234,0.00014309226],"domain_scores_gemma":[0.9995821,0.000004890836,0.000120300116,0.00022179085,0.000027026039,0.00004390391],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000057803805,0.00011664855,0.00012200246,0.000037742615,0.00003356464,0.000013436619,0.0000961476,0.00012181251,0.000023459617],"category_scores_gemma":[0.000016542712,0.000100722755,0.000019106372,0.000050661885,0.00007230939,0.000006697103,0.000053028692,0.000056261495,0.0000010985323],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012259529,0.000097882585,0.031159615,0.00071579136,0.00005506146,0.000008139014,0.0009820465,0.027489733,0.9094345,0.00027389848,0.00011879576,0.029541925],"study_design_scores_gemma":[0.0016498127,0.00077165995,0.15395132,0.00043433698,0.0000724843,0.0002614978,0.00049046916,0.79497945,0.044297565,0.0020868026,0.00044164847,0.0005629515],"about_ca_topic_score_codex":0.000019204726,"about_ca_topic_score_gemma":0.000011073804,"teacher_disagreement_score":0.8651369,"about_ca_system_score_codex":0.000029512641,"about_ca_system_score_gemma":0.00004933971,"threshold_uncertainty_score":0.41073546},"labels":[],"label_agreement":null},{"id":"W2122812051","doi":"10.1093/bioinformatics/btq653","title":"HiTEC: accurate error correction in high-throughput sequencing data","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":138,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Throughput; DNA sequencing; Source code; Algorithm; Biology; DNA; Genetics","score_opus":0.03351851025080672,"score_gpt":0.2747700612401669,"score_spread":0.2412515509893602,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122812051","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9942961,0.000096699194,0.0016683879,0.000089675304,0.001476123,0.00015103712,0.00008000428,0.0000075076787,0.0021344775],"genre_scores_gemma":[0.98469007,0.000114747534,0.014369705,0.00020256273,0.00020028588,0.000005756678,0.00025185314,0.000013231331,0.0001517811],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992427,0.000010473895,0.00028545212,0.0001751327,0.000079150144,0.00020707485],"domain_scores_gemma":[0.99912614,0.00001116118,0.000106506326,0.0006698406,0.00004315518,0.000043203312],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021112368,0.00012695405,0.00011916316,0.00004155372,0.00007325647,0.00003330386,0.0003343611,0.00012873669,0.00000931842],"category_scores_gemma":[0.00012595847,0.00011800493,0.000024473438,0.00008329534,0.000054137792,0.0000049013415,0.00036304916,0.00013620214,0.000024242792],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007844098,0.000085795626,0.013005625,0.00010276451,0.000120306526,0.0000053618005,0.0014849636,0.0014225824,0.9202802,0.0003950705,0.02231654,0.040702343],"study_design_scores_gemma":[0.0043781823,0.0008657739,0.096699424,0.00009982216,0.00013128697,0.0003003741,0.005397421,0.23169719,0.22756915,0.0008348823,0.4295568,0.0024697026],"about_ca_topic_score_codex":0.00009494205,"about_ca_topic_score_gemma":0.0005458117,"teacher_disagreement_score":0.69271106,"about_ca_system_score_codex":0.000013412456,"about_ca_system_score_gemma":0.00008030411,"threshold_uncertainty_score":0.48121014},"labels":[],"label_agreement":null},{"id":"W2122898583","doi":"10.1093/bioinformatics/btu681","title":"mimicMe: a web server for prediction and analysis of host-like proteins in microbial pathogens","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bacteriophages and microbial interactions","field":"Environmental Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Host (biology); Proteome; Pathogen; Biology; Web server; Function (biology); Computational biology; Microbiology; Bioinformatics; Computer science; World Wide Web; Genetics; The Internet","score_opus":0.00748936859276984,"score_gpt":0.20999672857677043,"score_spread":0.2025073599840006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122898583","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99542063,0.000002916429,0.0033255923,0.000047675618,0.00007801689,0.00032535984,0.00039228224,0.000011225105,0.00039630043],"genre_scores_gemma":[0.98771405,0.000015251642,0.011860808,0.00012975805,0.000012373607,0.000020761407,0.00009009949,0.0000056657796,0.00015120118],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99944174,0.000011534319,0.00028741342,0.000081608014,0.00005427597,0.00012339628],"domain_scores_gemma":[0.99969494,0.000021953501,0.000111470064,0.00012835755,0.000008859751,0.000034441648],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014912209,0.000073739335,0.0001460431,0.00009644982,0.000041152405,0.000019038038,0.00006382941,0.000055322773,0.00012433622],"category_scores_gemma":[0.000019300971,0.00006682808,0.00006956385,0.00026076642,0.000052771422,0.00021820299,0.000058678146,0.000042935815,0.000010493399],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058851547,0.00015923822,0.03306899,0.00013486676,0.00014554714,2.417364e-7,0.0025722964,0.00076126645,0.9507403,0.000041904903,0.0013380756,0.010978418],"study_design_scores_gemma":[0.00096075324,0.00022616549,0.6279532,0.00004157266,0.000366797,0.0000068978848,0.0002288994,0.3334271,0.009612818,0.000012610662,0.026943564,0.00021965854],"about_ca_topic_score_codex":0.00009487816,"about_ca_topic_score_gemma":0.0008422962,"teacher_disagreement_score":0.9411275,"about_ca_system_score_codex":0.00004344544,"about_ca_system_score_gemma":0.0000056464087,"threshold_uncertainty_score":0.272517},"labels":[],"label_agreement":null},{"id":"W2123032056","doi":"10.1093/bioinformatics/btu166","title":"relax: the analysis of biomolecular kinetics and thermodynamics using NMR relaxation dispersion data","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":62,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"H2020 European Research Council","keywords":"Kinetics; Dispersion (optics); Relaxation (psychology); Thermodynamics; Chemistry; Physical chemistry; Statistical physics; Materials science; Physics","score_opus":0.011225486809506306,"score_gpt":0.24577192386449237,"score_spread":0.23454643705498607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123032056","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62004596,0.000216784,0.3790933,0.00004226936,0.00003993003,0.000120075965,0.00007555602,0.0000056507492,0.000360495],"genre_scores_gemma":[0.9763975,0.00017418411,0.022460392,0.00012345874,0.00003413463,9.1165407e-7,0.0007859929,0.000010283793,0.000013113311],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992636,0.000039451967,0.000287597,0.00014066052,0.0001460264,0.0001226703],"domain_scores_gemma":[0.9987607,0.000019519552,0.00023817732,0.0008825753,0.000062832485,0.000036192265],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002713125,0.000113728995,0.00014937614,0.00007625595,0.0000731759,0.000025264972,0.000321652,0.00012603235,0.0000018518211],"category_scores_gemma":[0.00014575476,0.00007903537,0.000057183406,0.00027108722,0.00012279929,0.000011174648,0.0003282351,0.000056509154,4.987327e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001523527,0.000108039865,0.009830957,0.0002769042,0.0021901152,9.702861e-7,0.0010211633,0.021149654,0.86668825,0.0060756677,0.0002699142,0.09223599],"study_design_scores_gemma":[0.00016970039,0.00007846259,0.0038611619,0.000008986466,0.0004993769,0.000005721562,0.000100133904,0.9901114,0.003214635,0.00013076692,0.0016947637,0.00012488721],"about_ca_topic_score_codex":0.000019940593,"about_ca_topic_score_gemma":0.000032597272,"teacher_disagreement_score":0.9689618,"about_ca_system_score_codex":0.000008221144,"about_ca_system_score_gemma":0.000019026935,"threshold_uncertainty_score":0.3222969},"labels":[],"label_agreement":null},{"id":"W2123128942","doi":"10.1093/bioinformatics/btr184","title":"Comrad: detection of expressed rearrangements by integrated analysis of RNA-Seq and low coverage genome sequence data","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; BC Cancer Agency","funders":"Canadian Institutes of Health Research","keywords":"Genome; Computational biology; LNCaP; Biology; RNA-Seq; Gene; Genetics; Gene expression; Prostate cancer; Cancer; Transcriptome","score_opus":0.03551003974175679,"score_gpt":0.24134292339191143,"score_spread":0.20583288365015465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123128942","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9883481,0.00049302523,0.009047937,0.0000025152817,0.000042209333,0.000108056185,0.001459791,0.0000018118151,0.0004965339],"genre_scores_gemma":[0.99550855,0.0013265421,0.0024781404,0.000027778176,0.0000059179133,0.0000027549354,0.00060802716,0.000005313569,0.000036951802],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999384,0.000015243293,0.00030880683,0.00011747896,0.0000777521,0.00009675125],"domain_scores_gemma":[0.9992249,0.000006926333,0.00021125072,0.00044433252,0.00008010573,0.00003248972],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012842086,0.00009477208,0.00019014347,0.00006352087,0.000028030086,0.000005977187,0.00021331357,0.000064664666,0.000007821685],"category_scores_gemma":[0.00003191283,0.00008443341,0.000037104655,0.00014701238,0.00008694155,0.0000034109278,0.00019565749,0.000028443092,4.1012373e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003684402,0.000029944425,0.001916567,0.00005361097,0.0006019557,1.1622891e-7,0.0003863619,0.000017681179,0.99388564,0.0000028511806,0.00009461675,0.002973821],"study_design_scores_gemma":[0.0008136742,0.00048151484,0.021691028,0.000021850421,0.0007539019,0.0000019122383,0.0006636972,0.016862174,0.9514531,0.000028081864,0.006901983,0.0003271043],"about_ca_topic_score_codex":0.00011898454,"about_ca_topic_score_gemma":0.000028527103,"teacher_disagreement_score":0.042432554,"about_ca_system_score_codex":0.0000045023207,"about_ca_system_score_gemma":0.000018518407,"threshold_uncertainty_score":0.34430948},"labels":[],"label_agreement":null},{"id":"W2123271845","doi":"10.1093/bioinformatics/bts555","title":"Phylogenetics, likelihood, evolution and complexity","year":2012,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"National Institutes of Health; National Institute of General Medical Sciences; National Natural Science Foundation of China","keywords":"Phylogenetics; Evolutionary biology; Computational biology; Computer science; Biology; Genetics; Gene","score_opus":0.022273995039399662,"score_gpt":0.23694598210685225,"score_spread":0.21467198706745258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123271845","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.987091,0.0042517735,0.0029707195,0.000041270985,0.00016319174,0.0001403021,0.000019352696,0.000005596169,0.0053167962],"genre_scores_gemma":[0.98688793,0.00038233955,0.012176188,0.00017816064,0.0002641255,0.000006195765,0.00002583439,0.0000097287075,0.00006950211],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9993586,0.000013475442,0.00018118155,0.000082059814,0.000074874595,0.00028982793],"domain_scores_gemma":[0.999577,0.000005568676,0.000064780994,0.00019360485,0.000043825075,0.00011521918],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014477906,0.00011907996,0.00009882286,0.000024950632,0.00010310668,0.000015794834,0.00007738034,0.00007841612,0.0000046026344],"category_scores_gemma":[0.000027694025,0.00010995898,0.000036544683,0.000038130594,0.00011902399,0.0000016867452,0.00015735826,0.000037405538,0.00001999546],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010358802,0.00032086213,0.6267393,0.00030170922,0.00040847523,4.456171e-7,0.002635377,0.000043814824,0.29312763,0.011832699,0.021554334,0.04293176],"study_design_scores_gemma":[0.0011659851,0.0004722093,0.7321664,0.000016147918,0.000086152744,0.000068012516,0.0012833892,0.0015437282,0.034726378,0.0017514677,0.22589114,0.0008289575],"about_ca_topic_score_codex":0.000008853504,"about_ca_topic_score_gemma":0.000009699077,"teacher_disagreement_score":0.25840127,"about_ca_system_score_codex":0.000010347115,"about_ca_system_score_gemma":0.00001979607,"threshold_uncertainty_score":0.4483997},"labels":[],"label_agreement":null},{"id":"W2123317029","doi":"10.1093/bioinformatics/bti035","title":"tPatternHunter: gapped, fast and sensitive translated homology search","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; University of Waterloo; Bioinformatics Solutions (Canada)","funders":"Killam Trusts; Canada Research Chairs","keywords":"Software; Computer science; Homology (biology); Frame (networking); Translation (biology); Information retrieval; Theoretical computer science; Artificial intelligence; Programming language; Biology; Genetics; Amino acid; Gene","score_opus":0.01029322687539442,"score_gpt":0.22948157494675012,"score_spread":0.2191883480713557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123317029","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9901962,0.00043312227,0.0075424435,0.00024204532,0.00007983726,0.00014933017,0.000052635467,0.00000531491,0.0012990364],"genre_scores_gemma":[0.9942428,0.00040712798,0.004721403,0.00042348882,0.00006298284,0.000004199309,0.00004221896,0.000011621537,0.00008414373],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999375,0.000013575769,0.0001880117,0.00013083468,0.00006718741,0.00022540348],"domain_scores_gemma":[0.9996739,0.000005945661,0.000036147918,0.00016214607,0.000055373886,0.00006650653],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000083881365,0.00013074168,0.00012707252,0.000035946305,0.00008355242,0.000020298872,0.000076650285,0.00010252769,0.0000024678986],"category_scores_gemma":[0.000007772757,0.00011882455,0.000042086598,0.000043035507,0.00012648248,0.0000012283832,0.00008587768,0.00006244892,0.000017801385],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003466026,0.00022638748,0.011458238,0.0003626533,0.00082277885,0.00004306536,0.021347532,0.002578975,0.87734765,0.0011535794,0.00080703816,0.08350549],"study_design_scores_gemma":[0.010889609,0.0038159918,0.07097403,0.00013142341,0.00020393598,0.0013789147,0.0090673985,0.004057177,0.854622,0.0008200002,0.04182543,0.0022140606],"about_ca_topic_score_codex":0.000027163878,"about_ca_topic_score_gemma":0.00003467855,"teacher_disagreement_score":0.08129143,"about_ca_system_score_codex":0.000008122978,"about_ca_system_score_gemma":0.00004165614,"threshold_uncertainty_score":0.48455244},"labels":[],"label_agreement":null},{"id":"W2124012659","doi":"10.1093/bioinformatics/btr378","title":"Biologically inspired EM image alignment and neural reconstruction","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Advanced Electron Microscopy Techniques and Applications","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Biotechnology and Biological Sciences Research Council","keywords":"Computer science; Artificial intelligence; Pattern recognition (psychology); Computer vision; Dynamic programming; Segmentation; Shortest path problem; Algorithm; Theoretical computer science","score_opus":0.01341737314837253,"score_gpt":0.2679032938747742,"score_spread":0.25448592072640164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2124012659","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87843084,0.00011748745,0.117786035,0.000043084943,0.000044375196,0.00025871603,0.000020974285,0.00005816417,0.0032403362],"genre_scores_gemma":[0.65316814,0.00040663194,0.34576625,0.00040550678,0.000042744698,0.00003933699,0.00006775379,0.0000098321125,0.00009380523],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995646,0.000006228247,0.0001692644,0.00009848779,0.000029565601,0.0001318537],"domain_scores_gemma":[0.9996963,0.0000016042377,0.00007426207,0.000156173,0.000028482675,0.000043134572],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000045971217,0.0000850833,0.00006401804,0.000017189961,0.00006345576,0.000015792793,0.00007375916,0.00007564071,0.000012724023],"category_scores_gemma":[0.000009574247,0.00007162196,0.000024919047,0.000036033172,0.00007475434,0.000008115525,0.0000597113,0.0000409685,0.000004489897],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004084144,0.000042566968,0.0009191926,0.00002075848,0.000018536128,4.001843e-7,0.00020749638,9.855215e-7,0.9013959,0.0010527765,0.0009861651,0.09531439],"study_design_scores_gemma":[0.0003902297,0.00066891854,0.0026229366,0.000010988268,0.00001732515,0.00013034222,0.0004546285,0.0013750092,0.9735954,0.0013976364,0.01897917,0.0003574076],"about_ca_topic_score_codex":0.0000024821134,"about_ca_topic_score_gemma":0.0000018053659,"teacher_disagreement_score":0.22798021,"about_ca_system_score_codex":0.0000067978403,"about_ca_system_score_gemma":0.000009823278,"threshold_uncertainty_score":0.29206586},"labels":[],"label_agreement":null},{"id":"W2124018109","doi":"10.1093/bioinformatics/btr241","title":"Predicting site-specific human selective pressure using evolutionary signatures","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University; Université du Québec à Montréal","funders":"","keywords":"Computer science; Computational biology; Artificial intelligence; Biological system; Biology","score_opus":0.015591928864699595,"score_gpt":0.22112838834859713,"score_spread":0.20553645948389754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2124018109","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98644435,0.00074424624,0.0029805237,0.0000028504994,0.0001458434,0.0002079676,0.00007789346,0.000032169144,0.009364176],"genre_scores_gemma":[0.96599585,0.00004711453,0.033319317,0.000054786888,0.00016287155,0.0000056373688,0.00018112871,0.000022863962,0.00021041208],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991612,0.000019116878,0.0002943222,0.00015617519,0.00012237715,0.00024684586],"domain_scores_gemma":[0.99936306,0.000004912351,0.00016819147,0.00028605375,0.000109685534,0.00006811118],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009746398,0.00016340688,0.00011754948,0.00004794608,0.00021563748,0.000024968333,0.00019040877,0.00019837463,0.000031213283],"category_scores_gemma":[0.000017567161,0.00016101619,0.000076114884,0.000072978204,0.0000651489,0.000009215696,0.0001440943,0.00012275383,0.000010732358],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017397523,0.0004016909,0.0643274,0.0004005537,0.0005605894,0.000008567218,0.008016943,0.007940101,0.89841586,0.0028907333,0.015483073,0.001380511],"study_design_scores_gemma":[0.0035663724,0.0021703213,0.10874257,0.00023223192,0.00044670154,0.0002797797,0.004057337,0.6109244,0.1950623,0.0023419682,0.06896932,0.0032066812],"about_ca_topic_score_codex":0.000020919277,"about_ca_topic_score_gemma":0.000011885596,"teacher_disagreement_score":0.7033536,"about_ca_system_score_codex":0.000022702843,"about_ca_system_score_gemma":0.000052428783,"threshold_uncertainty_score":0.65660495},"labels":[],"label_agreement":null},{"id":"W2124137325","doi":"10.1093/bioinformatics/btv008","title":"Deep profiling of multitube flow cytometry data","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vancouver General Hospital; University of British Columbia; BC Cancer Agency","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Michael Smith Health Research BC","keywords":"Bioconductor; Cluster analysis; Computer science; Profiling (computer programming); Imputation (statistics); Computational biology; Data mining; Flow cytometry; Artificial intelligence; Pattern recognition (psychology); Biological system; Biology; Molecular biology; Machine learning; Genetics; Missing data; Gene","score_opus":0.0601042930517372,"score_gpt":0.2783396199601503,"score_spread":0.21823532690841307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2124137325","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49513093,0.0010320877,0.4951928,0.00004920293,0.000885364,0.0004034941,0.00026791982,0.000045842113,0.006992347],"genre_scores_gemma":[0.73947257,0.00007769015,0.2587804,0.00014752292,0.00017796467,0.0000027384483,0.0012486767,0.000018242681,0.00007423241],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99921894,0.000012980312,0.0003201846,0.0001212938,0.00016394284,0.00016264366],"domain_scores_gemma":[0.99903286,0.000007549363,0.00009791748,0.00064466364,0.00011778367,0.00009922108],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024966354,0.000109586654,0.00013543056,0.00004572171,0.000026382297,0.000017477556,0.0004184386,0.00012100234,0.0000033282074],"category_scores_gemma":[0.000196216,0.00009748454,0.000039059974,0.000100874415,0.000058090805,0.0000141076125,0.00018870173,0.0000608324,0.00001538132],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008486092,0.0010312286,0.08182401,0.0015967696,0.00061829825,0.000010280423,0.0036329431,0.007962152,0.7505071,0.00033113686,0.018421518,0.13321593],"study_design_scores_gemma":[0.0017074975,0.0003603404,0.00033321333,0.00003167325,0.000047776553,0.000019952284,0.0008011158,0.62773174,0.35122573,0.000025493713,0.01734384,0.00037162655],"about_ca_topic_score_codex":0.000012719991,"about_ca_topic_score_gemma":0.000015056706,"teacher_disagreement_score":0.6197696,"about_ca_system_score_codex":0.00000997135,"about_ca_system_score_gemma":0.00010239401,"threshold_uncertainty_score":0.3975304},"labels":[],"label_agreement":null},{"id":"W2124312647","doi":"10.1093/bioinformatics/bth186","title":"Exploiting the kernel trick to correlate fragment ions for peptide identification via tandem mass spectrometry","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":111,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Kernel (algebra); Tandem mass spectrometry; Identification (biology); Software; Fragment (logic); Correlative; Mass spectrometry; Artificial intelligence; Data mining; Algorithm; Chemistry; Mathematics; Operating system","score_opus":0.016772802314836435,"score_gpt":0.2691784092850094,"score_spread":0.252405606970173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2124312647","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027763577,0.000021498397,0.96733207,0.0008119924,0.00004505155,0.00063408713,0.000056704026,0.0001827557,0.0031522547],"genre_scores_gemma":[0.34509766,0.000057350833,0.6525385,0.00029646917,0.0001273995,0.0008455359,0.00009622984,0.000029548017,0.0009113668],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989329,0.0000022939937,0.00050946267,0.0001336362,0.00016689047,0.00025484586],"domain_scores_gemma":[0.9990543,0.00007071123,0.00026593372,0.00045052895,0.000077492245,0.00008102975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018168768,0.00014069273,0.00012363172,0.000056863613,0.00033702553,0.00007771192,0.00030984211,0.00008421442,0.00003019613],"category_scores_gemma":[0.00007792754,0.00011524695,0.000093210496,0.00024447226,0.000029937624,0.00015159757,0.00005813538,0.00015926515,0.00009110711],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008770039,0.00045334906,0.0005252942,0.000768061,0.00022374533,0.0000023512926,0.008034344,0.020065084,0.77966166,0.13354172,0.006922449,0.049714223],"study_design_scores_gemma":[0.0014691881,0.00010023547,0.00022300617,0.00021393753,0.00012253391,0.00003188096,0.0045727794,0.04105793,0.8044116,0.11466936,0.032295708,0.00083185075],"about_ca_topic_score_codex":0.000006586364,"about_ca_topic_score_gemma":0.0000017504946,"teacher_disagreement_score":0.3173341,"about_ca_system_score_codex":0.00023332823,"about_ca_system_score_gemma":0.000034778728,"threshold_uncertainty_score":0.46996343},"labels":[],"label_agreement":null},{"id":"W2124337127","doi":"10.1093/bioinformatics/bts650","title":"HD-CNV: hotspot detector for copy number variants","year":2012,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomic variations and chromosomal abnormalities","field":"Biochemistry, Genetics and Molecular Biology","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Copy-number variation; Computer science; Copy number analysis; Source code; Biology; Genetics; Genome; Gene; Programming language","score_opus":0.013509275045211431,"score_gpt":0.24548352605813237,"score_spread":0.23197425101292093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2124337127","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9366383,0.00025566207,0.046083488,0.000083955,0.0010087923,0.0005413194,0.00035055852,0.0000430758,0.014994868],"genre_scores_gemma":[0.9633028,0.000042923126,0.033935864,0.00031695148,0.0005189593,0.00004950515,0.00020666262,0.000018257282,0.0016080758],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99920666,0.000011240432,0.00027317213,0.00007870018,0.000085293395,0.00034494372],"domain_scores_gemma":[0.99945873,0.000014444552,0.00010379206,0.00024724475,0.000069455185,0.000106338055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017730621,0.0001331995,0.00011590967,0.000020454314,0.00011686381,0.000033962955,0.00013670715,0.00012921276,0.00011195604],"category_scores_gemma":[0.00005407404,0.00012058741,0.000086724875,0.000045608474,0.000029842147,0.000017704879,0.00006525012,0.000038160248,0.00015909519],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012626563,0.0018120192,0.3652882,0.0025201938,0.0019632338,0.00000307991,0.015660293,0.00033607762,0.21778786,0.061399613,0.28589192,0.04607486],"study_design_scores_gemma":[0.0025695995,0.00044848525,0.023759004,0.000036380807,0.00013705218,0.00015629818,0.002037413,0.0015412904,0.24061947,0.00034355323,0.7272498,0.0011016338],"about_ca_topic_score_codex":0.000005722679,"about_ca_topic_score_gemma":0.0000039518577,"teacher_disagreement_score":0.4413579,"about_ca_system_score_codex":0.000016483446,"about_ca_system_score_gemma":0.000052674226,"threshold_uncertainty_score":0.49174115},"labels":[],"label_agreement":null},{"id":"W2124714582","doi":"10.1093/bioinformatics/btr452","title":"OrganismTagger: detection, normalization and grounding of organism entities in biomedical documents","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; University of New Brunswick","funders":"","keywords":"Computer science; Organism; Information retrieval; Taxonomy (biology); Natural language processing; Precision and recall; Named-entity recognition; Artificial intelligence; Task (project management); Biology","score_opus":0.014569750501862155,"score_gpt":0.2312963566121826,"score_spread":0.21672660611032044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2124714582","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96604896,0.00015822852,0.03247619,0.000013069004,0.00018539249,0.00008216745,0.000006020935,0.000016710952,0.0010132758],"genre_scores_gemma":[0.98905873,0.00020885059,0.010553656,0.00004807671,0.000025912801,0.0000030412293,0.000026525055,0.000006269115,0.00006892676],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999385,0.000015276713,0.00028735035,0.00007756645,0.000104272694,0.00013054101],"domain_scores_gemma":[0.99971527,0.0000056399217,0.000094610165,0.000105681815,0.000032576805,0.000046222984],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016091255,0.00007850654,0.00010349312,0.00008681727,0.000034499106,0.000009690911,0.000085608364,0.00014316192,0.00002638835],"category_scores_gemma":[0.00010944555,0.00006837503,0.000017081667,0.000118387696,0.00017484628,0.00000971218,0.00008455734,0.000044542983,0.0000038191797],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030693744,0.00071713654,0.15931663,0.0015093614,0.0003059625,0.000016054675,0.03276987,0.0000018591141,0.45895916,0.0028391664,0.002062242,0.3411956],"study_design_scores_gemma":[0.0036895843,0.002256239,0.1154715,0.00022813381,0.00007855274,0.00016634235,0.013971632,0.0015271056,0.8269023,0.0017993827,0.033007942,0.0009013292],"about_ca_topic_score_codex":0.00003788023,"about_ca_topic_score_gemma":0.00002304403,"teacher_disagreement_score":0.3679431,"about_ca_system_score_codex":0.000008536392,"about_ca_system_score_gemma":0.00002702143,"threshold_uncertainty_score":0.2788253},"labels":[],"label_agreement":null},{"id":"W2124935821","doi":"10.1093/bioinformatics/bth413","title":"EC_oligos: automated and whole-genome primer design for exons within one or between two genomes","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Agriculture and Agri-Food Canada; McGill University; Ste. Anne's Hospital","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Executable; Oligonucleotide; Genome; Primer (cosmetics); Computational biology; Exon; Biology; File Transfer Protocol; Genetics; Computer science; Sequence (biology); DNA; Programming language; Gene; World Wide Web","score_opus":0.041176228304203685,"score_gpt":0.27209719614512895,"score_spread":0.23092096784092525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2124935821","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92769706,0.002431896,0.06718485,0.00026836942,0.0001521467,0.0013517113,0.0005151582,0.00006145345,0.00033735076],"genre_scores_gemma":[0.6966493,0.0004753132,0.3017801,0.00028659843,0.00023937483,0.00006842109,0.00023917937,0.000037277285,0.00022442469],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990028,0.000014206762,0.00039959,0.0001867564,0.00009306592,0.00030355898],"domain_scores_gemma":[0.9993498,0.000029496412,0.00015735897,0.00026623026,0.00008674791,0.00011039263],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022328674,0.00021205783,0.00024833964,0.00005228511,0.00017881222,0.000050611623,0.00016314909,0.000116798314,0.0000021033404],"category_scores_gemma":[0.00005235427,0.00017596238,0.000058590573,0.000072575654,0.0001079445,0.0000032038047,0.00013646281,0.00004812344,0.000011717814],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006321263,0.00031357567,0.0056189345,0.00096765923,0.0023889476,0.0000046774367,0.008249415,0.011927119,0.95594174,0.0012529023,0.001655327,0.011047562],"study_design_scores_gemma":[0.031252712,0.012572517,0.057183895,0.00036353557,0.0017630792,0.0002147374,0.0044969423,0.017081778,0.65340877,0.0082318485,0.20741805,0.006012126],"about_ca_topic_score_codex":0.000009657509,"about_ca_topic_score_gemma":0.000015224112,"teacher_disagreement_score":0.30253297,"about_ca_system_score_codex":0.000021284748,"about_ca_system_score_gemma":0.0001554233,"threshold_uncertainty_score":0.71755373},"labels":[],"label_agreement":null},{"id":"W2124965915","doi":"10.1093/bioinformatics/btu355","title":"GenomeVISTA—an integrated software package for whole-genome alignment and visualization","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"National Institute of General Medical Sciences","keywords":"Perl; Computer science; Visualization; Software; Java; Genome; Web application; Source code; Flexibility (engineering); World Wide Web; Data mining; Operating system; Biology; Genetics","score_opus":0.011843090348213053,"score_gpt":0.242854442158818,"score_spread":0.23101135181060495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2124965915","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46280077,0.00044763327,0.5354492,0.000056064924,0.0001356867,0.0004953182,0.00033542924,0.000015002679,0.00026489949],"genre_scores_gemma":[0.93249667,0.00029988855,0.06364271,0.0007715016,0.00024009116,0.00006617199,0.00206266,0.00004145779,0.00037887413],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993225,0.000019014386,0.00024888304,0.00015061983,0.00006987327,0.00018910918],"domain_scores_gemma":[0.9994688,0.000012730774,0.000098432865,0.00024124826,0.00009530869,0.0000834743],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001918146,0.00014839125,0.00013635309,0.000033643475,0.00012572958,0.00005431724,0.000107826934,0.00008773187,0.0000024542824],"category_scores_gemma":[0.000075372256,0.00013153802,0.000040197032,0.000040405903,0.000052013507,0.0000025354557,0.000079395075,0.000022930384,0.0000049931296],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001776964,0.00019436474,0.00484193,0.0006184281,0.00033984554,3.9078895e-7,0.003257374,0.00038252585,0.89675254,0.0036320826,0.0033471654,0.08645565],"study_design_scores_gemma":[0.0011863664,0.0014303861,0.005571479,0.000015116065,0.000060366485,0.000008167295,0.00090165687,0.0058897273,0.016306061,0.0003944113,0.96771103,0.00052521884],"about_ca_topic_score_codex":0.0000029787195,"about_ca_topic_score_gemma":0.000008498083,"teacher_disagreement_score":0.9643639,"about_ca_system_score_codex":0.00001148057,"about_ca_system_score_gemma":0.000024714931,"threshold_uncertainty_score":0.5363965},"labels":[],"label_agreement":null},{"id":"W2125045287","doi":"10.1093/bioinformatics/btq491","title":"Structural genomics of histone tail recognition","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Structural Genomics Consortium; University of Toronto","funders":"Knut och Alice Wallenbergs Stiftelse; Karolinska Institutet; Stiftelsen för Strategisk Forskning; Ontario Genomics Institute; Canadian Institutes of Health Research; National Institute for Health and Care Research; Ontario Genomics; Genome Canada; Ontario Innovation Trust; Wellcome Trust; GlaxoSmithKline","keywords":"Histone; Computational biology; Computer science; Epigenetics; Genomics; Graphics; Biology; Genetics; Genome; Gene; Computer graphics (images)","score_opus":0.008085528060864508,"score_gpt":0.23325997232090495,"score_spread":0.22517444426004044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125045287","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9961036,0.000030965704,0.0006273137,0.000019315767,0.0003344456,0.00010130574,0.00008664743,0.000007959175,0.0026884892],"genre_scores_gemma":[0.95126903,0.000047004796,0.047918472,0.00007792972,0.00010869716,0.000003193602,0.0004385761,0.000013929944,0.0001231651],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99939173,0.0000052255846,0.00030755022,0.00008101664,0.000077079494,0.00013741992],"domain_scores_gemma":[0.9993838,0.0000045248016,0.00018646756,0.00028119917,0.00009181829,0.000052191695],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000947576,0.00010283287,0.00010735269,0.00003379934,0.00004545612,0.000013836628,0.00015933307,0.00014145947,0.000033970704],"category_scores_gemma":[0.000042068827,0.00009953484,0.0000646229,0.000039846436,0.000079345264,0.0000049207674,0.000074250594,0.000091770984,0.00001853566],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028505527,0.000023167691,0.00063511066,0.00009193006,0.000037511134,3.5080066e-7,0.00029292345,0.000070350034,0.9752869,0.0002864061,0.0008773721,0.022369448],"study_design_scores_gemma":[0.0025935683,0.0008147516,0.010967155,0.000032258555,0.00011486724,0.00021971595,0.0012539403,0.09426458,0.84057933,0.0024965615,0.045327514,0.0013357586],"about_ca_topic_score_codex":0.00000665685,"about_ca_topic_score_gemma":0.000042270043,"teacher_disagreement_score":0.1347076,"about_ca_system_score_codex":0.000009895538,"about_ca_system_score_gemma":0.00006771025,"threshold_uncertainty_score":0.4058913},"labels":[],"label_agreement":null},{"id":"W2125122419","doi":"10.1093/bioinformatics/bts317","title":"An integrated open framework for thermodynamics of reactions that combines accuracy and coverage","year":2012,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Microbial Metabolic Engineering and Bioproduction","field":"Biochemistry, Genetics and Molecular Biology","cited_by":131,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Azrieli Foundation; Israel Academy of Sciences and Humanities","keywords":"Python (programming language); Computer science; Gibbs free energy; Ionic strength; Ionic bonding; Open source; Thermodynamics; Data mining; Chemistry; Software; Programming language; Physical chemistry; Physics; Ion; Aqueous solution","score_opus":0.018575142589848163,"score_gpt":0.2830708436086184,"score_spread":0.26449570101877024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125122419","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70514256,0.0001970038,0.2935861,0.00003984553,0.00035025872,0.00036173445,0.000102744205,0.0000134313605,0.00020631864],"genre_scores_gemma":[0.93269235,0.0003013061,0.06652568,0.00005138098,0.00011295486,0.000011635217,0.00023709054,0.000009977023,0.000057603407],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9996175,0.000009807863,0.00015903648,0.000062382474,0.00003391562,0.000117361946],"domain_scores_gemma":[0.9995628,0.0000102785725,0.000106659136,0.00021854817,0.000053754276,0.00004795258],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018424347,0.000083267456,0.00010256572,0.000023842493,0.00004500123,0.00003004121,0.0001246363,0.00010393101,0.000003001425],"category_scores_gemma":[0.00015185816,0.00006797481,0.000024825951,0.00004862027,0.000028900498,0.00003070517,0.000048247475,0.000045940018,6.446436e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016871271,0.00026605063,0.0018607053,0.00033848613,0.000115872586,3.0891716e-8,0.00076988165,0.00023803882,0.93596596,0.011005753,0.0009027361,0.04836779],"study_design_scores_gemma":[0.0014708842,0.00075999845,0.008954699,0.00015719718,0.00012386375,0.00005834286,0.0015504916,0.012948988,0.69200724,0.001203511,0.28003064,0.00073412346],"about_ca_topic_score_codex":0.0000158717,"about_ca_topic_score_gemma":0.0000019448837,"teacher_disagreement_score":0.2791279,"about_ca_system_score_codex":0.0000043914088,"about_ca_system_score_gemma":0.00001696942,"threshold_uncertainty_score":0.27719325},"labels":[],"label_agreement":null},{"id":"W2125339166","doi":"10.1093/bioinformatics/btn389","title":"DrugViz: a Cytoscape plugin for visualizing and analyzing small molecule drugs in biological networks","year":2008,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Plug-in; Computer science; Visualization; Software; Set (abstract data type); Cluster analysis; Data mining; Hierarchical clustering; Computational biology; Interactome; Biological network; Bioinformatics; Information retrieval; Biology; Machine learning; Programming language","score_opus":0.04813335152011109,"score_gpt":0.2986896161002469,"score_spread":0.2505562645801358,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125339166","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30364394,0.00014696868,0.6955301,0.00009198183,0.00007814295,0.00019920642,0.00000217901,0.000060988383,0.00024647944],"genre_scores_gemma":[0.47879303,0.00008257591,0.5206973,0.00033169377,0.00004030079,0.000024357936,0.000011655109,0.000007328426,0.000011728207],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998789,0.00007467973,0.0004559736,0.00020619683,0.00013868918,0.00033547607],"domain_scores_gemma":[0.99887884,0.0006246542,0.0001351498,0.00021617806,0.000054632856,0.00009053],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00065205357,0.00015890178,0.00023192023,0.00019757335,0.00014240503,0.00010513463,0.00038883957,0.000084667336,0.0000010312696],"category_scores_gemma":[0.00014525831,0.00014275798,0.00006862572,0.00047493653,0.00006871035,0.00042185237,0.00030844132,0.000121522535,0.0000035187581],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019980433,0.00058755546,0.03580632,0.0005702555,0.00019953735,0.00007690103,0.05582772,0.3419318,0.0005364307,0.25055575,0.0017774911,0.31193045],"study_design_scores_gemma":[0.00044564888,0.000058253547,0.00445773,0.000027958367,0.0000026863966,0.000029045332,0.00012447359,0.99322844,0.00014689032,0.0010094256,0.00027497677,0.0001944488],"about_ca_topic_score_codex":0.000009499246,"about_ca_topic_score_gemma":0.0000035807302,"teacher_disagreement_score":0.6512967,"about_ca_system_score_codex":0.00004916378,"about_ca_system_score_gemma":0.00007603607,"threshold_uncertainty_score":0.58215016},"labels":[],"label_agreement":null},{"id":"W2125353579","doi":"10.1093/bioinformatics/bth470","title":"SNP Chart: an integrated platform for visualization and interpretation of microarray genotyping data","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Paul's Hospital; University of British Columbia","funders":"Health Canada; Michael Smith Health Research BC","keywords":"SNP; Computer science; Replicate; Visualization; Chart; Genotyping; SNP genotyping; Data mining; SNP array; Single-nucleotide polymorphism; Data visualization; Computational biology; Biology; Genotype; Genetics; Statistics; Mathematics","score_opus":0.039674676826554726,"score_gpt":0.3162916687121121,"score_spread":0.2766169918855574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125353579","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18121462,0.00014604104,0.8180313,0.000031113657,0.00009095653,0.00024866243,0.000094671675,0.000010916129,0.00013169501],"genre_scores_gemma":[0.9649923,0.00014169389,0.031071313,0.00014418563,0.00004408176,0.000012504045,0.0035531418,0.000010485352,0.000030322653],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994946,0.000006093635,0.00024391018,0.00011840465,0.000057106685,0.00007985525],"domain_scores_gemma":[0.99940836,0.0000036180404,0.00015103658,0.00030218353,0.00009756,0.000037240487],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013827666,0.00007415892,0.00007593894,0.000048422913,0.000044355165,0.000022720094,0.00014508599,0.00008125554,0.0000020327268],"category_scores_gemma":[0.000059249964,0.00006619037,0.000015674503,0.000059699556,0.00003297284,0.0000326659,0.000052969546,0.00002167508,9.0554266e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026582388,0.00008120182,0.00013281223,0.00028705667,0.000043929307,4.189872e-8,0.0029387355,0.0003699281,0.8792762,0.0021234278,0.0010083099,0.1134725],"study_design_scores_gemma":[0.0019910343,0.0006301847,0.000611766,0.00014297609,0.0000458685,0.0000088367005,0.0033392224,0.20951204,0.74492776,0.00040653534,0.038054794,0.00032897058],"about_ca_topic_score_codex":0.000004550605,"about_ca_topic_score_gemma":0.0000138858895,"teacher_disagreement_score":0.78696,"about_ca_system_score_codex":0.000011136856,"about_ca_system_score_gemma":0.00007291107,"threshold_uncertainty_score":0.26991647},"labels":[],"label_agreement":null},{"id":"W2125598538","doi":"10.1093/bioinformatics/17.2.149","title":"An information-based sequence distance and its application to whole mitochondrial genome phylogeny","year":2001,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":542,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; City University of Hong Kong","keywords":"Phylogenetics; Sequence (biology); Biology; Genome; Distance matrices in phylogeny; Evolutionary biology; Mitochondrial DNA; Edit distance; Computational biology; Computer science; Genetics; Algorithm; Bioinformatics; Gene","score_opus":0.009646601906384321,"score_gpt":0.2431462677942042,"score_spread":0.23349966588781987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125598538","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49269444,0.00014397074,0.5046146,0.0002354014,0.0001295964,0.0010104902,0.00021930998,0.000046854333,0.00090533495],"genre_scores_gemma":[0.97039413,0.000058933823,0.027022788,0.0009484094,0.00019575501,0.00010653045,0.0011565064,0.000014391764,0.00010253975],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99918425,0.000012109439,0.00028499748,0.0001324242,0.00016357155,0.0002226687],"domain_scores_gemma":[0.99925584,0.0000043705168,0.00010695152,0.00035178065,0.00012211445,0.0001589556],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000093799405,0.00014329536,0.000099940575,0.00006889979,0.0000943647,0.000071138435,0.00021863291,0.00009365513,0.000007206448],"category_scores_gemma":[0.000032243217,0.00014377093,0.000028117473,0.00015282743,0.000027986742,0.000043834993,0.000048067235,0.000045040902,0.0001401819],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013179964,0.000075272386,0.0012424609,0.00014262169,0.000033980803,0.0000010386902,0.0008031449,0.0061979694,0.9622129,0.00019319492,0.00044248378,0.028523091],"study_design_scores_gemma":[0.0018028765,0.00084252463,0.0067250156,0.000021420943,0.000034341047,0.000024992583,0.00049561635,0.18870299,0.036102936,0.000058737074,0.7643053,0.0008832723],"about_ca_topic_score_codex":0.0000040509353,"about_ca_topic_score_gemma":0.0000103562015,"teacher_disagreement_score":0.92611,"about_ca_system_score_codex":0.000025671146,"about_ca_system_score_gemma":0.000055012857,"threshold_uncertainty_score":0.5862808},"labels":[],"label_agreement":null},{"id":"W2125604134","doi":"10.1093/bioinformatics/16.1.41","title":"The early introduction of dynamic programming into computational biology","year":2000,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"National Research Council Canada; American Mathematical Society","keywords":"Theme (computing); Field (mathematics); Sentence; Computer science; Mathematical economics; Mathematics; Artificial intelligence; World Wide Web","score_opus":0.0061490985847550295,"score_gpt":0.24222906463850982,"score_spread":0.23607996605375478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125604134","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016472198,0.00009114516,0.9819116,0.0008460985,0.00022760122,0.00012458999,0.0000034949878,0.00006662162,0.00025667943],"genre_scores_gemma":[0.11105308,0.00004636985,0.88860106,0.00004570924,0.000077041135,0.000006878483,0.000051017338,0.000003455502,0.000115395764],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993888,0.00001808474,0.0002701418,0.00007550442,0.00012550691,0.00012196146],"domain_scores_gemma":[0.99948174,0.00005136361,0.000100059966,0.0002795306,0.00006064368,0.000026646803],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018046328,0.000059473794,0.00006954047,0.00003384839,0.00018164518,0.000083640196,0.00042929317,0.000032011085,0.000009388317],"category_scores_gemma":[0.000014400226,0.000038148795,0.00002561103,0.00017327089,0.00008015891,0.0004208107,0.000097848344,0.00005962945,0.000044062122],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027985222,0.000011426391,0.000027348195,0.000007758294,0.0000052402115,7.556695e-8,0.00057829084,0.00032413987,0.0000084376325,0.011987818,0.00044061246,0.98660606],"study_design_scores_gemma":[0.00012031453,0.00009140178,0.0012700553,0.000005939188,0.0000019392949,0.0000071688783,0.000037297243,0.9163115,0.000028280123,0.0073702447,0.074689545,0.00006629246],"about_ca_topic_score_codex":0.00001579022,"about_ca_topic_score_gemma":0.0000019150264,"teacher_disagreement_score":0.9865398,"about_ca_system_score_codex":0.000016116024,"about_ca_system_score_gemma":0.00002929854,"threshold_uncertainty_score":0.15556628},"labels":[],"label_agreement":null},{"id":"W2125642929","doi":"10.1093/bioinformatics/btn440","title":"Local coherence in genetic interaction patterns reveals prevalent functional versatility","year":2008,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; Canada Research Chairs; Hospital for Sick Children; University of Toronto","funders":"","keywords":"Epistasis; Gene; Computational biology; In silico; Biology; Gene interaction; Cluster analysis; Saccharomyces cerevisiae; Genetics; Function (biology); Partition (number theory); Computer science; Artificial intelligence","score_opus":0.02005842178164167,"score_gpt":0.2350388322449486,"score_spread":0.21498041046330693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125642929","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86481667,0.00014092783,0.13256547,0.000036127527,0.00032972993,0.00028653882,0.000032877506,0.000014790313,0.0017768398],"genre_scores_gemma":[0.99536556,0.00022388124,0.003538147,0.00032165443,0.00010464713,0.000021234542,0.00017626116,0.000010174432,0.00023841525],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99884504,0.000027458229,0.0005448411,0.00014528571,0.00017529033,0.00026209958],"domain_scores_gemma":[0.99935335,0.000014775923,0.00016197434,0.00032237268,0.000061642044,0.00008587086],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017033746,0.00016340481,0.0001490388,0.000057097677,0.00007879729,0.000018023566,0.00015030612,0.00016052322,0.00007686271],"category_scores_gemma":[0.000025162399,0.0001564675,0.00007472131,0.000083334904,0.000089917696,0.000017830178,0.00010961256,0.00014804573,0.00006989422],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001562958,0.0011787884,0.6071604,0.0019057372,0.00047801307,0.000058714115,0.007495053,0.055231076,0.011575327,0.00040045255,0.0870857,0.22586781],"study_design_scores_gemma":[0.0032198906,0.00082295446,0.7906117,0.00021016812,0.00004229575,0.0005043371,0.0017118878,0.17240143,0.0063963663,0.0003507539,0.022579608,0.0011485975],"about_ca_topic_score_codex":0.000023253204,"about_ca_topic_score_gemma":0.000053690284,"teacher_disagreement_score":0.22471921,"about_ca_system_score_codex":0.000058774403,"about_ca_system_score_gemma":0.000082939696,"threshold_uncertainty_score":0.638056},"labels":[],"label_agreement":null},{"id":"W2125810118","doi":"10.1093/bioinformatics/btm224","title":"RankMotif++: a motif-search algorithm that accounts for relative ranks of K-mers in binding transcription factors","year":2007,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":67,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Ontario Genomics; Ontario Genomics Institute; Genome Canada","keywords":"Motif (music); DNA binding site; Computational biology; Computer science; Algorithm; Data mining; Biology; Genetics; Gene","score_opus":0.020642503547016827,"score_gpt":0.2618901333386715,"score_spread":0.24124762979165468,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125810118","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8300479,0.0000590404,0.16867962,0.000011101392,0.00015214512,0.000393923,0.00018670359,0.000005943192,0.00046360923],"genre_scores_gemma":[0.9583421,0.000097907985,0.040932387,0.000021128111,0.000030513213,0.0000060232073,0.0004005717,0.000020249057,0.00014915428],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989172,0.000013744221,0.00045133304,0.0001320062,0.00016930282,0.00031636335],"domain_scores_gemma":[0.99947554,0.000035464094,0.0001571276,0.0001916412,0.00007986287,0.00006034272],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006063162,0.00015463748,0.00019169644,0.00015628284,0.000055687306,0.000018991126,0.00017332088,0.00022040808,0.0000044010617],"category_scores_gemma":[0.000041044623,0.00014618065,0.00012548734,0.00012395161,0.00005862363,0.000019820889,0.000037467747,0.000102650745,0.0000023993152],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00077538454,0.00056536077,0.048419714,0.0014933184,0.0005802874,0.000004819028,0.022635913,0.002162886,0.78902894,0.0010486328,0.00040052665,0.13288423],"study_design_scores_gemma":[0.00983486,0.0014589796,0.059317075,0.00026515816,0.0001386195,0.000024082537,0.02709976,0.2031202,0.6930381,0.0005037948,0.0037728227,0.0014265563],"about_ca_topic_score_codex":0.000021310494,"about_ca_topic_score_gemma":0.00004243804,"teacher_disagreement_score":0.20095731,"about_ca_system_score_codex":0.000049372622,"about_ca_system_score_gemma":0.00005676147,"threshold_uncertainty_score":0.59610736},"labels":[],"label_agreement":null},{"id":"W2126122334","doi":"10.1093/bioinformatics/bts542","title":"Application and evaluation of automated methods to extract neuroanatomical connectivity statements from free text","year":2012,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; National Institutes of Health; Michael Smith Health Research BC","keywords":"Computer science; Artificial intelligence; Natural language processing; Text messaging; Software; Machine learning; Data mining; Programming language; World Wide Web","score_opus":0.045433913833232746,"score_gpt":0.4067668540895707,"score_spread":0.36133294025633794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126122334","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8663448,0.00029815314,0.13261653,0.00006957654,0.000093551054,0.00023246062,0.000054816017,0.000033962824,0.0002561669],"genre_scores_gemma":[0.8391016,0.00001566869,0.16062173,0.00010756605,0.000038022412,0.000020874822,0.000084552776,0.000005374633,0.0000045744046],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99920213,0.00011154146,0.00025717152,0.000095378324,0.00018737932,0.00014637152],"domain_scores_gemma":[0.9993555,0.00006335621,0.00012190107,0.0002724916,0.000085827654,0.00010090573],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009803182,0.0000860256,0.000121418,0.000034595283,0.000029880548,0.000009409923,0.00011297273,0.00011760335,0.000008086481],"category_scores_gemma":[0.000727378,0.00007363492,0.000023219693,0.000069801725,0.00005910088,0.000011198245,0.00012518006,0.000042339172,0.000006201956],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000490676,0.000110008084,0.005899813,0.00003603429,0.00006655669,3.6055795e-8,0.00055824686,0.000026526743,0.14767267,0.0000525468,0.002858721,0.8426698],"study_design_scores_gemma":[0.0021738235,0.00042078074,0.20325951,0.000032297507,0.00020293347,0.0000075363514,0.0009047189,0.44204527,0.30659345,0.0005540957,0.04335305,0.0004525509],"about_ca_topic_score_codex":0.000027468941,"about_ca_topic_score_gemma":0.0000049350506,"teacher_disagreement_score":0.8422172,"about_ca_system_score_codex":0.000013518856,"about_ca_system_score_gemma":0.000033409433,"threshold_uncertainty_score":0.3002745},"labels":[],"label_agreement":null},{"id":"W2126320151","doi":"10.1093/bioinformatics/btl410","title":"IndexToolkit: an open source toolbox to index protein databases for high-throughput proteomics","year":2006,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Search engine indexing; Database; Toolbox; MIT License; Interface (matter); Application programming interface; Information retrieval; Source code; Software; Open source; Database index; License; Database search engine; Index (typography); World Wide Web; Search engine; Programming language; Operating system","score_opus":0.03160131351498109,"score_gpt":0.3029832167974074,"score_spread":0.27138190328242634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126320151","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4562719,0.00004627103,0.5398793,0.00041548914,0.00012814174,0.0021353613,0.00030524886,0.000072619965,0.0007456607],"genre_scores_gemma":[0.37700716,0.0000048004404,0.6166115,0.0012161203,0.0005300122,0.00057720434,0.0016397539,0.000047437476,0.0023660222],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99870557,0.000025585907,0.00043965908,0.0002814917,0.000152621,0.0003950958],"domain_scores_gemma":[0.9989883,0.000017184244,0.00015608854,0.00060388277,0.00010079637,0.00013375237],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033969744,0.00021660948,0.00022774178,0.000056316665,0.00016464034,0.00016137476,0.00070622127,0.0002048404,0.000010362345],"category_scores_gemma":[0.0002653171,0.00018582423,0.000043384596,0.00012574963,0.000109097855,0.00003008997,0.00044539824,0.000090510795,0.0000209225],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023896925,0.0015536554,0.004754322,0.0009897939,0.00027107014,0.000006390358,0.0011178869,0.00130829,0.29787228,0.010454484,0.22019285,0.4590893],"study_design_scores_gemma":[0.0022443132,0.002193898,0.0021642616,0.000090928486,0.000027495824,0.00001766557,0.00067464693,0.003089821,0.167296,0.0006745776,0.8206998,0.000826578],"about_ca_topic_score_codex":0.0002922477,"about_ca_topic_score_gemma":0.00021383908,"teacher_disagreement_score":0.60050696,"about_ca_system_score_codex":0.000022423555,"about_ca_system_score_gemma":0.00015371284,"threshold_uncertainty_score":0.7577692},"labels":[],"label_agreement":null},{"id":"W2126333123","doi":"10.1093/bioinformatics/bts214","title":"Dissect: detection and characterization of novel structural alterations in transcribed sequences","year":2012,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; Simon Fraser University; University of British Columbia","funders":"SFU Community Trust Endowment Fund; Natural Sciences and Engineering Research Council of Canada; Canada's Michael Smith Genome Sciences Centre","keywords":"Transcriptome; Biology; Computational biology; Contig; Genome; Genetics; Reference genome; RNA-Seq; Gene; Gene expression","score_opus":0.014432972382788858,"score_gpt":0.23438011287422625,"score_spread":0.21994714049143738,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126333123","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9962733,0.00011414792,0.003290635,0.000012999672,0.00008646394,0.000090320995,0.00003310039,0.0000010226681,0.00009804521],"genre_scores_gemma":[0.9980863,0.000087256805,0.0017072615,0.000021082576,0.000042418666,0.0000051835063,0.000039134316,0.0000030236724,0.000008385223],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9996724,0.0000052280875,0.00016241758,0.000038348153,0.000033960958,0.00008763699],"domain_scores_gemma":[0.99984133,0.000003140948,0.000054667224,0.000057728535,0.000021144559,0.000022006237],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000054490676,0.000054596563,0.00006173877,0.000027015652,0.000031419473,0.0000069709913,0.000027780558,0.000039111845,0.0000010298149],"category_scores_gemma":[0.000008834616,0.000048256607,0.000014876973,0.000040351897,0.000030689942,0.000004141825,0.000014830185,0.000018438257,1.8155943e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008495198,0.000008885276,0.007624868,0.000021244461,0.00000784869,6.8963093e-9,0.0009968065,0.000011304072,0.98944306,0.000064943975,3.535113e-7,0.0018121696],"study_design_scores_gemma":[0.00044403353,0.00011206863,0.45139974,0.000010855632,0.000013004382,0.000012146654,0.00046102854,0.0049250303,0.5421222,0.000016491758,0.00034414977,0.00013923824],"about_ca_topic_score_codex":0.000009482281,"about_ca_topic_score_gemma":0.000031598414,"teacher_disagreement_score":0.44732088,"about_ca_system_score_codex":0.000003386992,"about_ca_system_score_gemma":0.000008117209,"threshold_uncertainty_score":0.19678473},"labels":[],"label_agreement":null},{"id":"W2126399647","doi":"10.1093/bioinformatics/btt539","title":"Pattern search in BioPAX models","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Institute of General Medical Sciences; National Human Genome Research Institute; National Institutes of Health","keywords":"Computer science; Java; Source code; Documentation; Software; License; Data mining; Programming language","score_opus":0.015280312212947483,"score_gpt":0.22755335150237607,"score_spread":0.2122730392894286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126399647","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8022751,0.0004033896,0.1558547,0.0004335067,0.00031333134,0.0009880669,0.00003603244,0.000041194606,0.039654657],"genre_scores_gemma":[0.99147683,0.00015302534,0.0067971824,0.0008879758,0.00010475058,0.00003146028,0.00012730632,0.000017259845,0.00040419068],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989272,0.000014579822,0.00043098265,0.000112306814,0.00013857157,0.0003763721],"domain_scores_gemma":[0.9993935,0.000007141232,0.000069342175,0.00036329852,0.00006210403,0.0001046108],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019197506,0.00015413116,0.00013698745,0.00008040737,0.00004461315,0.00007494874,0.00025430642,0.00017249731,0.000058866877],"category_scores_gemma":[0.0000079862675,0.00013626523,0.00006012203,0.00011047554,0.000052931748,0.000025872841,0.00017676139,0.00012854405,0.00031356802],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000065023334,0.00036017262,0.012721031,0.0006387513,0.00019017159,0.0000071221134,0.0051476867,0.0275028,0.014646272,0.002551362,0.08695773,0.8492119],"study_design_scores_gemma":[0.0011631808,0.00022778366,0.0030130916,0.000050748764,0.0000072609923,0.000028147522,0.001144695,0.980414,0.003602695,0.0016463036,0.008108723,0.0005934049],"about_ca_topic_score_codex":0.00009076085,"about_ca_topic_score_gemma":0.000033096025,"teacher_disagreement_score":0.95291114,"about_ca_system_score_codex":0.00001822159,"about_ca_system_score_gemma":0.000052128526,"threshold_uncertainty_score":0.5556735},"labels":[],"label_agreement":null},{"id":"W2126757300","doi":"10.1093/bioinformatics/bts662","title":"Visualization and Phospholipid Identification (VaLID): online integrated search engine capable of identifying and visualizing glycerophospholipids with given mass","year":2012,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Carleton University; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; Canadian Institutes of Health Research; University of Ottawa","keywords":"Lipidomics; Glycerophospholipids; Visualization; Identification (biology); Computer science; Glycerophospholipid; Computational biology; Degree of unsaturation; Phospholipid; Data visualization; Bioinformatics; Data science; Information retrieval; Chemistry; Data mining; Biology; Biochemistry; Chromatography","score_opus":0.020670412357506687,"score_gpt":0.2879347834479615,"score_spread":0.2672643710904548,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126757300","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95785356,0.0029678848,0.03868975,0.00001951756,0.000111082525,0.00019394544,0.000054311866,0.00001307362,0.000096889875],"genre_scores_gemma":[0.98028547,0.0034304298,0.015768893,0.000035460238,0.000076983844,0.0000070897295,0.0002617633,0.000019928533,0.000113998525],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99907315,0.000026016149,0.0003586874,0.00013353596,0.00016498036,0.00024362252],"domain_scores_gemma":[0.99938965,0.000013239615,0.00017946253,0.00018243157,0.00015008193,0.00008516024],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034873217,0.00015120568,0.00020948965,0.00010512991,0.00009421098,0.0000357069,0.00007545363,0.000086441396,0.0000058866494],"category_scores_gemma":[0.000063786494,0.00012924343,0.00002525033,0.00021792004,0.000106063606,0.00003816672,0.00009644957,0.00006530869,0.0000013059374],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002735522,0.00022098931,0.04116768,0.0010871043,0.0004303506,5.417722e-7,0.003804177,0.000055311357,0.9352788,0.0031472761,0.00049811363,0.014036132],"study_design_scores_gemma":[0.0014366906,0.0004493568,0.023766201,0.0001024111,0.0001490206,0.00003115191,0.005965254,0.010018666,0.94897693,0.000038922535,0.00860029,0.00046507284],"about_ca_topic_score_codex":0.00004028743,"about_ca_topic_score_gemma":0.000007935358,"teacher_disagreement_score":0.02292086,"about_ca_system_score_codex":0.000015309835,"about_ca_system_score_gemma":0.00002687447,"threshold_uncertainty_score":0.52703947},"labels":[],"label_agreement":null},{"id":"W2127143129","doi":"10.1093/bioinformatics/btl116","title":"PseudoPipe: an automated pseudogene identification pipeline","year":2006,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":212,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of Toronto","funders":"National Institutes of Health; National Human Genome Research Institute; University of Toronto","keywords":"Pseudogene; Genome; Biology; Genetics; Homology (biology); Computational biology; Gene; Retrotransposon; Intergenic region; Transposable element","score_opus":0.010396993762250138,"score_gpt":0.2506661242629637,"score_spread":0.24026913050071355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127143129","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98913443,0.00040699364,0.006575117,0.000074231066,0.00024656983,0.00020127394,0.000067475165,0.000057299218,0.0032365853],"genre_scores_gemma":[0.9881338,0.00010514388,0.010060667,0.00014692318,0.00034081217,0.000014889463,0.0004903535,0.000018204139,0.0006892327],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99909025,0.00001710586,0.00040774554,0.00015617353,0.00011690448,0.00021179054],"domain_scores_gemma":[0.9992893,0.000004095204,0.00014274263,0.00039512423,0.00011527384,0.00005349698],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015562208,0.0001477875,0.000113808615,0.000044098422,0.00011781755,0.000051330175,0.00018124962,0.00010474401,0.000006806094],"category_scores_gemma":[0.00001987937,0.00013999378,0.000055369914,0.00008674458,0.000053055137,0.0000029546143,0.00007061284,0.00003415492,0.00005002201],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029996803,0.00014819262,0.0035170077,0.000048958307,0.000041548727,0.0000010787162,0.00013136967,0.0016355198,0.9577105,0.0005492687,0.030499348,0.0056872033],"study_design_scores_gemma":[0.0018494459,0.0005118757,0.09652913,0.000017730981,0.000109931505,0.0000947186,0.0005124513,0.21108001,0.5692639,0.00073188735,0.11808777,0.0012111771],"about_ca_topic_score_codex":0.000028505823,"about_ca_topic_score_gemma":0.000033512708,"teacher_disagreement_score":0.38844663,"about_ca_system_score_codex":0.000010686094,"about_ca_system_score_gemma":0.000038060483,"threshold_uncertainty_score":0.570878},"labels":[],"label_agreement":null},{"id":"W2127166992","doi":"10.1093/bioinformatics/bth211","title":"A weighted least-squares approach for inferring phylogenies from incomplete distance matrices","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Distance matrices in phylogeny; Computer science; Least-squares function approximation; Mathematics; Algorithm; Statistics; Combinatorics","score_opus":0.01559600873354132,"score_gpt":0.2289389724992788,"score_spread":0.21334296376573747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127166992","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7317339,0.0028170245,0.26272762,0.00005665922,0.00015207344,0.00045771452,0.0004978028,0.000015665852,0.001541544],"genre_scores_gemma":[0.8275813,0.0002817642,0.17133524,0.0001496882,0.00022453541,0.00006554923,0.00030780613,0.00001919188,0.00003493754],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990777,0.000008300129,0.00033340463,0.00019342106,0.00010960362,0.0002775801],"domain_scores_gemma":[0.9993879,0.000017630742,0.00014960772,0.00029752371,0.00008274034,0.0000645589],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007922276,0.0002034767,0.00020152681,0.000040548985,0.00017384252,0.000054670938,0.00024055976,0.000104517036,0.0000018284815],"category_scores_gemma":[0.000032765376,0.00018057502,0.00011634905,0.000073965304,0.00008148666,0.0000031523946,0.0001443144,0.00004825125,0.0000057022844],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016644056,0.0011801289,0.045697916,0.0025207626,0.0035323694,0.0000061459964,0.015596773,0.028327914,0.8085484,0.01854445,0.006456564,0.06792415],"study_design_scores_gemma":[0.018352399,0.0032718969,0.046934124,0.00028242983,0.00067909854,0.000058701142,0.011651451,0.05587756,0.3878014,0.024509072,0.4450442,0.0055376748],"about_ca_topic_score_codex":0.000046183453,"about_ca_topic_score_gemma":0.000033850203,"teacher_disagreement_score":0.4385876,"about_ca_system_score_codex":0.000020705105,"about_ca_system_score_gemma":0.00005444354,"threshold_uncertainty_score":0.73636353},"labels":[],"label_agreement":null},{"id":"W2127303081","doi":"10.1093/bioinformatics/bts149","title":"Large-scale analysis of conserved rare codon clusters suggests an involvement in co-translational molecular recognition events","year":2012,"lang":"en","type":"article","venue":"Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"National Human Genome Research Institute; Fonds de Recherche du Québec - Santé; Québec Consortium for Drug Discovery","keywords":"Codon usage bias; Computational biology; Biology; Genetics; Start codon; Conserved sequence; Function (biology); Genome; Gene; Peptide sequence; Messenger RNA","score_opus":0.022005665556037578,"score_gpt":0.26770326568454134,"score_spread":0.24569760012850375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127303081","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9765336,0.00013787155,0.022438057,0.000026534772,0.00005550274,0.0002588413,0.00023491378,0.000006642289,0.0003080508],"genre_scores_gemma":[0.98598105,0.000054067666,0.010915514,0.00022820791,0.000022072476,0.000022387418,0.0027501713,0.0000102719305,0.000016258902],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989532,0.00008947064,0.00041917674,0.000102482925,0.00020312422,0.00023255021],"domain_scores_gemma":[0.99942285,0.00001285181,0.00017261464,0.00023475049,0.00006566637,0.00009124034],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005187608,0.00012298807,0.0001932896,0.00016701603,0.000032966902,0.000008399528,0.000115645315,0.00014719594,0.000061900384],"category_scores_gemma":[0.00002478128,0.0001231048,0.000116511794,0.00020858676,0.000022671771,0.000025573081,0.000027408078,0.000041678144,0.000008282919],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00051851594,0.00129949,0.21895899,0.0004403418,0.0014159436,0.000002131876,0.0072631426,0.0013030764,0.7555046,0.0002240067,0.00027049577,0.012799259],"study_design_scores_gemma":[0.0016822949,0.00032142727,0.03479971,0.00007312334,0.00043468128,0.0000034241634,0.0024516804,0.01242153,0.9453914,0.0001664589,0.0017540489,0.00050018396],"about_ca_topic_score_codex":0.000012062289,"about_ca_topic_score_gemma":0.00011568887,"teacher_disagreement_score":0.18988682,"about_ca_system_score_codex":0.000012781621,"about_ca_system_score_gemma":0.00003482194,"threshold_uncertainty_score":0.50200677},"labels":[],"label_agreement":null},{"id":"W2127313795","doi":"10.1093/bioinformatics/bth224","title":"PedSplit: pedigree management for stratified analysis","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Addiction and Mental Health","funders":"","keywords":"Executable; Documentation; Haplotype; Source code; Software; Computer science; Computational biology; Biology; Gene; Genetics; Programming language; Genotype","score_opus":0.016458840089778656,"score_gpt":0.2733222928392096,"score_spread":0.25686345274943095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127313795","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2925559,0.000108109794,0.6959109,0.0004337853,0.00015250004,0.00050222524,0.00009105865,0.000023406368,0.010222142],"genre_scores_gemma":[0.79897094,0.00012073226,0.1985018,0.00048304998,0.00011944072,0.000066847955,0.00065462675,0.000009929275,0.0010726422],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.99922967,0.000009350403,0.0003245492,0.00013019545,0.00007725967,0.00022894816],"domain_scores_gemma":[0.99944854,0.000010521379,0.00012811043,0.00029132157,0.00006448259,0.00005699884],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023363273,0.00010737582,0.00015543796,0.00007759081,0.0000927795,0.000019205525,0.00014049739,0.00011240076,0.000008900007],"category_scores_gemma":[0.000047851598,0.00009851161,0.00017345903,0.0001607923,0.000028562894,0.0000030869512,0.00005148445,0.000028930037,0.00001743305],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008066319,0.0020404535,0.16475533,0.0022600559,0.032548815,0.000014572831,0.00582188,0.31280723,0.0137252,0.16298485,0.12784778,0.17438723],"study_design_scores_gemma":[0.016342098,0.003470862,0.5446532,0.000059928985,0.007406477,0.000036244848,0.009320183,0.050572563,0.011794253,0.02690537,0.32576197,0.0036768706],"about_ca_topic_score_codex":0.0000069146954,"about_ca_topic_score_gemma":0.00005028359,"teacher_disagreement_score":0.506415,"about_ca_system_score_codex":0.000019578,"about_ca_system_score_gemma":0.000035089128,"threshold_uncertainty_score":0.40171868},"labels":[],"label_agreement":null},{"id":"W2127341158","doi":"10.1093/bioinformatics/bti700","title":"An attempt to define allergen-specific molecular surface features: a bioinformatic approach","year":2005,"lang":"en","type":"article","venue":"Bioinformatics","topic":"thermodynamics and calorimetric analyses","field":"Chemistry","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Infection and Immunity","funders":"Asthma and Lung UK","keywords":"Allergen; Computer science; Computational biology; Surface protein; Biology; Immunology; Allergy; Virology","score_opus":0.012981375310756502,"score_gpt":0.23812484423314886,"score_spread":0.22514346892239237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127341158","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69507587,0.0013901097,0.16198155,0.00032547666,0.00013126413,0.00038389795,0.00019041776,0.0005434399,0.13997795],"genre_scores_gemma":[0.781872,0.00018923442,0.21556316,0.00076173444,0.00016429122,0.000017554567,0.00044026127,0.000062429084,0.0009293709],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99793065,0.000011826496,0.0007405054,0.00022501245,0.0005462132,0.0005457726],"domain_scores_gemma":[0.9982741,0.00003514451,0.00021333894,0.0009671022,0.000108528315,0.00040177695],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00022622196,0.0003697584,0.00037774956,0.00018200214,0.00014755184,0.00019654099,0.00068813685,0.00021354771,0.00038631086],"category_scores_gemma":[0.000029126222,0.00032492782,0.00018154179,0.00062794285,0.000048328195,0.00045062293,0.00011832143,0.00025318764,0.0006038493],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00051247847,0.0032229994,0.0010246456,0.002994121,0.0017483195,0.0000453431,0.0300605,0.26211965,0.14085487,0.041574895,0.10154594,0.41429624],"study_design_scores_gemma":[0.002027679,0.00020857154,0.00043649288,0.0001196676,0.00015393525,0.00012978005,0.0072627384,0.76556647,0.024179848,0.00014789686,0.19754279,0.0022241601],"about_ca_topic_score_codex":0.000017673457,"about_ca_topic_score_gemma":0.0000055629193,"teacher_disagreement_score":0.50344676,"about_ca_system_score_codex":0.00015423202,"about_ca_system_score_gemma":0.000054243916,"threshold_uncertainty_score":0.99992025},"labels":[],"label_agreement":null},{"id":"W2128495797","doi":"10.1093/bioinformatics/btm068","title":"AMPer: a database and an automated discovery tool for antimicrobial peptides","year":2007,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Antimicrobial Peptides and Activities","field":"Immunology and Microbiology","cited_by":233,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Antimicrobial peptides; Hidden Markov model; Construct (python library); Computer science; Computational biology; Biological database; Database; Biology; Artificial intelligence; Bioinformatics; Peptide; Biochemistry","score_opus":0.014180595345511336,"score_gpt":0.2691789252803353,"score_spread":0.25499832993482396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128495797","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97381425,0.00010025182,0.023572445,0.00006145955,0.00044613163,0.0004579406,0.0007716401,0.00034594885,0.00042994533],"genre_scores_gemma":[0.9732068,0.000070766655,0.02379223,0.0006451214,0.00008801903,0.0000064529368,0.0011289435,0.000023945282,0.0010377251],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989491,0.000017428374,0.00040886726,0.00015842654,0.00002561921,0.00044057122],"domain_scores_gemma":[0.99939114,0.00014236502,0.00014663766,0.00023938609,0.00005133538,0.000029153867],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003828576,0.00020094612,0.000251061,0.000108155175,0.00034197458,0.00011169748,0.00014323325,0.00017249555,0.00001647321],"category_scores_gemma":[0.0000614757,0.00017123847,0.000070326765,0.00006910542,0.00030881417,0.0011952944,0.000099987046,0.00012422053,0.000051226412],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005779547,0.00024044306,0.001681968,0.00044173162,0.00017249591,0.0000047058006,0.002011348,0.000008658489,0.92137736,0.0041772504,0.058149334,0.011156757],"study_design_scores_gemma":[0.0073440364,0.0012346294,0.007274729,0.00040149927,0.00028487376,0.0006664411,0.0064129415,0.003627901,0.88709223,0.00017591879,0.08349174,0.0019930694],"about_ca_topic_score_codex":0.0000504918,"about_ca_topic_score_gemma":0.00004343923,"teacher_disagreement_score":0.034285136,"about_ca_system_score_codex":0.000020904801,"about_ca_system_score_gemma":0.00003893613,"threshold_uncertainty_score":0.6982902},"labels":[],"label_agreement":null},{"id":"W2128591967","doi":"10.1093/bioinformatics/18.3.440","title":"PatternHunter: faster and more sensitive homology search","year":2002,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":863,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bioinformatics Solutions (Canada)","funders":"","keywords":"Computer science; Java; Homology (biology); Genomics; MIT License; Computational biology; Computation; License; Biology; Bioinformatics; Data mining; Algorithm; Genome; Genetics; Operating system; Gene","score_opus":0.015699973549434185,"score_gpt":0.23243666661569154,"score_spread":0.21673669306625737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128591967","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98848367,0.00026441837,0.0051837377,0.00044462783,0.00009455485,0.00021106936,0.000036866815,0.000016053684,0.0052650124],"genre_scores_gemma":[0.99048287,0.0003417295,0.0061800475,0.0009150857,0.0001250664,0.0000069784887,0.00007551162,0.000017311162,0.0018554161],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999371,0.000018692752,0.00016192853,0.00012060222,0.000101253856,0.00022653774],"domain_scores_gemma":[0.9996264,0.000005954258,0.000036962283,0.00021008245,0.00004951935,0.0000710594],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000076897035,0.000115939205,0.000100428704,0.000047610767,0.000048613667,0.000028532893,0.00008244366,0.00009835843,0.000049069113],"category_scores_gemma":[0.000010571296,0.00010455193,0.000033862387,0.00004153347,0.00009690647,0.000006085493,0.00015048162,0.00006578237,0.000117093405],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017184723,0.00059568457,0.06667341,0.0011626919,0.0012517155,0.00016431883,0.035497352,0.00020059163,0.2175867,0.0002517019,0.06521757,0.61122644],"study_design_scores_gemma":[0.0125396615,0.005318941,0.13003814,0.00020893323,0.00031044902,0.0030727433,0.023731776,0.2770445,0.29549056,0.000081926715,0.24754833,0.004614041],"about_ca_topic_score_codex":0.000004509628,"about_ca_topic_score_gemma":0.0000025701747,"teacher_disagreement_score":0.6066124,"about_ca_system_score_codex":0.0000075764324,"about_ca_system_score_gemma":0.000005767653,"threshold_uncertainty_score":0.42635038},"labels":[],"label_agreement":null},{"id":"W2129058089","doi":"10.1093/bioinformatics/btr533","title":"Unsupervised detection of genes of influence in lung cancer using biological networks","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research","funders":"Canadian Institutes of Health Research","keywords":"Gene; Computational biology; Biology; Cancer; Gene expression; Lung cancer; Genome; Set (abstract data type); Genetics; Computer science; Medicine; Pathology","score_opus":0.024400771024373887,"score_gpt":0.24892734094882135,"score_spread":0.22452656992444747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129058089","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9610996,0.0012234399,0.037091695,0.0000012390402,0.00010189824,0.00017853062,0.000013114684,0.000004580119,0.0002858609],"genre_scores_gemma":[0.9912154,0.0008827655,0.007787682,0.000045890494,0.000036323385,0.0000069812136,0.000013872789,0.00000740012,0.0000036639974],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990286,0.000018677438,0.00059992576,0.00008254576,0.000072996154,0.00019726147],"domain_scores_gemma":[0.9993503,0.0000078429075,0.00028225605,0.00021809478,0.00009947896,0.00004200892],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019327673,0.00012349169,0.00019665196,0.000068099995,0.000024645535,0.00000479548,0.00017329681,0.0002226151,0.000009939453],"category_scores_gemma":[0.000019529141,0.0001055451,0.00006744409,0.00016040771,0.000106157124,0.00001330235,0.00010257227,0.000076383316,3.9566285e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00060774875,0.00025459452,0.2751931,0.0009622289,0.00028176585,0.000001834598,0.0033008435,0.08429918,0.5585537,0.00032680508,0.00006477081,0.076153465],"study_design_scores_gemma":[0.000900804,0.00031324197,0.033474565,0.00014487,0.000039256152,0.000010087333,0.0004568473,0.78061503,0.18340854,0.00006922642,0.00020824089,0.00035925707],"about_ca_topic_score_codex":0.00014076055,"about_ca_topic_score_gemma":0.000057361136,"teacher_disagreement_score":0.6963159,"about_ca_system_score_codex":0.000014918928,"about_ca_system_score_gemma":0.000052249754,"threshold_uncertainty_score":0.4304004},"labels":[],"label_agreement":null},{"id":"W2129179457","doi":"10.1093/bioinformatics/btt716","title":"Sequence-based Gaussian network model for protein dynamics","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Science Foundation of Zhejiang Province; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Sequence (biology); Protein structure prediction; Computer science; Gaussian; Protein function; Gaussian network model; Protein structure; Biological system; Algorithm; Statistical physics; Computational biology; Physics; Biology; Chemistry; Computational chemistry; Genetics","score_opus":0.011948010797763172,"score_gpt":0.23307142691906593,"score_spread":0.22112341612130276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129179457","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040977288,0.000049753635,0.95492053,0.00027600327,0.000101908125,0.0014638688,0.00011926446,0.00003989879,0.0020514785],"genre_scores_gemma":[0.59652835,0.0000068117483,0.40001664,0.00095642026,0.00020182274,0.00035228566,0.00091418886,0.000030431202,0.0009930357],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990315,0.0000096158865,0.00031298102,0.00014892509,0.00011661826,0.0003803504],"domain_scores_gemma":[0.9992325,0.0000053563103,0.00014103111,0.00039471118,0.000120889,0.000105551844],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000109827895,0.00018879074,0.0001438145,0.000028085366,0.00011934163,0.00006557895,0.00024249384,0.00022274577,0.000008261973],"category_scores_gemma":[0.000046744568,0.00016333612,0.00010521056,0.00007364176,0.000067864756,0.000013697658,0.000061024653,0.000076187454,0.000018078628],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00060566765,0.00027231078,0.002386388,0.0023219686,0.00046531635,0.0000034191269,0.00054976,0.5392172,0.12822254,0.07604415,0.073612966,0.17629834],"study_design_scores_gemma":[0.00040566988,0.00013821026,0.000023393763,0.00002049652,0.000010364747,0.0000028938946,0.000024087944,0.990146,0.0027557588,0.0044720443,0.0017598458,0.000241282],"about_ca_topic_score_codex":0.00000890408,"about_ca_topic_score_gemma":0.000036177425,"teacher_disagreement_score":0.55555105,"about_ca_system_score_codex":0.00003424611,"about_ca_system_score_gemma":0.00017068935,"threshold_uncertainty_score":0.6660654},"labels":[],"label_agreement":null},{"id":"W2129397798","doi":"10.1093/bioinformatics/btv279","title":"Data Safe Havens in health research and healthcare","year":2015,"lang":"en","type":"review","venue":"Bioinformatics","topic":"Electronic Health Records Systems","field":"Health Professions","cited_by":75,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of Ottawa; University of Toronto","funders":"Economic and Social Research Council; Medical Research Council; Canadian Institutes of Health Research; National Cancer Institute; Cancer Research UK; Wellcome Trust","keywords":"Context (archaeology); Health care; Interpretation (philosophy); Health informatics; Corporate governance; Data governance; Computer science; Biomedicine; Public relations; Data science; Work (physics); Trustworthiness; Knowledge management; Internet privacy; Political science; Business; Data quality; Law; Engineering; Service (business)","score_opus":0.7803968123818096,"score_gpt":0.6547543979116747,"score_spread":0.1256424144701349,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129397798","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[7.1186065e-7,0.9823826,0.00003049764,0.0021105793,0.0009998541,0.0078101913,0.0015362295,0.00008802949,0.0050412845],"genre_scores_gemma":[5.3237534e-7,0.99127287,0.0022895015,0.00058155466,0.00059904053,0.00043867537,0.0021779104,0.00010244745,0.0025374966],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9848327,0.005237528,0.0053352127,0.00060685904,0.0011602172,0.0028274981],"domain_scores_gemma":[0.99133617,0.0024290292,0.0018342333,0.0027703599,0.00049176393,0.001138447],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.034022063,0.0005174064,0.0033503,0.0010833695,0.00088132574,0.000038856677,0.001453502,0.0012226761,0.000037669404],"category_scores_gemma":[0.0014173664,0.00041505246,0.00006308269,0.0013605455,0.00015086676,0.00035787871,0.001702316,0.006068695,0.0015370214],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000004000884,0.000021288077,0.000039001836,0.2639764,0.000013897187,0.000003035411,0.0018235309,1.8613163e-8,1.5250624e-10,0.00092966296,0.09725432,0.6359348],"study_design_scores_gemma":[0.00035694378,0.00027480698,0.000004124059,0.065316126,0.000012030461,0.000028651139,0.0023999112,0.00037365136,2.8513633e-10,0.00016506386,0.93081,0.00025873035],"about_ca_topic_score_codex":0.0038155203,"about_ca_topic_score_gemma":0.010225056,"teacher_disagreement_score":0.83355564,"about_ca_system_score_codex":0.00440413,"about_ca_system_score_gemma":0.035087593,"threshold_uncertainty_score":0.9998301},"labels":[],"label_agreement":null},{"id":"W2129668934","doi":"10.1093/bioinformatics/btt274","title":"A combinatorial approach to the peptide feature matching problem for label-free quantification","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":70,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bipartite graph; Matching (statistics); Computer science; Feature (linguistics); Set (abstract data type); Function (biology); Software; Graph; Feature matching; Data mining; Pattern recognition (psychology); Algorithm; Artificial intelligence; Theoretical computer science; Feature extraction; Mathematics; Statistics","score_opus":0.019295810854236137,"score_gpt":0.26114302299562014,"score_spread":0.241847212141384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129668934","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0061546834,0.000019883792,0.9457263,0.0036831058,0.00006999106,0.002424648,0.00014975553,0.00031051342,0.041461132],"genre_scores_gemma":[0.02381947,0.00000824032,0.9712358,0.00028871844,0.00017046722,0.0030811005,0.00018989212,0.000025949052,0.0011803373],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992573,0.0000033271,0.00027099988,0.000119831806,0.0001374625,0.00021107981],"domain_scores_gemma":[0.99892026,0.000053256346,0.00016317867,0.0006752726,0.0001242922,0.00006371004],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013631237,0.00013025715,0.00011366266,0.000023424536,0.00025770362,0.00013825927,0.00055128505,0.00010968158,0.0000110722885],"category_scores_gemma":[0.00005045469,0.0000932367,0.00004833007,0.0001190689,0.000023991355,0.00019189387,0.00011730921,0.00016459641,0.000057359404],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032983186,0.0002565872,0.000030147432,0.0009419435,0.00004568462,3.4162984e-8,0.0033793023,0.00044004654,0.025396409,0.7038449,0.24638171,0.019250207],"study_design_scores_gemma":[0.0016920179,0.00007647418,0.00003108496,0.0001308875,0.00005999515,0.000015261758,0.002812174,0.10927071,0.057452686,0.3504748,0.47716668,0.00081721495],"about_ca_topic_score_codex":0.00001843786,"about_ca_topic_score_gemma":0.0000014642277,"teacher_disagreement_score":0.35337013,"about_ca_system_score_codex":0.000047743193,"about_ca_system_score_gemma":0.000024407256,"threshold_uncertainty_score":0.38020822},"labels":[],"label_agreement":null},{"id":"W2129907963","doi":"10.1093/bioinformatics/16.8.735","title":"<i>In silico</i> identification of transcripts and SNPs from a region of 4p linked with bipolar affective disorder","year":2000,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bipolar Disorder and Treatment","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre","funders":"Medical Research Council","keywords":"In silico; Identification (biology); Single-nucleotide polymorphism; Computational biology; Bipolar disorder; Genetics; Biology; Computer science; Gene; Neuroscience; Genotype","score_opus":0.008845474385124234,"score_gpt":0.22586827585500927,"score_spread":0.21702280146988503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129907963","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99497706,0.0028952395,0.0009389461,0.00016683617,0.000015358723,0.00047133124,0.000040875475,0.000012489473,0.0004818508],"genre_scores_gemma":[0.9977258,0.0008511266,0.0012285567,0.000036414538,0.000006707243,0.000010825804,0.000049672588,0.000008409396,0.0000825274],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9993299,0.000015166608,0.000341958,0.00008005947,0.00014104602,0.00009185285],"domain_scores_gemma":[0.99959666,0.000028643444,0.000106105435,0.00019007928,0.000038477443,0.00004005678],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005555287,0.00009942966,0.00023427773,0.000080112506,0.000017645227,0.0000049490905,0.00003275989,0.00006701708,0.00002077604],"category_scores_gemma":[0.0000070759233,0.00007352915,0.00003760237,0.00016502786,0.00008195469,0.00015644077,0.000004317284,0.000064280415,0.000004586983],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018848672,0.0021431108,0.57345337,0.001627088,0.0005298162,0.0000096484255,0.041433256,0.00004635899,0.00836789,0.00034766094,0.00012291789,0.37003404],"study_design_scores_gemma":[0.0073464555,0.0010721175,0.9701179,0.00037571465,0.0004057092,0.000042424686,0.0015482703,0.0038719268,0.01052411,0.00019031818,0.0043091406,0.00019585837],"about_ca_topic_score_codex":0.00039743097,"about_ca_topic_score_gemma":0.00023592138,"teacher_disagreement_score":0.39666462,"about_ca_system_score_codex":0.000016089309,"about_ca_system_score_gemma":0.000029766688,"threshold_uncertainty_score":0.29984316},"labels":[],"label_agreement":null},{"id":"W2129908184","doi":"10.1093/bioinformatics/btq456","title":"A Bayesian method for 3D macromolecular structure inference using class average images from single particle electron microscopy","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Advanced Electron Microscopy Techniques and Applications","field":"Biochemistry, Genetics and Molecular Biology","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"National Center for Research Resources; Canadian Institutes of Health Research; National Institutes of Health","keywords":"Inference; Computer science; Software; Cryo-electron microscopy; Data mining; Algorithm; Artificial intelligence; Pattern recognition (psychology); Physics; Nuclear magnetic resonance","score_opus":0.007808718169959317,"score_gpt":0.33609011869290295,"score_spread":0.32828140052294363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129908184","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26876068,0.00006697382,0.73040074,0.000042471715,0.000045002933,0.00033045775,0.000268245,0.00003420532,0.000051192146],"genre_scores_gemma":[0.3297489,0.000016806258,0.6694796,0.00027582227,0.00008337906,0.000026489475,0.00030609363,0.000024851597,0.000038030936],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989488,0.00001612191,0.00030587811,0.00024411982,0.000083955754,0.00040111443],"domain_scores_gemma":[0.9991479,0.000024447334,0.00016823673,0.0004698838,0.00010043554,0.00008911439],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008501235,0.00021019393,0.00016744406,0.000026010139,0.00017030083,0.00008123974,0.00024068904,0.00021612241,0.00002004329],"category_scores_gemma":[0.00006085242,0.000206512,0.00008149823,0.000099525234,0.000068023925,0.000018603798,0.00008160985,0.00018927468,0.0000022078864],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027801516,0.000031828953,0.000055260873,0.000016839193,0.000020351303,2.150188e-7,0.000041126863,0.00014335883,0.995333,0.00016155584,0.00022446008,0.003944198],"study_design_scores_gemma":[0.00028180942,0.00016529407,0.000010312981,0.000007171752,0.000026314397,0.000009994724,0.000015394675,0.05353,0.9212067,0.0010406036,0.023464762,0.00024165332],"about_ca_topic_score_codex":0.000022766792,"about_ca_topic_score_gemma":0.00004583533,"teacher_disagreement_score":0.07412631,"about_ca_system_score_codex":0.000024907229,"about_ca_system_score_gemma":0.00008644897,"threshold_uncertainty_score":0.84213156},"labels":[],"label_agreement":null},{"id":"W2130062792","doi":"10.1093/bioinformatics/btu687","title":"E-MEM: efficient computation of maximal exact matches for very large genomes","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Compressed suffix array; Computer science; Computation; Genome; Suffix; Suffix array; Source code; Code (set theory); Algorithm; Parallel computing; Theoretical computer science; Data structure; Suffix tree; Set (abstract data type); Programming language; Biology","score_opus":0.010695451651004901,"score_gpt":0.23836099971157,"score_spread":0.22766554806056508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130062792","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.571646,0.00026540877,0.42615533,0.00003209816,0.00017358879,0.0003928044,0.00007299923,0.000015982478,0.0012458161],"genre_scores_gemma":[0.9492652,0.000041453088,0.050048433,0.00007688302,0.00011220627,0.000016962887,0.00032060774,0.000016336438,0.00010195228],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999266,0.000012413275,0.0002925768,0.000096867814,0.00012406384,0.00020802887],"domain_scores_gemma":[0.9995113,0.0000148782265,0.00015657464,0.00018030821,0.00009342678,0.00004348979],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002867302,0.000111766225,0.00014101918,0.00005185331,0.000048882164,0.000016571352,0.000120426266,0.0000809865,0.000005084784],"category_scores_gemma":[0.00003898563,0.00010372753,0.000087416076,0.00005223588,0.000032782576,0.0000037356542,0.00006908927,0.00002598557,0.000015923306],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001017486,0.0021640726,0.01510547,0.010702926,0.0014819382,0.00000179991,0.008419343,0.05280419,0.550809,0.005400803,0.026039345,0.3260536],"study_design_scores_gemma":[0.005407262,0.0019740204,0.00744104,0.000093566756,0.00014571084,0.000014912647,0.0016529432,0.67229646,0.18482032,0.0003656027,0.12485601,0.0009321305],"about_ca_topic_score_codex":0.0000011304202,"about_ca_topic_score_gemma":0.0000011748508,"teacher_disagreement_score":0.6194923,"about_ca_system_score_codex":0.000011157606,"about_ca_system_score_gemma":0.000028062612,"threshold_uncertainty_score":0.4229886},"labels":[],"label_agreement":null},{"id":"W2130311175","doi":"10.1093/bioinformatics/btu671","title":"Novel function discovery with GeneMANIA: a new integrated resource for gene function prediction in <i>Escherichia coli</i>","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina; University of Toronto","funders":"National Institute of General Medical Sciences; Canadian Institutes of Health Research","keywords":"Function (biology); Computational biology; Biology; Computer science; Escherichia coli; Biogenesis; Resource (disambiguation); Protein function; Gene; Genetics","score_opus":0.007439553823589437,"score_gpt":0.18784870305743182,"score_spread":0.18040914923384238,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130311175","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09124698,0.00007661189,0.90621173,0.00006050676,0.00025104513,0.0005417218,0.00008038659,0.000030837007,0.0015001964],"genre_scores_gemma":[0.7917241,0.00011287928,0.18655902,0.0052847383,0.0022474097,0.00025808532,0.0075226617,0.00015590645,0.0061352276],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99882615,0.00001545643,0.00050342793,0.00019418614,0.00014499779,0.00031578686],"domain_scores_gemma":[0.9992358,0.000017750232,0.00022682929,0.0003389488,0.00007776775,0.00010289584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003238682,0.00023455238,0.00020019975,0.00007884855,0.000099722274,0.00009829278,0.00013982748,0.00025548687,0.0000042133247],"category_scores_gemma":[0.00003351924,0.0001938291,0.00007609457,0.00019518007,0.00004412199,0.000043736356,0.000053463766,0.00013870238,0.000008657546],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.012308817,0.0007540523,0.0032622577,0.0010684144,0.0009673773,8.849967e-7,0.0018580672,0.067683496,0.5431287,0.005238521,0.21826296,0.14546642],"study_design_scores_gemma":[0.0072685042,0.00403529,0.0036113039,0.00013420773,0.00020004807,0.00003053008,0.0008388228,0.3231097,0.012766151,0.000362781,0.6468239,0.00081877556],"about_ca_topic_score_codex":0.000025466601,"about_ca_topic_score_gemma":0.00013472093,"teacher_disagreement_score":0.7196527,"about_ca_system_score_codex":0.000041153075,"about_ca_system_score_gemma":0.00014060721,"threshold_uncertainty_score":0.7904121},"labels":[],"label_agreement":null},{"id":"W2130324133","doi":"10.1093/bioinformatics/btt562","title":"INVEX—a web-based tool for integrative visualization of expression data","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":89,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institutes of Health; Canadian Institutes of Health Research; Killam Trusts","keywords":"Metadata; Visualization; Annotation; Context (archaeology); Computer science; Variety (cybernetics); Key (lock); Data visualization; Web application; Information retrieval; World Wide Web; Data mining; Biology; Artificial intelligence","score_opus":0.02978220196318498,"score_gpt":0.3035044129120842,"score_spread":0.2737222109488992,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130324133","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14837153,0.00016568493,0.8472932,0.00019318235,0.00026925598,0.0012541775,0.00022943485,0.000033737506,0.0021897806],"genre_scores_gemma":[0.9518408,0.000051202325,0.04429166,0.00039517693,0.000078962454,0.00013233114,0.0028838299,0.000015492446,0.0003105541],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993372,0.000020341193,0.00030245795,0.00012799836,0.000111835056,0.00010017566],"domain_scores_gemma":[0.99898636,0.0000148671415,0.00020986414,0.00054651685,0.00020656336,0.000035799458],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012673784,0.00009460346,0.00009560072,0.000050564322,0.000041771124,0.000022798129,0.00027304242,0.00010255217,0.00003638041],"category_scores_gemma":[0.00017137233,0.000072278555,0.000036426885,0.00008011375,0.000039024046,0.000022443115,0.00009072901,0.000024308425,0.00000963956],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037069003,0.000046210786,0.00057435344,0.00010667792,0.000010467398,7.462284e-9,0.000092624796,0.000041830557,0.8789755,0.00018892268,0.11206588,0.007860436],"study_design_scores_gemma":[0.0007824724,0.00015584893,0.0004568612,0.00005927535,0.000010755666,2.9153512e-7,0.0002567268,0.09471695,0.84456706,0.00007287024,0.058781184,0.000139684],"about_ca_topic_score_codex":0.0000022397278,"about_ca_topic_score_gemma":0.0000014109522,"teacher_disagreement_score":0.80346924,"about_ca_system_score_codex":0.0000074461955,"about_ca_system_score_gemma":0.0001207103,"threshold_uncertainty_score":0.2947434},"labels":[],"label_agreement":null},{"id":"W2130549711","doi":"10.1093/bioinformatics/btr337","title":"Annotation concept synthesis and enrichment analysis: a logic-based approach to the interpretation of high-throughput experiments","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Interpretation (philosophy); Annotation; Throughput; Computer science; Programming language; Artificial intelligence","score_opus":0.029208102939729797,"score_gpt":0.26855426814801336,"score_spread":0.23934616520828356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130549711","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16953667,0.0003270509,0.8282483,0.000088122724,0.00006376992,0.00022965165,0.000030072042,0.000014850248,0.0014615086],"genre_scores_gemma":[0.9067502,0.00001316717,0.09281859,0.0002969745,0.000012328191,0.000038873146,0.00005272229,0.0000029978987,0.000014115792],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994119,0.000034858687,0.00023960858,0.00010442335,0.00010899024,0.000100253084],"domain_scores_gemma":[0.9995625,0.000022362432,0.0001227998,0.0002040753,0.00004881174,0.000039457045],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015076454,0.00008575934,0.00013543948,0.00005567857,0.000038956558,0.000010770274,0.00012719407,0.00007796014,0.000005308812],"category_scores_gemma":[0.00012116881,0.000055202254,0.000049281047,0.00015426392,0.00010946235,0.000003928813,0.00005429946,0.000027155675,0.0000020523976],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017931781,0.002025048,0.010276518,0.00072929676,0.005448422,0.000002409202,0.12646034,0.012252893,0.019683702,0.0056044636,0.013067384,0.80265635],"study_design_scores_gemma":[0.0020709292,0.002910198,0.04440457,0.0001246712,0.0015476835,0.000009045292,0.031675987,0.29733384,0.6118309,0.0003043469,0.0066992315,0.0010885925],"about_ca_topic_score_codex":0.000029419476,"about_ca_topic_score_gemma":0.0000030547235,"teacher_disagreement_score":0.80156773,"about_ca_system_score_codex":0.000006635244,"about_ca_system_score_gemma":0.000019143277,"threshold_uncertainty_score":0.22510825},"labels":[],"label_agreement":null},{"id":"W2130614771","doi":"10.1093/bioinformatics/btt265","title":"DAPPLE: a pipeline for the homology-based prediction of phosphorylation sites","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Phosphorylation; Pipeline (software); Computer science; Computational biology; Homology (biology); Model organism; Organism; Software; Sequence homology; Biology; World Wide Web; Bioinformatics; Programming language; Cell biology; Biochemistry; Genetics; Peptide sequence; Gene","score_opus":0.011620847573372952,"score_gpt":0.23903340122398387,"score_spread":0.22741255365061092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130614771","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11846112,0.0003175187,0.8759515,0.0006624527,0.00029621457,0.0018150671,0.00024669225,0.000056790126,0.002192622],"genre_scores_gemma":[0.89807355,0.000053198786,0.098822944,0.00073340134,0.00017914087,0.0001957065,0.001414569,0.000023885743,0.00050357624],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991331,0.00001473669,0.00046763875,0.00007634201,0.0001344176,0.00017374152],"domain_scores_gemma":[0.99898714,0.00008748436,0.00029584783,0.00037105833,0.0002210991,0.000037399703],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027969113,0.00012737131,0.000119758195,0.000043490225,0.00010649514,0.000027181906,0.00021031835,0.00013998969,0.000046959525],"category_scores_gemma":[0.00032733026,0.00008915481,0.000090783615,0.0000919463,0.000104712875,0.000013422577,0.00005251233,0.00007750009,0.00002356796],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000538529,0.0004958388,0.046162102,0.0022425347,0.00053774193,2.3983245e-7,0.002841758,0.05156481,0.15093404,0.0028327857,0.54226565,0.19958395],"study_design_scores_gemma":[0.0007135457,0.0002740587,0.0035273524,0.000013188175,0.000037513917,0.0000042125034,0.00021584854,0.9334764,0.02559215,0.00006406936,0.03596637,0.00011530241],"about_ca_topic_score_codex":0.000013032259,"about_ca_topic_score_gemma":0.0000041867256,"teacher_disagreement_score":0.8819116,"about_ca_system_score_codex":0.000009431477,"about_ca_system_score_gemma":0.000060803406,"threshold_uncertainty_score":0.3635628},"labels":[],"label_agreement":null},{"id":"W2130706354","doi":"10.1093/bioinformatics/bth092","title":"TANDEM: matching proteins with tandem mass spectra","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":2606,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Canadian Institutes of Health Research; University of Chicago","keywords":"Tandem; Matching (statistics); Tandem repeat; Tandem mass spectrometry; Computer science; Computational biology; Chemistry; Biology; Genetics; Mass spectrometry; Chromatography; Mathematics; Genome; Statistics; Materials science","score_opus":0.01073187936705139,"score_gpt":0.2430020231674446,"score_spread":0.2322701438003932,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130706354","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04117195,0.00001851368,0.9030672,0.00026425542,0.00000871055,0.00031819675,0.00001761064,0.00041368633,0.05471988],"genre_scores_gemma":[0.20126976,0.00003572869,0.7980249,0.00010493494,0.000060548013,0.00012557243,0.000027391605,0.000024240564,0.00032692408],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991833,0.0000011921636,0.0002802607,0.0001103555,0.00017966873,0.00024523152],"domain_scores_gemma":[0.99935037,0.000010050002,0.00016460878,0.00035701852,0.000037108806,0.00008084349],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000056710847,0.00015900235,0.000138786,0.000029187368,0.00015731037,0.000057891742,0.00020560644,0.0000939029,0.00008316615],"category_scores_gemma":[0.0000066971415,0.0001285405,0.000040588628,0.00011919249,0.00005266445,0.0002144014,0.00003402944,0.00021886977,0.000050272276],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012974865,0.00069815083,0.003965604,0.0018313112,0.00032132553,0.00006755292,0.007887445,0.012988905,0.44106695,0.50614864,0.00082827575,0.0240661],"study_design_scores_gemma":[0.0017049923,0.000115287214,0.00005613579,0.00039184798,0.00004413615,0.00012377741,0.0012195965,0.0017980867,0.83830535,0.13858072,0.016823936,0.0008360979],"about_ca_topic_score_codex":0.00001173502,"about_ca_topic_score_gemma":0.0000065872614,"teacher_disagreement_score":0.39723843,"about_ca_system_score_codex":0.00013299387,"about_ca_system_score_gemma":0.00007424059,"threshold_uncertainty_score":0.52417296},"labels":[],"label_agreement":null},{"id":"W2131675589","doi":"10.1093/bioinformatics/btt769","title":"SNPdryad: predicting deleterious non-synonymous human SNPs using only orthologous protein sequences","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Classifier (UML); Biology; Computational biology; Protein sequencing; Genome; Sequence alignment; Human proteome project; Proteome; Computer science; Artificial intelligence; Machine learning; Genetics; Gene; Peptide sequence; Proteomics","score_opus":0.015261747681945676,"score_gpt":0.24683134273027246,"score_spread":0.23156959504832678,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131675589","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9906318,0.00014316458,0.0051753414,0.000023069253,0.00014994103,0.0003444066,0.000023361194,0.000015171382,0.0034937263],"genre_scores_gemma":[0.97535896,0.000026110185,0.02387984,0.00020175146,0.00027662734,0.000017963868,0.000039145525,0.00002535804,0.00017426255],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987563,0.000034216984,0.00045613642,0.0002164937,0.00015267896,0.0003841915],"domain_scores_gemma":[0.99917835,0.000009325092,0.00024314108,0.00038539048,0.00009417506,0.00008960406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028750702,0.00023775829,0.0002277065,0.000053800584,0.00032535286,0.00006299873,0.00026424488,0.00016634952,0.0000047228364],"category_scores_gemma":[0.00007159198,0.00021565965,0.000095800395,0.00007406644,0.00013724109,0.0000033548854,0.00022358228,0.00009777059,0.000011775461],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025079034,0.00005245999,0.016492795,0.00017964063,0.00013409783,0.000004412805,0.00083638733,0.00074361323,0.96728826,0.00016629531,0.00023680297,0.013840135],"study_design_scores_gemma":[0.006710344,0.009005519,0.04990917,0.0006198909,0.00050974713,0.0013142749,0.0048278905,0.111964546,0.70984626,0.0017502074,0.09796305,0.0055790804],"about_ca_topic_score_codex":0.000059811086,"about_ca_topic_score_gemma":0.000066046065,"teacher_disagreement_score":0.257442,"about_ca_system_score_codex":0.000019612595,"about_ca_system_score_gemma":0.0000867446,"threshold_uncertainty_score":0.8794345},"labels":[],"label_agreement":null},{"id":"W2131776976","doi":"10.1093/bioinformatics/bts727","title":"Assessing identity, redundancy and confounds in Gene Ontology annotations over time","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":66,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institute of General Medical Sciences; Canadian Institutes of Health Research; National Institutes of Health; Michael Smith Health Research BC","keywords":"Redundancy (engineering); Computer science; Gene ontology; Identity (music); Ontology; Gene; Annotation; Computational biology; Artificial intelligence; Biology; Genetics","score_opus":0.011262456417417537,"score_gpt":0.2673509985252674,"score_spread":0.25608854210784987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131776976","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9782272,0.00035387874,0.010619672,0.00017915788,0.00016209994,0.00031933276,0.000012068382,0.00001649069,0.010110113],"genre_scores_gemma":[0.9722679,0.00018654104,0.02550514,0.0010141594,0.00012371321,0.000028270473,0.00024513734,0.000018332994,0.0006107739],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990371,0.000018868672,0.0004552867,0.0001153835,0.00009913866,0.00027421032],"domain_scores_gemma":[0.9994456,0.000016000136,0.00014891135,0.00023936231,0.00006503565,0.00008505248],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018938948,0.00014523492,0.00016483913,0.00008305836,0.00008785028,0.00026221763,0.00014610129,0.00018731525,0.00007088373],"category_scores_gemma":[0.000036506673,0.0001408357,0.000038995106,0.00010433106,0.00010495492,0.000108994966,0.00015764487,0.00010475838,0.00010638424],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015232492,0.0008472912,0.0994464,0.0014345989,0.0009222966,0.000027956627,0.010944813,0.0018326313,0.35838175,0.024692927,0.13856243,0.36275458],"study_design_scores_gemma":[0.0076312316,0.0009180853,0.37950248,0.0002658645,0.00013881555,0.00052059063,0.002985972,0.533566,0.008468502,0.018523285,0.0444718,0.0030073796],"about_ca_topic_score_codex":0.00005162949,"about_ca_topic_score_gemma":0.00005315016,"teacher_disagreement_score":0.5317334,"about_ca_system_score_codex":0.000019086221,"about_ca_system_score_gemma":0.00006522592,"threshold_uncertainty_score":0.5743113},"labels":[],"label_agreement":null},{"id":"W2131813051","doi":"10.1093/bioinformatics/btu762","title":"EPGA: <i>de novo</i> assembly using the distributions of reads and insert size","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Contig; Sequence assembly; Hybrid genome assembly; De Bruijn graph; Computer science; Sequence (biology); Insert (composites); Genome; De Bruijn sequence; Graph; Extension (predicate logic); Reference genome; Algorithm; Computational biology; Biology; Theoretical computer science; Genetics; Mathematics; Combinatorics","score_opus":0.011039391652501954,"score_gpt":0.24156995759420027,"score_spread":0.23053056594169832,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131813051","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9385754,0.00012545177,0.059388787,0.0000944111,0.00005198189,0.00012183665,0.000038629707,0.0000067411975,0.0015967462],"genre_scores_gemma":[0.9806467,0.000107955835,0.018881638,0.00014225167,0.000069590664,0.000003834654,0.000041216328,0.00000791077,0.000098843346],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994871,0.000022311522,0.00019072962,0.00006185513,0.000084944346,0.0001530612],"domain_scores_gemma":[0.99952745,0.00003418355,0.000097566364,0.00024178888,0.000057085443,0.000041909963],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026283297,0.000081303595,0.00008696079,0.000012505338,0.00007717452,0.000020737016,0.000121105106,0.00006820361,0.0000015888139],"category_scores_gemma":[0.0002044556,0.00006017957,0.0000362048,0.000066929206,0.00008356795,0.0000048402976,0.000098177276,0.000043904693,0.0000020757739],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024435009,0.000115968265,0.014297439,0.00030652087,0.00018119867,6.6799583e-7,0.0010656421,0.00020673446,0.9678826,0.002358935,0.0031049522,0.010454933],"study_design_scores_gemma":[0.0029689411,0.0010314395,0.038835526,0.00011705908,0.00032828044,0.0002771586,0.001950388,0.08319799,0.6194039,0.0010086005,0.2500797,0.0008010657],"about_ca_topic_score_codex":0.00000799857,"about_ca_topic_score_gemma":0.0000036545875,"teacher_disagreement_score":0.3484787,"about_ca_system_score_codex":0.000009315894,"about_ca_system_score_gemma":0.00003804818,"threshold_uncertainty_score":0.24540515},"labels":[],"label_agreement":null},{"id":"W2131848438","doi":"10.1093/bioinformatics/bti671","title":"Using information theory to search for co-evolving residues in proteins","year":2005,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":287,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Multiple sequence alignment; Phylogenetic tree; Computational biology; Computer science; Normalization (sociology); In silico; Sequence alignment; Protein sequencing; Conserved sequence; Mutual information; Biology; Genetics; Peptide sequence; Artificial intelligence; Gene","score_opus":0.029206417434222313,"score_gpt":0.2963293837242249,"score_spread":0.2671229662900026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131848438","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9202262,0.00019262274,0.075394996,0.0001391598,0.000054680077,0.00091783894,0.00006729455,0.0000053672175,0.0030018173],"genre_scores_gemma":[0.82237494,0.00004328556,0.17665671,0.00057402987,0.00015309243,0.000052170446,0.000054489978,0.000010734306,0.000080551814],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992913,0.000015506166,0.0002991304,0.00007278304,0.00008875036,0.00023251238],"domain_scores_gemma":[0.99960893,0.000016197393,0.000056263736,0.00017388433,0.00009439445,0.00005032528],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040599497,0.00010208246,0.00010091207,0.00009625998,0.000088239285,0.0000410056,0.00012545622,0.00007400123,0.0000036717806],"category_scores_gemma":[0.0000890286,0.00009668152,0.000039853956,0.00007213145,0.000024844263,0.000008099729,0.000083816776,0.000038735016,0.00001646557],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009539637,0.00020989314,0.025350727,0.00093016564,0.0002631759,6.873553e-7,0.02587542,0.04963628,0.64371365,0.0062471298,0.0102210445,0.23659788],"study_design_scores_gemma":[0.0025457696,0.0009242512,0.017920734,0.000117071904,0.000032482123,0.000015618556,0.0056128413,0.048926994,0.6529571,0.00042479034,0.26952177,0.001000574],"about_ca_topic_score_codex":0.000010311114,"about_ca_topic_score_gemma":0.000031974225,"teacher_disagreement_score":0.25930074,"about_ca_system_score_codex":0.00003228492,"about_ca_system_score_gemma":0.000071746595,"threshold_uncertainty_score":0.3942558},"labels":[],"label_agreement":null},{"id":"W2131994815","doi":"10.1093/bioinformatics/btu604","title":"SignalSpider: probabilistic pattern discovery on multiple normalized ChIP-Seq signal profiles","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Chromatin immunoprecipitation; Computational biology; Cluster analysis; DECIPHER; Computer science; ENCODE; Biology; Tiling array; Probabilistic logic; Transcription factor; Genome; Enhancer; ChIP-sequencing; DNA microarray; Gene; Genetics; Promoter; Artificial intelligence; Chromatin remodeling; Gene expression","score_opus":0.007426637499481214,"score_gpt":0.20666372978038328,"score_spread":0.19923709228090206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131994815","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9477441,0.000031319432,0.04843431,0.00008050761,0.00018549983,0.0004493711,0.0001237533,0.00003541443,0.002915726],"genre_scores_gemma":[0.99437547,0.000027992372,0.0037289436,0.00066244876,0.00022868071,0.000042784093,0.0005535479,0.00003436902,0.00034574987],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99867934,0.000046737176,0.00048110593,0.00022387212,0.00021022708,0.00035870547],"domain_scores_gemma":[0.9990534,0.00006375054,0.00022620913,0.00048163554,0.00006665469,0.000108349916],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024829066,0.00026802137,0.00022557357,0.000051627758,0.00012684862,0.000118450276,0.00030086352,0.0001644926,0.000021578122],"category_scores_gemma":[0.0001977271,0.00022735796,0.00013552733,0.000060622242,0.00008050688,0.000015056783,0.00014871964,0.00011338033,0.000071275164],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010687549,0.0021999255,0.06576928,0.0036546327,0.000909887,0.000014237761,0.0025415705,0.056597427,0.68109727,0.00715763,0.022556974,0.1564324],"study_design_scores_gemma":[0.0043412284,0.0027460384,0.012562947,0.00020611873,0.00010685681,0.000043461052,0.00045088882,0.8320525,0.11817355,0.0010308562,0.026422035,0.0018634812],"about_ca_topic_score_codex":0.000009900183,"about_ca_topic_score_gemma":0.00002406275,"teacher_disagreement_score":0.7754551,"about_ca_system_score_codex":0.000024590205,"about_ca_system_score_gemma":0.000065051434,"threshold_uncertainty_score":0.92713886},"labels":[],"label_agreement":null},{"id":"W2132028676","doi":"10.1093/bioinformatics/btp567","title":"Adaptive multi-agent architecture for functional sequence motifs recognition","year":2009,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Calgary Laboratory Services","keywords":"Computer science; Artificial intelligence; Machine learning; Robustness (evolution); Classifier (UML); Solver; Distributed computing; Biology","score_opus":0.041040487647807274,"score_gpt":0.2765442407598718,"score_spread":0.2355037531120645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132028676","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027757699,0.000063086554,0.9680744,0.00030501722,0.00027459904,0.0006652597,0.00021013884,0.000070163005,0.0025796567],"genre_scores_gemma":[0.27206898,0.000053546668,0.7207454,0.00314572,0.00043540858,0.00005854847,0.002698007,0.000029796243,0.00076459616],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989692,0.000020402033,0.00039356053,0.00014838472,0.00017875258,0.00028971757],"domain_scores_gemma":[0.99922776,0.00002248963,0.00021041272,0.00027529817,0.00016583891,0.00009819402],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021246093,0.00020752459,0.00014018331,0.00007173783,0.00014749248,0.000044268596,0.00016847013,0.00017999836,0.00001624404],"category_scores_gemma":[0.00024066449,0.00018721016,0.00012765698,0.00008620014,0.000054181142,0.000016078422,0.000043656197,0.0001510782,0.000060594095],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011833723,0.00056999736,0.00075789617,0.0005631225,0.0003500814,0.0000035679138,0.0030315877,0.034520593,0.054605834,0.0012517,0.048472855,0.8546894],"study_design_scores_gemma":[0.0055108303,0.0045225876,0.0072725946,0.00017379929,0.00014800773,0.00026891156,0.0011139965,0.7910222,0.039077815,0.0019079858,0.1471514,0.00182991],"about_ca_topic_score_codex":0.0000017586553,"about_ca_topic_score_gemma":0.0000048776687,"teacher_disagreement_score":0.8528595,"about_ca_system_score_codex":0.000031260362,"about_ca_system_score_gemma":0.00007725321,"threshold_uncertainty_score":0.7634209},"labels":[],"label_agreement":null},{"id":"W2132034930","doi":"10.1093/bioinformatics/btm057","title":"Cerebral: a Cytoscape plugin for layout of and interaction with biological networks using subcellular localization annotation","year":2007,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":179,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Genome Prairie; Canada Research Chairs; Genome British Columbia; Michael Smith Health Research BC","keywords":"Plug-in; Annotation; Computer science; Java; Subcellular localization; Rendering (computer graphics); Software; Computational biology; Biological network; Function (biology); Artificial intelligence; Biology; Programming language; Gene","score_opus":0.017316755269191048,"score_gpt":0.2790989649097475,"score_spread":0.26178220964055643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132034930","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40572476,0.000051656498,0.59400225,0.00000240004,0.000006020651,0.0001314164,0.0000014975901,0.000008834002,0.000071196955],"genre_scores_gemma":[0.949195,0.000048016846,0.050344888,0.0000692277,0.000042379394,0.0000035648457,0.00027827712,0.00000878385,0.000009859835],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994467,0.000010634588,0.00027288156,0.00009408567,0.00005831028,0.00011740713],"domain_scores_gemma":[0.99951106,0.000015639507,0.00019230024,0.00012390573,0.00012728201,0.000029799005],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024455762,0.00008879653,0.00011019977,0.000064300286,0.000039957067,0.000017104481,0.000046046734,0.00011430106,0.0000015526815],"category_scores_gemma":[0.00003897556,0.00007172953,0.000036416983,0.00009954739,0.000057606623,0.000014878205,0.0000288677,0.00003281916,1.5440781e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019167461,0.00030054452,0.072637156,0.00062114943,0.00043773794,0.0000038357452,0.0016359325,0.0375978,0.82991916,0.00049634126,0.0016068805,0.05282673],"study_design_scores_gemma":[0.00040700394,0.00044893348,0.00047052503,0.000032538137,0.000054235203,0.000017250162,0.00042692397,0.69736874,0.2984242,0.00001922517,0.002175614,0.00015482737],"about_ca_topic_score_codex":0.0000101375235,"about_ca_topic_score_gemma":0.000016250146,"teacher_disagreement_score":0.6597709,"about_ca_system_score_codex":0.000012160616,"about_ca_system_score_gemma":0.000012806187,"threshold_uncertainty_score":0.29250455},"labels":[],"label_agreement":null},{"id":"W2132091595","doi":"10.1093/bioinformatics/btv376","title":"GenomeD3Plot: a library for rich, interactive visualizations of genomic data in web applications","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University; Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Genome Canada","keywords":"Visualization; Computer science; JSON; JavaScript; Annotation; World Wide Web; Scalable Vector Graphics; Metadata; Web application; Data visualization; Interactive visualization; Genome browser; Genome; Information retrieval; Genomics; Data mining; Biology","score_opus":0.03629197658024201,"score_gpt":0.29539592336120235,"score_spread":0.2591039467809603,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132091595","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92246646,0.00344975,0.05947014,0.00024778093,0.0002357391,0.0021753288,0.004847759,0.000019300776,0.007087749],"genre_scores_gemma":[0.93792385,0.00061906315,0.058343,0.00022365047,0.00015725415,0.00017000266,0.0023600368,0.00003038704,0.00017278365],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99936867,0.000010776917,0.00031855237,0.00012480313,0.000053334636,0.00012384579],"domain_scores_gemma":[0.99927104,0.00002172684,0.00013484758,0.00045467998,0.00006659958,0.000051114603],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001163225,0.000089242516,0.00012471626,0.0000654571,0.000028005104,0.000014362272,0.00034558924,0.000056689507,0.000002114884],"category_scores_gemma":[0.000048617596,0.000087135915,0.000026930418,0.00009388,0.00004626908,0.0000060278785,0.0004098561,0.000026920174,0.0000063316347],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013349112,0.0025639243,0.12663218,0.0019595684,0.002005701,0.000002091466,0.024279095,0.005971822,0.5830627,0.01564854,0.1795199,0.057019573],"study_design_scores_gemma":[0.0022681274,0.000486281,0.004697874,0.000023833727,0.00007225131,0.000007749518,0.004149428,0.032707673,0.015036418,0.0010723647,0.93899864,0.0004793416],"about_ca_topic_score_codex":0.0000021559258,"about_ca_topic_score_gemma":0.000018434333,"teacher_disagreement_score":0.75947875,"about_ca_system_score_codex":0.000009397469,"about_ca_system_score_gemma":0.00019626199,"threshold_uncertainty_score":0.35532996},"labels":[],"label_agreement":null},{"id":"W2132186599","doi":"10.1093/bioinformatics/btp225","title":"PICKY: a novel SVD-based NMR spectra peak picking method","year":2009,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":72,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; University of Waterloo","funders":"National Institutes of Health; Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Computer science; Singular value decomposition; Process (computing); Pruning; NMR spectra database; Algorithm; Artificial intelligence; Pattern recognition (psychology); Spectral line; Physics","score_opus":0.009756982460976367,"score_gpt":0.26225474069432003,"score_spread":0.25249775823334364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132186599","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021670546,0.00014586169,0.96851844,0.00028888328,0.00012133165,0.00025509103,0.000033661207,0.0000519039,0.008914297],"genre_scores_gemma":[0.33471903,0.000019552268,0.6615051,0.0030700737,0.00026098252,0.000005796409,0.0002012005,0.000017393651,0.00020085408],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99903166,0.000014452645,0.00031596754,0.00016140024,0.00017051269,0.0003060299],"domain_scores_gemma":[0.99925417,0.000010937124,0.00014463122,0.00043243708,0.00006325821,0.000094590534],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018923302,0.00019742266,0.00016818442,0.00006013677,0.00009091429,0.000053321448,0.00024709248,0.00018513843,0.000010670232],"category_scores_gemma":[0.00007920023,0.00017631755,0.00011643463,0.00011683381,0.00003329509,0.000009192358,0.000045238,0.00012187951,0.000013934447],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026561285,0.00031952758,0.0008225902,0.00025869807,0.00017906007,0.000013654698,0.00079035806,0.006071442,0.8089826,0.012719162,0.0053069843,0.1642703],"study_design_scores_gemma":[0.0056862175,0.0024950795,0.012099819,0.00014709844,0.00018195537,0.0002806251,0.00047114317,0.30914927,0.4930854,0.0035336523,0.1705357,0.002334037],"about_ca_topic_score_codex":0.000005821376,"about_ca_topic_score_gemma":0.000008847932,"teacher_disagreement_score":0.3158972,"about_ca_system_score_codex":0.00002208235,"about_ca_system_score_gemma":0.00012356314,"threshold_uncertainty_score":0.7190021},"labels":[],"label_agreement":null},{"id":"W2132239943","doi":"10.1093/bioinformatics/bts308","title":"BATMAN—an R package for the automated quantification of metabolites from nuclear magnetic resonance spectra using a Bayesian model","year":2012,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":178,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Biotechnology and Biological Sciences Research Council; Directorate for Biological Sciences","keywords":"Bayesian probability; Deconvolution; Markov chain Monte Carlo; Computer science; Spectral line; Algorithm; Monte Carlo method; Biological system; NMR spectra database; Artificial intelligence; Nuclear magnetic resonance; Pattern recognition (psychology); Mathematics; Statistics; Physics; Biology","score_opus":0.027805285930278055,"score_gpt":0.27322679553577145,"score_spread":0.2454215096054934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132239943","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7396108,0.0152544305,0.24305019,0.000091983835,0.0002800526,0.0006620878,0.0005539687,0.00006290464,0.00043362673],"genre_scores_gemma":[0.8356566,0.00072507584,0.16320604,0.00009313894,0.00013676549,0.000012522791,0.000106965716,0.00002230996,0.000040619143],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99910784,0.000021862103,0.0003633504,0.00011830033,0.00011920186,0.00026942755],"domain_scores_gemma":[0.9991432,0.000032347907,0.00019570767,0.00048452883,0.0000837646,0.000060477243],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002788205,0.00014771259,0.0001967446,0.000041140356,0.00014181109,0.00003000494,0.0002229319,0.00009024038,0.000011673525],"category_scores_gemma":[0.00010459146,0.00010858372,0.00009303709,0.000102564656,0.000084391955,0.000022945658,0.00006835302,0.000045862154,0.0000030976564],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009868713,0.00014367094,0.00071212824,0.00006906945,0.00012063715,5.0428028e-8,0.0011972268,0.0003892276,0.9810886,0.010022922,0.0012441191,0.004913689],"study_design_scores_gemma":[0.00040017432,0.00011887306,0.0039848043,0.000009436311,0.00015466583,0.0000020939171,0.0006862491,0.8611419,0.12213464,0.0002446925,0.010912312,0.00021014664],"about_ca_topic_score_codex":0.000023800503,"about_ca_topic_score_gemma":0.000007443664,"teacher_disagreement_score":0.8607527,"about_ca_system_score_codex":0.000009579895,"about_ca_system_score_gemma":0.00003070676,"threshold_uncertainty_score":0.44279158},"labels":[],"label_agreement":null},{"id":"W2132620282","doi":"10.1093/bioinformatics/btp035","title":"The protein–small-molecule database, a non-redundant structural resource for the analysis of protein-ligand binding","year":2009,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Database; Protein structure database; Redundancy (engineering); Protein Data Bank (RCSB PDB); Protein Data Bank; Annotation; Small molecule; Function (biology); Protein structure; Data mining; Computational biology; Chemistry; Biology; Artificial intelligence; Biochemistry; Genetics","score_opus":0.025551784374906905,"score_gpt":0.295789393044796,"score_spread":0.2702376086698891,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132620282","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17135091,0.00008362769,0.8258479,0.0010480868,0.00006362674,0.0012575941,0.000051410178,0.000035989815,0.0002608317],"genre_scores_gemma":[0.4589469,0.000004916637,0.5403115,0.00027787054,0.00006301593,0.000102171616,0.000060263694,0.00001087989,0.00022246048],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99848306,0.00006197823,0.0005569366,0.00016221823,0.00043722815,0.0002985831],"domain_scores_gemma":[0.99795634,0.0006189179,0.00040513658,0.0008170883,0.00014550381,0.000056988058],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011457843,0.00015935904,0.00022335128,0.00018386444,0.000499081,0.0003581108,0.0013542614,0.000036239788,8.253542e-7],"category_scores_gemma":[0.00030389,0.000089373134,0.00019290672,0.0012960786,0.00009257149,0.00038471306,0.00025302055,0.00011730931,0.0000022520815],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028763604,0.00014855736,0.0000828593,0.00042974533,0.002528971,0.000005963904,0.01379701,0.1316913,0.020528186,0.2631241,0.0015191986,0.56585646],"study_design_scores_gemma":[0.00022156604,0.000081922284,0.0008002377,0.000036903737,0.00011018436,0.0000029659514,0.00021027907,0.98277164,0.013294067,0.0009693591,0.0013648224,0.00013608119],"about_ca_topic_score_codex":0.000009968207,"about_ca_topic_score_gemma":0.000009843784,"teacher_disagreement_score":0.8510803,"about_ca_system_score_codex":0.000039686576,"about_ca_system_score_gemma":0.0001511717,"threshold_uncertainty_score":0.3838578},"labels":[],"label_agreement":null},{"id":"W2132840768","doi":"10.1093/bioinformatics/btu719","title":"deML: robust demultiplexing of Illumina sequences using a likelihood-based approach","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":215,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Max-Planck-Gesellschaft","keywords":"Pooling; Quality Score; Multiplexing; Computer science; Sample (material); Set (abstract data type); Illumina dye sequencing; Index (typography); Software; DNA sequencing; Sequence (biology); Data mining; Computational biology; Algorithm; Biology; Genetics; Artificial intelligence; DNA; Metric (unit); Engineering","score_opus":0.027482901823111562,"score_gpt":0.23428084675742514,"score_spread":0.20679794493431358,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132840768","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7685913,0.0002799312,0.22799169,0.000013112234,0.00008715615,0.00014707055,0.000019336678,0.00000509818,0.0028653357],"genre_scores_gemma":[0.75637746,0.000023628587,0.24337985,0.00010087363,0.000069459435,0.000004424555,0.000022240232,0.0000103638085,0.00001169863],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991755,0.000025038706,0.00033139277,0.0001256572,0.00011527349,0.00022717667],"domain_scores_gemma":[0.9993772,0.000017994364,0.00019170114,0.00026337616,0.000092288574,0.000057472407],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024695045,0.00014310268,0.00017858502,0.0000451882,0.00008763322,0.00001533818,0.0001792099,0.00010158428,0.0000019712263],"category_scores_gemma":[0.00008461151,0.00012691326,0.00008666429,0.00007933062,0.0001272908,0.000001555155,0.00008881859,0.000042545897,0.0000016997673],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008973693,0.0001922461,0.034885608,0.0008588044,0.00026624388,4.5736942e-7,0.0012305941,0.1297118,0.8197285,0.00066182093,0.0004620438,0.011912136],"study_design_scores_gemma":[0.0009649552,0.00039037172,0.0022997526,0.00005193236,0.0000759329,0.00001335042,0.00093219173,0.8398023,0.14851403,0.00014717299,0.0063119116,0.0004960759],"about_ca_topic_score_codex":0.00002247176,"about_ca_topic_score_gemma":0.0000070724086,"teacher_disagreement_score":0.7100905,"about_ca_system_score_codex":0.000008997421,"about_ca_system_score_gemma":0.00007144505,"threshold_uncertainty_score":0.51753724},"labels":[],"label_agreement":null},{"id":"W2133001645","doi":"10.1093/bioinformatics/btu644","title":"PINBPA: Cytoscape app for network analysis of GWAS data","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"National Multiple Sclerosis Society","keywords":"Genome-wide association study; Computer science; Interface (matter); Data mining; Computational biology; Biology; Gene; Genetics; Operating system; Single-nucleotide polymorphism","score_opus":0.024696411385221217,"score_gpt":0.2854148186385947,"score_spread":0.2607184072533735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133001645","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14155197,0.00026964798,0.8532306,0.00022935009,0.0002524598,0.00031430274,0.00045611765,0.000017570308,0.0036779828],"genre_scores_gemma":[0.81751645,0.00015604697,0.17542908,0.0007129185,0.00034250066,0.00001817384,0.00551082,0.000014061763,0.00029999175],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990735,0.00003674084,0.0004489095,0.00014504383,0.00006842558,0.00022738361],"domain_scores_gemma":[0.998715,0.00008167715,0.00029013812,0.00077057886,0.00009454956,0.000048062262],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00077725295,0.00009748068,0.00028846468,0.000056769117,0.00006259708,0.0000076197957,0.0003618607,0.00014961879,0.0000091846305],"category_scores_gemma":[0.000499926,0.00008751048,0.00012205339,0.00021889736,0.00004662207,0.000003795818,0.00019388576,0.00003091124,0.0000048773813],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019634933,0.0002616516,0.264603,0.00039233966,0.009032979,1.4542613e-7,0.00046392312,0.1189526,0.0069342027,0.005637037,0.51618123,0.07734457],"study_design_scores_gemma":[0.00056952046,0.00030756026,0.043181125,0.00000714686,0.0010202317,0.0000012174194,0.000112177564,0.6927654,0.00040252207,0.0003103776,0.2610633,0.00025941135],"about_ca_topic_score_codex":0.00000766773,"about_ca_topic_score_gemma":0.00004781954,"teacher_disagreement_score":0.67780155,"about_ca_system_score_codex":0.0000048392276,"about_ca_system_score_gemma":0.000036083227,"threshold_uncertainty_score":0.3568574},"labels":[],"label_agreement":null},{"id":"W2133360663","doi":"10.1093/bioinformatics/btq166","title":"Picante: R tools for integrating phylogenies and ecology","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Ecology and Vegetation Dynamics Studies","field":"Environmental Science","cited_by":6383,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Gordon and Betty Moore Foundation; Chinese Academy of Sciences; National Science Foundation","keywords":"R package; Phylogenetic tree; Trait; Phylogenetic diversity; Set (abstract data type); License; Open source; Diversity (politics); Software package; Computer science; Software; Biology; Data science; Ecology; Evolutionary biology; Sociology; Programming language; Anthropology","score_opus":0.01060361882652631,"score_gpt":0.23638697334989223,"score_spread":0.22578335452336593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133360663","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98229647,0.0000048562515,0.0041094334,0.0003366525,0.00024403604,0.00020800658,0.000011083,0.000024895566,0.012764576],"genre_scores_gemma":[0.9156446,0.000011899865,0.083656915,0.000408272,0.00001779166,0.00003306851,0.0000064520086,0.000003186737,0.00021780469],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99962646,0.0000043314085,0.00014890019,0.000057316716,0.0000348792,0.0001281423],"domain_scores_gemma":[0.99959683,0.00023789468,0.000063522966,0.00006647449,0.000008215133,0.00002702903],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014504427,0.000060372182,0.00008004256,0.000014180392,0.00018625714,0.000024789697,0.0000670633,0.0000611879,0.00008828917],"category_scores_gemma":[0.0003223503,0.00004852168,0.000018111105,0.0000341597,0.00021727398,0.00020863776,0.0000816304,0.00008407011,0.00005098351],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003331531,0.000086313936,0.76522243,0.00012650706,0.000073286516,0.0000011783948,0.010698385,0.00013321207,0.007579598,0.058503687,0.0060003833,0.1515417],"study_design_scores_gemma":[0.0008940421,0.00034301128,0.75012356,0.000006883387,0.00004085961,0.000037468144,0.0038314166,0.20846747,0.0006846554,0.009909185,0.025257766,0.000403654],"about_ca_topic_score_codex":0.0000035733267,"about_ca_topic_score_gemma":0.0010558263,"teacher_disagreement_score":0.20833427,"about_ca_system_score_codex":0.000010366439,"about_ca_system_score_gemma":0.000004990425,"threshold_uncertainty_score":0.19786568},"labels":[],"label_agreement":null},{"id":"W2133525847","doi":"10.1093/bioinformatics/btl235","title":"Integrating image data into biomedical text categorization","year":2006,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":118,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; Xerox Foundation","keywords":"Computer science; Annotation; Categorization; Information retrieval; Task (project management); Text categorization; Feature (linguistics); Artificial intelligence; Natural language processing","score_opus":0.015740115506897037,"score_gpt":0.27755073193468244,"score_spread":0.2618106164277854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133525847","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09527966,0.0009655965,0.8895961,0.0009874966,0.0006739546,0.000269079,0.00010508599,0.00017701185,0.011946032],"genre_scores_gemma":[0.5522034,0.0001095603,0.43686774,0.00043154263,0.00087833125,0.0000121103885,0.008828098,0.0000282436,0.0006409833],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.999037,0.000020529336,0.00036669135,0.00018269848,0.00018594417,0.0002071253],"domain_scores_gemma":[0.9991942,0.0000186774,0.000113242095,0.0005507763,0.00005636639,0.000066752276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021034133,0.00013292719,0.00012005378,0.000054302425,0.00010124279,0.000056434015,0.00047428109,0.00020261633,0.000015981992],"category_scores_gemma":[0.0003676369,0.000104074934,0.000032279022,0.00014949194,0.00024047996,0.000012832029,0.00035264372,0.00009435246,0.000060916926],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047055903,0.00026719095,0.0014170372,0.00027058064,0.00007955966,0.000009451599,0.0006668491,0.000010129125,0.1989892,0.0018681919,0.36062112,0.4357536],"study_design_scores_gemma":[0.0009132369,0.0003930226,0.0010990805,0.000050987517,0.00003826678,0.00004147502,0.0019675707,0.052102864,0.019970244,0.00097023515,0.9219054,0.0005475927],"about_ca_topic_score_codex":0.00007881515,"about_ca_topic_score_gemma":0.000046285204,"teacher_disagreement_score":0.5612843,"about_ca_system_score_codex":0.000012573142,"about_ca_system_score_gemma":0.00008570074,"threshold_uncertainty_score":0.42440525},"labels":[],"label_agreement":null},{"id":"W2133550211","doi":"10.1093/bioinformatics/btr058","title":"A common layer of interoperability for biomedical ontologies based on OWL EL","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"National Human Genome Research Institute; Biotechnology and Biological Sciences Research Council; European Commission; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; European Bioinformatics Institute","keywords":"Computer science; Interoperability; Ontology; Open Biomedical Ontologies; Web Ontology Language; IDEF5; Semantics (computer science); Knowledge representation and reasoning; Ontology components; Upper ontology; Description logic; Software; Information retrieval; Semantic Web; Software engineering; World Wide Web; Programming language; Artificial intelligence; Ontology alignment","score_opus":0.057446294203414114,"score_gpt":0.30675205372400544,"score_spread":0.2493057595205913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133550211","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88447136,0.00015868603,0.10136669,0.00038467546,0.0006155584,0.00063540076,0.00023957623,0.000099250195,0.012028812],"genre_scores_gemma":[0.9407356,0.0000105120025,0.058649845,0.00040367708,0.000037140842,0.000026781345,0.00008843445,0.000007937777,0.00004008432],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991385,0.000026680991,0.00037766361,0.00012746948,0.00012632697,0.00020337578],"domain_scores_gemma":[0.9993163,0.00005734751,0.00012245766,0.00036420664,0.000068942165,0.00007078873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028142217,0.0001265233,0.0002125016,0.00005173254,0.00003857222,0.0000058183223,0.000263602,0.00023279674,0.000022325186],"category_scores_gemma":[0.00043343657,0.000091534566,0.00011497295,0.00005834296,0.00037529477,0.0000027854437,0.000075293014,0.00007157047,0.000006496762],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0057376036,0.004215334,0.04664154,0.002681939,0.00054386084,0.000008089479,0.006869613,0.000032326534,0.04147654,0.0024710346,0.06885915,0.82046294],"study_design_scores_gemma":[0.009186793,0.028623244,0.042657487,0.00051026815,0.00020000675,0.00003006186,0.005947692,0.065544575,0.5635243,0.002331256,0.2796894,0.0017549351],"about_ca_topic_score_codex":0.000015439555,"about_ca_topic_score_gemma":0.0000123512045,"teacher_disagreement_score":0.818708,"about_ca_system_score_codex":0.000009850085,"about_ca_system_score_gemma":0.00006395516,"threshold_uncertainty_score":0.37326714},"labels":[],"label_agreement":null},{"id":"W2133594999","doi":"10.1093/bioinformatics/btr146","title":"<i>anota</i>: analysis of differential translation in genome-wide studies","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":65,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University and Génome Québec Innovation Centre","funders":"Knut och Alice Wallenbergs Stiftelse","keywords":"Bioconductor; Translation (biology); Computational biology; Polysome; Biology; Microarray analysis techniques; Gene expression profiling; Eukaryotic translation; Messenger RNA; DNA microarray; Gene expression; Computer science; Gene; Ribosome; Genetics; RNA","score_opus":0.04230599683304403,"score_gpt":0.2562835172677359,"score_spread":0.21397752043469187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133594999","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9736605,0.00059936475,0.023852272,0.000009221214,0.0000591684,0.00014672194,0.000020303189,0.000005644786,0.0016467673],"genre_scores_gemma":[0.98964214,0.0004042272,0.009786952,0.000042291736,0.000013785073,0.00001031455,0.000059598213,0.0000055909873,0.000035080946],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99933857,0.00002407988,0.00034946398,0.000079774145,0.00009156568,0.00011653684],"domain_scores_gemma":[0.9996047,0.00001548365,0.00011862917,0.00019478636,0.00004216783,0.000024245417],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013273432,0.000090682595,0.00020805393,0.0001507576,0.000018978582,0.000004056718,0.00010935079,0.000080888036,0.000033947126],"category_scores_gemma":[0.000044697088,0.00007829375,0.00011263079,0.00020610071,0.000036811252,0.0000057369784,0.00002991558,0.000024780717,0.0000032145965],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041721124,0.00032339312,0.03489598,0.00040266005,0.0039966875,0.0000029448947,0.018248266,0.00025961082,0.89940876,0.0005464835,0.00009768067,0.041400306],"study_design_scores_gemma":[0.00078113674,0.0003710087,0.053007048,0.000033345474,0.0007525632,0.0000012083318,0.0020170056,0.0022304854,0.93868226,0.00029615586,0.0014297147,0.00039808275],"about_ca_topic_score_codex":0.000007627342,"about_ca_topic_score_gemma":0.000050955157,"teacher_disagreement_score":0.041002225,"about_ca_system_score_codex":0.000004994433,"about_ca_system_score_gemma":0.000014131082,"threshold_uncertainty_score":0.31927264},"labels":[],"label_agreement":null},{"id":"W2133601033","doi":"10.1093/bioinformatics/btp602","title":"Evaluation of linguistic features useful in extraction of interactions from PubMed; Application to annotating known, high-throughput and predicted interactions in I2D","year":2009,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":77,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"U.S. National Library of Medicine; Ontario Genomics; Ontario Genomics Institute; Genome Canada","keywords":"Computer science; Sentence; Identification (biology); Recall; Precision and recall; Software; Natural language processing; Information retrieval; Process (computing); Artificial intelligence; Data mining; Machine learning; Programming language; Biology","score_opus":0.02690545087677414,"score_gpt":0.33233209653783674,"score_spread":0.3054266456610626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133601033","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98546547,0.00016314784,0.013295823,0.00015572057,0.00015442519,0.0003218228,0.000050954954,0.000010189084,0.0003824269],"genre_scores_gemma":[0.98367447,0.0000384864,0.015930893,0.00004696717,0.00006602434,0.00005734764,0.00017000461,0.0000038774324,0.0000119183305],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99906427,0.000051974577,0.00045594436,0.00012534419,0.00018667377,0.00011580759],"domain_scores_gemma":[0.99932367,0.00006731104,0.00021339093,0.00016469619,0.00019171278,0.000039207494],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041718828,0.000086695756,0.00014331797,0.0001571379,0.00002106148,0.000010512494,0.000073527706,0.000081777114,0.0000038702055],"category_scores_gemma":[0.001315053,0.000083524435,0.000022079415,0.00019980516,0.000041448824,0.000017942846,0.000030871266,0.00011056555,7.210114e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020457713,0.00039954405,0.012912579,0.00008085277,0.00006205768,5.806223e-7,0.00582157,0.001775689,0.10265445,0.00011971431,0.0007185027,0.87524986],"study_design_scores_gemma":[0.0012039198,0.00030849918,0.9274669,0.00022537768,0.00008318397,0.000008941101,0.001757645,0.034665313,0.029581523,0.001145742,0.00334788,0.00020503385],"about_ca_topic_score_codex":0.00023482478,"about_ca_topic_score_gemma":0.0006741241,"teacher_disagreement_score":0.91455436,"about_ca_system_score_codex":0.000044331307,"about_ca_system_score_gemma":0.000054480523,"threshold_uncertainty_score":0.34060276},"labels":[],"label_agreement":null},{"id":"W2134335091","doi":"10.1093/bioinformatics/btn211","title":"A correction for estimating error when using the Local Pooled Error Statistical Test","year":2008,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University and Génome Québec Innovation Centre","funders":"","keywords":"Bioconductor; Sample size determination; Software; Statistics; Computer science; Type I and type II errors; Sample (material); R package; Standard error; Statistical hypothesis testing; Multiple comparisons problem; Data mining; Mathematics; Programming language; Biology","score_opus":0.03975235909724276,"score_gpt":0.3027381671937055,"score_spread":0.2629858080964627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134335091","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017180527,0.00004404487,0.9811809,0.00013502975,0.000616133,0.00029927702,0.00003188669,0.000019433895,0.00049276906],"genre_scores_gemma":[0.7083268,0.000010438308,0.28968632,0.0005474672,0.00032069857,0.0000643137,0.00021836229,0.00002197129,0.00080362195],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992625,0.00001842157,0.00028544696,0.00012035052,0.00013124206,0.00018201943],"domain_scores_gemma":[0.99939364,0.000057447323,0.0001465761,0.00023925964,0.00010324967,0.00005984386],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013298604,0.00011355931,0.00009464611,0.000027845335,0.00030249843,0.00002471217,0.00013027423,0.00009655086,0.000014294083],"category_scores_gemma":[0.0003468358,0.00008289269,0.0000520018,0.000059982598,0.00011993085,0.000008592972,0.00004475419,0.00006914607,0.000007959964],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004280258,0.0003477676,0.0023834195,0.0003277449,0.00015719044,0.0000029827038,0.0040409816,0.020136962,0.25282064,0.00042606198,0.60682994,0.11209829],"study_design_scores_gemma":[0.00043431818,0.00016085163,0.00040519136,0.000022105678,0.000029860708,0.00006601199,0.0007039601,0.96009904,0.018917533,0.000056860255,0.018955406,0.00014885662],"about_ca_topic_score_codex":0.000008288161,"about_ca_topic_score_gemma":0.0000055244564,"teacher_disagreement_score":0.9399621,"about_ca_system_score_codex":0.000029215284,"about_ca_system_score_gemma":0.00014599563,"threshold_uncertainty_score":0.3380266},"labels":[],"label_agreement":null},{"id":"W2134384386","doi":"10.1093/bioinformatics/btl109","title":"Construction of null statistics in permutation-based multiple testing for multi-factorial microarray experiments","year":2006,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Null distribution; Statistics; Permutation (music); Test statistic; Mathematics; Null (SQL); Statistical hypothesis testing; Statistic; False discovery rate; Null hypothesis; Asymptotic distribution; Ancillary statistic; p-value; Data mining; Computer science; Biology; Genetics","score_opus":0.4215325324378103,"score_gpt":0.49919503487273753,"score_spread":0.07766250243492723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134384386","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02986747,0.0000057556963,0.96674436,0.0000104961955,0.00092597865,0.0010218861,0.0011657914,0.000056123736,0.00020215454],"genre_scores_gemma":[0.033535928,4.7979336e-7,0.9661198,0.000026407924,0.00015138747,0.0000691583,0.000050823455,0.000029223665,0.000016774764],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997182,0.00013125876,0.0019135965,0.00016448446,0.00030764635,0.00030098832],"domain_scores_gemma":[0.9697432,0.02877404,0.0008119204,0.0002487982,0.00036101768,0.00006100233],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0010926531,0.00020886282,0.00054689666,0.00014209992,0.000067524794,0.000033530847,0.00015965186,0.00018504779,0.000029599756],"category_scores_gemma":[0.05953895,0.00019833897,0.00008582432,0.00022435594,0.0001897007,0.000100000696,0.000026820895,0.00013316424,0.0000058126443],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003242555,0.0075300555,0.28312105,0.013316523,0.00039162685,0.000020217742,0.006372569,0.0037543133,0.06072812,0.47939205,0.014226501,0.12790442],"study_design_scores_gemma":[0.012380282,0.0003957723,0.0033327485,0.00031785955,0.00010724924,0.0000032630378,0.00065145025,0.6248128,0.048242707,0.3089438,0.00023088639,0.00058116566],"about_ca_topic_score_codex":0.00007040043,"about_ca_topic_score_gemma":0.000025926382,"teacher_disagreement_score":0.62105846,"about_ca_system_score_codex":0.000106159496,"about_ca_system_score_gemma":0.0001533628,"threshold_uncertainty_score":0.948383},"labels":[],"label_agreement":null},{"id":"W2134425821","doi":"10.1093/bioinformatics/btt031","title":"Computational phosphorylation site prediction in plants using random forests and organism-specific instance weights","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Phosphorylation; Organism; Random forest; Computer science; Arabidopsis thaliana; Arabidopsis; Computational biology; Interface (matter); Biology; Artificial intelligence; Biochemistry; Mutant; Genetics; Gene","score_opus":0.009811674771357713,"score_gpt":0.2033164158562933,"score_spread":0.19350474108493557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134425821","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98912096,0.00072478724,0.0095078815,0.000014820893,0.000094245115,0.0002461654,0.000035995457,0.0000032113946,0.00025195314],"genre_scores_gemma":[0.98750526,0.0003209299,0.0119355,0.000048401587,0.000051106217,0.00000785643,0.0001012231,0.000007300306,0.000022441978],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99945575,0.000009955936,0.00023779529,0.00009748615,0.00007820265,0.000120829056],"domain_scores_gemma":[0.9997442,0.000011804031,0.00007663422,0.000085164625,0.000047966092,0.00003427058],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006487834,0.000093875286,0.00009399604,0.000041012187,0.00007403889,0.0000320622,0.00004093139,0.00006906946,0.0000074092677],"category_scores_gemma":[0.000007949219,0.00008660252,0.000017079925,0.00004489591,0.000038565486,0.0000056209133,0.000045439327,0.00003490996,0.000011816244],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048760546,0.00017892277,0.7217471,0.0002177927,0.00019648658,0.0000029925322,0.007007163,0.053768773,0.18523286,0.000599456,0.0049354048,0.025625417],"study_design_scores_gemma":[0.0034083358,0.0001838087,0.6458574,0.000048243877,0.000010972372,0.000031791413,0.0004225792,0.33335862,0.010150117,0.0017616345,0.004424132,0.00034240168],"about_ca_topic_score_codex":0.000013860429,"about_ca_topic_score_gemma":0.000024537132,"teacher_disagreement_score":0.27958983,"about_ca_system_score_codex":0.000014804758,"about_ca_system_score_gemma":0.000021609729,"threshold_uncertainty_score":0.35315484},"labels":[],"label_agreement":null},{"id":"W2134459098","doi":"10.1093/bioinformatics/btt574","title":"PLIDA: cross-platform gene expression normalization using perturbed topic models","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Normalization (sociology); Computer science; Data mining; Multiplicative function; Database normalization; Machine learning; MATLAB; Artificial intelligence; Pattern recognition (psychology); Programming language; Mathematics","score_opus":0.033973699461407575,"score_gpt":0.27516427195463017,"score_spread":0.2411905724932226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134459098","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7656616,0.00018372487,0.22917588,0.000033362878,0.00025505223,0.00032132768,0.0000082433235,0.00003185685,0.004328936],"genre_scores_gemma":[0.9702059,0.00012287275,0.027603067,0.00037995633,0.00018571084,0.00004132536,0.0002519184,0.000019170115,0.0011901],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991098,0.000011616876,0.0003379942,0.0001531515,0.00017662352,0.00021079059],"domain_scores_gemma":[0.99920434,0.0000035860146,0.00016090515,0.00037551858,0.00016161738,0.00009402575],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007398752,0.0001445749,0.000101854625,0.000058244626,0.0001468131,0.000114493196,0.00017734319,0.00018244621,0.00007041459],"category_scores_gemma":[0.00002269738,0.000121839345,0.0000594309,0.00009182587,0.000038007154,0.00006859027,0.00010124407,0.000056211262,0.000039291455],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017408523,0.000029250272,0.0009457632,0.000047444733,0.000011214303,1.3541354e-7,0.0002840554,0.0049802777,0.98609406,0.00014071517,0.003772013,0.0036776739],"study_design_scores_gemma":[0.0005888404,0.00006200184,0.0014101155,0.00002933014,0.0000096065805,0.000012120562,0.00021131051,0.24120606,0.74872017,0.00034931963,0.0071134646,0.00028766782],"about_ca_topic_score_codex":0.000012583937,"about_ca_topic_score_gemma":8.162337e-7,"teacher_disagreement_score":0.23737389,"about_ca_system_score_codex":0.0000296127,"about_ca_system_score_gemma":0.00006511102,"threshold_uncertainty_score":0.49684644},"labels":[],"label_agreement":null},{"id":"W2134594748","doi":"10.1093/bioinformatics/18.10.1305","title":"Short inversions and conserved gene cluster","year":2002,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Cluster (spacecraft); Gene; Computational biology; Genetics; Gene cluster; Conserved sequence; Biology; Computer science; Base sequence; Programming language","score_opus":0.012863111426107332,"score_gpt":0.2023517259428525,"score_spread":0.18948861451674517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134594748","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9933256,0.00024501144,0.0015361516,0.00016621371,0.000078385994,0.000118402444,0.000027928787,0.000011324213,0.0044909925],"genre_scores_gemma":[0.982735,0.0005958795,0.014899653,0.0008618349,0.00005087996,0.000004851984,0.00009002256,0.0000117358395,0.000750178],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99951565,0.000007992443,0.0001815805,0.00008698636,0.00006146066,0.00014633057],"domain_scores_gemma":[0.9996293,0.0000056412337,0.00003638307,0.000218364,0.000029773988,0.00008049361],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000060157232,0.000097447875,0.000080007834,0.000023994615,0.000077385164,0.000030723062,0.00009500373,0.00009805865,0.000021033306],"category_scores_gemma":[0.000019787996,0.00009112588,0.000036346322,0.0000332062,0.00005984599,0.000004154887,0.00013064926,0.00004289969,0.000032461183],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014663793,0.00061158504,0.061802033,0.00086711696,0.00082838465,0.00002083658,0.005028234,0.0011681819,0.44142255,0.0017112363,0.381428,0.10496522],"study_design_scores_gemma":[0.0028419974,0.00064082915,0.009435473,0.0000447207,0.00011913696,0.00040259806,0.0012093422,0.7463837,0.0552419,0.00019786108,0.1820899,0.0013925089],"about_ca_topic_score_codex":0.0000016409009,"about_ca_topic_score_gemma":0.000006387341,"teacher_disagreement_score":0.74521554,"about_ca_system_score_codex":0.0000067587416,"about_ca_system_score_gemma":0.000008395955,"threshold_uncertainty_score":0.37160057},"labels":[],"label_agreement":null},{"id":"W2134773344","doi":"10.1093/bioinformatics/btn385","title":"An integrated approach for automating validation of extracted ion chromatographic peaks","year":2008,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Office of Experimental Program to Stimulate Competitive Research; National Center for Research Resources; National Institutes of Health; Canadian Institute for Theoretical Astrophysics","keywords":"Computer science; Data mining; Software; Chromatography; Chemistry; Programming language","score_opus":0.023520908674632343,"score_gpt":0.27449157440997285,"score_spread":0.2509706657353405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134773344","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3727931,0.0000065756362,0.6246712,0.0000040997847,0.0000061057594,0.00023756213,0.0000660782,0.00025510052,0.001960167],"genre_scores_gemma":[0.4577435,0.000014676038,0.54137045,0.000006130443,0.000017772907,0.00011379503,0.0007026693,0.000011311428,0.000019703464],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991629,0.0000043258947,0.00047925036,0.00009586823,0.000116273746,0.00014139203],"domain_scores_gemma":[0.99908036,0.000030280175,0.00036814876,0.00032510023,0.00014761223,0.00004851033],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000101410085,0.00011851829,0.00015499945,0.000073562,0.00014691772,0.00001468959,0.00018155345,0.00012756222,0.000019526457],"category_scores_gemma":[0.00003813397,0.00011078418,0.00006737535,0.00019911308,0.00006250424,0.0002827382,0.000016478007,0.00009927488,0.0000010937381],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007857374,0.00088226364,0.003340939,0.0024331973,0.00008850359,5.575815e-7,0.0040765,0.0031440894,0.9450697,0.007003265,0.0007476889,0.033134736],"study_design_scores_gemma":[0.00026782122,0.00003744459,0.000078418096,0.000036141468,0.00001380037,0.00001846047,0.00042786865,0.41036096,0.58765036,0.000282859,0.00067084876,0.00015499031],"about_ca_topic_score_codex":0.000007773719,"about_ca_topic_score_gemma":1.84441e-7,"teacher_disagreement_score":0.40721688,"about_ca_system_score_codex":0.000025908648,"about_ca_system_score_gemma":0.00004066019,"threshold_uncertainty_score":0.4517648},"labels":[],"label_agreement":null},{"id":"W2134880148","doi":"10.1093/bioinformatics/btk028","title":"Inferring global levels of alternative splicing isoforms using a generative model of microarray data","year":2006,"lang":"en","type":"article","venue":"Bioinformatics","topic":"RNA Research and Splicing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Alternative splicing; DNA microarray; Exon; Microarray; Microarray analysis techniques; Computational biology; Context (archaeology); RNA splicing; Biology; Exon skipping; Gene chip analysis; Gene; Genetics; Gene expression; RNA","score_opus":0.06752830136639101,"score_gpt":0.32512590210927544,"score_spread":0.2575976007428844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134880148","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7311903,0.000079427795,0.2673245,0.0000066486964,0.000022127986,0.00011324096,0.0004860209,0.0000033080428,0.00077442377],"genre_scores_gemma":[0.90104634,0.000021837726,0.098600574,0.000031262658,0.00006346767,0.000001195428,0.00014116454,0.000008560246,0.00008562405],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99890774,0.000014800616,0.00047679627,0.00014119162,0.00021136177,0.00024808856],"domain_scores_gemma":[0.99902546,0.0000079357715,0.00026468447,0.0004991901,0.00015438987,0.000048346144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023792512,0.00013165672,0.00019637562,0.000047805705,0.000055563203,0.000018115514,0.00040337726,0.000082786144,0.0000025487439],"category_scores_gemma":[0.000064709675,0.000112815884,0.000054630153,0.00010890854,0.00010004561,0.00003156921,0.0004177531,0.000057283887,9.836414e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029093717,0.000031709413,0.002043599,0.00009563421,0.00005482144,3.8934795e-7,0.00010122628,0.044658203,0.9512412,0.0003577997,0.00012433763,0.0012620093],"study_design_scores_gemma":[0.00028743048,0.00005396353,0.00026841764,0.00003416515,0.000009610058,0.000004848272,0.00012491744,0.57782423,0.4211516,0.0001281034,0.00002173603,0.00009097495],"about_ca_topic_score_codex":0.00035543882,"about_ca_topic_score_gemma":0.00008599562,"teacher_disagreement_score":0.533166,"about_ca_system_score_codex":0.00003233311,"about_ca_system_score_gemma":0.00017920809,"threshold_uncertainty_score":0.46004984},"labels":[],"label_agreement":null},{"id":"W2135061646","doi":"10.1093/bioinformatics/bts188","title":"NanoStringNorm: an extensible R package for the pre-processing of NanoString mRNA and miRNA data","year":2012,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Molecular Biology Techniques and Applications","field":"Biochemistry, Genetics and Molecular Biology","cited_by":271,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network; University of Toronto; Ontario Institute for Cancer Research","funders":"","keywords":"Computer science; R package; Sample (material); Extensibility; Process (computing); Data mining; Data extraction; Computational science; Programming language","score_opus":0.03881180580201618,"score_gpt":0.31692176082460377,"score_spread":0.2781099550225876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135061646","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5749081,0.004912209,0.41782486,0.00019974167,0.000108375694,0.0010410077,0.00035758203,0.000043726017,0.0006044045],"genre_scores_gemma":[0.94062084,0.00041552237,0.058147665,0.00017475779,0.000100666555,0.00003656453,0.00043462822,0.000013667633,0.000055675384],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99936986,0.000010650059,0.0002372871,0.00011849684,0.000060657658,0.00020302027],"domain_scores_gemma":[0.99898946,0.00001803141,0.00015025988,0.0007214543,0.0000603257,0.00006048304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032787633,0.00010249497,0.00009805567,0.000021424265,0.00014353749,0.000021908118,0.00036199522,0.00011263775,0.0000013863074],"category_scores_gemma":[0.00007303197,0.00007301103,0.000028766264,0.00005659776,0.00010411516,0.000024145615,0.00027977154,0.000048158825,5.130198e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000065960776,0.00012893428,0.0048697605,0.00026985412,0.00008049814,1.09413996e-7,0.00042192964,0.000005993177,0.823822,0.0014840384,0.0043795123,0.16447136],"study_design_scores_gemma":[0.0005058253,0.00031636772,0.0056958613,0.000044291777,0.000110552064,0.000051448795,0.00052009,0.0089399265,0.8598412,0.00010059021,0.12353903,0.00033476288],"about_ca_topic_score_codex":0.0000087749795,"about_ca_topic_score_gemma":0.0000045768084,"teacher_disagreement_score":0.36571276,"about_ca_system_score_codex":0.0000029180987,"about_ca_system_score_gemma":0.000032370364,"threshold_uncertainty_score":0.29773036},"labels":[],"label_agreement":null},{"id":"W2135338058","doi":"10.1093/bioinformatics/bts154","title":"Bayesian integration of networks without gold standards","year":2012,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Biotechnology and Biological Sciences Research Council; Directorate for Biological Sciences","keywords":"Computer science; Bayesian network; Nexus (standard); Data mining; Data integration; Bayesian probability; Reference data; Gold standard (test); Machine learning; Artificial intelligence; Statistics; Mathematics","score_opus":0.008798978695646387,"score_gpt":0.2461073266602108,"score_spread":0.2373083479645644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135338058","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040611226,0.0008185684,0.93358046,0.0000310046,0.000567936,0.0002982934,0.00007651576,0.000022320413,0.023993688],"genre_scores_gemma":[0.97695905,0.00017414981,0.02179351,0.00022382743,0.00034299598,0.0000071291934,0.00020269286,0.000016574799,0.00028006503],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99887514,0.000017346076,0.00050545833,0.000066659704,0.00020464088,0.00033078314],"domain_scores_gemma":[0.99912363,0.000008104255,0.00025671278,0.00034554448,0.0001372494,0.00012875666],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054619735,0.00016249498,0.00018217663,0.00004695601,0.00004410059,0.00002382771,0.00016777028,0.00020463993,0.000021028942],"category_scores_gemma":[0.000045631234,0.00013679244,0.000093675546,0.00009787124,0.000077213146,0.00002346347,0.0000940811,0.00010540193,0.00000677698],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00087320677,0.00068653864,0.04273422,0.0009531377,0.0008922205,8.641544e-7,0.008141727,0.0110618,0.036381867,0.019519698,0.2377738,0.6409809],"study_design_scores_gemma":[0.0030000373,0.0012126333,0.0053869765,0.00027193132,0.00020863695,0.000095959884,0.0029214227,0.63512117,0.05125737,0.00039690852,0.29841796,0.0017089887],"about_ca_topic_score_codex":0.000004438654,"about_ca_topic_score_gemma":0.000008190704,"teacher_disagreement_score":0.93634784,"about_ca_system_score_codex":0.000024105611,"about_ca_system_score_gemma":0.00006411617,"threshold_uncertainty_score":0.55782336},"labels":[],"label_agreement":null},{"id":"W2135511965","doi":"10.1093/bioinformatics/btq023","title":"rMAT - an R/Bioconductor package for analyzing ChIP-chip experiments","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Clinical Research Institute","funders":"","keywords":"Bioconductor; Tiling array; Chromatin immunoprecipitation; DNA microarray; Computer science; Chip; Mac OS; R package; ChIP-on-chip; Histone; Computational biology; Chromatin; ChIP-sequencing; DNA; Biology; Software; Genetics; Computational science; Gene; Operating system; Nucleosome; Gene expression","score_opus":0.01463581004984009,"score_gpt":0.2662241722125298,"score_spread":0.2515883621626897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135511965","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9911471,0.000046498448,0.007110778,0.000025378858,0.00046690236,0.00032904334,0.00012525434,0.000025066633,0.0007239623],"genre_scores_gemma":[0.93936944,0.000021056872,0.058998734,0.00020261283,0.00030338066,0.00003772563,0.00083366304,0.000035379348,0.00019800657],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99906087,0.000009778762,0.00035107872,0.0001744759,0.00009528753,0.00030852054],"domain_scores_gemma":[0.99902934,0.00000798715,0.0001616385,0.00057694543,0.00007357445,0.0001505193],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017648867,0.00019504262,0.00015420905,0.000048041537,0.00014802511,0.00009496399,0.0003204552,0.00019736096,0.000023912791],"category_scores_gemma":[0.00005539932,0.00018184292,0.00010982813,0.000048679227,0.000058471964,0.000017853297,0.000101119316,0.00010464842,0.00001986021],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021462929,0.000067135996,0.0010566222,0.000060908278,0.000045198838,2.9550338e-7,0.0003765629,0.000011530273,0.9948309,0.0006093649,0.00081767194,0.002102324],"study_design_scores_gemma":[0.0016504388,0.00058979157,0.0019151903,0.0000149812395,0.000051280345,0.000034915316,0.0008734274,0.020434385,0.9289477,0.00033764573,0.044332437,0.00081781443],"about_ca_topic_score_codex":0.0000035714543,"about_ca_topic_score_gemma":0.000028744867,"teacher_disagreement_score":0.06588323,"about_ca_system_score_codex":0.00000986007,"about_ca_system_score_gemma":0.000063740896,"threshold_uncertainty_score":0.7415339},"labels":[],"label_agreement":null},{"id":"W2135833397","doi":"10.1093/bioinformatics/16.11.1054","title":"BLAST Search Updater: a notification system for new database matches","year":2000,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Medical Research Council; Natural Sciences and Engineering Research Council of Canada","keywords":"Unix; Computer science; Information retrieval; Database; Software; World Wide Web; Programming language","score_opus":0.02132106413948929,"score_gpt":0.24514800362597097,"score_spread":0.2238269394864817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135833397","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9739667,0.0004928217,0.01950936,0.00028147566,0.00021366958,0.00072828535,0.00049829885,0.000020039048,0.0042893225],"genre_scores_gemma":[0.9500662,0.00033968658,0.045304596,0.00018602358,0.00041042452,0.000041333333,0.0007385097,0.000025260664,0.0028879591],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993123,0.000008711151,0.00025285006,0.00013433276,0.00008420103,0.00020759957],"domain_scores_gemma":[0.999461,0.000009275919,0.000047918653,0.00034766123,0.000054267024,0.000079886006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013426822,0.00011850365,0.00010903485,0.000024373321,0.00010305608,0.000042051717,0.00016862553,0.0000698353,0.000019112073],"category_scores_gemma":[0.000010559865,0.000106866246,0.000058785296,0.000046530753,0.000031723754,0.0000020989796,0.000051510997,0.000028870807,0.00009797409],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000681267,0.00017056677,0.0015347592,0.0016179307,0.0005026683,0.0000016103188,0.0031191357,0.0018277392,0.6572806,0.0016648665,0.083661236,0.24793762],"study_design_scores_gemma":[0.0018440447,0.00042749188,0.0016132465,0.00006666868,0.00008358668,0.000037668073,0.0019804689,0.012898907,0.3908483,0.00004155518,0.58953726,0.0006207932],"about_ca_topic_score_codex":0.00001888321,"about_ca_topic_score_gemma":0.000009596355,"teacher_disagreement_score":0.505876,"about_ca_system_score_codex":0.0000129217815,"about_ca_system_score_gemma":0.00007168249,"threshold_uncertainty_score":0.4357879},"labels":[],"label_agreement":null},{"id":"W2135884466","doi":"10.1093/bioinformatics/btm060","title":"Semantic Web Service provision: a realistic framework for Bioinformatics programmers","year":2007,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Genome Alberta; Genome Canada","keywords":"Computer science; Java; Interoperability; Web service; World Wide Web; Documentation; Software engineering; Semantic Web; Software deployment; Service (business); Programming language","score_opus":0.12229443389299481,"score_gpt":0.3935934427364254,"score_spread":0.27129900884343056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135884466","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0053681987,0.00002731435,0.9803214,0.001432366,0.0020749648,0.0014040091,0.000121191995,0.00027436204,0.008976206],"genre_scores_gemma":[0.071847565,0.0000076571,0.92394,0.0026952226,0.0002663931,0.000032293014,0.00017283557,0.000027923226,0.0010101238],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99448687,0.00003334477,0.0021308549,0.0004153452,0.0020672877,0.00086628855],"domain_scores_gemma":[0.99349517,0.002593352,0.000866488,0.0019059241,0.0007998205,0.0003392311],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0118819745,0.00029616893,0.00040449962,0.00065662473,0.0004993177,0.001381464,0.0017602338,0.00016895925,0.00007018091],"category_scores_gemma":[0.0068769855,0.00021631442,0.00018799101,0.0026513042,0.00012402331,0.0007962255,0.0005924709,0.00020495061,0.0010770013],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009802121,0.00016259155,0.0005449615,0.00054623815,0.000055041193,0.0000064839874,0.0061060158,0.0004998842,0.0000047483927,0.03988447,0.12401285,0.8280787],"study_design_scores_gemma":[0.00051215204,0.00013984388,0.00043670283,0.00013232414,0.00004290553,0.000015859916,0.0095521165,0.72288835,0.000026906702,0.017730447,0.24815911,0.000363286],"about_ca_topic_score_codex":0.000019698637,"about_ca_topic_score_gemma":0.000080939404,"teacher_disagreement_score":0.8277154,"about_ca_system_score_codex":0.00008015728,"about_ca_system_score_gemma":0.0001742949,"threshold_uncertainty_score":0.9997008},"labels":[],"label_agreement":null},{"id":"W2136104033","doi":"10.1093/bioinformatics/btm225","title":"Homology search for genes","year":2007,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"U.S. Public Health Service","keywords":"Gene; Homology (biology); Gene prediction; Genome; Annotation; Gene Annotation; Exon; Genetics; Computational biology; Biology; Computer science; Human genome; Ensembl; Genomics","score_opus":0.01585314769633712,"score_gpt":0.2663310844368851,"score_spread":0.25047793674054797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136104033","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13191244,0.000655515,0.85209495,0.00012215503,0.00051137514,0.00056932087,0.000053890664,0.000031063002,0.014049293],"genre_scores_gemma":[0.76490974,0.00036976524,0.2275815,0.0023453517,0.0013702001,0.00003847488,0.00084233173,0.00006138562,0.0024812205],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989429,0.000006227505,0.00040380596,0.000107023865,0.00009846995,0.00044154923],"domain_scores_gemma":[0.99935335,0.000028721364,0.000088428045,0.00031014835,0.00010714906,0.00011217508],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006687936,0.00013863498,0.00012995777,0.00006318209,0.000118049764,0.000029141496,0.0002207822,0.00021501438,0.0000103388975],"category_scores_gemma":[0.000020078052,0.00012603361,0.00010212397,0.00007273247,0.000082001854,0.0000058846435,0.00010597158,0.000070155,0.000038608418],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00082459877,0.0002119231,0.0041096634,0.00069097016,0.00042431976,0.000005631072,0.0016563773,0.0010694043,0.060461234,0.023835631,0.07670341,0.83000684],"study_design_scores_gemma":[0.0023366082,0.0011620015,0.0012952257,0.000018257175,0.00004704505,0.00014461679,0.001442399,0.021094033,0.15333447,0.00075183436,0.8175195,0.00085401896],"about_ca_topic_score_codex":0.0000028890522,"about_ca_topic_score_gemma":0.000015576004,"teacher_disagreement_score":0.8291528,"about_ca_system_score_codex":0.000013650094,"about_ca_system_score_gemma":0.000063988264,"threshold_uncertainty_score":0.51395017},"labels":[],"label_agreement":null},{"id":"W2136180457","doi":"10.1093/bioinformatics/btr023","title":"PhyloPro: a web-based tool for the generation and visualization of phylogenetic profiles across Eukarya","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"Canadian Institutes of Health Research; Hospital for Sick Children","keywords":"Phylogenetic tree; Visualization; Computer science; Web application; World Wide Web; Data science; Computational biology; Data mining; Biology; Genetics","score_opus":0.029211893887241266,"score_gpt":0.2650650657588872,"score_spread":0.23585317187164595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136180457","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9726521,0.00087113905,0.025535129,0.000019447973,0.000106059524,0.0005739042,0.00010453806,0.0000034680593,0.00013420703],"genre_scores_gemma":[0.9853561,0.00027649553,0.013950383,0.00012937546,0.00009395919,0.00008945789,0.000060333427,0.000012434525,0.000031459647],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994036,0.000012526326,0.00026419736,0.000103243176,0.000070219736,0.0001462231],"domain_scores_gemma":[0.9994837,0.00001733677,0.00014437252,0.00020417474,0.0001293395,0.000021051765],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001888931,0.00011139334,0.00010305943,0.000017046475,0.00013391316,0.000016878419,0.000104905026,0.000072955496,0.0000025464174],"category_scores_gemma":[0.000051063573,0.000080482314,0.000050740644,0.000049474336,0.00010771647,0.0000015114392,0.00006059727,0.000017344202,7.458708e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015493933,0.00010131226,0.02943346,0.00035311555,0.0001882114,1.1119175e-7,0.0028018206,0.00030983533,0.9395008,0.0008057627,0.0012877226,0.02506292],"study_design_scores_gemma":[0.0016607648,0.0008856521,0.04474095,0.000017495138,0.00008967803,0.0000044364087,0.0005748068,0.08282028,0.85955477,0.000095819305,0.009208015,0.0003473109],"about_ca_topic_score_codex":0.0000049792475,"about_ca_topic_score_gemma":0.000014555629,"teacher_disagreement_score":0.08251045,"about_ca_system_score_codex":0.0000034844036,"about_ca_system_score_gemma":0.000048801878,"threshold_uncertainty_score":0.32819733},"labels":[],"label_agreement":null},{"id":"W2136207878","doi":"10.1093/bioinformatics/btu595","title":"BigDataScript: a scripting language for data pipelines","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University and Génome Québec Innovation Centre","funders":"National Institute of Diabetes and Digestive and Kidney Diseases; Canadian Institutes of Health Research; National Institutes of Health; Natural Sciences and Engineering Research Council of Canada; McGill University","keywords":"Computer science; Pipeline transport; Software portability; Serialization; Scripting language; Programming language; Debugging; Robustness (evolution); Python (programming language); Operating system","score_opus":0.03272703732389456,"score_gpt":0.27702773098020317,"score_spread":0.2443006936563086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136207878","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6566678,0.0041486025,0.32422003,0.000640135,0.0017592511,0.0011564974,0.0025959068,0.000045322206,0.008766424],"genre_scores_gemma":[0.7685835,0.00026421555,0.22368729,0.0018787988,0.0013003249,0.000035424637,0.0034450556,0.00004234807,0.0007630861],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99932677,0.000009792899,0.00023649362,0.00015790608,0.00006661859,0.00020243046],"domain_scores_gemma":[0.9990789,0.000017145265,0.00008749848,0.00071496406,0.000055190754,0.00004625356],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031156585,0.00011522218,0.00011560237,0.000023832865,0.00009706368,0.00003772396,0.00040678316,0.000060169823,0.0000020687844],"category_scores_gemma":[0.00031868703,0.00010008174,0.000039139577,0.000035431876,0.000029655586,0.000002219598,0.0003643917,0.000027603413,0.000011929338],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011424383,0.00010189501,0.0029897592,0.0005552256,0.00029297607,5.1613745e-7,0.0015901069,0.00011507696,0.46965817,0.0012801752,0.26522738,0.25807446],"study_design_scores_gemma":[0.0006677944,0.00017882303,0.00034043056,0.00001308849,0.000038722606,0.0000072931107,0.00075078005,0.054962512,0.014684646,0.00007921188,0.9280015,0.00027517337],"about_ca_topic_score_codex":0.000010336485,"about_ca_topic_score_gemma":0.000025792913,"teacher_disagreement_score":0.66277415,"about_ca_system_score_codex":0.0000028885022,"about_ca_system_score_gemma":0.000023544742,"threshold_uncertainty_score":0.40812153},"labels":[],"label_agreement":null},{"id":"W2136265964","doi":"10.1093/bioinformatics/btt613","title":"Mouse model phenotypes provide information about human drug targets","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Drug repositioning; Phenotype; Computational biology; Drug; Identification (biology); Similarity (geometry); Drug development; Drug discovery; Biology; Phenotypic screening; Repurposing; Computer science; Bioinformatics; Genetics; Pharmacology; Artificial intelligence; Gene","score_opus":0.010892537661136478,"score_gpt":0.24047240124778707,"score_spread":0.22957986358665058,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136265964","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9066766,0.0003607554,0.071609326,0.00063545624,0.00023285061,0.00082567584,0.000084116524,0.00023835924,0.019336846],"genre_scores_gemma":[0.88072866,0.000108779335,0.11069623,0.0023493082,0.0001737662,0.00011844824,0.0007876281,0.000024204912,0.0050129485],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990495,0.000012349291,0.0003964109,0.00009045317,0.00017361852,0.0002776875],"domain_scores_gemma":[0.99931777,0.0000070150772,0.00015258878,0.00029982242,0.00011447663,0.00010832904],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012850447,0.00015793068,0.00013276178,0.000055358483,0.00013072533,0.00009294614,0.00024405312,0.00016751465,0.00003027851],"category_scores_gemma":[0.00011709072,0.00012702102,0.00006263519,0.000053133634,0.000118869575,0.00004473508,0.00012834076,0.00009768109,0.0002806815],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059533195,0.00021304222,0.0013171111,0.00072354864,0.00019936214,5.589257e-7,0.0067034233,0.0018450689,0.09248764,0.002009405,0.5479224,0.34651893],"study_design_scores_gemma":[0.0027024138,0.000640244,0.0020567465,0.00008955082,0.00006306006,0.0000148603,0.0032857233,0.275576,0.20493366,0.0021520632,0.5068073,0.0016783639],"about_ca_topic_score_codex":0.000038423703,"about_ca_topic_score_gemma":0.000009690529,"teacher_disagreement_score":0.3448406,"about_ca_system_score_codex":0.000014033566,"about_ca_system_score_gemma":0.000060066955,"threshold_uncertainty_score":0.51797664},"labels":[],"label_agreement":null},{"id":"W2136359150","doi":"10.1093/bioinformatics/btp610","title":"Methods for combining peptide intensities to estimate relative protein abundance","year":2009,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":64,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University and Génome Québec Innovation Centre","funders":"Canadian Institutes of Health Research; Genome Canada; Natural Sciences and Engineering Research Council of Canada; McGill University","keywords":"Intensity (physics); Peptide; Mass spectrometry; Abundance (ecology); Biological system; Detector; Chemistry; Algorithm; Analytical Chemistry (journal); Mathematics; Physics; Biology; Chromatography; Optics","score_opus":0.025978251458796814,"score_gpt":0.37441554503384433,"score_spread":0.3484372935750475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136359150","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0056968485,0.000019443622,0.97716045,0.0006634945,0.000012059354,0.0005832855,0.000026814298,0.000275654,0.01556195],"genre_scores_gemma":[0.013656316,0.000002976176,0.98408777,0.00037708308,0.00002565375,0.0003423321,0.000029589135,0.000014333413,0.0014639576],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992292,0.000004313486,0.000358426,0.000112012465,0.00006691254,0.00022915588],"domain_scores_gemma":[0.99924594,0.00008303844,0.00017032611,0.0002912853,0.00013072265,0.000078715646],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018355655,0.0001430365,0.00018143975,0.000039293718,0.00016252334,0.00004577251,0.00018308409,0.000078092904,0.00001009655],"category_scores_gemma":[0.00021865862,0.0001378087,0.00006143956,0.000099894845,0.00003421107,0.00022870506,0.000045501027,0.00013752627,0.000015463665],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014754794,0.00010684087,0.000027666783,0.0005063085,0.00005120982,8.8379505e-7,0.005508943,0.00069801323,0.2510966,0.4194335,0.0029862477,0.31943622],"study_design_scores_gemma":[0.0003792831,0.00017121133,0.000016387428,0.00033420054,0.000021458534,0.000009804566,0.00063748285,0.08774798,0.70651674,0.14051692,0.06320147,0.00044707194],"about_ca_topic_score_codex":0.0000015845611,"about_ca_topic_score_gemma":5.3017544e-7,"teacher_disagreement_score":0.45542014,"about_ca_system_score_codex":0.00006889203,"about_ca_system_score_gemma":0.000026299213,"threshold_uncertainty_score":0.56196755},"labels":[],"label_agreement":null},{"id":"W2136499634","doi":"10.1093/bioinformatics/bts572","title":"FeatureStack: Perl module for comparative visualization of gene features","year":2012,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; SFU Community Trust Endowment Fund; Simon Fraser University; Michael Smith Health Research BC; Canadian Institutes of Health Research; Western Canada Research Grid","keywords":"Perl; Computer science; Visualization; Programming language; Computational biology; Biology; Artificial intelligence","score_opus":0.03286352512112129,"score_gpt":0.3336641445107511,"score_spread":0.3008006193896298,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136499634","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5905744,0.004857524,0.37200204,0.00032550807,0.0018380623,0.0035049887,0.0010421996,0.00008974834,0.025765557],"genre_scores_gemma":[0.9353391,0.0003352207,0.061073333,0.00026672683,0.00047040568,0.00003941967,0.0014005633,0.000021370377,0.0010538828],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99859565,0.000026871954,0.00046977933,0.00010452714,0.00034660083,0.0004565599],"domain_scores_gemma":[0.99891186,0.00003545008,0.00021044702,0.0003138152,0.00031472198,0.00021368053],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004083261,0.00018518594,0.00023907083,0.000097265554,0.000098086544,0.000029754246,0.00025408537,0.00023954525,0.000012065347],"category_scores_gemma":[0.00022874025,0.00015106938,0.00013078278,0.00013128565,0.00018155666,0.000022081433,0.000097178585,0.000074998985,0.000015905409],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016406742,0.0020662006,0.01725791,0.004539953,0.0011736946,7.290393e-7,0.021549432,0.00051716686,0.4876067,0.01354448,0.3958722,0.054230843],"study_design_scores_gemma":[0.0016692162,0.0011584057,0.01176454,0.0000465972,0.00006476257,0.000020992882,0.002136925,0.008100714,0.8297606,0.000072503906,0.14466694,0.0005378025],"about_ca_topic_score_codex":0.0000041921603,"about_ca_topic_score_gemma":0.000006122698,"teacher_disagreement_score":0.3447647,"about_ca_system_score_codex":0.000013974828,"about_ca_system_score_gemma":0.0000961726,"threshold_uncertainty_score":0.61604303},"labels":[],"label_agreement":null},{"id":"W2137112190","doi":"10.1093/bioinformatics/btm004","title":"SGN Sim, a Stochastic Genetic Networks Simulator","year":2007,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":65,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Set (abstract data type); Gene regulatory network; Stochastic simulation; Master regulator; Translation (biology); Stochastic modelling; Stochastic process; Simulation; Algorithm; Theoretical computer science; Gene; Transcription factor; Genetics; Mathematics; Gene expression; Programming language; Biology; Messenger RNA","score_opus":0.0066315848812003135,"score_gpt":0.2278340997158765,"score_spread":0.2212025148346762,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137112190","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38966602,0.00084336085,0.6084004,0.000014074788,0.00021261591,0.00019867894,0.000004499202,0.000036893263,0.00062342035],"genre_scores_gemma":[0.9880878,0.0000336396,0.010461356,0.00033583594,0.0005806698,0.000005252143,0.000070727016,0.000035082026,0.00038963777],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99841315,0.000019891497,0.0005573303,0.00021501094,0.00024308564,0.000551528],"domain_scores_gemma":[0.99880445,0.000028632136,0.0001919764,0.00063184224,0.00011201545,0.00023106426],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035765613,0.00024915548,0.00021677707,0.00009896496,0.00012335331,0.000041302985,0.00028605803,0.00024936875,0.00003085533],"category_scores_gemma":[0.00006571206,0.00023925136,0.00018228093,0.00027166406,0.000090683665,0.0000061100054,0.00014927449,0.000109017616,0.00006815102],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000084847205,0.00008329745,0.0027139243,0.00003921,0.00025795272,0.0000072397984,0.000120781406,0.9693455,0.002382574,0.00005847092,0.0048222817,0.02008392],"study_design_scores_gemma":[0.00094185915,0.00035699288,0.008397883,0.000025437337,0.0001765771,0.0000577278,0.00023884034,0.96568817,0.0027139361,0.000043586948,0.020595737,0.0007632389],"about_ca_topic_score_codex":0.0000030253004,"about_ca_topic_score_gemma":0.000026107966,"teacher_disagreement_score":0.59842175,"about_ca_system_score_codex":0.000030357347,"about_ca_system_score_gemma":0.00006184615,"threshold_uncertainty_score":0.97563875},"labels":[],"label_agreement":null},{"id":"W2138003801","doi":"10.1093/bioinformatics/bth351","title":"Protein complex prediction via cost-based clustering","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":668,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research; University of Toronto","funders":"National Institute of General Medical Sciences; National Institutes of Health; University of Toronto","keywords":"Cluster analysis; Computer science; Scalability; Data mining; Partition (number theory); Identification (biology); Biological network; Protein function prediction; Caenorhabditis elegans; Computational biology; Protein function; Machine learning; Biology; Mathematics; Genetics","score_opus":0.015073963754215663,"score_gpt":0.22761972047215107,"score_spread":0.2125457567179354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2138003801","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036874175,0.00004687402,0.9569559,0.00019349852,0.00020582006,0.0008047072,0.00007127411,0.000060501323,0.0047872122],"genre_scores_gemma":[0.9034337,0.00001277748,0.09423505,0.0010602069,0.000246778,0.00006489016,0.0007903316,0.000026221831,0.00013003872],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989736,0.000009415706,0.00044027527,0.00011712072,0.000155955,0.00030364154],"domain_scores_gemma":[0.99929565,0.0000031140619,0.0001598446,0.00036160185,0.00006591915,0.00011385174],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001739111,0.00018101135,0.0001337806,0.00005127281,0.00013293892,0.000056008026,0.00019352496,0.00017952874,0.000017752853],"category_scores_gemma":[0.000015742682,0.00017047647,0.00008561479,0.000089186724,0.00006971605,0.000012480778,0.00009735288,0.00010480433,0.00007018661],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00076037337,0.0006673419,0.00081762037,0.0016305655,0.0004466685,0.000011426472,0.0016942811,0.36341426,0.37197933,0.002482502,0.01887151,0.23722413],"study_design_scores_gemma":[0.005308786,0.0010489651,0.0011398268,0.00016835931,0.00004643011,0.0000754146,0.0002920673,0.8001881,0.054375358,0.0007267407,0.13570549,0.0009244187],"about_ca_topic_score_codex":0.000008920393,"about_ca_topic_score_gemma":0.000024520576,"teacher_disagreement_score":0.8665595,"about_ca_system_score_codex":0.000047616046,"about_ca_system_score_gemma":0.0001015658,"threshold_uncertainty_score":0.6951829},"labels":[],"label_agreement":null},{"id":"W2138044641","doi":"10.1093/bioinformatics/btn395","title":"Site-specific evolutionary rates in proteins are better modeled as non-independent and strictly relative","year":2008,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; Canadian Institutes of Health Research; North Carolina State University","keywords":"Bayes' theorem; Prior probability; A priori and a posteriori; Bayesian probability; Statistics; Posterior probability; Mathematics; Maximum a posteriori estimation; Bayes factor; Sequence (biology); Computer science; Algorithm; Biology; Maximum likelihood; Genetics","score_opus":0.008864132810185162,"score_gpt":0.21585627109962052,"score_spread":0.20699213828943536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2138044641","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98876816,0.0006497166,0.007611779,0.000093967064,0.000052299947,0.0004912768,0.000051217587,0.000011788825,0.002269813],"genre_scores_gemma":[0.97898185,0.00066506286,0.019405441,0.00028086378,0.00008060719,0.00003709847,0.00018531289,0.000014416916,0.00034931613],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991568,0.000019254963,0.00028810313,0.00016628826,0.00015507436,0.0002145244],"domain_scores_gemma":[0.9994969,0.000009196572,0.00012886222,0.00023156294,0.00006481208,0.00006870953],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006607177,0.00016728298,0.00015660566,0.00007406337,0.00010473199,0.000016675936,0.000104989434,0.00020657018,0.000007486457],"category_scores_gemma":[0.000028216762,0.00014920141,0.00004560349,0.000099273595,0.000087362474,0.000021914504,0.000118786644,0.0001499942,0.000023463072],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021859736,0.0008955647,0.61340946,0.00094009977,0.00060599163,0.00036922633,0.013139898,0.0055204197,0.31084818,0.006001397,0.027646054,0.018437732],"study_design_scores_gemma":[0.011468597,0.0030169638,0.61819565,0.00043002397,0.000096924174,0.00085311034,0.0027460437,0.16025297,0.1341205,0.012059742,0.052581947,0.00417755],"about_ca_topic_score_codex":0.000015266147,"about_ca_topic_score_gemma":0.000014996657,"teacher_disagreement_score":0.17672767,"about_ca_system_score_codex":0.000031443473,"about_ca_system_score_gemma":0.0000688231,"threshold_uncertainty_score":0.6084257},"labels":[],"label_agreement":null},{"id":"W2138334294","doi":"10.1093/bioinformatics/18.11.1544","title":"Poxvirus Orthologous Clusters (POCs)","year":2002,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":66,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"National Institute of Allergy and Infectious Diseases; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Genome; Computer science; Gene; Computational biology; Interface (matter); Biology; Java; Genetics; Programming language; Operating system","score_opus":0.016935666276901438,"score_gpt":0.21779803493254102,"score_spread":0.20086236865563958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2138334294","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.946039,0.0019786637,0.0015721879,0.00024194247,0.00043472793,0.00022643963,0.000040709212,0.000015371705,0.049450915],"genre_scores_gemma":[0.9890595,0.000955182,0.0072737294,0.0010553822,0.00014858511,0.000010536132,0.00001953765,0.000015464313,0.0014620994],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993247,0.000011095909,0.0002298103,0.000115198214,0.00008732527,0.00023186991],"domain_scores_gemma":[0.999519,0.000006456038,0.000075162025,0.00029509977,0.000039796858,0.00006451696],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007254823,0.00013341849,0.00011183015,0.00003140787,0.00009635902,0.000022892997,0.00015822923,0.00009613855,0.00003842882],"category_scores_gemma":[0.000033134253,0.00011929664,0.00007313125,0.000055009852,0.00006915691,0.0000010131881,0.00012916952,0.000048227383,0.00017317472],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018756062,0.0006346835,0.034270495,0.00041912237,0.0011345486,0.00003961347,0.0075893863,0.0020324257,0.23470706,0.0016105238,0.4029183,0.31445625],"study_design_scores_gemma":[0.0017512265,0.000893524,0.008396599,0.000017415628,0.00007282337,0.0001691416,0.0009911244,0.011426601,0.023253094,0.00014931611,0.9518519,0.0010272076],"about_ca_topic_score_codex":0.0000030788788,"about_ca_topic_score_gemma":0.0000071829645,"teacher_disagreement_score":0.5489336,"about_ca_system_score_codex":0.00000712883,"about_ca_system_score_gemma":0.000009029201,"threshold_uncertainty_score":0.48647755},"labels":[],"label_agreement":null},{"id":"W2138379687","doi":"10.1093/bioinformatics/18.8.1034","title":"Improving gene recognition accuracy by combiningpredictions from two gene-finding programs","year":2002,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Children's & Women's Health Centre of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Exon; Correctness; Computer science; Gene prediction; Gene; Consistency (knowledge bases); Computational biology; Genetics; Data mining; Artificial intelligence; Biology; Algorithm; Genome","score_opus":0.01937588661777488,"score_gpt":0.22736097331829,"score_spread":0.20798508670051513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2138379687","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9756164,0.00040845742,0.021717006,0.000041328884,0.00029661768,0.00026394275,0.00040411678,0.000057628124,0.0011945325],"genre_scores_gemma":[0.9218596,0.00060150574,0.07079334,0.00025774026,0.00031877545,0.00003801478,0.005860368,0.000042813954,0.00022781304],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998946,0.000016773545,0.00041566385,0.00018840324,0.00013801099,0.0002951392],"domain_scores_gemma":[0.9992083,0.000015601523,0.00025546915,0.0003400483,0.000069833965,0.0001107879],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000096955824,0.00018753781,0.00013591012,0.000039208702,0.00019476305,0.00012341511,0.00020909394,0.00015257097,0.000042670126],"category_scores_gemma":[0.00006576238,0.00019585411,0.00009056902,0.00008828236,0.000048010752,0.000018744164,0.00012210416,0.000112133,0.000090708425],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020860667,0.00023968007,0.002713543,0.000065375425,0.00021825537,0.0000028648453,0.000978899,0.00018495922,0.6022373,0.000020260228,0.008742957,0.38457507],"study_design_scores_gemma":[0.003804082,0.000721748,0.00039341938,0.00007363209,0.0001864177,0.00009073711,0.0011210138,0.7455482,0.22136664,0.00033084876,0.02504457,0.00131871],"about_ca_topic_score_codex":0.000050683386,"about_ca_topic_score_gemma":0.000013219183,"teacher_disagreement_score":0.74536324,"about_ca_system_score_codex":0.00003189719,"about_ca_system_score_gemma":0.000022067405,"threshold_uncertainty_score":0.7986699},"labels":[],"label_agreement":null},{"id":"W2138453085","doi":"10.1093/bioinformatics/bts430","title":"Gemma: a resource for the reuse, sharing and meta-analysis of expression profiling data","year":2012,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":158,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institute of General Medical Sciences; Canadian Institutes of Health Research; National Institutes of Health; Michael Smith Health Research BC","keywords":"Computer science; License; Gemma; Profiling (computer programming); Plug-in; Software; World Wide Web; Data science; Database; Information retrieval; Biology; Operating system","score_opus":0.15434453868251755,"score_gpt":0.3402158842362292,"score_spread":0.18587134555371168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2138453085","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34252423,0.040678903,0.60306317,0.0024607647,0.000410055,0.0036483428,0.0016705786,0.00007762246,0.0054663448],"genre_scores_gemma":[0.96166885,0.00018570395,0.036321882,0.0002723377,0.00009573508,0.00008319569,0.0008471676,0.000013234728,0.00051190594],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999406,0.000013519022,0.00024538545,0.000114754,0.00009991208,0.00012044964],"domain_scores_gemma":[0.9985304,0.000033714092,0.00018449053,0.0011675924,0.000042459113,0.000041340612],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004937082,0.00007659453,0.0001767499,0.000049511396,0.00008703265,0.000019341558,0.0004421673,0.00006204421,0.00000977264],"category_scores_gemma":[0.00019604119,0.00004513747,0.00011397944,0.00012412277,0.000035040444,0.000015058578,0.0004853045,0.000031722324,4.8454234e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042607344,0.00027802153,0.010886452,0.0007389361,0.078097895,8.956393e-8,0.0046783625,0.0019277022,0.79007936,0.0023790016,0.10243509,0.008073034],"study_design_scores_gemma":[0.00059117685,0.000089272864,0.001658189,0.000008854529,0.08694382,0.0000032969554,0.0027063175,0.11159178,0.5423403,0.000049051807,0.25363624,0.00038175288],"about_ca_topic_score_codex":0.0000015299933,"about_ca_topic_score_gemma":0.0000012173697,"teacher_disagreement_score":0.6191446,"about_ca_system_score_codex":0.0000026885762,"about_ca_system_score_gemma":0.000013019557,"threshold_uncertainty_score":0.18406527},"labels":[],"label_agreement":null},{"id":"W2138839185","doi":"10.1093/bioinformatics/btt770","title":"Enhanced flowType/RchyOptimyx: a Bioconductor pipeline for discovery in high-dimensional cytometry data","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"National Institute of Biomedical Imaging and Bioengineering; Terry Fox Research Institute; Canadian Institutes of Health Research; Terry Fox Foundation; National Institutes of Health; Michael Smith Health Research BC","keywords":"Bioconductor; Pipeline (software); Flow cytometry; Mass cytometry; Computer science; Throughput; Cytometry; Software; License; Computational biology; Data mining; Biology; Molecular biology; Operating system; Gene","score_opus":0.024644175101572536,"score_gpt":0.2594918384563199,"score_spread":0.23484766335474735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2138839185","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67611676,0.00009372561,0.32224503,0.000080679725,0.000498078,0.00031672843,0.00038256013,0.000017206385,0.00024923185],"genre_scores_gemma":[0.9574892,0.000039704784,0.038066994,0.0005782367,0.00036366473,0.000016911767,0.0030294799,0.000025605807,0.00039023382],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99885505,0.000021713644,0.00043199377,0.0002582573,0.00014141393,0.0002915702],"domain_scores_gemma":[0.9990342,0.00004142363,0.00010225411,0.0006818468,0.00006731339,0.000072941606],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003364261,0.00018564511,0.00021671026,0.00009223511,0.00005582817,0.000051022434,0.0004234328,0.00017485936,0.0000076096208],"category_scores_gemma":[0.00025249532,0.00016350581,0.00006319534,0.00012637922,0.000060667608,0.00003583716,0.0001762487,0.00008848737,0.000016138718],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005979691,0.00034956762,0.0008454526,0.0003642431,0.00007689868,8.3874215e-7,0.0001395215,0.0008261874,0.9652662,0.00047423816,0.008608028,0.022450805],"study_design_scores_gemma":[0.006590775,0.00079315074,0.0012439758,0.00012417525,0.000071351744,0.000012975717,0.000107136344,0.35382104,0.59244007,0.0002167831,0.043493405,0.0010851513],"about_ca_topic_score_codex":0.000026624373,"about_ca_topic_score_gemma":0.00007327747,"teacher_disagreement_score":0.3728262,"about_ca_system_score_codex":0.00001810412,"about_ca_system_score_gemma":0.00008711512,"threshold_uncertainty_score":0.66675735},"labels":[],"label_agreement":null},{"id":"W2139020869","doi":"10.1093/bioinformatics/btq111","title":"Mutual information is critically dependent on prior assumptions: would the <i>correct</i> estimate of mutual information please identify itself?","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mutual information; Computer science; Prior information; Critically ill; Information theory; Econometrics; Statistics; Artificial intelligence; Mathematics; Medicine; Intensive care medicine","score_opus":0.008144480487158157,"score_gpt":0.2617045430190412,"score_spread":0.25356006253188307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139020869","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.817385,0.00016104625,0.13541582,0.0026509594,0.004378808,0.0029840965,0.0015960786,0.00018861228,0.03523959],"genre_scores_gemma":[0.97455674,0.00020965346,0.015097178,0.008212857,0.00032745715,0.00008648986,0.0012783103,0.000029858737,0.00020148109],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974201,0.000030913598,0.00137361,0.00012999865,0.0005771337,0.00046827018],"domain_scores_gemma":[0.9977297,0.00007176369,0.0006323301,0.0008691452,0.0005123431,0.00018471346],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00074696896,0.00034355136,0.0002675156,0.00016806435,0.0003101484,0.00028762792,0.0006203643,0.00061627134,0.00009566323],"category_scores_gemma":[0.0005272509,0.00026425466,0.00019238862,0.00019506615,0.00022369283,0.00026255136,0.00026856398,0.0007321968,0.0006691462],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001636723,0.00073302333,0.002318371,0.0020908571,0.0008422265,0.0000035328935,0.020078294,0.0038851728,0.020721562,0.02938004,0.27002344,0.64828676],"study_design_scores_gemma":[0.006027702,0.0019487249,0.0060659596,0.00028069998,0.00040568726,0.00033369428,0.006408568,0.21784309,0.083458275,0.0014797988,0.6734028,0.0023450206],"about_ca_topic_score_codex":0.00001376359,"about_ca_topic_score_gemma":0.000028098359,"teacher_disagreement_score":0.64594173,"about_ca_system_score_codex":0.00002809218,"about_ca_system_score_gemma":0.00021537201,"threshold_uncertainty_score":0.999981},"labels":[],"label_agreement":null},{"id":"W2139168653","doi":"10.1093/bioinformatics/btt312","title":"NGS++: a library for rapid prototyping of epigenomics software tools","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Ministère du Développement Économique, de l’Innovation et de l’Exportation","keywords":"Computer science; Documentation; Interface (matter); Software; Source code; Application programming interface; File format; Rapid prototyping; Software engineering; World Wide Web; Programming language; Operating system","score_opus":0.013074813625190692,"score_gpt":0.2167227787658998,"score_spread":0.2036479651407091,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139168653","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9694426,0.0024113308,0.020360278,0.0001854272,0.00024816042,0.003989929,0.0009006975,0.000062563304,0.0023989952],"genre_scores_gemma":[0.4984327,0.0021232772,0.49042606,0.0020862445,0.0006408165,0.0011803125,0.0036529151,0.00014918268,0.0013085097],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993183,0.0000066987222,0.00033024582,0.00009777783,0.000055000237,0.00019196296],"domain_scores_gemma":[0.9994094,0.000018961484,0.00015296992,0.00026197504,0.000079026344,0.000077715005],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000051314277,0.00011727754,0.00013496175,0.00003609759,0.00005439043,0.000054782995,0.00019381108,0.00010097995,0.00005053302],"category_scores_gemma":[0.00009195999,0.00010318939,0.00012881313,0.00004610912,0.000043072603,0.00002383823,0.00010227858,0.00002872188,0.00001885239],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004910413,0.000417125,0.0035548937,0.003292003,0.0005121746,0.0000016652002,0.0012092044,0.00016894877,0.053831507,0.0016122301,0.103399396,0.8315098],"study_design_scores_gemma":[0.001961159,0.0011685083,0.0058943867,0.00011284863,0.00007539958,0.00002233565,0.0010282424,0.0045889346,0.21368875,0.0014388544,0.76913345,0.0008871019],"about_ca_topic_score_codex":0.0000017958586,"about_ca_topic_score_gemma":3.0594785e-7,"teacher_disagreement_score":0.83062273,"about_ca_system_score_codex":0.0000041958165,"about_ca_system_score_gemma":0.000120470824,"threshold_uncertainty_score":0.42079413},"labels":[],"label_agreement":null},{"id":"W2139203357","doi":"10.1093/bioinformatics/btu196","title":"Association analysis using next-generation sequence data from publicly available control groups: the robust variance score statistic","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Ontario Ministry of Research and Innovation; European Commission; Epilepsy Research UK; Canadian Institutes of Health Research; National Institute for Health and Care Research; Cancer Research UK; Wellcome Trust; South London and Maudsley NHS Foundation Trust","keywords":"Type I and type II errors; Minor allele frequency; Statistic; Computer science; Confounding; Statistics; Selection (genetic algorithm); Variance (accounting); Allele frequency; Statistical power; Sequence (biology); Data mining; Genotype; Biology; Mathematics; Artificial intelligence; Genetics","score_opus":0.11260539496948144,"score_gpt":0.2841004375756698,"score_spread":0.17149504260618834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139203357","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18664292,0.00021023361,0.8111688,0.00035646354,0.0002226551,0.00018779362,0.0009344523,0.000014666068,0.00026203235],"genre_scores_gemma":[0.90105855,0.00012831553,0.08812085,0.0010529611,0.0005612033,0.00001447424,0.008663012,0.000014932333,0.00038571155],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984289,0.00024654524,0.00052924355,0.0002867225,0.0002085647,0.00030005933],"domain_scores_gemma":[0.99795943,0.00018528776,0.0006034945,0.0009820084,0.00020700182,0.00006279034],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016357938,0.00015236561,0.0002519083,0.000051128667,0.00027197198,0.00017610734,0.000496564,0.00020182342,0.000083553336],"category_scores_gemma":[0.0019354308,0.00012131585,0.00006924122,0.0002812231,0.000044631204,0.00004488865,0.00015004157,0.00010395171,0.000050045954],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004529285,0.00013706299,0.56872433,0.000051720515,0.0048099062,9.489042e-7,0.00044902953,0.2031373,0.04555411,0.0009016495,0.17021264,0.005976024],"study_design_scores_gemma":[0.00030931784,0.000036937912,0.0100040175,0.0000034101354,0.0005180514,0.0000011981704,0.000073529896,0.9819083,0.00006776078,0.00006851034,0.0068523525,0.00015659974],"about_ca_topic_score_codex":0.00049139035,"about_ca_topic_score_gemma":0.00069292734,"teacher_disagreement_score":0.77877104,"about_ca_system_score_codex":0.000077754,"about_ca_system_score_gemma":0.000114578084,"threshold_uncertainty_score":0.49471167},"labels":[],"label_agreement":null},{"id":"W2139249401","doi":"10.1093/bioinformatics/btt673","title":"The International Society of Computational Biology presents: the Great Lakes Bioinformatics Conference, May 16–18, 2014, Cincinnati, Ohio","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Data science; Computational biology; Bioinformatics; Library science; Biology; Computer science","score_opus":0.025539242809749486,"score_gpt":0.2896759633183911,"score_spread":0.2641367205086416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139249401","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33139884,0.002786238,0.30578265,0.05085901,0.0068148645,0.009049064,0.0023884105,0.0002747706,0.29064614],"genre_scores_gemma":[0.86138165,0.012294071,0.096854046,0.006803271,0.0013098167,0.0003302295,0.0045000114,0.00009098524,0.016435897],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974409,0.000051216073,0.0011006799,0.00015946962,0.0007147754,0.0005329904],"domain_scores_gemma":[0.99756473,0.00022122105,0.0004960138,0.0006030326,0.0009430786,0.00017191481],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007998594,0.00027762732,0.00024552745,0.0000742325,0.0003632823,0.0002509855,0.0013656234,0.0002817378,0.00023381144],"category_scores_gemma":[0.0003602727,0.00015504794,0.00024608488,0.00016606074,0.0011534033,0.000048668968,0.00066999026,0.00025762446,0.00022323105],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005054032,0.00009706835,0.0018870282,0.00023623447,0.00048888737,1.4207392e-7,0.0009709166,0.00020404079,0.0019071485,0.0018786034,0.92109984,0.071179576],"study_design_scores_gemma":[0.0016550965,0.0005756903,0.0024484103,0.000057909452,0.000044720455,0.000031521024,0.005045533,0.26853034,0.00819594,0.003754471,0.7091303,0.0005300969],"about_ca_topic_score_codex":0.000038084367,"about_ca_topic_score_gemma":0.000032532418,"teacher_disagreement_score":0.5299828,"about_ca_system_score_codex":0.000047247147,"about_ca_system_score_gemma":0.00038162514,"threshold_uncertainty_score":0.6322671},"labels":[],"label_agreement":null},{"id":"W2139417287","doi":"10.1093/bioinformatics/btg064","title":"Phylogenetic Web Profiler","year":2003,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"","keywords":"Phylogenetic tree; Genome; Annotation; Similarity (geometry); Web server; Biology; Selection (genetic algorithm); Web service; Computer science; Computational biology; World Wide Web; Genetics; Artificial intelligence; The Internet; Gene","score_opus":0.011792514245245885,"score_gpt":0.22211089526825645,"score_spread":0.21031838102301056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139417287","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9422233,0.0019632275,0.0008149972,0.000036475256,0.000328116,0.00027885239,0.000030644722,0.000008377296,0.054316003],"genre_scores_gemma":[0.9826736,0.00033214322,0.015491953,0.00035302492,0.00008318438,0.000023106311,0.00001903269,0.000017013785,0.0010069303],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992886,0.000019524285,0.00022592508,0.00012708745,0.00009455723,0.00024430171],"domain_scores_gemma":[0.9994881,0.0000055909536,0.00006867961,0.000310106,0.00005880212,0.00006869167],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012139548,0.00014370354,0.0001099137,0.000030077601,0.00008531537,0.000014529809,0.00012605873,0.00008873325,0.000026882937],"category_scores_gemma":[0.000061164144,0.00012754106,0.000066825654,0.00006778861,0.00005789061,6.2378683e-7,0.000058338646,0.000041697625,0.00008188807],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005112455,0.00020248113,0.07071716,0.0001895005,0.00039184754,0.0000033217002,0.0006561389,0.00040520466,0.8790758,0.00991296,0.02822892,0.010165488],"study_design_scores_gemma":[0.000981886,0.00037638165,0.009611954,0.000009775141,0.000036397236,0.0000475507,0.00042199733,0.0006033629,0.16089685,0.0002995453,0.82614774,0.0005665543],"about_ca_topic_score_codex":8.250061e-7,"about_ca_topic_score_gemma":0.0000040109067,"teacher_disagreement_score":0.7979188,"about_ca_system_score_codex":0.000006573247,"about_ca_system_score_gemma":0.00008251212,"threshold_uncertainty_score":0.5200974},"labels":[],"label_agreement":null},{"id":"W2139627484","doi":"10.1093/bioinformatics/btp030","title":"IslandViewer: an integrated interface for computational identification and visualization of genomic islands","year":2009,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Salmonella and Campylobacter epidemiology","field":"Agricultural and Biological Sciences","cited_by":392,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"SFU Community Trust Endowment Fund; Canadian Institutes of Health Research; Michael Smith Health Research BC; Genome Canada","keywords":"Upload; Computer science; Graphical user interface; Interface (matter); Visualization; MIT License; License; Source code; Identification (biology); Web service; User interface; Genomics; Data mining; Comparative genomics; Chromosome; Hidden Markov model; Computational biology; Genome; World Wide Web; Biology; Artificial intelligence; Gene; Operating system; Genetics","score_opus":0.026748915155144534,"score_gpt":0.2853578140212567,"score_spread":0.25860889886611216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139627484","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97498,0.00008733203,0.024286669,0.00020674882,0.000051021576,0.00018056785,0.00006489913,0.00002681349,0.00011595664],"genre_scores_gemma":[0.99729085,0.00004687959,0.0018392357,0.00022677197,0.000033420816,0.0000029575701,0.0005283552,3.8509302e-7,0.00003115782],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99943525,0.000026306723,0.00033032714,0.00007393622,0.00004976984,0.00008439207],"domain_scores_gemma":[0.9995893,0.0000911664,0.00016825991,0.000028640421,0.00009156443,0.00003105839],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020912003,0.00006522936,0.00012210102,0.000013740387,0.000051259995,0.000023862935,0.00007733824,0.000058174126,0.00002526115],"category_scores_gemma":[0.00004065251,0.000027628526,0.000025885636,0.0000766655,0.000025638186,0.0001395038,0.000008590488,0.000021181682,0.0000045575002],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019572425,0.00033413986,0.028663319,0.00011481911,0.00004725671,1.6516343e-7,0.004905733,0.00087279093,0.1362846,0.0047680805,0.00617901,0.81763434],"study_design_scores_gemma":[0.0004258436,0.0011971282,0.5344011,0.00002683895,0.00002874073,0.000011945495,0.001186022,0.44776762,0.0016187255,0.005051627,0.008046568,0.00023784327],"about_ca_topic_score_codex":0.0000045219977,"about_ca_topic_score_gemma":0.000010319599,"teacher_disagreement_score":0.8173965,"about_ca_system_score_codex":0.000008025504,"about_ca_system_score_gemma":0.000003184968,"threshold_uncertainty_score":0.11266586},"labels":[],"label_agreement":null},{"id":"W2139856280","doi":"10.1093/bioinformatics/bts392","title":"Fractionation, rearrangement and subgenome dominance","year":2012,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Fractionation; Polyploid; Biology; Gene duplication; Genome; Computer science; Gene; Genetics; Chemistry; Chromatography","score_opus":0.010925370706434448,"score_gpt":0.23500801163734025,"score_spread":0.2240826409309058,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139856280","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96457636,0.0031779131,0.01681772,0.00026613337,0.0004861393,0.00043237477,0.000024865878,0.000029738338,0.014188755],"genre_scores_gemma":[0.9666914,0.00082492357,0.030300833,0.00029237327,0.00038285524,0.000027871756,0.00012736843,0.000015780306,0.0013366408],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994396,0.000009336771,0.00016476966,0.00007003064,0.00011428749,0.00020195686],"domain_scores_gemma":[0.9996265,0.0000044821873,0.00007262181,0.00017158565,0.00004572669,0.00007907739],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019957474,0.00009037541,0.00006726849,0.000036617275,0.000066919856,0.000019863797,0.00006406844,0.00006117195,0.000030236868],"category_scores_gemma":[0.000027770831,0.00008540658,0.000024055942,0.000052487325,0.000034100845,0.000016623708,0.00006607482,0.00003467863,0.00007079688],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020324725,0.00074877293,0.21244152,0.0008086173,0.0006692751,0.0000021750334,0.0076016854,0.00010874373,0.4218367,0.006007081,0.07891098,0.27066118],"study_design_scores_gemma":[0.0007798968,0.0001341798,0.084221795,0.000009852126,0.000028998924,0.000032989963,0.0004894317,0.00048111592,0.015984213,0.000056078647,0.8974363,0.0003451324],"about_ca_topic_score_codex":0.0000025660108,"about_ca_topic_score_gemma":0.0000014861268,"teacher_disagreement_score":0.8185253,"about_ca_system_score_codex":0.000014218639,"about_ca_system_score_gemma":0.00001343113,"threshold_uncertainty_score":0.34827793},"labels":[],"label_agreement":null},{"id":"W2139886875","doi":"10.1093/bioinformatics/btm064","title":"Clustering by common friends finds locally significant proteins mediating modules","year":2007,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada; Ontario Innovation Trust","keywords":"Cluster analysis; Computer science; Precision and recall; Cluster (spacecraft); Domain (mathematical analysis); Computational biology; Function (biology); Cytoplasm; Set (abstract data type); Data mining; Theoretical computer science; Biology; Genetics; Artificial intelligence; Mathematics; Computer network","score_opus":0.008097790721321434,"score_gpt":0.22604835040608212,"score_spread":0.21795055968476068,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139886875","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11862055,0.00033773037,0.8645717,0.00009751275,0.0003470548,0.00052423374,0.00010549894,0.000060990624,0.015334714],"genre_scores_gemma":[0.92386186,0.00010792765,0.07383855,0.00077998545,0.00034160673,0.000018534827,0.0006676673,0.0000388844,0.00034500993],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982382,0.000014314362,0.0007805944,0.00016103737,0.00025014096,0.0005556945],"domain_scores_gemma":[0.9989687,0.00002471727,0.00030171062,0.00043647137,0.0000715134,0.00019688105],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007260708,0.00025538678,0.00021861307,0.00006283212,0.00017574464,0.00008118013,0.00034605726,0.00028880377,0.000013180673],"category_scores_gemma":[0.00003671278,0.00023390293,0.00009590763,0.00012454334,0.00009988437,0.000017663373,0.00024377156,0.00019545916,0.00003056706],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005070717,0.00040401428,0.0040616174,0.0009975674,0.0005572218,0.000019151119,0.0047639534,0.005430913,0.24649489,0.0010355577,0.07362777,0.66210026],"study_design_scores_gemma":[0.0037387214,0.0018341597,0.0018808639,0.00021970317,0.000117480595,0.00010881893,0.0044116033,0.56638783,0.24812971,0.0004308045,0.17008841,0.0026519],"about_ca_topic_score_codex":0.000014921154,"about_ca_topic_score_gemma":0.00004616839,"teacher_disagreement_score":0.8052413,"about_ca_system_score_codex":0.000033406624,"about_ca_system_score_gemma":0.000052698997,"threshold_uncertainty_score":0.95382845},"labels":[],"label_agreement":null},{"id":"W2139909337","doi":"10.1093/bioinformatics/btg191","title":"Greedy method for inferring tandem duplication history","year":2003,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomic variations and chromosomal abnormalities","field":"Biochemistry, Genetics and Molecular Biology","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; City University of Hong Kong","keywords":"Computer science; Gene duplication; Tandem exon duplication; Tandem; Computational biology; Biology; Genetics; Gene; Engineering","score_opus":0.02016407766159523,"score_gpt":0.2511239886199717,"score_spread":0.23095991095837648,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139909337","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045775108,0.00048532238,0.9252919,0.00006330434,0.00039927382,0.00042499762,0.000027034865,0.00003151238,0.02750152],"genre_scores_gemma":[0.5310648,0.00007806319,0.46313393,0.00069015526,0.00018008388,0.00013007695,0.00025169895,0.000026460466,0.0044447156],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99945307,0.000016847142,0.00023326154,0.000089368026,0.000056843262,0.00015062986],"domain_scores_gemma":[0.9995485,0.000012909107,0.0001035684,0.00021428321,0.000077595185,0.000043157044],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023496017,0.00009159208,0.00008300425,0.000030523475,0.000069914575,0.000013780581,0.00008720423,0.0000903976,0.000030301037],"category_scores_gemma":[0.000090939604,0.0000899091,0.00006394052,0.0000273521,0.000018087761,0.000007799739,0.00002208746,0.000030222265,0.000012674718],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015868274,0.0005254798,0.023208326,0.0012523816,0.00076362485,0.0000013845973,0.008614464,0.003786821,0.2598524,0.49953562,0.1559336,0.046367202],"study_design_scores_gemma":[0.00053263747,0.00013291891,0.0006230457,0.0000061398036,0.000026355465,0.000021931384,0.0004356601,0.0043682717,0.033239298,0.000509806,0.959877,0.00022693328],"about_ca_topic_score_codex":0.0000056629056,"about_ca_topic_score_gemma":0.0000066040902,"teacher_disagreement_score":0.8039434,"about_ca_system_score_codex":0.000056049827,"about_ca_system_score_gemma":0.000111115005,"threshold_uncertainty_score":0.36663866},"labels":[],"label_agreement":null},{"id":"W2139911807","doi":"10.1093/bioinformatics/btr372","title":"In-depth annotation of SNPs arising from resequencing projects using NGS-SNP","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic diversity and population structure","field":"Biochemistry, Genetics and Molecular Biology","cited_by":121,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"SNP; Annotation; Single-nucleotide polymorphism; Computational biology; Computer science; Biology; Genetics; Artificial intelligence; Genotype; Gene","score_opus":0.08122098224689127,"score_gpt":0.2782390111609927,"score_spread":0.19701802891410142,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139911807","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9909409,0.000047255326,0.005977897,0.0000051712996,0.00012540467,0.000110519475,0.000022853907,0.0000043272003,0.0027656194],"genre_scores_gemma":[0.9317714,0.000013170591,0.067998044,0.00007622995,0.000037709066,5.578096e-7,0.000072483155,0.000005006359,0.00002540479],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99941355,0.000018690645,0.00025904903,0.000085403975,0.00010745508,0.00011584374],"domain_scores_gemma":[0.99957037,0.0000044449653,0.00016518607,0.00016579522,0.00006517848,0.000029018072],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008980399,0.000080091326,0.000096122945,0.00007199176,0.00003594068,0.000009707844,0.00009985574,0.00011891914,0.000020668409],"category_scores_gemma":[0.000043063683,0.00008026663,0.000033488905,0.00010442543,0.00003588857,0.00001747291,0.0000599878,0.000050753446,0.000003676586],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037692627,0.00014222387,0.3166228,0.00043746608,0.00018805126,0.000014186325,0.0499824,0.0033616205,0.61417806,0.0009530333,0.0013920948,0.012351151],"study_design_scores_gemma":[0.0017030949,0.00029252973,0.16790935,0.00016530756,0.00007598135,0.000022637232,0.008427196,0.015492659,0.8012649,0.0020233688,0.002012944,0.0006100688],"about_ca_topic_score_codex":0.0003315221,"about_ca_topic_score_gemma":0.00006796628,"teacher_disagreement_score":0.18708679,"about_ca_system_score_codex":0.000012757657,"about_ca_system_score_gemma":0.00006201908,"threshold_uncertainty_score":0.32731783},"labels":[],"label_agreement":null},{"id":"W2139993758","doi":"10.1093/bioinformatics/bts484","title":"PRISM: Pair-read informed split-read mapping for base-pair level detection of insertion, deletion and structural variants","year":2012,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":128,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Hospital for Sick Children; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; China Scholarship Council","keywords":"Base (topology); Prism; Computer science; Software; Algorithm; Mathematics; Physics; Optics; Programming language","score_opus":0.03396231251202535,"score_gpt":0.24663264072529348,"score_spread":0.21267032821326814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139993758","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9638235,0.00040752484,0.034957446,0.000043438078,0.0002304569,0.00032366902,0.00006970577,0.0000057646057,0.00013852512],"genre_scores_gemma":[0.96845716,0.00009540328,0.031016259,0.00009358306,0.00012615763,0.000024212273,0.00009940542,0.0000108353115,0.00007699597],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9992152,0.000011962952,0.00036639578,0.00008677109,0.000083520754,0.00023615136],"domain_scores_gemma":[0.9994403,0.00002386507,0.000202931,0.00016738099,0.00009917409,0.00006634037],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019969032,0.00013965396,0.0001464921,0.000053027063,0.00011842725,0.000014677792,0.0000684204,0.00012720673,0.0000024016194],"category_scores_gemma":[0.00012630521,0.0001250449,0.000057462967,0.000057318848,0.00005515036,0.000009302035,0.00006958738,0.000036987774,0.0000015588938],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002397575,0.00006140827,0.044593334,0.00089677126,0.00032372525,9.658376e-8,0.003525487,0.000053501823,0.76957196,0.0003738454,0.000993612,0.1793665],"study_design_scores_gemma":[0.0022562172,0.0007213645,0.6877967,0.000071628034,0.00011286884,0.00005024767,0.0018450995,0.015863074,0.2361807,0.00032962425,0.054093976,0.00067851256],"about_ca_topic_score_codex":0.000018967801,"about_ca_topic_score_gemma":0.0000149504185,"teacher_disagreement_score":0.6432034,"about_ca_system_score_codex":0.000016817328,"about_ca_system_score_gemma":0.000040352672,"threshold_uncertainty_score":0.5099183},"labels":[],"label_agreement":null},{"id":"W2140001356","doi":"10.1093/bioinformatics/btp259","title":"Application and evaluation of automated semantic annotation of gene expression experiments","year":2009,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; National Institutes of Health; Michael Smith Health Research BC","keywords":"Computer science; Unified Medical Language System; Annotation; Natural language processing; Documentation; Information retrieval; Controlled vocabulary; Software; Expression (computer science); Pipeline (software); Context (archaeology); Artificial intelligence; Source code; Programming language","score_opus":0.023997876135531407,"score_gpt":0.326307267117323,"score_spread":0.3023093909817916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140001356","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.978955,0.00040800142,0.02015871,0.000021769883,0.00002331042,0.00015908267,0.000005713944,0.000019182506,0.00024927422],"genre_scores_gemma":[0.9707243,0.000036255013,0.029095061,0.000023846302,0.000011485851,0.0000056569334,0.00009703212,0.0000020517416,0.0000043286695],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99944514,0.000021332915,0.00023646188,0.00006190261,0.00017599677,0.00005913682],"domain_scores_gemma":[0.9995524,0.000005579229,0.00017055872,0.00013175428,0.00011811349,0.00002155098],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023592322,0.00005380949,0.00008322101,0.00003323749,0.000018460722,0.0000033064837,0.00005001254,0.0000868661,0.0000013278946],"category_scores_gemma":[0.00007684234,0.000045208577,0.000016930913,0.000051928844,0.000046984984,0.0000043245213,0.000014158131,0.00001554983,6.542655e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017283854,0.00003535222,0.00033363554,0.00003125377,0.0000069014577,1.7165018e-8,0.0003261479,0.00005715789,0.92248255,0.000011136379,0.00023320857,0.07646535],"study_design_scores_gemma":[0.00046006867,0.00021670952,0.012045289,0.000025374482,0.000018582505,0.0000020651041,0.00025954086,0.10768537,0.8790534,0.0000558829,0.00012233458,0.00005536854],"about_ca_topic_score_codex":0.0000017186709,"about_ca_topic_score_gemma":2.1740624e-7,"teacher_disagreement_score":0.10762821,"about_ca_system_score_codex":0.0000045938464,"about_ca_system_score_gemma":0.000025341657,"threshold_uncertainty_score":0.18435523},"labels":[],"label_agreement":null},{"id":"W2140028978","doi":"10.1093/bioinformatics/btq429","title":"Datamonkey 2010: a suite of phylogenetic analysis tools for evolutionary biology","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1235,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"AIDS Vancouver","funders":"National Institute of Allergy and Infectious Diseases; Canadian Institutes of Health Research","keywords":"Suite; Phylogenetic tree; Biology; Identification (biology); Documentation; Selection (genetic algorithm); Computer science; Evolutionary biology; Computational biology; Data science; Machine learning; Genetics; Gene; Ecology; Geography; Programming language","score_opus":0.018902856069135335,"score_gpt":0.25981028669467615,"score_spread":0.24090743062554082,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140028978","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9787778,0.000521558,0.018060423,0.000057615962,0.0003950534,0.00037587096,0.0010876307,0.0000045192332,0.0007195123],"genre_scores_gemma":[0.94316393,0.00015269459,0.055513762,0.00009509825,0.00014297006,0.000039849598,0.0007543848,0.000011285097,0.00012604053],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9991049,0.0000120320665,0.00040818364,0.00016975563,0.00006761334,0.00023749395],"domain_scores_gemma":[0.9989965,0.000054583805,0.00019695646,0.00051821396,0.00017229906,0.00006145543],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017361455,0.00014919115,0.0002503297,0.0001092182,0.00007754713,0.000016566484,0.00027600155,0.00016720405,0.0000150581955],"category_scores_gemma":[0.00019314933,0.00013401239,0.00020535513,0.00017036822,0.00015745395,0.000002389954,0.00015957937,0.000058580485,0.00000487023],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056065343,0.00006539922,0.03063592,0.000067973146,0.00092677196,9.3644e-8,0.00012477768,0.0001881585,0.9567704,0.0010361596,0.0023702942,0.007757947],"study_design_scores_gemma":[0.00292147,0.0018410466,0.38617894,0.000013323032,0.0018802704,0.000023153527,0.00067214,0.020118019,0.26168233,0.0019519598,0.32128453,0.0014328186],"about_ca_topic_score_codex":0.000016136548,"about_ca_topic_score_gemma":0.000053864507,"teacher_disagreement_score":0.6950881,"about_ca_system_score_codex":0.0000038239186,"about_ca_system_score_gemma":0.0000688798,"threshold_uncertainty_score":0.5464867},"labels":[],"label_agreement":null},{"id":"W2140048165","doi":"10.1093/bioinformatics/bth239","title":"Estimating and comparing the rates of gene discovery and expressed sequence tag (EST) frequencies in EST surveys","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Advanced Research; Dalhousie University","funders":"Genome Atlantic; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research; Alfred P. Sloan Foundation","keywords":"Redundancy (engineering); Sample (material); Sequence (biology); Sample size determination; Computer science; False discovery rate; Gene; Statistics; Biology; Genetics; Mathematics","score_opus":0.03646441197339777,"score_gpt":0.281118808471943,"score_spread":0.2446543964985452,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140048165","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9788576,0.00043392918,0.02022554,0.000072640796,0.000039945546,0.000107318,0.000009834468,0.000004054201,0.00024917652],"genre_scores_gemma":[0.98760116,0.00018192185,0.012090927,0.000044611395,0.000020086023,0.000010158682,0.00003206654,0.0000048104616,0.000014258535],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994485,0.00003286058,0.0002447328,0.000094543124,0.00007703785,0.00010236446],"domain_scores_gemma":[0.99961185,0.000015461266,0.00013126414,0.00018414888,0.00003031573,0.00002696854],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030011105,0.00008418401,0.00010150054,0.000028944385,0.000056366727,0.000047465044,0.000098387296,0.000049924816,4.703363e-7],"category_scores_gemma":[0.000083717525,0.000060712002,0.0000146255925,0.00006901709,0.00013220335,0.00002294211,0.000063175336,0.00004834506,3.776618e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012951257,0.000022122693,0.030855926,0.00013570755,0.000011785169,4.9244545e-7,0.0015618665,0.0041969083,0.96026003,0.00034573424,0.000034324625,0.002562122],"study_design_scores_gemma":[0.0011553523,0.000118940334,0.08527324,0.00019253365,0.000013366272,0.000022488703,0.0023637826,0.03298044,0.87678283,0.00063945644,0.00018161858,0.00027597562],"about_ca_topic_score_codex":0.000098604294,"about_ca_topic_score_gemma":0.00006582488,"teacher_disagreement_score":0.08347725,"about_ca_system_score_codex":0.0000098984465,"about_ca_system_score_gemma":0.00006368423,"threshold_uncertainty_score":0.24757636},"labels":[],"label_agreement":null},{"id":"W2140154634","doi":"10.1093/bioinformatics/btr046","title":"SHRiMP2: Sensitive yet Practical Short Read Mapping","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":365,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Executable; Computer science; Shrimp; Space (punctuation); Sensitivity (control systems); Source code; Code (set theory); Data mining; Programming language; Biology; Operating system; Engineering; Set (abstract data type)","score_opus":0.0499284744864106,"score_gpt":0.2654698643525903,"score_spread":0.21554138986617968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140154634","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8718505,0.00018438525,0.011346815,0.0001088044,0.00043804466,0.0003117165,0.000052699805,0.000016354288,0.115690716],"genre_scores_gemma":[0.9292775,0.00024602588,0.0695459,0.00047187592,0.000119928314,0.00000925669,0.000039498344,0.000015921662,0.00027411256],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992459,0.000017364366,0.00026237027,0.00013441895,0.00009653297,0.00024343276],"domain_scores_gemma":[0.9994694,0.000013219219,0.00006625839,0.00028001048,0.00009109812,0.00008003413],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015659568,0.00014455219,0.00013294084,0.00003284373,0.00008388453,0.000016112352,0.00009326126,0.00011353507,0.000015329111],"category_scores_gemma":[0.00009087575,0.00013034709,0.00006876078,0.000054020016,0.00008217278,0.000002093192,0.00016708634,0.00007029137,0.000051159022],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00080815045,0.00092932815,0.042376094,0.00051273603,0.0026937395,0.00013323134,0.03653371,0.000044876542,0.6844125,0.012430555,0.09276902,0.12635608],"study_design_scores_gemma":[0.0016652058,0.0017912267,0.11700013,0.0000992282,0.00023691537,0.00068853755,0.016560094,0.0036551498,0.40854022,0.0010069014,0.4464517,0.0023046925],"about_ca_topic_score_codex":0.0000092459195,"about_ca_topic_score_gemma":0.000007701881,"teacher_disagreement_score":0.35368267,"about_ca_system_score_codex":0.000008981299,"about_ca_system_score_gemma":0.000059469417,"threshold_uncertainty_score":0.53154004},"labels":[],"label_agreement":null},{"id":"W2140163842","doi":"10.1093/bioinformatics/btu178","title":"rTANDEM, an R/Bioconductor package for MS/MS protein identification","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Bioconductor; R package; Computer science; Pipeline (software); Identification (biology); JavaScript; Interface (matter); Software; Data mining; Operating system; Programming language; Biology","score_opus":0.02169888587174565,"score_gpt":0.28549764496068214,"score_spread":0.26379875908893646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140163842","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16669068,0.000008333807,0.8242201,0.00012806754,0.000029638655,0.00084389583,0.00015271966,0.00038202727,0.0075445105],"genre_scores_gemma":[0.5291407,0.000008643942,0.46692574,0.00011440228,0.00023034346,0.0012470927,0.00055928313,0.000041243133,0.0017325656],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991021,0.000004580157,0.00043044653,0.00014426914,0.00011512687,0.00020346351],"domain_scores_gemma":[0.99889666,0.000027726797,0.0002700674,0.0006194557,0.000097701806,0.00008841322],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019645125,0.00013713111,0.00013566273,0.00003328458,0.00016625067,0.00008293966,0.0002809458,0.00013033887,0.00008576999],"category_scores_gemma":[0.00008823034,0.0001296111,0.000060206286,0.00007034083,0.0000459282,0.00034871633,0.00003407489,0.00009807648,0.000046923262],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001913849,0.00010242547,0.00007015794,0.00051983906,0.000014457022,5.768619e-8,0.0003420857,0.000008639863,0.89526385,0.07545745,0.0011408313,0.027061047],"study_design_scores_gemma":[0.0003170666,0.000042481126,0.000021668542,0.000033354885,0.000013437228,0.0000022371178,0.00009581744,0.020868724,0.8857942,0.01622706,0.076338306,0.00024563776],"about_ca_topic_score_codex":0.0000045885945,"about_ca_topic_score_gemma":0.0000032144187,"teacher_disagreement_score":0.36245003,"about_ca_system_score_codex":0.000044288034,"about_ca_system_score_gemma":0.00002325452,"threshold_uncertainty_score":0.52853876},"labels":[],"label_agreement":null},{"id":"W2140505514","doi":"10.1093/bioinformatics/btt217","title":"A weighted sampling algorithm for the design of RNA sequences with targeted secondary structure and nucleotide distribution","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":60,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University","funders":"","keywords":"Sampling (signal processing); Algorithm; Nucleic acid secondary structure; Nucleotide; Computational biology; RNA; Distribution (mathematics); Computer science; Mathematics; Biology; Combinatorics; Genetics; Gene","score_opus":0.011839337860578933,"score_gpt":0.2168797599005093,"score_spread":0.2050404220399304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140505514","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08498838,0.00036336653,0.91362065,0.00006122426,0.00003992309,0.00066367065,0.00023732753,0.00000709622,0.000018377632],"genre_scores_gemma":[0.50592095,0.00013667587,0.49342918,0.00010008655,0.000059159855,0.00005956162,0.00025306005,0.000012319705,0.000028980312],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994984,0.000018242303,0.00018740818,0.00008114531,0.00008017985,0.00013459084],"domain_scores_gemma":[0.99951774,0.000051156694,0.00014079724,0.00015377348,0.00010116919,0.00003537358],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012338268,0.000106241976,0.0001044706,0.000012510195,0.000108264154,0.000036851,0.00011137371,0.00008516751,0.000021008796],"category_scores_gemma":[0.00003005197,0.00006131324,0.000026799027,0.000044106684,0.00007893571,0.000013770616,0.000028328732,0.000039868006,8.4230123e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006033964,0.000012274276,0.000030101666,0.00012654775,0.00015711055,2.0141853e-7,0.00023710809,0.00014093451,0.61936575,0.00021616645,0.00068312994,0.37897035],"study_design_scores_gemma":[0.0004474674,0.00045792642,0.00026201355,0.00003302944,0.000044561046,0.000018810952,0.00047647604,0.057314597,0.9373306,0.0010328852,0.002396857,0.00018477073],"about_ca_topic_score_codex":0.000012343941,"about_ca_topic_score_gemma":0.0000013015409,"teacher_disagreement_score":0.4209326,"about_ca_system_score_codex":0.000004711512,"about_ca_system_score_gemma":0.0000518374,"threshold_uncertainty_score":0.25002813},"labels":[],"label_agreement":null},{"id":"W2140593394","doi":"10.1093/bioinformatics/btq265","title":"FuncBase : a resource for quantitative gene function annotation","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Institute of Neurological Disorders and Stroke; National Human Genome Research Institute; National Heart, Lung, and Blood Institute","keywords":"Annotation; Function (biology); Gene ontology; Computer science; Resource (disambiguation); Gene Annotation; Web resource; Linkage (software); Gene; Ontology; Computational biology; Focus (optics); Information retrieval; Biology; World Wide Web; Genome; Artificial intelligence; Genetics; Gene expression","score_opus":0.012546597740124498,"score_gpt":0.2442021333390203,"score_spread":0.2316555355988958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140593394","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26708478,0.00014346019,0.72395647,0.00021956504,0.000906611,0.00085397443,0.000195799,0.00005080719,0.0065885372],"genre_scores_gemma":[0.615453,0.000046137746,0.37572733,0.0025414892,0.0010074197,0.0001606692,0.003444428,0.00006379106,0.0015557224],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991403,0.000009293368,0.00036910584,0.00012606032,0.0001079539,0.00024728657],"domain_scores_gemma":[0.9992205,0.00002814361,0.00019427662,0.00032487148,0.00014161097,0.000090587026],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033808575,0.00015294451,0.00011780791,0.000055106702,0.00015417294,0.00005668638,0.00014162571,0.00020297774,0.000012907321],"category_scores_gemma":[0.00010475561,0.0001410791,0.00009867304,0.00008322889,0.000064114356,0.00001528897,0.00005464311,0.00012394923,0.00003487257],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001985414,0.00024892433,0.000511391,0.00050738046,0.0004174481,0.0000010955704,0.0025489193,0.0019693966,0.5631466,0.036528006,0.20145279,0.19068265],"study_design_scores_gemma":[0.0020037405,0.0013311125,0.0006751722,0.000016224181,0.00008216394,0.000027218448,0.0010607142,0.13141985,0.02881852,0.0017238668,0.83222234,0.0006190604],"about_ca_topic_score_codex":0.0000019958172,"about_ca_topic_score_gemma":0.000025473293,"teacher_disagreement_score":0.63076955,"about_ca_system_score_codex":0.0000071072154,"about_ca_system_score_gemma":0.00006602211,"threshold_uncertainty_score":0.57530385},"labels":[],"label_agreement":null},{"id":"W2141010659","doi":"10.1093/bioinformatics/btm570","title":"Automatic synchronization and distribution of biological databases and software over low-bandwidth networks among developing countries","year":2007,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"International Development Research Centre","keywords":"BitTorrent; Download; File Transfer Protocol; Computer science; Distributed database; Software; Bandwidth (computing); Developing country; Database; Synchronization (alternating current); Computer network; The Internet; World Wide Web; Operating system","score_opus":0.014920001751989988,"score_gpt":0.2693107648705665,"score_spread":0.2543907631185765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141010659","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6249876,0.00039596672,0.3742501,0.000018244364,0.000058821453,0.00017315692,0.00007124782,0.000015014361,0.000029866358],"genre_scores_gemma":[0.9783744,0.0036886432,0.016246602,0.0001538891,0.00008135428,0.0000040352847,0.001425831,0.000009189221,0.000016023358],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9987123,0.00001993385,0.0005590263,0.00013578814,0.00023980798,0.00033315166],"domain_scores_gemma":[0.9992288,0.00008558805,0.00019862129,0.00019278526,0.00014934553,0.00014489857],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061254035,0.00016493656,0.00019483233,0.00005961865,0.00012248158,0.000045841738,0.00011429153,0.00020030561,0.000008674207],"category_scores_gemma":[0.0004277944,0.0001304476,0.00003104952,0.00012543087,0.0005594395,0.00002592098,0.00024046416,0.0000827097,0.0000016396096],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031459503,0.00019336809,0.63530785,0.0046622977,0.00030462674,0.000009252509,0.0011966511,0.00014535719,0.0017699607,0.0017454069,0.005230632,0.34911996],"study_design_scores_gemma":[0.0023208598,0.0009951175,0.76811767,0.0006462802,0.00007820208,0.00006326072,0.0011640923,0.1865762,0.020195017,0.00011530935,0.018692994,0.0010349768],"about_ca_topic_score_codex":0.00001279278,"about_ca_topic_score_gemma":0.000035341473,"teacher_disagreement_score":0.3580035,"about_ca_system_score_codex":0.000024546369,"about_ca_system_score_gemma":0.00008417172,"threshold_uncertainty_score":0.5319499},"labels":[],"label_agreement":null},{"id":"W2141010693","doi":"10.1093/bioinformatics/btm217","title":"Bayesian association of haplotypes and non-genetic factors to regulatory and phenotypic variation in human populations","year":2007,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Wellcome Trust; Microsoft Research","keywords":"Biology; Single-nucleotide polymorphism; Haplotype; Genetics; Genetic variation; Genetic association; Phenotype; Copy-number variation; Tag SNP; Quantitative trait locus; Genotype; Gene; Computational biology; Genome","score_opus":0.011397283085800163,"score_gpt":0.2575955666381467,"score_spread":0.24619828355234655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141010693","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97230613,0.00004660147,0.027072664,0.000059540256,0.00005556052,0.00016213914,0.000009826295,0.0000043909417,0.00028314625],"genre_scores_gemma":[0.9797351,0.000018025461,0.02000439,0.000072679664,0.00003233122,0.0000029088342,0.000044226497,0.000007088745,0.0000832449],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99921227,0.000024668627,0.00041433718,0.00010234545,0.000080363156,0.00016603661],"domain_scores_gemma":[0.99952435,0.000030041356,0.00020849505,0.00011916071,0.000056868663,0.00006109969],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049194077,0.00008686297,0.00014283434,0.000112267095,0.000062231404,0.000008648316,0.000046207817,0.0001683023,0.0000024636274],"category_scores_gemma":[0.00022875708,0.00008743548,0.000020883312,0.00010001545,0.000020120451,0.0000063322577,0.000046358728,0.00004198593,7.943155e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006873591,0.000019823614,0.9772715,0.000024277344,0.00001810444,6.4475266e-8,0.000924424,0.00030139406,0.019857835,0.00017572689,0.00017309132,0.0012268651],"study_design_scores_gemma":[0.000224349,0.000098512435,0.9967953,0.000008082754,0.000013201309,5.5167175e-7,0.00021009054,0.0010640598,0.0010616899,0.00029793486,0.00013434289,0.000091910464],"about_ca_topic_score_codex":0.00008060944,"about_ca_topic_score_gemma":0.00052556756,"teacher_disagreement_score":0.019523755,"about_ca_system_score_codex":0.000037044636,"about_ca_system_score_gemma":0.000020380332,"threshold_uncertainty_score":0.35655153},"labels":[],"label_agreement":null},{"id":"W2141014201","doi":"10.1093/bioinformatics/btt182","title":"Predicting the functional consequences of cancer-associated amino acid substitutions","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":282,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Nutrition, Metabolism and Diabetes; Biotechnology and Biological Sciences Research Council; Directorate for Biological Sciences; Medical Research Council; University of Bristol","keywords":"Missense mutation; Computational biology; Computer science; Mutation; Exome; Neutral mutation; Genome; Cancer; Exome sequencing; Genetics; Biology; Gene","score_opus":0.014641703727665044,"score_gpt":0.23337261783227423,"score_spread":0.21873091410460918,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141014201","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9952684,0.00076519616,0.0009155847,0.00034575228,0.0003212652,0.00020682719,0.0001626568,0.000009416993,0.0020048807],"genre_scores_gemma":[0.99833804,0.00045875143,0.00049013813,0.00030826565,0.00010572219,0.00004934677,0.00011555559,0.000005134238,0.00012903176],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99941695,0.000010275999,0.0002571022,0.00006557707,0.000108852095,0.00014122778],"domain_scores_gemma":[0.9994208,0.00003249607,0.000171061,0.00016802683,0.00016800262,0.00003958349],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008704988,0.000080462916,0.00008125212,0.000019184836,0.000123729,0.000029431734,0.00013023085,0.00007232954,0.00006121434],"category_scores_gemma":[0.00019703367,0.00005849775,0.000054342043,0.000078052646,0.00022192863,0.000007246771,0.000059889226,0.00005312451,0.000014378868],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005439361,0.00022815641,0.30993736,0.00016873446,0.00065741036,7.649112e-7,0.0012902285,0.0049112844,0.59911263,0.006245536,0.06416274,0.013230785],"study_design_scores_gemma":[0.001737977,0.0005394507,0.27084053,0.00013185189,0.00022107539,0.000025065998,0.003100872,0.016823934,0.6720494,0.0009783512,0.032855842,0.00069562724],"about_ca_topic_score_codex":0.0004178316,"about_ca_topic_score_gemma":0.00022273212,"teacher_disagreement_score":0.07293682,"about_ca_system_score_codex":0.00002144496,"about_ca_system_score_gemma":0.00020849283,"threshold_uncertainty_score":0.23854691},"labels":[],"label_agreement":null},{"id":"W2141064379","doi":"10.1093/bioinformatics/bts262","title":"Two effective methods for correcting experimental high-throughput screening data","year":2012,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université du Québec à Montréal","funders":"","keywords":"Computer science; Preprocessor; Process (computing); Data mining; Throughput; Systematic error; Error detection and correction; Data pre-processing; Statistics; Algorithm; Artificial intelligence; Mathematics","score_opus":0.09587939461284134,"score_gpt":0.4428652021612223,"score_spread":0.346985807548381,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141064379","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032424761,0.0003192278,0.99281275,0.00006111146,0.0019813604,0.0006278152,0.000025155794,0.00017710951,0.00075298146],"genre_scores_gemma":[0.06860549,0.0000010324618,0.9306645,0.00028520887,0.000282208,0.0000565851,0.00007402754,0.0000146763705,0.000016298578],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99837786,0.00024338125,0.00042437247,0.00023775474,0.00024963883,0.00046698647],"domain_scores_gemma":[0.9961226,0.0025260088,0.00024373185,0.00089176575,0.000078841535,0.0001370733],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029682415,0.00019705325,0.00024019303,0.00010796981,0.0002460779,0.00021794926,0.0012480542,0.000048757876,0.000005256851],"category_scores_gemma":[0.0006141424,0.0001851692,0.00007047397,0.0003196844,0.000042049887,0.0039017394,0.001532477,0.00012634772,0.000024785399],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013059701,0.00008209816,0.000155469,0.000048534064,0.000057975856,2.3783728e-7,0.004357199,0.0032071525,0.00020331179,0.032001607,0.00082269055,0.95905066],"study_design_scores_gemma":[0.00063741737,0.000058826452,0.00055273296,0.000027401906,0.000014947539,0.00003495298,0.00053974474,0.9776395,0.014937623,0.00086986413,0.0044271466,0.00025983286],"about_ca_topic_score_codex":0.00002628187,"about_ca_topic_score_gemma":5.6296375e-7,"teacher_disagreement_score":0.97443235,"about_ca_system_score_codex":0.000088475485,"about_ca_system_score_gemma":0.000059042377,"threshold_uncertainty_score":0.7550981},"labels":[],"label_agreement":null},{"id":"W2141222038","doi":"10.1093/bioinformatics/btn305","title":"FindPeaks 3.1: a tool for identifying areas of enrichment from massively parallel short-read sequencing technology","year":2008,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":270,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency","funders":"Genome British Columbia; Michael Smith Health Research BC; Genome Canada","keywords":"Computer science; Massive parallel sequencing; Software; Java; DNA sequencing; Genomics; Massively parallel; Source code; File format; Genome; Database; Operating system; Biology; DNA; Genetics; Gene","score_opus":0.024781069853669895,"score_gpt":0.25104059722478206,"score_spread":0.22625952737111216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141222038","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8861658,0.00022587505,0.11254501,0.00003986828,0.00011062406,0.00033051896,0.00016229948,0.000018892135,0.00040110268],"genre_scores_gemma":[0.8541085,0.00022841075,0.14487676,0.00007896983,0.00006191545,0.000048624726,0.00041841666,0.000019774781,0.00015863386],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988862,0.000007781993,0.0005395982,0.00017137961,0.00013101468,0.00026397398],"domain_scores_gemma":[0.99917686,0.000018808247,0.00022667841,0.0004008414,0.00012982248,0.00004701804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009935283,0.00017779417,0.00023170268,0.0000857481,0.00011581075,0.000015302701,0.00028080939,0.00023363534,0.000008278516],"category_scores_gemma":[0.000082811835,0.00017424108,0.00012512364,0.000090865,0.00009850815,0.000008648849,0.00015794583,0.00007218698,0.0000057690618],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030754248,0.000324344,0.045574185,0.00080008013,0.0010131118,0.000023819628,0.0036592612,0.0045813518,0.9108207,0.0028284022,0.0054756785,0.024591515],"study_design_scores_gemma":[0.008490362,0.0026155396,0.029322667,0.0005179095,0.0004937681,0.0004815533,0.009138464,0.23549236,0.6620359,0.007560111,0.04020988,0.0036415046],"about_ca_topic_score_codex":0.000010346571,"about_ca_topic_score_gemma":0.000009343149,"teacher_disagreement_score":0.24878484,"about_ca_system_score_codex":0.000048084345,"about_ca_system_score_gemma":0.00015766667,"threshold_uncertainty_score":0.7105345},"labels":[],"label_agreement":null},{"id":"W2141316905","doi":"10.1093/bioinformatics/bts726","title":"G<scp>e</scp>S<scp>to</scp>D<scp>ifferent</scp>: a Cytoscape plugin for the generation and the identification of gene regulatory networks describing a stochastic cell differentiation process","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Institute of General Medical Sciences","keywords":"Identification (biology); Computer science; Gene regulatory network; Plug-in; Computational biology; Systems biology; Biology; Theoretical computer science; Gene; Genetics; Gene expression","score_opus":0.013052161573079488,"score_gpt":0.21098444103755504,"score_spread":0.19793227946447556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141316905","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61882526,0.0014325811,0.37808126,0.00003400552,0.00017747706,0.0013610809,0.000022138847,0.000021203654,0.000045026623],"genre_scores_gemma":[0.9953734,0.00023831187,0.0019621383,0.00016949249,0.0004816985,0.00050656166,0.00052586757,0.000057448637,0.00068505976],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973614,0.00013381877,0.0011203594,0.00040174057,0.00044368883,0.00053899834],"domain_scores_gemma":[0.996879,0.00053233653,0.001006616,0.00087009865,0.00054570386,0.00016624617],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008483384,0.00041143855,0.00042234038,0.00015073596,0.00046437563,0.00028630398,0.00052133395,0.00032200842,0.0000015559635],"category_scores_gemma":[0.0009283048,0.00029076304,0.00025156818,0.0003765902,0.0002059961,0.000058785205,0.00016716798,0.00017280613,0.000010734748],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037300724,0.0003058424,0.0014801002,0.0007490088,0.0012532589,3.1403368e-7,0.012640309,0.38341245,0.55370754,0.0004847651,0.03667578,0.009253314],"study_design_scores_gemma":[0.0011760623,0.00011148927,0.0040025287,0.000038880808,0.00048499048,0.0000073223327,0.002926005,0.84900326,0.1416364,0.000115082265,0.00041520875,0.00008274697],"about_ca_topic_score_codex":0.000010444101,"about_ca_topic_score_gemma":0.000024436607,"teacher_disagreement_score":0.46559083,"about_ca_system_score_codex":0.000042906013,"about_ca_system_score_gemma":0.000098087854,"threshold_uncertainty_score":0.99995446},"labels":[],"label_agreement":null},{"id":"W2141363231","doi":"10.1093/bioinformatics/btq416","title":"OWL2Perl: creating Perl modules from OWL class definitions","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Paul's Hospital","funders":"Natural Sciences and Engineering Research Council of Canada; Genome Canada; Canarie","keywords":"Perl; Computer science; RDF; Class (philosophy); Programming language; World Wide Web; Software; Resource (disambiguation); License; Semantic Web; Software engineering; Artificial intelligence; Operating system","score_opus":0.024532266281811578,"score_gpt":0.25449899228227674,"score_spread":0.22996672600046517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141363231","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96917903,0.0001677508,0.007995066,0.00026415527,0.00047970455,0.00009222009,0.00015830282,0.00008345958,0.02158032],"genre_scores_gemma":[0.8331248,0.0001081092,0.1650572,0.000504079,0.00039627877,0.000016641661,0.00049414206,0.000015974285,0.0002827293],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99921536,0.0000134527445,0.00027054828,0.00013753305,0.00013124579,0.00023185545],"domain_scores_gemma":[0.9993413,0.000046385525,0.00008958242,0.00035861283,0.00005788555,0.000106254076],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011223298,0.00013842071,0.00012992314,0.00003357642,0.00015642741,0.000051181578,0.00022069926,0.00028735722,0.00007214741],"category_scores_gemma":[0.00040707225,0.00011420211,0.00007971929,0.000060668477,0.00019526678,0.0000055181617,0.00011037169,0.00019728801,0.0001032904],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000086976506,0.00034181363,0.00988348,0.00013993405,0.00030503154,0.000009778388,0.0032699897,0.000033976066,0.46263602,0.007827753,0.049658246,0.46580702],"study_design_scores_gemma":[0.0020457956,0.00066940323,0.025206966,0.00010042911,0.000120778335,0.000083059735,0.0056791147,0.022925653,0.11608863,0.0031538655,0.82260114,0.0013251742],"about_ca_topic_score_codex":0.00003245949,"about_ca_topic_score_gemma":0.00009575998,"teacher_disagreement_score":0.7729429,"about_ca_system_score_codex":0.000004918493,"about_ca_system_score_gemma":0.000052157135,"threshold_uncertainty_score":0.46570268},"labels":[],"label_agreement":null},{"id":"W2141415922","doi":"10.1093/bioinformatics/btr017","title":"Computational refinement of post-translational modifications predicted from tandem mass spectrometry","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"Ontario Ministry of Research and Innovation; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Computer science; Cluster analysis; Database search engine; Noise (video); Tandem mass spectrometry; Posttranslational modification; Proteome; Data mining; Algorithm; Artificial intelligence; Pattern recognition (psychology); Bioinformatics; Mass spectrometry; Search engine; Chemistry; Biology","score_opus":0.02368803982480069,"score_gpt":0.2529056610913337,"score_spread":0.22921762126653303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141415922","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051434454,0.000025894813,0.9069249,0.00010580894,0.000016170057,0.00016347096,0.00162357,0.00015021228,0.039555494],"genre_scores_gemma":[0.35671455,0.00001290468,0.64223874,0.00002960149,0.000020587584,0.000034794517,0.00088440423,0.000007840981,0.00005660785],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990735,0.000002964342,0.0004995302,0.00009706695,0.00020977546,0.00011714944],"domain_scores_gemma":[0.99921495,0.000048280213,0.00025217654,0.00026428656,0.0001665799,0.000053753465],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000044764474,0.00010535026,0.00012269604,0.00006369161,0.000072325005,0.000008646281,0.00019567586,0.00008321649,0.0011699124],"category_scores_gemma":[0.000017111826,0.0001057807,0.00005826614,0.0001405844,0.00006572972,0.000121560835,0.000024394829,0.00010582574,0.000016149368],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002757956,0.002047196,0.033019695,0.0007399924,0.0008706704,0.0000030324263,0.0125452755,0.0068006706,0.37067404,0.55195534,0.00344276,0.017625486],"study_design_scores_gemma":[0.0019747016,0.00013441933,0.024542479,0.0001749526,0.00017859048,0.000009999882,0.0015227938,0.31423402,0.3956272,0.25643927,0.004247343,0.0009142714],"about_ca_topic_score_codex":0.00002729106,"about_ca_topic_score_gemma":0.0000017776631,"teacher_disagreement_score":0.30743334,"about_ca_system_score_codex":0.000031917978,"about_ca_system_score_gemma":0.000060549013,"threshold_uncertainty_score":0.99974316},"labels":[],"label_agreement":null},{"id":"W2141462396","doi":"10.1093/bioinformatics/btm629","title":"A hybrid model for robust detection of transcription factor binding sites","year":2008,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"University of Toronto; Ontario Genomics Institute; Genome Canada","keywords":"Transcription factor; Computer science; Factor (programming language); DNA binding site; Binding site; Computational biology; Biology; Genetics; Promoter; Gene; Programming language; Gene expression","score_opus":0.02511979486837297,"score_gpt":0.21658238976924557,"score_spread":0.19146259490087258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141462396","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62008256,0.000030958472,0.37950355,0.0000042295233,0.00004379357,0.00013047247,0.0001407414,0.000006812608,0.00005686083],"genre_scores_gemma":[0.95491534,0.00014167099,0.044451274,0.000024826757,0.000036770118,0.000011619233,0.00024659524,0.000013592879,0.00015829907],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99941915,0.0000041669773,0.00027966005,0.000082637176,0.00007403797,0.00014036782],"domain_scores_gemma":[0.99959415,0.000005144436,0.00013387666,0.00015500456,0.000074848685,0.00003698304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000053666477,0.000101657446,0.00011004045,0.00004648481,0.00008835526,0.000008663454,0.00009054081,0.00007972265,0.0000016670876],"category_scores_gemma":[0.000023576074,0.00009988222,0.00010298587,0.0000313173,0.000035252677,0.000008245096,0.000019354238,0.000032710115,0.0000021639871],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003601187,0.000029084016,0.00011983112,0.00013704425,0.000027680682,1.1206148e-7,0.00038616292,0.011389448,0.98603374,0.00001873308,0.00014109828,0.001681036],"study_design_scores_gemma":[0.0003260172,0.00012784069,0.00009991142,0.000005698933,0.000010627286,0.00001462598,0.000056170426,0.74413913,0.25489077,0.000024897141,0.0002007608,0.00010357518],"about_ca_topic_score_codex":0.0000016688468,"about_ca_topic_score_gemma":0.000007730948,"teacher_disagreement_score":0.73274964,"about_ca_system_score_codex":0.000015723439,"about_ca_system_score_gemma":0.000043070486,"threshold_uncertainty_score":0.4073079},"labels":[],"label_agreement":null},{"id":"W2141629057","doi":"10.1093/bioinformatics/btl030","title":"Efficient estimation of graphlet frequency distributions in protein–protein interaction networks","year":2006,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":137,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Ontario Institute for Cancer Research; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Heuristics; Scalability; Heuristic; Computer science; Biological network; Software; Algorithm; Theoretical computer science; Artificial intelligence; Mathematics","score_opus":0.005303035860545529,"score_gpt":0.21728683723952533,"score_spread":0.2119838013789798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141629057","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.64836144,0.00012916839,0.34867412,0.000037165257,0.000096970456,0.0004958018,0.000044508175,0.000013410488,0.0021474268],"genre_scores_gemma":[0.9787393,0.0000069639123,0.020376176,0.000018207476,0.000070840346,0.000042453164,0.00068767875,0.000009829186,0.000048559905],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987863,0.000020992939,0.0007093691,0.00010610189,0.00012732863,0.00024994745],"domain_scores_gemma":[0.99928296,0.0000070888827,0.00031692337,0.00028139798,0.00007095039,0.00004067559],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023843236,0.00015514204,0.00015777138,0.000097024706,0.00006143951,0.0000277931,0.00014095506,0.00018356308,0.000008564265],"category_scores_gemma":[0.000030099683,0.00014808956,0.0000859948,0.00022712185,0.000075861826,0.000010515338,0.00006351959,0.00012983258,0.000007598035],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001314646,0.00047778923,0.0010563364,0.00037217332,0.000062713116,0.0000020910477,0.00021913325,0.90405905,0.04267135,0.028043434,0.0019644487,0.020939993],"study_design_scores_gemma":[0.0006771012,0.00017848733,0.0015453246,0.0001440051,0.000013099114,0.000009009855,0.000119486685,0.98022,0.01475383,0.0014320128,0.000623905,0.00028374276],"about_ca_topic_score_codex":0.00007755327,"about_ca_topic_score_gemma":0.000058254136,"teacher_disagreement_score":0.33037788,"about_ca_system_score_codex":0.000037589576,"about_ca_system_score_gemma":0.000046952795,"threshold_uncertainty_score":0.60389173},"labels":[],"label_agreement":null},{"id":"W2142027180","doi":"10.1093/bioinformatics/bts716","title":"SCARPA: scaffolding reads with practical algorithms","year":2012,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":69,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; University of Toronto","keywords":"Scaffold; Contig; Computer science; Algorithm; Heuristic; Process (computing); Genome; Biology; Artificial intelligence; Programming language; Genetics","score_opus":0.021609353128708805,"score_gpt":0.2760012413538531,"score_spread":0.2543918882251443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142027180","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7777434,0.0013853833,0.1630442,0.0006407886,0.0010062525,0.0011563167,0.000052333657,0.00017451837,0.054796834],"genre_scores_gemma":[0.63254124,0.00016357609,0.36497253,0.00029368798,0.0008176852,0.000034240777,0.0001925581,0.00004952505,0.0009349442],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988878,0.000020395528,0.00023865391,0.000119161945,0.00025675836,0.00047727255],"domain_scores_gemma":[0.99924093,0.000011565291,0.000116292555,0.0003617461,0.00007755056,0.00019192061],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000312186,0.00017993314,0.00013456609,0.00005433242,0.000090142894,0.000045934656,0.00012787363,0.00012817173,0.00003230295],"category_scores_gemma":[0.00005146603,0.00014266037,0.000053463922,0.00012586763,0.00007214023,0.00003238073,0.000117281255,0.00008393248,0.00015136386],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011280233,0.0034423512,0.25608456,0.0018032527,0.0036725271,0.00006845351,0.011055846,0.0006894957,0.22395438,0.009257323,0.19975731,0.2890865],"study_design_scores_gemma":[0.00445413,0.0021639676,0.017048873,0.00013332463,0.00039043181,0.0014315028,0.004736749,0.012098815,0.15227202,0.000045505833,0.80272204,0.0025026302],"about_ca_topic_score_codex":0.0000029078203,"about_ca_topic_score_gemma":0.0000015055513,"teacher_disagreement_score":0.60296476,"about_ca_system_score_codex":0.000024542538,"about_ca_system_score_gemma":0.00006431904,"threshold_uncertainty_score":0.5817521},"labels":[],"label_agreement":null},{"id":"W2142280055","doi":"10.1093/bioinformatics/btt710","title":"ChromoHub V2: cancer genomics","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Protein Degradation and Inhibitors","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Structural Genomics Consortium; University of Toronto","funders":"Ministero dello Sviluppo Economico; Ontario Ministry of Economic Development and Innovation; Ontario Genomics Institute; Canadian Institutes of Health Research; Ontario Genomics; Genome Canada; Wellcome Trust; Eli Lilly Canada; GlaxoSmithKline; Pfizer; Eli Lilly and Company","keywords":"Chromatin; Genomics; Epigenetics; Histone; Computational biology; Biology; Genome; Cancer; Chromatin remodeling; Genetics; Gene","score_opus":0.008853294606747695,"score_gpt":0.229220323251506,"score_spread":0.2203670286447583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142280055","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9627424,0.0007504146,0.0058731697,0.00080009375,0.0006085951,0.00066675287,0.000041520838,0.000056588255,0.028460499],"genre_scores_gemma":[0.95646405,0.0011327876,0.027994849,0.004334094,0.00093474094,0.00021969326,0.00036400743,0.0000478326,0.008507934],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99947447,0.0000070223996,0.00019952327,0.00007773157,0.00008146575,0.00015979518],"domain_scores_gemma":[0.999564,0.0000021520257,0.000075658565,0.00021928799,0.00006631509,0.000072597926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000048437,0.00009367688,0.000069262016,0.000025446405,0.000052819483,0.00004504428,0.00013253311,0.00009127314,0.0002528446],"category_scores_gemma":[0.000026462661,0.000081302,0.000044767174,0.000048161546,0.000037478083,0.00001130033,0.00006872349,0.000044920853,0.00037106988],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001642726,0.00007320631,0.0019063092,0.00011112785,0.000101801204,5.330092e-7,0.00039062885,0.000076845434,0.4686484,0.0006451112,0.42238253,0.105647095],"study_design_scores_gemma":[0.00038337457,0.000094190116,0.0012769714,0.000012261694,0.000007756982,0.000006863481,0.00015896048,0.0034932387,0.3288261,0.00006609242,0.6654099,0.00026428798],"about_ca_topic_score_codex":0.000036319536,"about_ca_topic_score_gemma":0.000008280322,"teacher_disagreement_score":0.24302737,"about_ca_system_score_codex":0.000018869448,"about_ca_system_score_gemma":0.00006780973,"threshold_uncertainty_score":0.47694764},"labels":[],"label_agreement":null},{"id":"W2142295792","doi":"10.1093/bioinformatics/btu522","title":"Individual-level analysis of differential expression of genes and pathways for personalized medicine","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":138,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Normalization (sociology); Gene; Personalized medicine; Population; Computational biology; Biology; Computer science; Bioinformatics; Genetics; Medicine","score_opus":0.04343514193106566,"score_gpt":0.27577847301456077,"score_spread":0.2323433310834951,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142295792","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76654536,0.0003381793,0.23236112,0.000034820525,0.00006802537,0.00015111238,0.00014951527,0.0000042056467,0.00034764872],"genre_scores_gemma":[0.99256057,0.00018199379,0.00665244,0.000043247655,0.000046563455,0.000013681693,0.00041793028,0.000005014446,0.00007854945],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99938464,0.000019139374,0.00030160285,0.00008786981,0.00013264547,0.00007409307],"domain_scores_gemma":[0.99939823,0.000020784828,0.00025520727,0.00018985737,0.00009522768,0.00004066682],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014909952,0.000077744764,0.00020423804,0.00011807436,0.00002940967,0.000004077227,0.000096369884,0.00008122767,0.000016677011],"category_scores_gemma":[0.00007501833,0.00005722548,0.00007404778,0.000105441744,0.00009316032,0.0000033740953,0.000047508944,0.000016202637,1.0425999e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060423554,0.000020688922,0.0012976385,0.00012099362,0.000120283876,4.1376915e-9,0.00053958,0.00001394907,0.98534423,0.0006616986,0.0008063634,0.0110141495],"study_design_scores_gemma":[0.0014866238,0.00034238308,0.015668415,0.00004900832,0.00050365226,4.83509e-7,0.0006839117,0.009469842,0.96399486,0.000104623636,0.0075623607,0.00013382046],"about_ca_topic_score_codex":0.0000021386693,"about_ca_topic_score_gemma":0.000001846654,"teacher_disagreement_score":0.22601521,"about_ca_system_score_codex":0.000002045454,"about_ca_system_score_gemma":0.000017472597,"threshold_uncertainty_score":0.23335874},"labels":[],"label_agreement":null},{"id":"W2142319534","doi":"10.1093/bioinformatics/btg072","title":"Using multiple interdependencyto separate functional from phylogenetic correlations in protein alignments","year":2003,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":126,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Ontario Institute for Cancer Research","funders":"","keywords":"Phylogenetic tree; Multiple sequence alignment; Sequence (biology); Computational biology; Substitution (logic); Cluster analysis; Biology; Sequence alignment; Phylogenetics; Protein superfamily; Protein sequencing; Evolutionary biology; Computer science; Genetics; Peptide sequence; Artificial intelligence; Gene","score_opus":0.019866193769249967,"score_gpt":0.2498401684537612,"score_spread":0.22997397468451122,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142319534","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8674704,0.00014077536,0.13017339,0.0000055092282,0.00016764365,0.00033183998,0.000058815174,0.000008151942,0.0016434944],"genre_scores_gemma":[0.95950866,0.000008229603,0.03993274,0.00009138406,0.000043379318,0.00002086448,0.00021834813,0.000011641648,0.0001647394],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999207,0.000034748435,0.00030416093,0.00013906462,0.00012625901,0.00018873953],"domain_scores_gemma":[0.999573,0.0000077755385,0.00010193408,0.00022752635,0.000037210473,0.00005253623],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000083440944,0.00013692134,0.00010457494,0.00005089685,0.000061751976,0.000023391549,0.00009268369,0.0001480481,0.000033457658],"category_scores_gemma":[0.0000791136,0.00013411907,0.000047016638,0.000088184745,0.000033976477,0.000010296712,0.0000503165,0.00008255563,0.000022986955],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021902163,0.00021383355,0.10993671,0.00007648563,0.00020009685,0.000009226059,0.0007123331,0.031080317,0.8512227,0.0012471962,0.0005345694,0.004547509],"study_design_scores_gemma":[0.00695093,0.0004845764,0.028376656,0.00019659466,0.00009524093,0.00009611433,0.0011707499,0.43266675,0.5034802,0.0077427216,0.01694269,0.0017967973],"about_ca_topic_score_codex":0.000031323874,"about_ca_topic_score_gemma":0.00010125801,"teacher_disagreement_score":0.4015864,"about_ca_system_score_codex":0.00003483987,"about_ca_system_score_gemma":0.000093310264,"threshold_uncertainty_score":0.5469217},"labels":[],"label_agreement":null},{"id":"W2142963728","doi":"10.1093/bioinformatics/btt602","title":"Exploring high dimensional data with Butterfly: a novel classification algorithm based on discrete dynamical systems","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; University Health Network","funders":"Government of Ontario; Eli Lilly Canada; University Health Network; Natural Sciences and Engineering Research Council of Canada; Ottawa Hospital Research Institute; Ontario Institute for Cancer Research; Eli Lilly and Company","keywords":"Computer science; Cluster analysis; Representation (politics); Set (abstract data type); Univariate; Dynamical systems theory; Visualization; Algorithm; Artificial intelligence; External Data Representation; Pattern recognition (psychology); Data mining; Machine learning; Multivariate statistics","score_opus":0.09020328266180674,"score_gpt":0.2489412473830473,"score_spread":0.15873796472124055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142963728","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005074134,0.000003261535,0.9923884,0.0015903136,0.00018973777,0.00040224876,0.000058223904,0.00013805604,0.00015561738],"genre_scores_gemma":[0.52488977,0.000003266848,0.47412884,0.00040169418,0.00008901251,0.00017987209,0.0002676105,0.000010614241,0.000029306986],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99883497,0.000012277272,0.00030553114,0.00023857172,0.00037863434,0.00023004685],"domain_scores_gemma":[0.9983134,0.00009709791,0.00014767403,0.0012520915,0.0000749985,0.00011471383],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011426306,0.00014453978,0.00012857141,0.00006352768,0.00015020807,0.00034273692,0.000894906,0.00003584333,0.000003284105],"category_scores_gemma":[0.0000068920062,0.00009971956,0.000018457617,0.00027941813,0.00003948871,0.0015822474,0.0002287697,0.00012779434,0.00013865091],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030204046,0.00083330664,0.0003694001,0.0002926992,0.00011481557,0.0000075875787,0.00044195435,0.13524532,0.0010492813,0.31574252,0.014677291,0.53119564],"study_design_scores_gemma":[0.00024073648,0.000062314015,0.0019783443,0.000061574065,0.000005234124,0.000007350255,0.000027791932,0.9966363,0.00002026958,0.00004270864,0.0007621841,0.00015524254],"about_ca_topic_score_codex":0.00005383507,"about_ca_topic_score_gemma":0.0000012564429,"teacher_disagreement_score":0.86139095,"about_ca_system_score_codex":0.000037814454,"about_ca_system_score_gemma":0.000042439326,"threshold_uncertainty_score":0.40664455},"labels":[],"label_agreement":null},{"id":"W2143093088","doi":"10.1093/bioinformatics/btp378","title":"ISOLATE: a computational strategy for identifying the primary origin of cancers using high-throughput sequencing","year":2009,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Cancer Diagnosis and Treatment","field":"Medicine","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computational biology; Biology; Profiling (computer programming); Sample size determination; Gene expression profiling; Computer science; Gene; Machine learning; Artificial intelligence; Gene expression; Genetics; Statistics; Mathematics","score_opus":0.09569313300894752,"score_gpt":0.35252440953347447,"score_spread":0.256831276524527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143093088","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90981275,0.0008766053,0.08567131,0.00069337804,0.0002843234,0.0013395849,0.0001070496,0.000048612535,0.0011663587],"genre_scores_gemma":[0.9269885,0.00006707738,0.07206396,0.0007043493,0.00008348381,0.000012678016,0.000053519692,0.0000072868124,0.000019166937],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991828,0.000005492888,0.00037984306,0.00007120184,0.00020220953,0.0001584388],"domain_scores_gemma":[0.9994364,0.00007531999,0.00019850228,0.00013766567,0.00011027607,0.00004187303],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000115907234,0.000102155136,0.00021758693,0.000049545062,0.00009834449,0.00002846557,0.00005317491,0.00003811009,0.00001160481],"category_scores_gemma":[0.0000109908715,0.000069694936,0.00008574812,0.00012794789,0.000039223578,0.00015089725,0.000010745069,0.000057030065,0.0000019934573],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011970357,0.00078355364,0.00671238,0.007389808,0.0020818592,0.00004538242,0.02401248,0.6122601,0.005947854,0.055174213,0.013418231,0.2709771],"study_design_scores_gemma":[0.008369695,0.0019783687,0.04408246,0.0016249391,0.0010828848,0.00018799062,0.0048330897,0.9244944,0.004485838,0.0069614886,0.0013876371,0.0005112335],"about_ca_topic_score_codex":0.00027039403,"about_ca_topic_score_gemma":0.000014899924,"teacher_disagreement_score":0.31223428,"about_ca_system_score_codex":0.00067587814,"about_ca_system_score_gemma":0.0006229456,"threshold_uncertainty_score":0.2842077},"labels":[],"label_agreement":null},{"id":"W2143124024","doi":"10.1093/bioinformatics/btn416","title":"ZOOM! Zillions of oligos mapped","year":2008,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":211,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Western University","funders":"National Human Genome Research Institute","keywords":"Zoom; Computer science; Reference genome; Human genome; Software; Sequence assembly; Computational biology; Genome; DNA sequencing; Biology; Genetics; Gene; Operating system; Transcriptome","score_opus":0.016696739985166367,"score_gpt":0.2223268851516874,"score_spread":0.205630145166521,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143124024","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98245174,0.00043865424,0.0019485126,0.000042318563,0.00016541244,0.00012179909,0.000044548076,0.0000038097278,0.014783232],"genre_scores_gemma":[0.9869395,0.0009788556,0.011320262,0.00012273286,0.00006640693,0.00000578071,0.00002630283,0.000008101834,0.0005320539],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994702,0.0000063124057,0.00024094689,0.000067184075,0.000078362325,0.00013703796],"domain_scores_gemma":[0.9995613,0.000005850286,0.00008927804,0.00023627352,0.00006538839,0.000041923046],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00004851145,0.000088997855,0.0001143906,0.000030740077,0.00007278309,0.000002880812,0.000119748365,0.00006435472,0.000006319687],"category_scores_gemma":[0.000027636592,0.00007900243,0.000069580965,0.000058878486,0.0000970716,6.0747806e-7,0.00009183719,0.000027139133,0.000018465724],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000940063,0.00023414326,0.031008024,0.00022732506,0.00043216505,0.0000047486715,0.0031808037,0.00043444516,0.9055952,0.0014262551,0.048227437,0.009135494],"study_design_scores_gemma":[0.0016269095,0.00085578795,0.048405483,0.000027629187,0.000057614776,0.0001499109,0.0010288199,0.001472065,0.5165744,0.00022379185,0.42884833,0.0007292491],"about_ca_topic_score_codex":0.0000054430575,"about_ca_topic_score_gemma":0.0000027673334,"teacher_disagreement_score":0.38902074,"about_ca_system_score_codex":0.0000032573007,"about_ca_system_score_gemma":0.000045325396,"threshold_uncertainty_score":0.32216254},"labels":[],"label_agreement":null},{"id":"W2143227538","doi":"10.1093/bioinformatics/btq637","title":"Differential effects of chromatin regulators and transcription factors on gene regulation: a nucleosomal perspective","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Nucleosome; Chromatin; Biology; Gene; Transcription factor; Promoter; Transcriptional regulation; Genetics; Regulation of gene expression; Saccharomyces cerevisiae; Computational biology; Transcription (linguistics); Histone; Gene expression","score_opus":0.0034549751453332596,"score_gpt":0.1960566982394446,"score_spread":0.19260172309411133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143227538","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99761367,0.000020340352,0.0013767414,0.000024683255,0.0002717195,0.00021741263,0.000027100046,0.000012229661,0.00043611575],"genre_scores_gemma":[0.99543256,0.000024128543,0.004272798,0.00002094502,0.00008761761,0.000004373241,0.000089248664,0.000015940905,0.000052414638],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999338,0.0000125466095,0.00025124932,0.0001326566,0.00012772346,0.00013786185],"domain_scores_gemma":[0.99944454,0.000013771676,0.00014971543,0.0002579315,0.00006639014,0.00006764646],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000034845878,0.0001563953,0.00015127372,0.000054144697,0.00007079533,0.000023933997,0.00009851488,0.00017441431,0.000013633016],"category_scores_gemma":[0.000044314704,0.00013756579,0.0000747834,0.000047484067,0.00010106038,0.000007827692,0.00003794423,0.0000899845,0.000001875001],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029484443,0.00005281669,0.0006679811,0.00009988209,0.000043124714,2.0294246e-7,0.0008560379,0.000017620032,0.9948526,0.00272453,0.000051670217,0.0006040588],"study_design_scores_gemma":[0.0009309311,0.0005679417,0.09171818,0.000026964586,0.00004481845,0.000012397955,0.0004394149,0.008853252,0.8965574,0.00039167533,0.00020093819,0.0002561111],"about_ca_topic_score_codex":0.000007170622,"about_ca_topic_score_gemma":0.000012992803,"teacher_disagreement_score":0.09829522,"about_ca_system_score_codex":0.000012160078,"about_ca_system_score_gemma":0.000027622355,"threshold_uncertainty_score":0.560977},"labels":[],"label_agreement":null},{"id":"W2143438047","doi":"10.1093/bioinformatics/btr224","title":"Mapping ancestral genomes with massive gene loss: A matrix sandwich problem","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Agence Nationale de la Recherche","keywords":"Genome; Extant taxon; Biology; Gene; Computational biology; Heuristic; Gene duplication; Genetics; Evolutionary biology; Computer science; Artificial intelligence","score_opus":0.018437889191453578,"score_gpt":0.22572372873115842,"score_spread":0.20728583953970484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143438047","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9335054,0.0014743154,0.04149363,0.00008038468,0.00015321784,0.0010278737,0.000073917545,0.00008211629,0.022109134],"genre_scores_gemma":[0.52021426,0.0005174914,0.47737506,0.00013622905,0.00020684983,0.00006410352,0.00020885398,0.000043841424,0.0012333015],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989671,0.000013070092,0.0003026802,0.00017426875,0.00017327421,0.00036958585],"domain_scores_gemma":[0.99929076,0.0000027013205,0.00017428592,0.00033446978,0.00009346853,0.00010431813],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011512796,0.00020769575,0.00016116191,0.000075764314,0.00007806101,0.000035204146,0.00024447267,0.00011184525,0.000051846826],"category_scores_gemma":[0.000005489391,0.00016630536,0.00005955572,0.00014281501,0.00008992968,0.000015053424,0.00010284193,0.000074813914,0.00007417513],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018828328,0.0017832131,0.3622558,0.0050473143,0.0056174034,0.00042255307,0.06463186,0.0014479343,0.4001594,0.0021648323,0.017068543,0.13751833],"study_design_scores_gemma":[0.016830094,0.008751523,0.0751034,0.0005506192,0.00053032534,0.0014603918,0.02086022,0.009898743,0.5904527,0.0015138335,0.26694795,0.0071002427],"about_ca_topic_score_codex":0.000007953504,"about_ca_topic_score_gemma":0.0000063067987,"teacher_disagreement_score":0.43588144,"about_ca_system_score_codex":0.000019992718,"about_ca_system_score_gemma":0.00009162502,"threshold_uncertainty_score":0.67817354},"labels":[],"label_agreement":null},{"id":"W2143693563","doi":"10.1093/bioinformatics/btu373","title":"Mirsynergy: detecting synergistic miRNA regulatory modules by overlapping neighbourhood expansion","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"MicroRNA in disease regulation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":84,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bioconductor; microRNA; Computational biology; Cluster analysis; Computer science; Biology; Gene regulatory network; Gene; Gene expression; Machine learning; Genetics","score_opus":0.006147777979144508,"score_gpt":0.21085898556060106,"score_spread":0.20471120758145656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143693563","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9167828,0.0003845323,0.08018164,0.00003223805,0.00020884008,0.00016211536,0.000021587537,0.000059247363,0.0021669893],"genre_scores_gemma":[0.99233145,0.000028964578,0.0067360746,0.00019918647,0.00021586496,0.000012431209,0.00025163635,0.0000338443,0.00019054797],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987725,0.00004805873,0.00042325413,0.00021527294,0.00022679614,0.0003141452],"domain_scores_gemma":[0.99896795,0.00002398401,0.00024796964,0.0005402348,0.000081775754,0.00013808941],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024470603,0.00021898694,0.00016976336,0.00006238691,0.00016440255,0.000059173806,0.00020369147,0.00019788579,0.000022504026],"category_scores_gemma":[0.00025642835,0.00021780818,0.000104354775,0.00009287289,0.00006406028,0.00001867707,0.0001219291,0.00007953163,0.00003252946],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002666215,0.00003607233,0.00023071574,0.00014012896,0.000045411507,3.674281e-7,0.00008110305,0.0006754969,0.96877366,0.0002897829,0.005286642,0.024413934],"study_design_scores_gemma":[0.0015666808,0.00031141448,0.010449349,0.00022790841,0.00009613446,0.000030373862,0.0003256638,0.15849024,0.7749834,0.00034390166,0.052034937,0.0011399698],"about_ca_topic_score_codex":0.000010164731,"about_ca_topic_score_gemma":0.000005609724,"teacher_disagreement_score":0.19379026,"about_ca_system_score_codex":0.000040326646,"about_ca_system_score_gemma":0.00004219492,"threshold_uncertainty_score":0.88819593},"labels":[],"label_agreement":null},{"id":"W2143801201","doi":"10.1093/bioinformatics/btn463","title":"Improving subcellular localization prediction using text classification and the gene ontology","year":2008,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; University of Alberta","keywords":"Gene ontology; Computer science; Hierarchy; Mechanism (biology); Protein function prediction; Ontology; Function (biology); Artificial intelligence; Data mining; Sequence (biology); Protein sequencing; Information retrieval; Natural language processing; Computational biology; Machine learning; Gene; Protein function; Biology; Peptide sequence; Genetics; Gene expression","score_opus":0.015766448245103544,"score_gpt":0.22927907549808127,"score_spread":0.21351262725297773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143801201","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40834475,0.00030311185,0.58964294,0.00009061704,0.00017216132,0.00033781017,0.000010782267,0.000035763755,0.0010621059],"genre_scores_gemma":[0.96609634,0.0003938427,0.032461878,0.00041788947,0.00016858953,0.000012218487,0.00028883672,0.000018986117,0.00014140499],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990371,0.00006193342,0.00044230086,0.0001147339,0.00015793268,0.00018602004],"domain_scores_gemma":[0.9992217,0.000021464248,0.00028506425,0.00032591764,0.00009459635,0.000051302304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035353593,0.00014250122,0.00013421338,0.000053723466,0.00036219475,0.000034267377,0.00013702697,0.00017440296,0.000004565366],"category_scores_gemma":[0.00022436386,0.000106062966,0.0000469305,0.0000998403,0.00031662572,0.00002212711,0.0000998583,0.00011643777,0.000008673292],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025376985,0.00048182163,0.3202045,0.0026078175,0.0009923095,0.000017529781,0.032975454,0.08160797,0.430546,0.01989461,0.013243782,0.09489053],"study_design_scores_gemma":[0.0010291048,0.00007759335,0.0025348058,0.000007467267,0.00003193764,0.00027382324,0.00024430195,0.98707515,0.0038304338,0.00002212465,0.004739525,0.00013372685],"about_ca_topic_score_codex":0.000034257904,"about_ca_topic_score_gemma":0.000006019415,"teacher_disagreement_score":0.9054672,"about_ca_system_score_codex":0.000025099796,"about_ca_system_score_gemma":0.000068434056,"threshold_uncertainty_score":0.43251222},"labels":[],"label_agreement":null},{"id":"W2143859503","doi":"10.1093/bioinformatics/btr100","title":"Human variation database: an open-source database template for genomic discovery","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"BC Cancer Agency","funders":"Genome British Columbia; Michael Smith Health Research BC; Genome Canada","keywords":"Computer science; Database; Database schema; Java; Source code; Application programming interface; Pooling; Software; Interface (matter); Database application; Graphical user interface; Modular design; Open source; Database testing; Information retrieval; Database design; Operating system","score_opus":0.03992812043407963,"score_gpt":0.28016559752281417,"score_spread":0.24023747708873455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143859503","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8744603,0.00014634285,0.1199495,0.000012508313,0.0002238497,0.0008876567,0.0024688658,0.000026922926,0.0018240846],"genre_scores_gemma":[0.90316284,0.000107708474,0.08012196,0.00065900903,0.00030511638,0.00009666862,0.01432711,0.00006475061,0.00115485],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991381,0.000017939643,0.00032414438,0.0002131949,0.0000733952,0.0002332264],"domain_scores_gemma":[0.99895394,0.000005004266,0.0001760776,0.00068388693,0.000059135094,0.00012194711],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022648796,0.00016049146,0.00012823867,0.000042387488,0.00021379141,0.00015215974,0.0005563412,0.00008154804,0.00002553164],"category_scores_gemma":[0.000030090514,0.00014835189,0.00005247263,0.00003888995,0.000039454644,0.00008284981,0.00043849432,0.000041338273,0.00001625341],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006063889,0.00092390936,0.0011469026,0.00048722234,0.0003042106,0.000007346491,0.002018788,0.00012346971,0.9549376,0.006340959,0.029136058,0.0039671925],"study_design_scores_gemma":[0.014353838,0.0064449115,0.054431032,0.0002449362,0.0009020664,0.00022463752,0.0049703154,0.025515677,0.21890876,0.0017590243,0.6670933,0.0051515466],"about_ca_topic_score_codex":0.000099077886,"about_ca_topic_score_gemma":0.000052620228,"teacher_disagreement_score":0.7360288,"about_ca_system_score_codex":0.000013570016,"about_ca_system_score_gemma":0.00009846591,"threshold_uncertainty_score":0.6049614},"labels":[],"label_agreement":null},{"id":"W2144015117","doi":"10.1093/bioinformatics/btu277","title":"Deep learning of the tissue-regulated splicing code","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"RNA Research and Splicing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":487,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Canadian Institute for Advanced Research","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Computer science; Context (archaeology); Artificial intelligence; RNA splicing; Deep learning; Source code; Machine learning; Alternative splicing; Hyperparameter; Computational biology; Graphics processing unit; Biology; Gene; RNA; Genetics; Exon","score_opus":0.008313087259342699,"score_gpt":0.25031227657918176,"score_spread":0.24199918931983905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144015117","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9640225,0.00007323049,0.0314331,0.00007266258,0.000059269187,0.00011986989,0.00000159763,0.000010623407,0.0042071533],"genre_scores_gemma":[0.9955649,0.000028881059,0.00230406,0.00009367936,0.00005432748,0.0000022700726,0.000016630236,0.0000097298325,0.0019255171],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993294,0.0000388907,0.00021607534,0.00006761872,0.00015714271,0.0001908882],"domain_scores_gemma":[0.9994767,0.000015109032,0.00011020901,0.00028286153,0.00006528315,0.000049853148],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025458788,0.00007746069,0.00009368925,0.000023927176,0.00010143624,0.000016527494,0.00022069932,0.00007481412,0.000008387356],"category_scores_gemma":[0.00024911057,0.000053181524,0.000050077306,0.000091245114,0.000066096465,0.000004063669,0.00013755736,0.000092848364,0.0000129214795],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023057262,0.000015496365,0.004054567,0.00010104327,0.00003276238,1.4526567e-7,0.00022506637,0.0032996135,0.94123995,0.00047940068,0.0005907729,0.04993813],"study_design_scores_gemma":[0.00047173814,0.0002684475,0.00509589,0.000047446796,0.000012260127,0.000011749663,0.0002420307,0.23901033,0.7099431,0.000032751555,0.044704527,0.0001597149],"about_ca_topic_score_codex":0.000014363974,"about_ca_topic_score_gemma":0.000016380474,"teacher_disagreement_score":0.23571071,"about_ca_system_score_codex":0.0000064109217,"about_ca_system_score_gemma":0.000022469463,"threshold_uncertainty_score":0.21686795},"labels":[],"label_agreement":null},{"id":"W2144222696","doi":"10.1093/bioinformatics/btu346","title":"CLImAT: accurate detection of copy number alteration and loss of heterozygosity in impure and aneuploid tumor samples using whole-genome sequencing data","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":55,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"BC Cancer Agency; National Natural Science Foundation of China","keywords":"Loss of heterozygosity; Biology; Genome; Aneuploidy; Genetics; Computational biology; Whole genome sequencing; DNA sequencing; Ploidy; Normalization (sociology); Copy-number variation; Allele; Gene; Chromosome","score_opus":0.02941690551158587,"score_gpt":0.27309311595221203,"score_spread":0.24367621044062615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144222696","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9800642,0.000119017444,0.019312399,0.000007575276,0.00004257434,0.00011467408,0.0003129373,0.000002257842,0.000024324636],"genre_scores_gemma":[0.9921122,0.00026324423,0.007270898,0.00005374452,0.00004174603,0.0000011897251,0.00024877218,0.000007187832,9.989313e-7],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993613,0.000018153043,0.00033366962,0.0001183659,0.00006033009,0.00010821821],"domain_scores_gemma":[0.99940664,0.000025688543,0.00021260208,0.00026831232,0.00005113315,0.000035605488],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022039803,0.00009056243,0.00015035208,0.000034231874,0.000035942936,0.000025517558,0.00008839763,0.00006232888,9.14314e-7],"category_scores_gemma":[0.000100628975,0.000090955844,0.000014348741,0.000048181024,0.00006925012,0.0000240341,0.00018958775,0.00004192053,4.0278175e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006449478,0.000017679266,0.027850898,0.00040050907,0.000018470291,6.595956e-7,0.00037331888,0.0008820555,0.96870655,0.000032261873,0.0000075610974,0.0016455248],"study_design_scores_gemma":[0.0025585392,0.00066185015,0.033512913,0.00021245006,0.00011226897,0.00028580075,0.0008680612,0.38509163,0.5723467,0.00025100732,0.003423807,0.0006749862],"about_ca_topic_score_codex":0.00011472378,"about_ca_topic_score_gemma":0.00015478536,"teacher_disagreement_score":0.39635986,"about_ca_system_score_codex":0.00001816239,"about_ca_system_score_gemma":0.00004516729,"threshold_uncertainty_score":0.37090716},"labels":[],"label_agreement":null},{"id":"W2144514889","doi":"10.1093/bioinformatics/btl125","title":"Dragon Promoter Mapper (DPM): a Bayesian framework for modelling promoter structures","year":2006,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Promoter; Enhancer; Motif (music); Computational biology; Sequence motif; Gene; Bayesian probability; Computer science; Biology; Genetics; Artificial intelligence; Transcription factor; Gene expression; Physics","score_opus":0.007655762186004872,"score_gpt":0.22247093817564653,"score_spread":0.21481517598964167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144514889","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25368747,0.00008478384,0.7445284,0.000102250204,0.00015458454,0.0004957023,0.00007859942,0.000022766586,0.0008454256],"genre_scores_gemma":[0.546045,0.000014823005,0.45260116,0.00019310552,0.0003273053,0.0000355904,0.00041052484,0.000036623172,0.0003358383],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889135,0.000009739014,0.00041326828,0.00019738669,0.00012591768,0.00036234065],"domain_scores_gemma":[0.99928147,0.000010235205,0.0001631138,0.0003985351,0.00008287786,0.000063788866],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000114781134,0.00022746008,0.00016941961,0.000046347075,0.00012698659,0.00010235659,0.00022467604,0.00030009315,0.0000123659765],"category_scores_gemma":[0.000018422592,0.00020088443,0.00013610399,0.00005435402,0.00004746019,0.000009084562,0.00008327394,0.00009987958,0.000007914778],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013522337,0.0017444204,0.005932717,0.0077363257,0.0014749033,0.000022857494,0.008294619,0.3388706,0.22567101,0.2759624,0.054883774,0.0780541],"study_design_scores_gemma":[0.00093681173,0.0004102707,0.00023083879,0.00006525856,0.00005797946,0.000038920945,0.00020751996,0.86385936,0.029023679,0.071639426,0.03273133,0.0007985906],"about_ca_topic_score_codex":0.000008499754,"about_ca_topic_score_gemma":0.000008562669,"teacher_disagreement_score":0.5249888,"about_ca_system_score_codex":0.000020565838,"about_ca_system_score_gemma":0.000056938778,"threshold_uncertainty_score":0.81918293},"labels":[],"label_agreement":null},{"id":"W2144629166","doi":"10.1093/bioinformatics/bts078","title":"WaVPeak: picking NMR peaks through wavelet-based smoothing and volume-based filtering","year":2012,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":64,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Hong Kong University of Science and Technology; York University; King Abdullah University of Science and Technology; Renmin University of China; National Natural Science Foundation of China; Fundamental Research Funds for the Central Universities; University of Toronto","keywords":"Smoothing; Wavelet; Filter (signal processing); Computer science; False positive paradox; Benchmark (surveying); Maxima and minima; Noise (video); Spectral line; Volume (thermodynamics); Artificial intelligence; Nuclear magnetic resonance; Pattern recognition (psychology); Algorithm; Biological system; Mathematics; Physics; Computer vision","score_opus":0.01111331327904974,"score_gpt":0.23334582484257474,"score_spread":0.222232511563525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144629166","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5072881,0.0010296853,0.48592913,0.00016901395,0.00035543522,0.00035401815,0.000046787445,0.00007375633,0.0047540613],"genre_scores_gemma":[0.8477874,0.000024859852,0.15047693,0.0012125418,0.00021574029,0.000010266417,0.00015909606,0.00002349771,0.00008969831],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99899966,0.000020232406,0.0002928761,0.00013034449,0.000149092,0.0004077922],"domain_scores_gemma":[0.99935365,0.000014037657,0.00013771967,0.00034273954,0.000044245677,0.00010759295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019384651,0.0002046037,0.00015592779,0.000038806018,0.0001517025,0.00006454174,0.00014783356,0.00018810286,0.000014028612],"category_scores_gemma":[0.000075224234,0.0001876807,0.00007048435,0.00006665803,0.00007907434,0.000031236992,0.00011108797,0.00012262574,0.000011667295],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00070799905,0.0005880112,0.12617017,0.005692367,0.0006757928,0.00002650682,0.012346669,0.0044973693,0.46104184,0.005404865,0.013151732,0.36969665],"study_design_scores_gemma":[0.004475442,0.00078043767,0.016584285,0.00035317108,0.00018022137,0.0001186791,0.0010056649,0.26947603,0.3146729,0.0002777128,0.3895262,0.0025493056],"about_ca_topic_score_codex":0.000012600303,"about_ca_topic_score_gemma":0.0000048824822,"teacher_disagreement_score":0.37637445,"about_ca_system_score_codex":0.000021692398,"about_ca_system_score_gemma":0.00006415525,"threshold_uncertainty_score":0.7653397},"labels":[],"label_agreement":null},{"id":"W2145023212","doi":"10.1093/bioinformatics/btr657","title":"Prediction and analysis of nucleotide-binding residues using sequence and sequence-derived structural descriptors","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":137,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Killam Trusts","keywords":"Sequence (biology); Computational biology; Sequence alignment; Peptide sequence; Sequence analysis; Nucleotide; Multiple sequence alignment; Protein sequencing; Binding site; Sequence logo; Sequence motif; Consensus sequence; Conserved sequence; Biology; Biochemistry; Gene","score_opus":0.05324823264434206,"score_gpt":0.2742169801333416,"score_spread":0.22096874748899956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145023212","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9951564,0.000065370514,0.0038995817,0.0000040375653,0.000068000954,0.00012467563,0.00010655221,0.000020376241,0.00055498554],"genre_scores_gemma":[0.90818727,0.00010924884,0.09148451,0.000035469155,0.000017338847,0.0000014359931,0.00013748025,0.000010261431,0.000016979408],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99903136,0.000029656658,0.00047586122,0.00012724273,0.00014559571,0.00019029343],"domain_scores_gemma":[0.9992514,0.000011941692,0.00032664166,0.00024309166,0.00008375175,0.0000831293],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021302488,0.00016317883,0.00022687568,0.00020388722,0.00012038138,0.000034204444,0.0001214308,0.00013137118,0.000014111852],"category_scores_gemma":[0.00012372782,0.0001471214,0.000057821417,0.00024022136,0.00023692475,0.00004445947,0.00014227416,0.00009225012,6.7198397e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010380045,0.0000166267,0.5978204,0.00047109104,0.0010786871,0.0000019930364,0.0114404205,0.00074318924,0.3825969,0.00045104307,0.000060939004,0.0052148863],"study_design_scores_gemma":[0.0006273041,0.00047076706,0.14926386,0.00009826153,0.0010318557,0.00008415028,0.0029735654,0.75660604,0.08804028,0.0000994066,0.00016391497,0.0005406129],"about_ca_topic_score_codex":0.000073199895,"about_ca_topic_score_gemma":0.00001735336,"teacher_disagreement_score":0.75586283,"about_ca_system_score_codex":0.000017842445,"about_ca_system_score_gemma":0.0000381757,"threshold_uncertainty_score":0.5999437},"labels":[],"label_agreement":null},{"id":"W2145258109","doi":"10.1093/bioinformatics/btg134","title":"Genescript: DNA sequence annotation pipeline","year":2003,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children","funders":"","keywords":"Annotation; Pipeline (software); Computer science; Sequence (biology); Download; DNA sequencing; Computational biology; DNA; Sequence analysis; Information retrieval; Data mining; Artificial intelligence; World Wide Web; Genetics; Programming language; Biology","score_opus":0.022625402548178693,"score_gpt":0.24450245365557152,"score_spread":0.22187705110739284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145258109","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96306837,0.001034576,0.014164769,0.00007939039,0.0004485476,0.00022417553,0.000048043912,0.000009739595,0.020922393],"genre_scores_gemma":[0.9771232,0.0004024279,0.021003144,0.0005394592,0.000089562294,0.000011137498,0.000061405386,0.0000123619175,0.000757313],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993855,0.000016429498,0.00022900621,0.000105209685,0.00008543836,0.00017842316],"domain_scores_gemma":[0.9995519,0.000004704529,0.00007701697,0.00023002614,0.00008482176,0.000051516585],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013239733,0.000114407754,0.00008823645,0.000024671992,0.00008200054,0.000021430944,0.0000960945,0.00006983484,0.000009428963],"category_scores_gemma":[0.000083539686,0.00010536165,0.000046817808,0.00006453854,0.000044603876,0.00000139566,0.00003544128,0.000031485888,0.000037351354],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024890109,0.000062922445,0.0044957884,0.00008053688,0.00007741228,0.0000018988327,0.0007079695,0.0004020987,0.9606608,0.0030763838,0.015459335,0.014949952],"study_design_scores_gemma":[0.00077843614,0.00024972283,0.0023025752,0.000011194265,0.000032665233,0.000052974763,0.0007372288,0.0026896815,0.35846287,0.000555887,0.63362104,0.0005057409],"about_ca_topic_score_codex":0.0000024944175,"about_ca_topic_score_gemma":0.000005619257,"teacher_disagreement_score":0.6181617,"about_ca_system_score_codex":0.000008771324,"about_ca_system_score_gemma":0.0000547109,"threshold_uncertainty_score":0.42965233},"labels":[],"label_agreement":null},{"id":"W2145433078","doi":"10.1093/bioinformatics/btm169","title":"Polyploids, genome halving and phylogeny","year":2007,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Chromosomal and Genetic Variations","field":"Agricultural and Biological Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Genome; Polyploid; Ploidy; Phylogenetics; Biology; Evolutionary biology; Genomics; Genome evolution; Computational biology; Genetics; Gene","score_opus":0.014016557060256464,"score_gpt":0.20459001863550538,"score_spread":0.19057346157524893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145433078","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99324286,0.00015574248,0.00015658724,0.00023546335,0.000059181813,0.00008120021,0.000021062886,0.00004103983,0.0060068327],"genre_scores_gemma":[0.99620676,0.000034470053,0.0031611256,0.00027125655,0.00015108165,0.0000010301981,0.00002490583,3.186015e-7,0.00014902849],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9995146,0.0000036797528,0.00016732913,0.000056768597,0.000087117296,0.00017053031],"domain_scores_gemma":[0.9997673,0.000059548565,0.00004488338,0.000027933074,0.00002062495,0.00007973591],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014489399,0.00006275497,0.00006171654,0.0000077848135,0.00014628678,0.00003966672,0.00007420814,0.00004363168,0.00011447254],"category_scores_gemma":[0.000018362187,0.00002340391,0.000024241916,0.00012272096,0.000025746387,0.00006810817,0.000050023747,0.00003712321,0.000049008228],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013011936,0.00007391968,0.020320386,0.000027882616,0.000026642203,0.0000042042475,0.0015877489,0.0000045759753,0.5087308,0.004028751,0.00016952754,0.4650125],"study_design_scores_gemma":[0.000107727006,0.000106148844,0.946014,0.0000066431217,0.00000886778,0.00002860776,0.0008229795,0.0006329337,0.0014215045,0.0005828757,0.050094213,0.00017353517],"about_ca_topic_score_codex":0.000025452158,"about_ca_topic_score_gemma":0.00014579245,"teacher_disagreement_score":0.9256936,"about_ca_system_score_codex":0.000007825633,"about_ca_system_score_gemma":0.000002904481,"threshold_uncertainty_score":0.1253394},"labels":[],"label_agreement":null},{"id":"W2145481313","doi":"10.1093/bioinformatics/btp044","title":"Radié: visualizing taxon properties and parsimonious mappings using a radial phylogenetic tree","year":2009,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Canada Research Chairs; Genome Atlantic; Auckland University of Technology, New Zealand","keywords":"Phylogenetic tree; Character (mathematics); Tree (set theory); Character evolution; Phylogenetics; Computer science; Java; Biology; Evolutionary biology; Combinatorics; Mathematics; Genetics; Clade","score_opus":0.03208165806107003,"score_gpt":0.23892651207457635,"score_spread":0.20684485401350633,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145481313","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99366134,0.0039518704,0.0010980342,0.0000785614,0.0001036137,0.00025005068,0.000009367333,0.000008502465,0.0008386708],"genre_scores_gemma":[0.9866205,0.0007837454,0.011865356,0.00045832692,0.00018570211,0.000005545444,0.000009784944,0.000013602561,0.00005743501],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99907666,0.000019442377,0.00031067905,0.0001775076,0.0001096732,0.00030605795],"domain_scores_gemma":[0.9995151,0.0000050793756,0.00011905948,0.00022265682,0.0000493125,0.00008877137],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000117657415,0.0002086817,0.00019506444,0.00005571485,0.00017199064,0.000062786494,0.00012993829,0.00011279568,0.0000012374705],"category_scores_gemma":[0.00003540076,0.00018339431,0.00006199218,0.00006974781,0.000099519944,0.0000027443107,0.000091997616,0.00005450217,0.0000031106288],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006649024,0.000045941753,0.003374925,0.00007043785,0.000090714435,0.000002030618,0.0011928596,0.00021707,0.9545229,0.000081653925,0.00041292515,0.039922018],"study_design_scores_gemma":[0.008083972,0.005955357,0.09618776,0.00040036824,0.0005494473,0.00068934687,0.00674529,0.112820156,0.5878899,0.0011442535,0.17504945,0.004484671],"about_ca_topic_score_codex":0.000010690044,"about_ca_topic_score_gemma":0.0000060680095,"teacher_disagreement_score":0.36663303,"about_ca_system_score_codex":0.000016261172,"about_ca_system_score_gemma":0.00004963792,"threshold_uncertainty_score":0.7478603},"labels":[],"label_agreement":null},{"id":"W2145494207","doi":"10.1093/bioinformatics/btn260","title":"Optimal vaccination schedules using simulated annealing","year":2008,"lang":"en","type":"article","venue":"Bioinformatics","topic":"vaccines and immunoinformatics approaches","field":"Biochemistry, Genetics and Molecular Biology","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Ministero dell'Università e della Ricerca; Alberta Agricultural Research Institute","keywords":"Simulated annealing; Computer science; Software; Genetic algorithm; Mathematical optimization; Distributed computing; Algorithm; Machine learning; Mathematics","score_opus":0.030868948883166217,"score_gpt":0.25857468700424174,"score_spread":0.22770573812107553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145494207","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96452063,0.000274531,0.033821475,0.00001737025,0.00010482541,0.00017341405,0.00001057827,0.00003077481,0.0010464229],"genre_scores_gemma":[0.9179186,0.0001926454,0.08131127,0.00011923251,0.00011274226,0.0000013164774,0.00022797247,0.000020278037,0.000095927724],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99904424,0.000011993054,0.00043824295,0.00010108253,0.00014641798,0.00025802242],"domain_scores_gemma":[0.999322,0.0000067057954,0.00017987742,0.0002988774,0.00012654361,0.00006598157],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013789779,0.00017234203,0.00014614771,0.000075596596,0.00024088689,0.000038183487,0.00017698572,0.00015090419,0.000017686443],"category_scores_gemma":[0.000068557805,0.00015825174,0.000085899825,0.00013488099,0.000025663456,0.000032878896,0.000116717296,0.000081490696,0.000024819667],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034838685,0.000304677,0.01789537,0.00062560546,0.00052561203,0.000010474936,0.0039120843,0.8991537,0.060882613,0.0009287526,0.0035519341,0.0118608065],"study_design_scores_gemma":[0.00086439017,0.00015591574,0.0020321603,0.000017291046,0.000021788834,0.00012840184,0.0005980569,0.9552296,0.036576856,0.000010616169,0.0040228316,0.0003420992],"about_ca_topic_score_codex":0.0000068793174,"about_ca_topic_score_gemma":4.900256e-7,"teacher_disagreement_score":0.056075905,"about_ca_system_score_codex":0.0000200887,"about_ca_system_score_gemma":0.00007950283,"threshold_uncertainty_score":0.6453319},"labels":[],"label_agreement":null},{"id":"W2145562754","doi":"10.1093/bioinformatics/btu462","title":"ASTRAL: genome-scale coalescent-based species tree estimation","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1422,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Howard Hughes Medical Institute; University of Alberta; National Science Foundation","keywords":"Coalescent theory; Tree (set theory); Genome; Population; Computational biology; Concatenation (mathematics); Scale (ratio); Computer science; Biology; Data mining; Theoretical computer science; Gene; Geography; Mathematics; Genetics; Phylogenetic tree; Cartography; Combinatorics","score_opus":0.010755306190773325,"score_gpt":0.21322452821859994,"score_spread":0.2024692220278266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145562754","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8057655,0.00020567188,0.17576545,0.00023393174,0.0002796013,0.0002872648,0.0000502385,0.000019902858,0.017392423],"genre_scores_gemma":[0.9497785,0.0000501481,0.049059525,0.00038047772,0.00015599835,0.000009419794,0.0001728802,0.00001463166,0.0003784259],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992834,0.000015898126,0.00025630515,0.0001196371,0.00011343481,0.00021136165],"domain_scores_gemma":[0.99946535,0.000010447925,0.000103115104,0.00029719682,0.000056604204,0.000067289664],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013085823,0.00014500841,0.00013112754,0.000036206715,0.00009526879,0.00003657953,0.0001547767,0.000082355604,0.000010286309],"category_scores_gemma":[0.00003867704,0.00013306554,0.000075512435,0.00004966328,0.000077181474,0.0000013944638,0.000062630126,0.00004106376,0.0000450549],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019243892,0.00034256646,0.02447205,0.0005708141,0.00025245393,0.0000011446419,0.0012016686,0.035928052,0.83372915,0.0013401879,0.013588866,0.08838063],"study_design_scores_gemma":[0.0025634794,0.0011535506,0.17480423,0.000042058284,0.00010075899,0.0000142228055,0.0005855403,0.20605737,0.16769436,0.00022909847,0.44565415,0.0011011699],"about_ca_topic_score_codex":0.0000024428798,"about_ca_topic_score_gemma":0.000020638332,"teacher_disagreement_score":0.66603476,"about_ca_system_score_codex":0.000011298767,"about_ca_system_score_gemma":0.000034166005,"threshold_uncertainty_score":0.5426255},"labels":[],"label_agreement":null},{"id":"W2145636602","doi":"10.1093/bioinformatics/btq092","title":"High quality SNP calling using Illumina data at shallow coverage","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":55,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency","funders":"","keywords":"Single-nucleotide polymorphism; SNP; Genome; Reference genome; Software; Computer science; Computational biology; Data mining; Genetics; Biology; Gene; Genotype","score_opus":0.059569126268171346,"score_gpt":0.30447150022535385,"score_spread":0.2449023739571825,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145636602","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9948426,0.00016852772,0.002793658,0.0000422289,0.000544282,0.00013401042,0.00034329115,0.000006143216,0.0011252641],"genre_scores_gemma":[0.9623852,0.00018149921,0.03624902,0.00026542865,0.0002869324,0.0000024664857,0.00043438564,0.000017107823,0.0001779831],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989681,0.000016178958,0.00039534192,0.00021476648,0.00014572627,0.00025985177],"domain_scores_gemma":[0.9986568,0.000019743302,0.00017870388,0.0009841444,0.00007149318,0.000089080575],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035843698,0.00016842042,0.0001851076,0.00002213251,0.00019203406,0.00003761202,0.000449297,0.00016019061,0.000023376977],"category_scores_gemma":[0.00014327797,0.00015464307,0.000055917535,0.000045814944,0.000099400684,0.0000035858834,0.00089785864,0.00010922079,0.000022480644],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043229626,0.000046656318,0.009270504,0.000087740416,0.00012451223,0.0000016593731,0.00026761726,0.0002970251,0.98359036,0.00037489357,0.0013415832,0.0045541963],"study_design_scores_gemma":[0.0041745882,0.0005680878,0.08285879,0.000059493086,0.00030434047,0.00017034443,0.0010349271,0.05912187,0.31166127,0.00071279914,0.5362922,0.0030413002],"about_ca_topic_score_codex":0.000109590335,"about_ca_topic_score_gemma":0.00037974937,"teacher_disagreement_score":0.6719291,"about_ca_system_score_codex":0.0000136737535,"about_ca_system_score_gemma":0.00007263764,"threshold_uncertainty_score":0.6306161},"labels":[],"label_agreement":null},{"id":"W2145991146","doi":"10.1093/bioinformatics/btt352","title":"Harnessing virtual machines to simplify next-generation DNA sequencing analysis","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Institute for Research in Immunology and Cancer","funders":"Institut National de la Recherche Agronomique","keywords":"Computer science; Software; Benchmarking; Pace; Data science; Field (mathematics); Software engineering; Operating system","score_opus":0.18150046374526624,"score_gpt":0.35659954027095925,"score_spread":0.175099076525693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145991146","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.52728707,0.0000072770017,0.467569,0.0006771473,0.00075188413,0.00021427122,0.000015444899,0.000081265396,0.0033966338],"genre_scores_gemma":[0.9463526,8.8245827e-7,0.049991008,0.0012073468,0.00015392994,0.000009896057,0.00007383803,0.0000059718113,0.0022045334],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971415,0.00006215965,0.000939613,0.0003355649,0.001226729,0.00029444572],"domain_scores_gemma":[0.99791044,0.00027072078,0.00027363023,0.001054449,0.00030450893,0.00018627856],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0026361598,0.00014624104,0.0002604623,0.0009192735,0.00037777747,0.0035504377,0.0008227527,0.000043313805,0.0005599093],"category_scores_gemma":[0.0016662687,0.00010411714,0.00012699001,0.0029643462,0.000037259415,0.0016026563,0.00046077583,0.000068025955,0.0033662717],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000022505221,0.000020693557,0.002075526,0.000007476049,0.000095184405,0.000001175972,0.0038245453,0.05684528,0.0021980016,0.0010849776,0.14109294,0.79275197],"study_design_scores_gemma":[0.00006674025,0.00002156119,0.0032452052,0.000005850874,0.000046920828,0.00000116347,0.0024248126,0.9859264,0.00020620605,0.00039524894,0.0075022643,0.00015762137],"about_ca_topic_score_codex":0.00014413489,"about_ca_topic_score_gemma":0.00007029796,"teacher_disagreement_score":0.92908114,"about_ca_system_score_codex":0.000077202676,"about_ca_system_score_gemma":0.00004966371,"threshold_uncertainty_score":0.99748397},"labels":[],"label_agreement":null},{"id":"W2146076890","doi":"10.1093/bioinformatics/btp204","title":"Prediction of sub-cavity binding preferences using an adaptive physicochemical structure representation","year":2009,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Bill and Melinda Gates Foundation","keywords":"Structural similarity; Computer science; Structural bioinformatics; Leverage (statistics); Similarity (geometry); Representation (politics); Template; Set (abstract data type); Drug discovery; Binding site; Protein structure; Computational biology; Data mining; Biological system; Artificial intelligence; Bioinformatics; Chemistry; Biology; Genetics","score_opus":0.08881122272780319,"score_gpt":0.32411579657060197,"score_spread":0.2353045738427988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146076890","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54677147,0.0000037565248,0.45286706,0.000010809289,0.000086013315,0.00008058063,0.0000249708,0.000037916376,0.00011741158],"genre_scores_gemma":[0.6970941,0.0000013835587,0.30281606,0.000019234134,0.000037663267,5.065129e-7,0.000028533806,0.0000018291912,7.278655e-7],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989408,0.00006974371,0.00034253232,0.00014388665,0.00037078385,0.00013220144],"domain_scores_gemma":[0.99919283,0.00008396798,0.00026399395,0.00027452683,0.00013008213,0.000054574888],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016973143,0.00010431526,0.0001435022,0.00011031181,0.000069317575,0.00007975932,0.0003292213,0.000057686204,0.0000016153518],"category_scores_gemma":[0.00005478539,0.000096753414,0.000043692093,0.00041906734,0.000036651276,0.0020096654,0.00007118857,0.00009531881,0.0000012399298],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009467154,0.00042079133,0.0018244309,0.00012366113,0.00007754279,0.0000019694953,0.013153462,0.292056,0.27419695,0.043608576,0.00016682438,0.37427512],"study_design_scores_gemma":[0.00012820502,0.00012863948,0.009089273,0.000026020622,0.000008351321,0.0000065642025,0.00013668509,0.88703644,0.08864663,0.01471027,0.0000017512041,0.00008116002],"about_ca_topic_score_codex":0.000007598077,"about_ca_topic_score_gemma":7.0959914e-7,"teacher_disagreement_score":0.5949804,"about_ca_system_score_codex":0.000056248133,"about_ca_system_score_gemma":0.00009049961,"threshold_uncertainty_score":0.39454895},"labels":[],"label_agreement":null},{"id":"W2146158248","doi":"10.1093/bioinformatics/bth934","title":"Genomic features in the breakpoint regions between syntenic blocks","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Breakpoint; Synteny; Genome; Biology; Genetics; Computational biology; Event (particle physics); Chromosome; Chromosomal inversion; Gene; Karyotype; Physics","score_opus":0.012190793580367123,"score_gpt":0.22931640811605053,"score_spread":0.2171256145356834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146158248","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9936379,0.0008902447,0.000640175,0.0009453295,0.00008087234,0.00024381434,0.000033345877,0.0000042116285,0.0035240862],"genre_scores_gemma":[0.9961378,0.00034769607,0.0025688997,0.00062620896,0.00017230681,0.000016338807,0.000039425686,0.0000097081565,0.00008161194],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99928886,0.00001592088,0.00025572377,0.000112632464,0.00009468024,0.0002322143],"domain_scores_gemma":[0.9994837,0.000016473152,0.00007532921,0.00035967713,0.000027731101,0.000037096757],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017864913,0.00013599927,0.00012570368,0.000040272735,0.00010250261,0.000031444793,0.00030933358,0.00009857305,0.0000014148407],"category_scores_gemma":[0.00003372226,0.00009558392,0.00008295076,0.00008441995,0.000076169235,9.986533e-7,0.00011747377,0.000100429366,0.000014480375],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043222943,0.0012492762,0.21506888,0.0007229071,0.002444172,0.00007875706,0.061400805,0.015707215,0.53394425,0.030147642,0.07738432,0.061419576],"study_design_scores_gemma":[0.004099813,0.0011325962,0.7972528,0.00010490118,0.00019679395,0.00036113907,0.00818453,0.00008972328,0.036220066,0.0090650525,0.14188987,0.0014027639],"about_ca_topic_score_codex":0.000046978326,"about_ca_topic_score_gemma":0.000112217895,"teacher_disagreement_score":0.5821839,"about_ca_system_score_codex":0.000019717007,"about_ca_system_score_gemma":0.0000642407,"threshold_uncertainty_score":0.38977993},"labels":[],"label_agreement":null},{"id":"W2146223044","doi":"10.1093/bioinformatics/btt050","title":"Oxfold: kinetic folding of RNA using stochastic context-free grammars and evolutionary information","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Biotechnology and Biological Sciences Research Council; Engineering and Physical Sciences Research Council; Directorate for Biological Sciences","keywords":"Folding (DSP implementation); Context (archaeology); Rule-based machine translation; Computer science; RNA; Nucleic acid secondary structure; Protein folding; Kinetics; Computational biology; Theoretical computer science; Artificial intelligence; Biology; Physics; Genetics; Gene; Engineering; Biochemistry","score_opus":0.011620894942128486,"score_gpt":0.2146457541753658,"score_spread":0.20302485923323732,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146223044","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7625636,0.0006263957,0.23539643,0.00009865466,0.00017621795,0.00061313715,0.000038174687,0.00001870409,0.00046872636],"genre_scores_gemma":[0.93852943,0.00005256657,0.06114972,0.00013650418,0.000040609553,0.000018556273,0.000040481405,0.000009206716,0.000022894417],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991364,0.000018423701,0.00040204506,0.00007107562,0.00019166282,0.0001803903],"domain_scores_gemma":[0.9992699,0.000018220235,0.00022692422,0.00029874107,0.000114172784,0.00007201364],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013209095,0.0001311721,0.00014204052,0.00008306841,0.000070873466,0.000044261968,0.00020307951,0.00013877278,0.000025303441],"category_scores_gemma":[0.00017223552,0.00012082815,0.000049492948,0.00006792543,0.000067553985,0.0000564837,0.00017799108,0.000043596676,0.000012891681],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001297419,0.00011555894,0.0004120799,0.001008192,0.00024951083,6.440426e-7,0.001739245,0.0023468796,0.768479,0.015662262,0.0067687426,0.20308816],"study_design_scores_gemma":[0.006850536,0.0026364059,0.0044685723,0.0009165255,0.0003504957,0.00032270534,0.010164236,0.39034835,0.53227437,0.03119102,0.017906709,0.002570067],"about_ca_topic_score_codex":0.00008131485,"about_ca_topic_score_gemma":0.0000019988574,"teacher_disagreement_score":0.38800147,"about_ca_system_score_codex":0.000012694352,"about_ca_system_score_gemma":0.000043490472,"threshold_uncertainty_score":0.49272287},"labels":[],"label_agreement":null},{"id":"W2146279700","doi":"10.1093/bioinformatics/bti675","title":"METIS: multiple extraction techniques for informative sentences","year":2005,"lang":"en","type":"article","venue":"Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; Ministry of Economy, Trade and Industry","keywords":"Metis; Annotation; Computer science; Sentence; Information retrieval; Support vector machine; Component (thermodynamics); Natural language processing; Artificial intelligence; World Wide Web","score_opus":0.016057162470740523,"score_gpt":0.27316759891147785,"score_spread":0.25711043644073733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146279700","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.093218535,0.00042615714,0.88871986,0.0006929485,0.00035259704,0.002019887,0.00014812684,0.00018026339,0.014241649],"genre_scores_gemma":[0.4531848,0.00025356564,0.5444602,0.00074748363,0.00037120472,0.0002456,0.00015570615,0.000017695527,0.0005637404],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99930716,0.000012669837,0.00030230518,0.00008530844,0.00010829019,0.00018426396],"domain_scores_gemma":[0.9994791,0.000027709013,0.0001639556,0.00018680366,0.00009225835,0.000050162947],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024361564,0.00012534593,0.00010580215,0.000048344344,0.00010505564,0.00003881115,0.00014010601,0.00013502075,0.000016770884],"category_scores_gemma":[0.00014175606,0.00010666509,0.00008617617,0.00004396381,0.000031643587,0.000036024783,0.000038551178,0.00003833998,0.000031652966],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013789188,0.00006332967,0.0001046586,0.00010973618,0.0000703201,1.6004171e-7,0.00067845435,0.000031092055,0.26268354,0.00044204277,0.009029708,0.72664905],"study_design_scores_gemma":[0.00017344924,0.0001742451,0.000024805191,0.000012178228,0.000009086521,0.000009156009,0.00058398326,0.005708058,0.71716666,0.00004995133,0.27595282,0.00013561005],"about_ca_topic_score_codex":0.0000022867373,"about_ca_topic_score_gemma":0.00000885275,"teacher_disagreement_score":0.72651345,"about_ca_system_score_codex":0.000013789862,"about_ca_system_score_gemma":0.000032996937,"threshold_uncertainty_score":0.43496758},"labels":[],"label_agreement":null},{"id":"W2146384526","doi":"10.1093/bioinformatics/btl611","title":"Dynamic exploration and editing of KEGG pathway diagrams","year":2006,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":88,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Leibniz-Institut für Pflanzengenetik und Kulturpflanzenforschung; Institute of Genetics","keywords":"KEGG; Visualization; Computer science; Encyclopedia; Markup language; Resource (disambiguation); Data visualization; Graph drawing; World Wide Web; Information retrieval; Presentation (obstetrics); Human–computer interaction; Information visualization; Data mining; XML; Biology","score_opus":0.006553937449244133,"score_gpt":0.2026285416479405,"score_spread":0.19607460419869638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146384526","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6371254,0.001221426,0.3436873,0.00024135754,0.0005235925,0.00053898885,0.000107918844,0.00004330789,0.016510716],"genre_scores_gemma":[0.98197013,0.00015825767,0.017106472,0.00007792813,0.00013606218,0.000007313097,0.00035749946,0.00001088955,0.00017543187],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992609,0.000007926045,0.0004024472,0.000073187344,0.00009433657,0.0001611843],"domain_scores_gemma":[0.9995202,0.000007995816,0.00020832205,0.00017315755,0.000053325137,0.00003698944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015771537,0.00011150228,0.000117232084,0.000035052075,0.000056078443,0.000028603637,0.00008174436,0.000117018935,0.0000028292661],"category_scores_gemma":[0.000016642474,0.000101043006,0.000042795695,0.00005743994,0.00006915298,0.000017451199,0.00007643443,0.000050655086,0.000005052465],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020132684,0.00045212533,0.00929352,0.0021318195,0.00031072248,0.0000049678033,0.0037792455,0.008549571,0.1671001,0.0387847,0.03234121,0.7370507],"study_design_scores_gemma":[0.0037228984,0.0013381663,0.0067241467,0.00024850265,0.00010423881,0.00009846328,0.004365647,0.7680323,0.09628215,0.013985585,0.10344137,0.0016565229],"about_ca_topic_score_codex":0.00000842271,"about_ca_topic_score_gemma":0.000037546426,"teacher_disagreement_score":0.75948274,"about_ca_system_score_codex":0.0000067103383,"about_ca_system_score_gemma":0.000024835845,"threshold_uncertainty_score":0.41204143},"labels":[],"label_agreement":null},{"id":"W2146705459","doi":"10.1093/bioinformatics/btr635","title":"Inferring sequence regions under functional divergence in duplicate genes","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Functional divergence; Divergence (linguistics); Biology; Gene duplication; Phylogenetic tree; Computational biology; Gene; Genetics; Evolutionary biology; Gene family; Genome","score_opus":0.05988863102699207,"score_gpt":0.24481273053407207,"score_spread":0.18492409950708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146705459","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6277242,0.000794765,0.33962318,0.00016557706,0.00084063894,0.0005819149,0.000051753792,0.000074466014,0.03014352],"genre_scores_gemma":[0.9838512,0.00046642928,0.014507932,0.00061635574,0.00010104667,0.000023796838,0.000108640605,0.000014486221,0.00031009625],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99905956,0.000010704324,0.00040061455,0.0001296364,0.00011099411,0.0002884636],"domain_scores_gemma":[0.9993809,0.000006572637,0.0001274553,0.00034488688,0.0000524465,0.00008774651],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001683674,0.00015247012,0.00011508523,0.00004817365,0.000085193766,0.00002096435,0.00022188673,0.00015098606,0.000048286784],"category_scores_gemma":[0.000014462019,0.00014250024,0.000063360065,0.0001318231,0.000091212554,0.000019677396,0.00018797039,0.00010840468,0.00008285981],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011493807,0.0013859571,0.31796354,0.0012687893,0.0010791214,0.000053167245,0.01603761,0.039130043,0.11325934,0.18283969,0.0478747,0.27795866],"study_design_scores_gemma":[0.007520795,0.0017148519,0.36474687,0.00051400444,0.00021374639,0.0007184454,0.008390986,0.30390117,0.08816887,0.036375154,0.18134828,0.006386805],"about_ca_topic_score_codex":0.000037354243,"about_ca_topic_score_gemma":0.00007911417,"teacher_disagreement_score":0.35612702,"about_ca_system_score_codex":0.000023121567,"about_ca_system_score_gemma":0.000063571424,"threshold_uncertainty_score":0.5810991},"labels":[],"label_agreement":null},{"id":"W2146891463","doi":"10.1093/bioinformatics/btm604","title":"Mutual information without the influence of phylogeny or entropy dramatically improves residue contact prediction","year":2007,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":537,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Canada Research Chairs","keywords":"Mutual information; Entropy (arrow of time); Computer science; Phylogenetic tree; Metric (unit); Information theory; Multiple sequence alignment; Computational biology; Protein family; Identification (biology); Artificial intelligence; Statistical physics; Theoretical computer science; Sequence alignment; Biology; Mathematics; Genetics; Physics; Statistics; Gene; Peptide sequence","score_opus":0.0039831791568075295,"score_gpt":0.2248982414525908,"score_spread":0.22091506229578325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146891463","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94729555,0.000025825448,0.050970912,0.000030147954,0.000094937765,0.00043148996,0.00006203777,0.000018620147,0.0010704693],"genre_scores_gemma":[0.98932725,0.000043921507,0.009918805,0.00041775196,0.00008683902,0.000008523823,0.00013329055,0.0000070043134,0.000056639532],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988525,0.000016470489,0.0006116377,0.00006894654,0.00022965187,0.0002208115],"domain_scores_gemma":[0.99904567,0.000031390686,0.00032068696,0.00035623382,0.0001852902,0.000060719543],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038473538,0.00014025974,0.00013521091,0.00005001023,0.00008754973,0.000036883757,0.0002398418,0.0001732177,0.000004035571],"category_scores_gemma":[0.00034564934,0.00008543733,0.000057300116,0.00011004881,0.0001150513,0.0000467852,0.00009053966,0.000104681625,0.000009401018],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025659434,0.0000867661,0.014444496,0.0007225488,0.00031535595,0.000002122902,0.004158066,0.0013693925,0.9259248,0.0081268605,0.0015230983,0.040760558],"study_design_scores_gemma":[0.004244458,0.0038668704,0.4121157,0.00018789922,0.00020919906,0.00021617035,0.0035764398,0.031322177,0.50609595,0.0010969403,0.03609903,0.00096917857],"about_ca_topic_score_codex":0.00001337989,"about_ca_topic_score_gemma":0.000028799908,"teacher_disagreement_score":0.41982886,"about_ca_system_score_codex":0.000017141258,"about_ca_system_score_gemma":0.00012148458,"threshold_uncertainty_score":0.3484033},"labels":[],"label_agreement":null},{"id":"W2147492358","doi":"10.1093/bioinformatics/18.12.1696","title":"DNACompress: fast and effective DNA sequence compression","year":2002,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":210,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bioinformatics Solutions (Canada); Western University","funders":"National Science Foundation","keywords":"Compression (physics); Sequence (biology); DNA; Computer science; DNA sequencing; Data compression; Computational biology; Algorithm; Genetics; Biology; Materials science; Composite material","score_opus":0.021486470274000594,"score_gpt":0.23858404324737703,"score_spread":0.21709757297337645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147492358","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010140772,0.0004212996,0.9797127,0.00024644288,0.00041981947,0.0004226744,0.000030446387,0.00033084862,0.008274978],"genre_scores_gemma":[0.48313513,0.00042030847,0.51483387,0.00092653284,0.00015211075,0.000048831662,0.000026945287,0.000020648245,0.00043559805],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989472,0.00003578318,0.00027077828,0.00019856724,0.00028678591,0.00026088412],"domain_scores_gemma":[0.99900657,0.00011126645,0.00013137539,0.0005524023,0.000052283827,0.00014612584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011938968,0.00017081582,0.00017647394,0.000084128435,0.0002248146,0.0002554013,0.0006145733,0.00007364666,0.000025906305],"category_scores_gemma":[0.000025562367,0.00013148492,0.00003371138,0.00019039902,0.00007764463,0.0015738495,0.0006807072,0.00014143523,0.00014710809],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000036432612,0.00007185995,0.00017765383,0.0001054138,0.000015255469,0.000012167613,0.003080603,0.00009029593,0.000985178,0.0057854885,0.011576383,0.97809607],"study_design_scores_gemma":[0.0003522176,0.00008035877,0.00097505614,0.000097140066,0.000004155529,0.000049434984,0.00005306657,0.98143953,0.0011916959,0.0003502422,0.015200429,0.00020668196],"about_ca_topic_score_codex":0.000007805942,"about_ca_topic_score_gemma":4.2702948e-7,"teacher_disagreement_score":0.98134923,"about_ca_system_score_codex":0.000024095145,"about_ca_system_score_gemma":0.000007257479,"threshold_uncertainty_score":0.5361799},"labels":[],"label_agreement":null},{"id":"W2147626660","doi":"10.1093/bioinformatics/btr591","title":"Optimized application of penalized regression methods to diverse genomic data","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":99,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Ontario Institute for Cancer Research","funders":"Division of Biological Infrastructure; National Science Foundation","keywords":"Elastic net regularization; Lasso (programming language); Feature selection; Computer science; Univariate; Regression; Data mining; R package; Predictive modelling; Regression analysis; Machine learning; Artificial intelligence; Statistics; Mathematics; Multivariate statistics","score_opus":0.08353315231449081,"score_gpt":0.3586795711320192,"score_spread":0.2751464188175284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147626660","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019890655,0.00013407612,0.97356766,0.000037352318,0.00013864091,0.0003769694,0.000048940903,0.000016265109,0.0057894182],"genre_scores_gemma":[0.09430418,0.00013415745,0.9045623,0.0002114171,0.00004714834,0.000030899337,0.0004509879,0.000012502014,0.0002464007],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99926484,0.000045800207,0.0003149631,0.00016842983,0.00009748202,0.00010851024],"domain_scores_gemma":[0.99860495,0.0000059120102,0.00021892141,0.0010112927,0.00007809938,0.000080794416],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033874655,0.00009611569,0.00012449776,0.00006124253,0.00004057409,0.000007331182,0.0005013639,0.00008885902,0.000040833238],"category_scores_gemma":[0.00007266497,0.00007788065,0.000037488804,0.00010460989,0.000031767926,0.000010126248,0.00041598655,0.000033701934,0.000026421503],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032031184,0.000060591614,0.00023570703,0.000049905226,0.000031537966,8.6740876e-8,0.0006885687,0.000046184065,0.88845426,0.00016695561,0.010449003,0.0994969],"study_design_scores_gemma":[0.0013519658,0.00018332156,0.0028839218,0.00003430721,0.000057029072,0.0000046780588,0.00091435976,0.019475475,0.81003314,0.000101293524,0.16464762,0.00031289292],"about_ca_topic_score_codex":0.000013533315,"about_ca_topic_score_gemma":0.0000013065393,"teacher_disagreement_score":0.15419863,"about_ca_system_score_codex":0.000009185056,"about_ca_system_score_gemma":0.00005026263,"threshold_uncertainty_score":0.31758806},"labels":[],"label_agreement":null},{"id":"W2147702777","doi":"10.1093/bioinformatics/btr229","title":"Sequence-based prediction of protein crystallization, purification and production propensity","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Enzyme Structure and Function","field":"Materials Science","cited_by":77,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Killam Trusts","keywords":"Crystallization; Protein crystallization; Computer science; Process (computing); Production (economics); Set (abstract data type); In silico; Selection (genetic algorithm); Sequence (biology); Quality (philosophy); Diffraction; Algorithm; Data mining; Biological system; Artificial intelligence; Chemistry; Biology; Physics; Genetics","score_opus":0.0539457064322674,"score_gpt":0.21324081686334262,"score_spread":0.15929511043107522,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147702777","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95257425,0.00001534176,0.044906605,0.00003964431,0.00024371433,0.0006038366,0.000024452553,0.000091051705,0.0015011065],"genre_scores_gemma":[0.9591786,0.000005544365,0.04064202,0.000014274331,0.00003833043,0.00001974739,0.000033951386,0.0000049325586,0.00006259422],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993512,0.000022056367,0.00029382698,0.00009531559,0.00015456323,0.00008302616],"domain_scores_gemma":[0.9993705,0.0000033597212,0.00022639296,0.00017571679,0.00019485889,0.000029183964],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025438442,0.00007129598,0.00008522147,0.00006106473,0.00007952403,0.000017863478,0.000053021657,0.000057657526,0.000055454788],"category_scores_gemma":[0.00008456478,0.000057842808,0.000012718047,0.00012562994,0.00009378711,0.0004802285,0.000012624751,0.00003549779,0.000009589921],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000062338564,0.000039071565,0.0015943963,0.0003014833,0.0000037916698,1.3225848e-7,0.0017323946,0.000054888922,0.9902826,0.0015954995,0.00016233367,0.0041710814],"study_design_scores_gemma":[0.00016626217,0.00018769689,0.010150854,0.000053521453,0.000016598733,0.000005761709,0.00013354886,0.0035915996,0.9846752,0.00063257216,0.0003071574,0.00007921025],"about_ca_topic_score_codex":0.00002137958,"about_ca_topic_score_gemma":0.0000050897665,"teacher_disagreement_score":0.008556457,"about_ca_system_score_codex":0.00002054355,"about_ca_system_score_gemma":0.000049406015,"threshold_uncertainty_score":0.23587613},"labels":[],"label_agreement":null},{"id":"W2147803109","doi":"10.1093/bioinformatics/btv274","title":"SpeeDB: fast structural protein searches","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; National Research Foundation","keywords":"Protein Data Bank (RCSB PDB); Computer science; Protein Data Bank; Protein superfamily; Interface (matter); Computational biology; Function (biology); Protein structure; Identification (biology); Stability (learning theory); Data mining; Information retrieval; Chemistry; Biology; Machine learning; Stereochemistry; Biochemistry; Genetics","score_opus":0.019252973532231186,"score_gpt":0.2571173499731011,"score_spread":0.2378643764408699,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147803109","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96877,0.0002316353,0.01233299,0.00015489398,0.00022476165,0.0005152306,0.00007070449,0.000049801532,0.017649949],"genre_scores_gemma":[0.9454456,0.000007502671,0.051991902,0.00025955003,0.00031462088,0.0000140063385,0.0003027533,0.000020776193,0.0016432635],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99918544,0.000018107474,0.00021705274,0.00011419089,0.0002106672,0.00025452656],"domain_scores_gemma":[0.99931574,0.0000022695035,0.000078518766,0.00032420555,0.00011124418,0.00016799422],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014589027,0.00014722117,0.00011130808,0.00003600102,0.000054461176,0.00005045371,0.00022402931,0.00013765477,0.0000082015085],"category_scores_gemma":[0.00010257002,0.00012044467,0.000053804593,0.00007874766,0.00008518203,0.000011604793,0.00016007776,0.000094422714,0.0000509021],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015489393,0.00017678831,0.016910259,0.0011464743,0.0007579317,0.000053975866,0.008250216,0.0026919935,0.55273134,0.023765296,0.0641805,0.3277863],"study_design_scores_gemma":[0.0067179725,0.0030482563,0.004377646,0.00012603353,0.00008315024,0.0005389407,0.005453297,0.078968324,0.54586285,0.013831256,0.33803186,0.0029603704],"about_ca_topic_score_codex":0.000010674982,"about_ca_topic_score_gemma":0.000012216283,"teacher_disagreement_score":0.3248259,"about_ca_system_score_codex":0.000020653924,"about_ca_system_score_gemma":0.00014792747,"threshold_uncertainty_score":0.4911591},"labels":[],"label_agreement":null},{"id":"W2147849606","doi":"10.1093/bioinformatics/btq171","title":"PepC: proteomics software for identifying differentially expressed proteins based on spectral counting","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Human Genome Research Institute; Canadian Institutes of Health Research; National Institutes of Health","keywords":"Pipeline (software); Computer science; Software; Proteomics; Java; MIT License; False discovery rate; Computational biology; Biology; Programming language; Biochemistry; Gene","score_opus":0.01931066443580819,"score_gpt":0.2745229701509697,"score_spread":0.2552123057151615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147849606","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13742502,0.0000015119805,0.8590798,0.00010234156,0.00007118233,0.0012062886,0.00023102282,0.00044597517,0.0014368624],"genre_scores_gemma":[0.1643492,0.0000022562112,0.83381724,0.00008827624,0.00018862798,0.0011358083,0.00019089958,0.00004619982,0.00018147475],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998733,0.0000025774393,0.00046817894,0.00019999869,0.00022954248,0.00036672715],"domain_scores_gemma":[0.9987453,0.00008935805,0.0003383034,0.000586508,0.00014862062,0.00009186536],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013811335,0.00023545387,0.00019774199,0.000064418455,0.00031716237,0.00017166836,0.00038854388,0.00020022593,0.00011569456],"category_scores_gemma":[0.00024352442,0.00022623735,0.000119285505,0.000098736644,0.000058862675,0.00020609656,0.000061526254,0.00041539926,0.000016265793],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009468036,0.00019410305,0.00040527663,0.0012496297,0.000019941266,7.5140656e-7,0.0002383695,0.00023180012,0.98451746,0.006868746,0.00041204752,0.005767199],"study_design_scores_gemma":[0.00070390076,0.00003902513,0.00003936786,0.00012804878,0.000021202886,0.0000024658393,0.000057505313,0.11016942,0.88019836,0.004030977,0.004241046,0.00036865904],"about_ca_topic_score_codex":0.0000038847156,"about_ca_topic_score_gemma":0.000007460222,"teacher_disagreement_score":0.10993762,"about_ca_system_score_codex":0.00005123331,"about_ca_system_score_gemma":0.00010008864,"threshold_uncertainty_score":0.9225691},"labels":[],"label_agreement":null},{"id":"W2148132327","doi":"10.1093/bioinformatics/18.12.1692","title":"RED: the analysis, management and dissemination ofexpressed sequence tags","year":2002,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Molecular Biology Techniques and Applications","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Medical Research Council; National Institutes of Health","keywords":"Sequence (biology); Sequence analysis; World Wide Web; Web site; Expressed sequence tag; DNA sequencing; Library science; Computer science; Database; Biology; Information retrieval; The Internet; Genetics; DNA; Complementary DNA; Gene","score_opus":0.012029396377031123,"score_gpt":0.2626744045564294,"score_spread":0.2506450081793983,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148132327","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22298688,0.0021748864,0.70232356,0.0059836023,0.00010377199,0.0020876394,0.00017248312,0.00018377567,0.06398339],"genre_scores_gemma":[0.9681774,0.0012782448,0.028348824,0.00043028264,0.000022994816,0.000077869656,0.00017227864,0.000006212704,0.0014859136],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995476,0.000014167148,0.00015573524,0.00010808756,0.00006773841,0.00010669069],"domain_scores_gemma":[0.99951637,0.000007638855,0.00007272535,0.0003474438,0.00002624107,0.000029597406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009776901,0.00008011854,0.000065252105,0.000038369424,0.000104576226,0.000025858943,0.00015341381,0.00006887322,0.000021790653],"category_scores_gemma":[0.000014703221,0.000056432313,0.000047858855,0.00016348678,0.00007653856,0.0000035183239,0.00009577667,0.000039288025,0.000005655077],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000395912,0.00032952265,0.0061885472,0.00027480468,0.0022666787,0.0000082727665,0.0012613694,0.00030003826,0.4169056,0.02290206,0.339265,0.21025853],"study_design_scores_gemma":[0.00046146088,0.00025298324,0.01542407,0.00004607476,0.00088659127,0.00005090759,0.000673689,0.12815395,0.104479425,0.0006000601,0.748142,0.0008288072],"about_ca_topic_score_codex":0.0000015013028,"about_ca_topic_score_gemma":0.0000021452968,"teacher_disagreement_score":0.7451905,"about_ca_system_score_codex":0.0000045230777,"about_ca_system_score_gemma":0.0000016917267,"threshold_uncertainty_score":0.2301243},"labels":[],"label_agreement":null},{"id":"W2148133654","doi":"10.1093/bioinformatics/btm221","title":"Modeling recurrent DNA copy number alterations in array CGH data","year":2007,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomic variations and chromosomal abnormalities","field":"Biochemistry, Genetics and Molecular Biology","cited_by":71,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Genome British Columbia; Michael Smith Health Research BC","keywords":"Comparative genomic hybridization; Inference; Computer science; Computational biology; Copy-number variation; Biology; Data set; Set (abstract data type); Artificial intelligence; Genetics; Genome; Gene","score_opus":0.029263217990079266,"score_gpt":0.2809631552105036,"score_spread":0.25169993722042433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148133654","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78376144,0.00010093179,0.20234826,0.00009156916,0.0003069957,0.00019089738,0.00016326888,0.000016451748,0.0130201895],"genre_scores_gemma":[0.9715514,0.00007754717,0.0265312,0.0001595295,0.00016383844,0.000004715698,0.0012912332,0.000009118694,0.00021141642],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991184,0.000011161418,0.00041657,0.00012876243,0.00009844338,0.0002266891],"domain_scores_gemma":[0.99933535,0.0000075764283,0.000059468824,0.00049090595,0.000050910705,0.000055783355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035484057,0.00010639435,0.00009085221,0.00003863166,0.000076527336,0.000043032574,0.00026234824,0.00008818463,0.00003405007],"category_scores_gemma":[0.000042236345,0.0001027812,0.000027976772,0.000079380545,0.000020495627,0.000022298027,0.00013027208,0.0000710165,0.00005421187],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024023603,0.0049191345,0.22800143,0.0026787189,0.0016566766,0.000073196374,0.058226585,0.1291576,0.26301193,0.06521515,0.09522587,0.14943133],"study_design_scores_gemma":[0.004490161,0.00053587434,0.0036206061,0.00025593603,0.000120780984,0.0002562291,0.014572491,0.64425147,0.13619854,0.0012883536,0.19191837,0.002491195],"about_ca_topic_score_codex":0.00003337274,"about_ca_topic_score_gemma":0.00027861155,"teacher_disagreement_score":0.51509386,"about_ca_system_score_codex":0.000021629658,"about_ca_system_score_gemma":0.00007508957,"threshold_uncertainty_score":0.41912958},"labels":[],"label_agreement":null},{"id":"W2148271643","doi":"10.1093/bioinformatics/btv060","title":"Computational identification of MoRFs in protein sequences","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":99,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Genome Canada","keywords":"Computer science; Support vector machine; Identification (biology); Sequence (biology); Artificial intelligence; Computational biology; Data mining; Set (abstract data type); Machine learning; Pattern recognition (psychology); Biology; Genetics","score_opus":0.01588503249904103,"score_gpt":0.2752276049529452,"score_spread":0.25934257245390413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148271643","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9578253,0.000062799416,0.036344036,0.00010643901,0.000088507004,0.0003332973,0.000022784561,0.00001603884,0.0052008135],"genre_scores_gemma":[0.95022297,0.000004140103,0.049266312,0.00005918998,0.000026629696,0.00001176775,0.00019791756,0.000006428236,0.0002046421],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99900097,0.000026134747,0.00056895573,0.00006508335,0.00022157599,0.00011729626],"domain_scores_gemma":[0.9993374,0.0000073281303,0.00028070883,0.00018704498,0.00013693799,0.00005058802],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047371292,0.000086075,0.000102460355,0.00008365383,0.000017514529,0.00001888121,0.00017364358,0.000081860475,0.0000035840626],"category_scores_gemma":[0.00028722314,0.00008087633,0.000029568493,0.00013623542,0.000071963725,0.000016019965,0.000063615706,0.000065665285,0.000025745147],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046790115,0.0006981196,0.110889606,0.0021892628,0.00021408286,0.0000059345393,0.016168721,0.696732,0.10190542,0.021209206,0.013201686,0.036318082],"study_design_scores_gemma":[0.0020566715,0.00059296156,0.011318178,0.00010790432,0.000014983853,0.000039489845,0.0023824815,0.8965242,0.07379486,0.002792018,0.009825882,0.00055036985],"about_ca_topic_score_codex":0.0000128807105,"about_ca_topic_score_gemma":0.000006545612,"teacher_disagreement_score":0.19979222,"about_ca_system_score_codex":0.000018742083,"about_ca_system_score_gemma":0.00013958136,"threshold_uncertainty_score":0.3298041},"labels":[],"label_agreement":null},{"id":"W2148315211","doi":"10.1093/bioinformatics/btl662","title":"Computing exact<i>P</i>-values for DNA motifs","year":2007,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Human Genome Research Institute","keywords":"Heuristic; Computation; Computer science; Dynamic programming; Ranking (information retrieval); Value (mathematics); Algorithm; Software; Exact solutions in general relativity; Position (finance); Theoretical computer science; Mathematics; Artificial intelligence; Machine learning","score_opus":0.008630630522480112,"score_gpt":0.244304805498116,"score_spread":0.2356741749756359,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148315211","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6904679,0.00006974413,0.30573055,0.000025287038,0.00022428164,0.00022243302,0.000027896776,0.000020808699,0.0032110834],"genre_scores_gemma":[0.8787253,0.000030478195,0.11983503,0.0004206687,0.00031226527,0.0000031118198,0.0002824721,0.000025567795,0.0003651074],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99910456,0.0000049512273,0.00036482204,0.000116907846,0.00009315499,0.00031558078],"domain_scores_gemma":[0.9993995,0.000026238027,0.00014672807,0.00026354683,0.00008333163,0.00008065067],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043289896,0.00013730439,0.00011947192,0.000036275847,0.00012046061,0.000037112524,0.00018907103,0.00012828603,0.00000306054],"category_scores_gemma":[0.00007241257,0.00013247452,0.00009572105,0.0000500858,0.000042917847,0.0000042296456,0.00009770643,0.00004564787,0.000012064683],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004907349,0.00060514396,0.011908399,0.0018021454,0.0007091965,0.000008986198,0.0057566334,0.005774013,0.5865321,0.007934676,0.057907768,0.3205702],"study_design_scores_gemma":[0.004031891,0.0014596607,0.01316097,0.00009781152,0.000117767864,0.00011575204,0.003959125,0.4072636,0.3590446,0.0016077865,0.20730191,0.0018390805],"about_ca_topic_score_codex":0.0000015833217,"about_ca_topic_score_gemma":0.000007983643,"teacher_disagreement_score":0.40148962,"about_ca_system_score_codex":0.000017941677,"about_ca_system_score_gemma":0.000041912735,"threshold_uncertainty_score":0.54021543},"labels":[],"label_agreement":null},{"id":"W2148425737","doi":"10.1093/bioinformatics/btu558","title":"BioBloom tools: fast, accurate and memory-efficient host species sequence screening using bloom filters","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":134,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"Genome British Columbia; Genome Canada","keywords":"Bloom filter; False positive paradox; Computer science; Set (abstract data type); Sequence (biology); Filter (signal processing); Host (biology); Software; False positives and false negatives; Data set; Data structure; Data mining; Algorithm; Artificial intelligence; Programming language; Biology","score_opus":0.04576000212109506,"score_gpt":0.2551211840184869,"score_spread":0.20936118189739183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148425737","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96230024,0.00043635545,0.035127982,0.00007746464,0.00016205093,0.00017247563,0.00008286147,0.000008465372,0.0016321276],"genre_scores_gemma":[0.9606536,0.00024674612,0.038351763,0.00035222678,0.00017577558,0.000004637796,0.000033704615,0.000017022645,0.00016449866],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990861,0.000023682012,0.00029850227,0.00018234548,0.00012198969,0.00028737917],"domain_scores_gemma":[0.99938226,0.000025761863,0.0001474146,0.00028627444,0.00006976294,0.00008855355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021347508,0.00019626452,0.00017517139,0.000046920497,0.0002001609,0.00010826549,0.00016445735,0.00008813606,0.0000049166033],"category_scores_gemma":[0.00009738307,0.00017531386,0.000058359896,0.000072556664,0.00015867161,0.000003592082,0.0002575504,0.000060557446,0.0000044461603],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056399673,0.00004977878,0.0023403764,0.00018047188,0.00020703836,0.0000022925828,0.0016413998,0.012918017,0.94170773,0.0002709495,0.0007666497,0.039858878],"study_design_scores_gemma":[0.0026205943,0.0009001035,0.018368771,0.00019106007,0.00022009041,0.00016575812,0.006077466,0.51419264,0.3545921,0.00005530751,0.10070299,0.0019131262],"about_ca_topic_score_codex":0.000011390647,"about_ca_topic_score_gemma":0.0000058008955,"teacher_disagreement_score":0.58711565,"about_ca_system_score_codex":0.000009244109,"about_ca_system_score_gemma":0.000029280776,"threshold_uncertainty_score":0.7149092},"labels":[],"label_agreement":null},{"id":"W2148683465","doi":"10.1093/bioinformatics/btq332","title":"Savant: genome browser for high-throughput sequencing data","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":117,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Throughput; Computer science; Genome; DNA sequencing; Genome browser; Computational biology; Biology; Genomics; Genetics; DNA; Gene; Operating system","score_opus":0.03208935018264604,"score_gpt":0.26003887064980213,"score_spread":0.2279495204671561,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148683465","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97872657,0.0002869421,0.016434848,0.00017338248,0.0008866838,0.00046839754,0.0008618804,0.0000122040565,0.002149077],"genre_scores_gemma":[0.8676395,0.00016705837,0.129997,0.00049037795,0.0006128811,0.000021055073,0.0007893181,0.000026167412,0.00025664733],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991287,0.000005420428,0.00029111054,0.00021328432,0.00008604313,0.0002754432],"domain_scores_gemma":[0.99877274,0.000017606859,0.000110601526,0.00094352284,0.000088782894,0.0000667566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022891488,0.00015548494,0.00014491809,0.000025582749,0.00014625955,0.000041639276,0.00050422066,0.00011603883,0.000008657086],"category_scores_gemma":[0.00011306778,0.00014001568,0.000046392233,0.00004010587,0.00007435792,0.000003677385,0.00043720577,0.00008029841,0.000021945525],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027950255,0.00002157858,0.00033114373,0.000091501584,0.00012388236,4.685764e-7,0.0002880003,0.000056299305,0.9868791,0.0011791601,0.0055391933,0.0054617217],"study_design_scores_gemma":[0.0018063078,0.00052250735,0.0068425043,0.000013455905,0.00012763783,0.000055261095,0.0006368938,0.006591462,0.11621275,0.0013590568,0.8648079,0.0010242753],"about_ca_topic_score_codex":0.000015534475,"about_ca_topic_score_gemma":0.00008883199,"teacher_disagreement_score":0.8706664,"about_ca_system_score_codex":0.000008263949,"about_ca_system_score_gemma":0.00010390724,"threshold_uncertainty_score":0.5709673},"labels":[],"label_agreement":null},{"id":"W2148694532","doi":"10.1093/bioinformatics/bts007","title":"CHROMATRA: a Galaxy tool for visualizing genome-wide chromatin signatures","year":2012,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Child and Family Research Institute; Simon Fraser University; University of British Columbia","funders":"Canadian Institutes of Health Research; Michael Smith Health Research BC","keywords":"Workflow; Visualization; Computer science; Genome; Computational biology; Software; Chromatin; Genome browser; Gene; Data mining; Biology; Genomics; Genetics; Database; Programming language","score_opus":0.00881905620344901,"score_gpt":0.24328570023083532,"score_spread":0.23446664402738632,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148694532","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9336983,0.0009918913,0.06270013,0.000046116977,0.00034623782,0.0006253973,0.000117345066,0.00004793877,0.001426623],"genre_scores_gemma":[0.907441,0.00011589796,0.09015474,0.0005893621,0.0005176395,0.00007455099,0.00067727186,0.000051206254,0.00037830917],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99861693,0.000017442471,0.00048698613,0.0001506327,0.00015394318,0.000574054],"domain_scores_gemma":[0.99912924,0.000036029596,0.00022358107,0.00039613032,0.000078274345,0.00013675392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035138722,0.00025515625,0.00021645415,0.000059248712,0.00016895651,0.00007103732,0.00027101385,0.00023918206,0.000022661601],"category_scores_gemma":[0.0001462672,0.00024091962,0.00017330529,0.00007976978,0.000052928208,0.000021353964,0.00013995435,0.000082432016,0.000040848412],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020024608,0.0005081989,0.018543242,0.0021667231,0.00070205005,0.000001881064,0.0050532334,0.0013886836,0.9183266,0.0053853136,0.03822396,0.009499866],"study_design_scores_gemma":[0.0065603643,0.0018294188,0.114273585,0.00020496946,0.00041217418,0.00018389059,0.0026676077,0.10387141,0.1765088,0.00070981827,0.58821875,0.0045591993],"about_ca_topic_score_codex":0.0000020703712,"about_ca_topic_score_gemma":0.0000032573594,"teacher_disagreement_score":0.7418178,"about_ca_system_score_codex":0.000040896834,"about_ca_system_score_gemma":0.000074014126,"threshold_uncertainty_score":0.9824417},"labels":[],"label_agreement":null},{"id":"W2148762636","doi":"10.1093/bioinformatics/bth436","title":"Modeling interactome: scale-free or geometric?","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":712,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Interactome; Geometric networks; Random graph; Network model; Scale (ratio); Complex network; Scale-free network; Measure (data warehouse); Artificial intelligence; Data mining; Theoretical computer science; Machine learning; Graph","score_opus":0.01418155438029658,"score_gpt":0.24152108462962651,"score_spread":0.22733953024932993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148762636","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3136464,0.0003771064,0.67557544,0.0002939013,0.00063793483,0.0004112712,0.000074253214,0.00007158805,0.0089120865],"genre_scores_gemma":[0.9018155,0.00038564217,0.095198944,0.0013316689,0.0003836962,0.000017150725,0.00022625472,0.000037259022,0.0006039007],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99868053,0.0000068839418,0.00056835334,0.00014533302,0.0002034941,0.00039541235],"domain_scores_gemma":[0.99891037,0.000008281428,0.00012223798,0.0007057073,0.00009743673,0.00015596898],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021929432,0.0002226453,0.00019119598,0.00014175868,0.000117562144,0.000095283656,0.00052714057,0.00021634488,0.000030573658],"category_scores_gemma":[0.00011006344,0.00017517965,0.000116627125,0.00027871504,0.000052614985,0.000023479053,0.00037696745,0.00015641346,0.00011345662],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021710298,0.0011260767,0.00096844614,0.0016448664,0.0011891894,0.00004214167,0.00792734,0.6107327,0.012666744,0.00464877,0.123761445,0.23312129],"study_design_scores_gemma":[0.013427195,0.0025946104,0.00024572082,0.00040750726,0.00018064532,0.00067550957,0.00432603,0.82444406,0.026583081,0.005074819,0.11886603,0.0031747837],"about_ca_topic_score_codex":0.000017614835,"about_ca_topic_score_gemma":0.00006018454,"teacher_disagreement_score":0.58816904,"about_ca_system_score_codex":0.000044323628,"about_ca_system_score_gemma":0.00014674364,"threshold_uncertainty_score":0.7143619},"labels":[],"label_agreement":null},{"id":"W2148889460","doi":"10.1093/bioinformatics/bti1128","title":"Recovering haplotype structure through recombination and gene conversion","year":2005,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Haplotype; Recombination; Gene conversion; Genetics; Gene; Computational biology; Computer science; Biology; Allele","score_opus":0.010641531232120648,"score_gpt":0.23894569477016747,"score_spread":0.22830416353804683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148889460","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.986415,0.00030611828,0.011165457,0.0004511292,0.00015612101,0.00010398399,0.00002194442,0.000013617923,0.0013666247],"genre_scores_gemma":[0.9158383,0.0006189667,0.08229934,0.0006606467,0.00012384677,0.0000021073565,0.00018519688,0.000008092372,0.00026351013],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994975,0.000018274986,0.00019881617,0.00009659289,0.000052268173,0.00013657124],"domain_scores_gemma":[0.9996717,0.000010213895,0.000104874955,0.0001348462,0.000045102308,0.000033277207],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010649036,0.00008423802,0.000091271984,0.000019009121,0.00008048899,0.000013968071,0.000060415194,0.00014545226,0.000020842865],"category_scores_gemma":[0.00008436974,0.000078502184,0.000025504733,0.000036746962,0.000027941245,0.000011332655,0.00006448999,0.000048405178,0.000015314848],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026112434,0.00023570986,0.1668028,0.0004352202,0.00059201696,0.0000020590046,0.0052053025,0.009078282,0.3093965,0.0026817007,0.11787698,0.3874323],"study_design_scores_gemma":[0.0033778057,0.0009779489,0.130372,0.000039365605,0.0000900906,0.00013292482,0.0009409641,0.07036386,0.14258245,0.002276885,0.64769316,0.0011525542],"about_ca_topic_score_codex":0.000006403714,"about_ca_topic_score_gemma":0.000011734294,"teacher_disagreement_score":0.5298162,"about_ca_system_score_codex":0.000018359715,"about_ca_system_score_gemma":0.00002075123,"threshold_uncertainty_score":0.32012263},"labels":[],"label_agreement":null},{"id":"W2148967786","doi":"10.1093/bioinformatics/btp431","title":"Path: a tool to facilitate pathway-based genetic association analysis","year":2009,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Canadian Institutes of Health Research","keywords":"dbSNP; Single-nucleotide polymorphism; SNP; KEGG; Genome browser; OMIM : Online Mendelian Inheritance in Man; Genetic association; Tag SNP; Genome-wide association study; Computational biology; Computer science; Biology; Genetics; Genome; Genomics; Gene; Genotype; Gene ontology","score_opus":0.017030154304975766,"score_gpt":0.23987850454393989,"score_spread":0.22284835023896413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148967786","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8272578,0.00007413784,0.16930072,0.0009201887,0.00010271825,0.00028916172,0.00018485278,0.00003365092,0.0018367795],"genre_scores_gemma":[0.8963325,0.000027672018,0.098244965,0.00397548,0.00008923588,0.000021814492,0.0004700611,0.00000798527,0.0008302854],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99868464,0.00006279472,0.0005072801,0.00018898597,0.0001906169,0.000365669],"domain_scores_gemma":[0.9990911,0.00003086072,0.0002256584,0.00038224846,0.00015926987,0.00011087872],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046668152,0.00016146709,0.00025339378,0.00013838631,0.000095483505,0.000034031676,0.00017026783,0.00021365384,0.000022286238],"category_scores_gemma":[0.0005482589,0.00015487568,0.00021490295,0.0004183584,0.000010730896,0.000004158552,0.000034104265,0.00006380732,0.00012244195],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021386174,0.00060722046,0.49315384,0.000117311494,0.0023982872,0.0000073114415,0.0021775381,0.13079537,0.043716103,0.00027711148,0.12438747,0.20214857],"study_design_scores_gemma":[0.0008881927,0.0010328505,0.83808535,0.000009697391,0.00033814888,0.0000019778633,0.00016868713,0.057995465,0.0022395498,0.00022938389,0.09832265,0.00068802095],"about_ca_topic_score_codex":0.0000130263315,"about_ca_topic_score_gemma":0.00002584782,"teacher_disagreement_score":0.34493154,"about_ca_system_score_codex":0.00007812813,"about_ca_system_score_gemma":0.000095247626,"threshold_uncertainty_score":0.6315647},"labels":[],"label_agreement":null},{"id":"W2149153852","doi":"10.1093/bioinformatics/btr245","title":"Optimally discriminative subnetwork markers predict response to chemotherapy","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":99,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"Canadian Institutes of Health Research","keywords":"Subnetwork; Generalizability theory; Discriminative model; Computer science; Artificial intelligence; Computational biology; Machine learning; Biology; Mathematics; Statistics","score_opus":0.013374317781432606,"score_gpt":0.22781538550732428,"score_spread":0.21444106772589167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2149153852","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.63648987,0.00027593953,0.2659799,0.0006140497,0.0010344122,0.0018371315,0.00016841164,0.00014243393,0.093457885],"genre_scores_gemma":[0.78042555,0.00017870696,0.21266969,0.003716544,0.00033346735,0.00007089204,0.00017164309,0.0000711821,0.002362362],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986334,0.000044588698,0.0004997755,0.00018425197,0.00018184852,0.00045613936],"domain_scores_gemma":[0.99891204,0.000020709387,0.00016748559,0.00055227196,0.00009879468,0.0002487],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006253873,0.000264664,0.00020021085,0.000084538086,0.000114071634,0.000044874876,0.00041128046,0.00020192702,0.0000852038],"category_scores_gemma":[0.00006910722,0.00023480665,0.00012056323,0.00016822218,0.00010147467,0.000016560967,0.00019859424,0.00011895074,0.000096726464],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.043511916,0.0009866061,0.00615368,0.00055141887,0.0018496278,0.00003445924,0.053398617,0.0022781098,0.022044992,0.0035774636,0.5474163,0.31819677],"study_design_scores_gemma":[0.010475702,0.0149904825,0.09123849,0.00049733627,0.00030504135,0.00026136276,0.013245739,0.09845301,0.052304167,0.0020049675,0.710504,0.0057197264],"about_ca_topic_score_codex":0.000005895382,"about_ca_topic_score_gemma":0.0000073533342,"teacher_disagreement_score":0.31247705,"about_ca_system_score_codex":0.000030631632,"about_ca_system_score_gemma":0.000102210586,"threshold_uncertainty_score":0.9575137},"labels":[],"label_agreement":null},{"id":"W2149202898","doi":"10.1093/bioinformatics/btq041","title":"Identifying biologically relevant differences between metagenomic communities","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Microbial Community Ecology and Physiology","field":"Environmental Science","cited_by":974,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Metagenomics; Software; Biology; Ecology; Pairwise comparison; Computer science; Computational biology; Data science; Artificial intelligence","score_opus":0.044821397992979205,"score_gpt":0.25582985422559856,"score_spread":0.21100845623261935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2149202898","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9883207,0.000005127452,0.00046653577,0.00008660745,0.00020796733,0.00010638737,0.00002002378,0.00005363547,0.010733015],"genre_scores_gemma":[0.98858124,0.000030089808,0.010840929,0.0002980613,0.000030112942,0.0000045971137,0.00007103985,0.0000046768223,0.0001392769],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9992306,0.00010347732,0.00029874936,0.000058050377,0.00006666225,0.00024245656],"domain_scores_gemma":[0.9991462,0.00028007006,0.00013097476,0.00037551945,0.000006335419,0.0000608905],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00036861392,0.0001238441,0.00020238261,0.000031424333,0.0004152124,0.000037331338,0.00066743407,0.00015947148,0.0055963267],"category_scores_gemma":[0.000040360308,0.00009408893,0.000054424207,0.0000811921,0.00053431577,0.00018782429,0.00058460643,0.00053388503,0.0015937706],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000367734,0.00018262706,0.8224443,0.000083779254,0.00014629177,0.000002741519,0.018283905,0.0000394423,0.122273184,0.0036467114,0.008154508,0.02470572],"study_design_scores_gemma":[0.0002940871,0.000199804,0.9617447,0.000010033964,0.000044013348,0.000015007937,0.0020699939,0.0009978617,0.0012666733,0.008633963,0.024297582,0.00042628415],"about_ca_topic_score_codex":0.0002584883,"about_ca_topic_score_gemma":0.0016011696,"teacher_disagreement_score":0.13930038,"about_ca_system_score_codex":0.000018126015,"about_ca_system_score_gemma":0.000008127505,"threshold_uncertainty_score":0.9991836},"labels":[],"label_agreement":null},{"id":"W2149260201","doi":"10.1093/bioinformatics/bts511","title":"Optimal timepoint sampling in high-throughput gene expression experiments","year":2012,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"Natural Sciences and Engineering Research Council of Canada; U.S. Department of Energy","keywords":"Sampling (signal processing); Computer science; Throughput; Selection (genetic algorithm); Data mining; False discovery rate; Expression (computer science); Machine learning; Computational biology; Gene; Biology; Genetics","score_opus":0.032554689900855506,"score_gpt":0.2989092124500508,"score_spread":0.2663545225491953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2149260201","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9433706,0.000642619,0.053539295,0.000043220833,0.00041992724,0.00019170185,0.000008725773,0.000020244523,0.0017636837],"genre_scores_gemma":[0.9035059,0.000113539354,0.095504805,0.00021451342,0.0002249407,0.000038608086,0.00016587891,0.000015012731,0.0002167861],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991012,0.000022651118,0.00031580607,0.00012413712,0.00014834612,0.000287864],"domain_scores_gemma":[0.9994183,0.000004460421,0.00011701115,0.00032747875,0.000028524335,0.00010421867],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016280066,0.00013125411,0.00010651526,0.00006176045,0.00005574726,0.000022275459,0.00013771707,0.00013296261,0.000042657102],"category_scores_gemma":[0.000027276657,0.000116909156,0.000041885312,0.0000842606,0.000026891566,0.000022905664,0.00012576148,0.0000660199,0.000055640026],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004196841,0.00009600208,0.0031558624,0.000019019617,0.000007381882,1.5466021e-7,0.0005780418,0.0003843643,0.99028975,0.000062648614,0.003340466,0.0020243658],"study_design_scores_gemma":[0.0005532138,0.000051035877,0.0044770236,0.000026489239,0.0000037460632,0.000005559169,0.00040467476,0.00046479626,0.96634257,0.0000070812976,0.027475994,0.00018778804],"about_ca_topic_score_codex":0.00000449806,"about_ca_topic_score_gemma":4.4428938e-7,"teacher_disagreement_score":0.04196551,"about_ca_system_score_codex":0.000036737463,"about_ca_system_score_gemma":0.000038191673,"threshold_uncertainty_score":0.4767417},"labels":[],"label_agreement":null},{"id":"W2150153992","doi":"10.1093/bioinformatics/btm560","title":"Petri net-based method for the analysis of the dynamics of signal propagation in signaling pathways","year":2007,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Petri net; Computer science; SIGNAL (programming language); Representation (politics); Signal-flow graph; Dynamics (music); Network dynamics; Process (computing); Signal transduction; Systems biology; Theoretical computer science; Computational biology; Distributed computing; Biology; Cell biology; Mathematics; Programming language","score_opus":0.011995817193112481,"score_gpt":0.2528520046799133,"score_spread":0.24085618748680082,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150153992","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25225544,0.000105707855,0.7472427,0.00003628241,0.000027316863,0.00024815067,0.000033431857,0.0000022250033,0.000048745118],"genre_scores_gemma":[0.96401197,0.0000066787843,0.03573275,0.00005582601,0.000026207434,0.000007618695,0.00013327782,0.000007486346,0.000018170324],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998913,0.000045957087,0.0005873516,0.000090198504,0.00019903369,0.00016444469],"domain_scores_gemma":[0.9988316,0.00015444604,0.00045086423,0.00037071004,0.00016904593,0.000023323446],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014355091,0.00010165409,0.00021303653,0.00016835665,0.000056092893,0.000007687243,0.00026139754,0.00010386043,0.000004210783],"category_scores_gemma":[0.00009236422,0.0000634798,0.00032789257,0.0009726385,0.000066890854,0.000003492941,0.00004762534,0.000051801624,1.284495e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000116506955,0.00007071592,0.013077965,0.00013898328,0.00092357985,1.1900425e-7,0.00029570435,0.8856693,0.074063644,0.0005638322,0.00005191951,0.02502774],"study_design_scores_gemma":[0.00022155952,0.00004787616,0.0051734434,0.000009749427,0.00053098507,2.6886607e-7,0.00036301778,0.8399397,0.15354362,0.000022397453,0.0000791964,0.00006817774],"about_ca_topic_score_codex":0.000017480215,"about_ca_topic_score_gemma":0.00038618065,"teacher_disagreement_score":0.7117565,"about_ca_system_score_codex":0.000029456392,"about_ca_system_score_gemma":0.0000994367,"threshold_uncertainty_score":0.2588631},"labels":[],"label_agreement":null},{"id":"W2150515766","doi":"10.1093/bioinformatics/btq305","title":"Efficient learning of microbial genotype–phenotype association rules","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Biology; Phenotype; Association (psychology); Computational biology; Phylogenetic tree; Genotype; Genome-wide association study; Association rule learning; Genetic association; Genotype-phenotype distinction; Gene; Genetics; Data mining; Computer science; Single-nucleotide polymorphism; Psychology","score_opus":0.006223568153281153,"score_gpt":0.22609678617860202,"score_spread":0.21987321802532087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150515766","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.986525,0.000040085662,0.008313331,0.000044497658,0.00037579122,0.00008460881,0.000009759784,0.000012500606,0.0045944094],"genre_scores_gemma":[0.9900779,0.000020505606,0.008911309,0.0000565466,0.00012472211,0.0000035654868,0.00009363598,0.000007911088,0.0007038883],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994442,0.00001482259,0.00023372953,0.00007405496,0.000120107135,0.000113099624],"domain_scores_gemma":[0.9994231,0.0000071737227,0.00024775421,0.00016474746,0.00012216976,0.000035058012],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019527084,0.00006779362,0.00007203092,0.000037229223,0.000053207285,0.000013808143,0.00009878782,0.00013995217,0.000032801996],"category_scores_gemma":[0.00014699044,0.00006195088,0.000046077348,0.00005637989,0.000021908594,0.0000017804379,0.000042760803,0.00010477506,0.000041600026],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017279397,0.000023812452,0.001559839,0.000020221776,0.000012156541,2.4494025e-8,0.000155089,0.00038091434,0.9909236,0.00028952592,0.0020204326,0.0045971354],"study_design_scores_gemma":[0.0006773915,0.00014466536,0.012080095,0.000014797828,0.000026584223,0.0000026716548,0.0002171073,0.020677695,0.7690082,0.000030025172,0.19687013,0.00025062816],"about_ca_topic_score_codex":0.0000027431602,"about_ca_topic_score_gemma":0.0000025134555,"teacher_disagreement_score":0.22191536,"about_ca_system_score_codex":0.000011920204,"about_ca_system_score_gemma":0.00005960533,"threshold_uncertainty_score":0.25262836},"labels":[],"label_agreement":null},{"id":"W2150547367","doi":"10.1093/bioinformatics/btu786","title":"Tissue-aware data integration approach for the inference of pathway interactions in metazoan organisms","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":103,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Human Genome Research Institute; National Institute of General Medical Sciences; Canadian Institute for Advanced Research","keywords":"Inference; Scalability; Computational biology; Compendium; Computer science; Genome; Biology; Software; Biological data; Source code; Data type; Bioinformatics; Gene; Database; Genetics; Artificial intelligence; Programming language","score_opus":0.03736471980374437,"score_gpt":0.2869714272434773,"score_spread":0.24960670743973293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150547367","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012582593,0.00006622909,0.99652696,0.00007759806,0.0001448404,0.0003852191,0.00018224839,0.0000062621143,0.0013523716],"genre_scores_gemma":[0.89620304,0.0000709232,0.10105137,0.00018098917,0.00013475664,0.000032788234,0.0021513586,0.000012623963,0.0001621316],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991627,0.00001941517,0.0004621382,0.00010981792,0.00008911378,0.00015683923],"domain_scores_gemma":[0.9988474,0.00007495028,0.00021783542,0.00073708914,0.00008998874,0.00003269033],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050525536,0.00012068594,0.00014708753,0.00004265209,0.00006746487,0.00003757614,0.00052810996,0.00007959269,0.0000071643335],"category_scores_gemma":[0.00016471524,0.000082740946,0.000033721633,0.0000972889,0.00006109578,0.00002483681,0.00022826371,0.000099110344,0.000004111558],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001047504,0.00015430515,0.00027250862,0.0003892332,0.00016440407,7.669463e-8,0.0019832952,0.0034245623,0.022775833,0.010039499,0.010598634,0.9500929],"study_design_scores_gemma":[0.0004590041,0.0001532447,0.0001391816,0.000022523773,0.00003106607,0.000005011794,0.0010463381,0.91450304,0.02389645,0.00027641078,0.059286404,0.0001813377],"about_ca_topic_score_codex":0.000018103283,"about_ca_topic_score_gemma":0.00010913686,"teacher_disagreement_score":0.94991153,"about_ca_system_score_codex":0.00000875013,"about_ca_system_score_gemma":0.000060991897,"threshold_uncertainty_score":0.33740777},"labels":[],"label_agreement":null},{"id":"W2150717117","doi":"10.1093/bioinformatics/btr444","title":"Bayesian prediction of tissue-regulated splicing using RNA sequence and cellular context","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"RNA Research and Splicing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":116,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"RNA splicing; Source code; Context (archaeology); Alternative splicing; Feature (linguistics); Computational biology; Exon; Computer science; Inference; Gibbs sampling; Bayesian probability; Biology; Gene; RNA; Artificial intelligence; Genetics","score_opus":0.03686261043592832,"score_gpt":0.2611324581602233,"score_spread":0.22426984772429498,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150717117","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9593289,0.0001726988,0.03940741,0.0000047140675,0.000037934034,0.0001504672,0.000020268038,0.000008839233,0.00086880365],"genre_scores_gemma":[0.98982584,0.000051538806,0.009874469,0.000028615555,0.000028879258,0.000001559147,0.000031163683,0.0000090567755,0.00014887207],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993429,0.000016002208,0.000262401,0.00009020975,0.00011085592,0.00017763348],"domain_scores_gemma":[0.99953574,0.000004154574,0.000105848034,0.00019630439,0.00007400659,0.00008396545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015672555,0.00009067313,0.000109607055,0.00005066419,0.000060661845,0.00001207696,0.00008911297,0.000095696356,0.00001181979],"category_scores_gemma":[0.000035833793,0.0000828215,0.000025426601,0.000068478264,0.00009592299,0.000013975696,0.000068732814,0.000052147312,0.0000018661872],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002485923,0.000010351894,0.0011023629,0.00007811081,0.000022242722,0.000001320495,0.00035025066,0.000013385313,0.9901726,0.00005938504,0.00004055207,0.008124538],"study_design_scores_gemma":[0.00027721986,0.00022665643,0.00047062093,0.000045396217,0.000013119961,0.000018862032,0.00040669736,0.057165198,0.94100857,0.000023567052,0.00025908553,0.00008499965],"about_ca_topic_score_codex":0.00014117298,"about_ca_topic_score_gemma":0.0000081375265,"teacher_disagreement_score":0.057151813,"about_ca_system_score_codex":0.000010056038,"about_ca_system_score_gemma":0.000043237513,"threshold_uncertainty_score":0.33773628},"labels":[],"label_agreement":null},{"id":"W2150856587","doi":"10.1093/bioinformatics/bth057","title":"Cluster Analyzer for Transcription Sites (CATS): a C++-based program for identifying clustered transcription factor binding sites","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"D-Wave Systems (Canada)","funders":"Howard Hughes Medical Institute","keywords":"Transcription factor; DNA binding site; Consensus sequence; Biology; Computational biology; Transcription (linguistics); Genome; Binding site; CATS; DNA; Genetics; DNA sequencing; Gene; Promoter; Computer science; Base sequence; Gene expression","score_opus":0.03079255120416373,"score_gpt":0.2834839935097028,"score_spread":0.2526914423055391,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150856587","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6423026,0.00006849737,0.3554758,0.00013030911,0.00014749996,0.0014166221,0.00038616,0.000045421122,0.00002709578],"genre_scores_gemma":[0.8032607,0.000028102357,0.19211906,0.00025038674,0.00013417898,0.00029283014,0.0037906491,0.000044156943,0.00007993957],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99865544,0.000012507336,0.0005472469,0.00024189387,0.00014045024,0.0004024571],"domain_scores_gemma":[0.9992394,0.000018999433,0.00021346333,0.00027605426,0.0001557721,0.00009630322],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00019018105,0.00026216108,0.00022128761,0.00012396218,0.00021865692,0.00018042498,0.00020336764,0.0002487915,0.000005326824],"category_scores_gemma":[0.00004494133,0.00025458934,0.00033857327,0.000107905646,0.000049274633,0.000031393687,0.000020025123,0.00006642445,0.0000060465404],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002659114,0.00020657621,0.00020416272,0.0010548983,0.00012785208,1.9906344e-7,0.0008571841,0.0036853515,0.9858394,0.00010416371,0.00039106177,0.0072632306],"study_design_scores_gemma":[0.012917278,0.002596447,0.0010018927,0.00019802271,0.0004318777,0.00001608373,0.0012866083,0.54220194,0.42466077,0.0006654729,0.012623503,0.0014001119],"about_ca_topic_score_codex":0.0000039076895,"about_ca_topic_score_gemma":0.00010627011,"teacher_disagreement_score":0.5611786,"about_ca_system_score_codex":0.000074148425,"about_ca_system_score_gemma":0.0000931059,"threshold_uncertainty_score":0.99999064},"labels":[],"label_agreement":null},{"id":"W2150869900","doi":"10.1093/bioinformatics/btt313","title":"SPANNER: taxonomic assignment of sequences using pyramid matching of similarity profiles","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Taxonomic rank; Computer science; Rank (graph theory); Similarity (geometry); Set (abstract data type); Biology; Artificial intelligence; Mathematics; Ecology; Combinatorics","score_opus":0.02345590031270034,"score_gpt":0.23882277232233448,"score_spread":0.21536687200963414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150869900","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9956296,0.00028825676,0.0028110603,0.00003340949,0.000084064144,0.000254627,0.00004612223,0.0000018816255,0.0008509784],"genre_scores_gemma":[0.958486,0.00013011348,0.04125787,0.000037167523,0.000036338155,0.000008935631,0.000013050055,0.000006968682,0.000023533497],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99930274,0.000013381234,0.00035632448,0.000084998035,0.000093055845,0.00014951172],"domain_scores_gemma":[0.9993806,0.000010083544,0.0002791446,0.0002082346,0.00008652749,0.00003539897],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011686898,0.00011303395,0.0001813815,0.000031165775,0.000043058597,0.000011877732,0.0001479607,0.0000744422,0.000010794655],"category_scores_gemma":[0.000019400613,0.00009640887,0.00006915006,0.000036885896,0.000120903554,0.0000029548598,0.00013826115,0.00003421325,0.0000030120161],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008913452,0.00003741635,0.008576595,0.00020235617,0.00010685951,9.047403e-8,0.00032985152,0.0026501706,0.9860018,0.0001819418,0.00034871255,0.0015553007],"study_design_scores_gemma":[0.00046516873,0.00037169247,0.014201204,0.000071788614,0.000057451576,0.000008175294,0.002664085,0.0119781,0.96699107,0.00075011194,0.0020703103,0.00037086083],"about_ca_topic_score_codex":0.00011229917,"about_ca_topic_score_gemma":0.000005387908,"teacher_disagreement_score":0.03844681,"about_ca_system_score_codex":0.0000110755045,"about_ca_system_score_gemma":0.00006269941,"threshold_uncertainty_score":0.39314395},"labels":[],"label_agreement":null},{"id":"W2150904363","doi":"10.1093/bioinformatics/btn239","title":"EM-random forest and new measures of variable importance for multi-locus quantitative trait linkage analysis","year":2008,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children; Lunenfeld-Tanenbaum Research Institute; University of Toronto; SickKids Foundation; Mount Sinai Hospital","funders":"Canadian Institutes of Health Research; Mitacs; National Heart, Lung, and Blood Institute; School of Medicine, Boston University","keywords":"Linkage (software); Random forest; Statistics; Mathematics; Trait; Correlation; Regression; Tree (set theory); Computer science; Artificial intelligence; Biology; Genetics; Combinatorics","score_opus":0.06807023609068835,"score_gpt":0.2974211814087506,"score_spread":0.22935094531806227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150904363","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46907735,0.0006028096,0.52978766,0.000031686905,0.00003169173,0.00020485299,0.000108656204,0.0000053289023,0.00014996501],"genre_scores_gemma":[0.53939223,0.000410003,0.45928332,0.00013268254,0.000039987703,0.000018345347,0.00025461725,0.000009540832,0.00045927765],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990929,0.000027121303,0.00048173426,0.00012892685,0.0000769324,0.0001924338],"domain_scores_gemma":[0.9992021,0.00007002499,0.0003027779,0.00019533923,0.00015031864,0.00007945403],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003439478,0.000120963974,0.00033397714,0.00007104386,0.00009135658,0.0000067872706,0.00010143128,0.0001579821,0.0000052832993],"category_scores_gemma":[0.00062546914,0.00010535287,0.00013923284,0.00017010405,0.000075620665,0.0000063630423,0.000032936743,0.00004091891,8.854789e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00067393685,0.00037427433,0.8963099,0.00041808642,0.0058555007,0.0000021176322,0.0071791452,0.032242704,0.019094883,0.0023813052,0.027965544,0.007502599],"study_design_scores_gemma":[0.011624706,0.0018686249,0.50239676,0.000039188293,0.0017762311,0.000036237612,0.0029547855,0.45174927,0.004779355,0.0012539094,0.02040312,0.0011178349],"about_ca_topic_score_codex":0.000060279053,"about_ca_topic_score_gemma":0.00040054892,"teacher_disagreement_score":0.41950655,"about_ca_system_score_codex":0.0000073727056,"about_ca_system_score_gemma":0.000111247646,"threshold_uncertainty_score":0.42961654},"labels":[],"label_agreement":null},{"id":"W2150937400","doi":"10.1093/bioinformatics/btr470","title":"A phylogenetic mixture model for the identification of functionally divergent protein residues","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Nova Scotia Health Research Foundation","keywords":"False positive paradox; Phylogenetic tree; Classifier (UML); Divergence (linguistics); Computer science; Computational biology; Phylogenetics; Biology; Artificial intelligence; Pattern recognition (psychology); Evolutionary biology; Genetics; Gene","score_opus":0.017432395873248546,"score_gpt":0.22471220463730546,"score_spread":0.2072798087640569,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150937400","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16123301,0.000453807,0.83669174,0.000044383163,0.000107356616,0.0008952419,0.00014275119,0.000009450385,0.00042227082],"genre_scores_gemma":[0.9604595,0.00005769018,0.03841051,0.000092999195,0.00005747962,0.00010994136,0.00010046205,0.000009728753,0.0007017365],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99938595,0.0000072777257,0.00031140645,0.000083032784,0.00010449865,0.00010785322],"domain_scores_gemma":[0.9993294,0.000005405927,0.00019886445,0.00030235213,0.0001402585,0.000023720684],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014956537,0.00008811081,0.000070639144,0.000020805795,0.00007775302,0.000008651574,0.00019631752,0.000094463845,0.0000041700264],"category_scores_gemma":[0.00006150315,0.00006025608,0.00007477244,0.000041594165,0.00006125563,0.0000046465757,0.00005946775,0.000032924137,0.0000019601048],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005823944,0.00011440114,0.0008439512,0.0004641206,0.00031086538,1.8233601e-7,0.0022096117,0.005130199,0.9633153,0.008355063,0.0033138539,0.015360029],"study_design_scores_gemma":[0.00060517585,0.00033033683,0.0048917662,0.000020015863,0.00010375995,0.0000057847647,0.00023815774,0.39301738,0.59144884,0.0064090523,0.0026484393,0.00028126844],"about_ca_topic_score_codex":0.0000035883065,"about_ca_topic_score_gemma":0.000015214084,"teacher_disagreement_score":0.79922646,"about_ca_system_score_codex":0.0000051317793,"about_ca_system_score_gemma":0.00006012557,"threshold_uncertainty_score":0.24571715},"labels":[],"label_agreement":null},{"id":"W2151031196","doi":"10.1093/bioinformatics/btr525","title":"Computational prediction of eukaryotic phosphorylation sites","year":2011,"lang":"en","type":"review","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":157,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Phosphorylation; Kinase; Computational biology; Protein phosphorylation; Mechanism (biology); Resource (disambiguation); Sequence (biology); Posttranslational modification; Biology; Computer science; Bioinformatics; Protein kinase A; Biochemistry; Enzyme","score_opus":0.029212896477216817,"score_gpt":0.2834585629456036,"score_spread":0.2542456664683868,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151031196","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000041138603,0.9768348,0.015081429,0.0000014280088,0.00026451668,0.00064599724,0.00039729188,0.000042987063,0.0066904183],"genre_scores_gemma":[0.000052313615,0.95579386,0.037013333,0.000025094929,0.00012291361,0.000021544107,0.006670414,0.00004264278,0.00025786142],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99813175,0.000053698408,0.0012332366,0.00015010835,0.00022580501,0.00020539729],"domain_scores_gemma":[0.9981927,0.00003936236,0.0011018394,0.00044092338,0.00015290054,0.00007222326],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00028268408,0.00034927807,0.0006695687,0.0001754697,0.00006393092,0.00002304487,0.00032376134,0.00046547098,0.000054587003],"category_scores_gemma":[0.000163801,0.00030292865,0.00033137994,0.00018715732,0.000101716665,0.000014054833,0.00016544192,0.00022149114,0.00010682927],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019411424,0.00011128058,0.0003456848,0.037501603,0.000514118,4.909408e-7,0.0005159305,0.0007836873,0.0000026345215,0.00088218565,0.008827915,0.95049506],"study_design_scores_gemma":[0.00021344585,0.0002709664,0.000081107704,0.0015849037,0.0003643629,0.000053684922,0.000029799698,0.012200681,0.000016801992,0.000050428607,0.98480344,0.0003304081],"about_ca_topic_score_codex":0.0000024522938,"about_ca_topic_score_gemma":6.4333517e-7,"teacher_disagreement_score":0.9759755,"about_ca_system_score_codex":0.000029636965,"about_ca_system_score_gemma":0.00024951214,"threshold_uncertainty_score":0.9999423},"labels":[],"label_agreement":null},{"id":"W2151043165","doi":"10.1093/bioinformatics/17.7.664","title":"T-REX: reconstructing and visualizing phylogenetic trees and reticulation networks","year":2001,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":156,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Phylogenetic tree; Phylogenetic network; Tree (set theory); Computer science; Inference; Tree structure; Software; Data mining; Artificial intelligence; Data structure; Biology; Combinatorics; Mathematics; Programming language","score_opus":0.013052082182155346,"score_gpt":0.23738933531856438,"score_spread":0.22433725313640904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151043165","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99296397,0.0026654038,0.0028412908,0.00004204939,0.000092524344,0.00012223261,0.0000033520992,0.0000053041226,0.0012638698],"genre_scores_gemma":[0.98804575,0.0033425167,0.008277988,0.00012677467,0.0001365745,0.0000051375637,0.000015107792,0.000011251925,0.000038912807],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9993682,0.000015668516,0.0002375264,0.00013926739,0.00005494276,0.00018441954],"domain_scores_gemma":[0.9996479,0.000016126307,0.00009656792,0.00013907778,0.000037632726,0.00006270233],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012509794,0.00012494413,0.00011980285,0.00003248871,0.00014267692,0.000046724203,0.000049016224,0.00009433881,0.000002016418],"category_scores_gemma":[0.000036934434,0.00012211567,0.000025300562,0.00005322545,0.00009775466,0.000002073117,0.00011320287,0.00004243448,9.604819e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000982468,0.000036745227,0.4377722,0.00012494574,0.00024817718,0.000003867421,0.0014931076,0.0023188295,0.15174162,0.0006549379,0.0003593008,0.405148],"study_design_scores_gemma":[0.0039536096,0.0014638939,0.5089127,0.00019651339,0.00028485685,0.0013447296,0.0044604097,0.40595645,0.021461194,0.0011914589,0.04851024,0.002263999],"about_ca_topic_score_codex":0.000005648057,"about_ca_topic_score_gemma":0.000013611079,"teacher_disagreement_score":0.40363762,"about_ca_system_score_codex":0.000004505176,"about_ca_system_score_gemma":0.000010782836,"threshold_uncertainty_score":0.49797326},"labels":[],"label_agreement":null},{"id":"W2151232515","doi":"10.1093/bioinformatics/btn611","title":"Sparse combinatorial inference with an application in cancer biology","year":2008,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kinexus Bioinformatics Corporation (Canada)","funders":"Basic Energy Sciences; National Institutes of Health; National Cancer Institute; Office of Science; AstraZeneca; U.S. Department of Energy","keywords":"Inference; Computer science; Curse of dimensionality; Boolean function; Focus (optics); Statistical inference; Function (biology); Theoretical computer science; Boolean expression; Boolean network; Machine learning; Artificial intelligence; Algorithm; Mathematics; Biology; Statistics","score_opus":0.015231213001381477,"score_gpt":0.2626038295757963,"score_spread":0.24737261657441484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151232515","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9905413,0.00012207212,0.008687826,0.000021614893,0.000066588,0.00014341975,0.0000073311744,0.000012194835,0.00039769828],"genre_scores_gemma":[0.99615204,0.00022498448,0.0031492645,0.00008555621,0.00012701265,0.000042326166,0.0001803737,0.00000930701,0.000029105247],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99935746,0.000024420944,0.00021749339,0.00013904725,0.000079370875,0.00018218836],"domain_scores_gemma":[0.9994283,0.0000049761193,0.00010512647,0.00033004407,0.00006681478,0.00006475598],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000083757586,0.000113325914,0.00013254568,0.00005653359,0.000054628243,0.0000067783867,0.0001557104,0.00012593034,0.000006145114],"category_scores_gemma":[0.0000115232015,0.00009633358,0.00002628113,0.00017921349,0.00009780528,0.0000087697545,0.00004237574,0.000056855548,0.000009080699],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037613267,0.00043442388,0.9230179,0.00007485839,0.00018933928,0.000005041783,0.0009861112,0.01679294,0.029940752,0.003085073,0.000984759,0.024112636],"study_design_scores_gemma":[0.013793172,0.00618864,0.29512665,0.00012399144,0.00030017394,0.00019448312,0.0011386051,0.3839336,0.13576628,0.0023835702,0.15699707,0.004053748],"about_ca_topic_score_codex":0.000095869065,"about_ca_topic_score_gemma":0.00036602243,"teacher_disagreement_score":0.62789124,"about_ca_system_score_codex":0.000020964877,"about_ca_system_score_gemma":0.00012551996,"threshold_uncertainty_score":0.39283693},"labels":[],"label_agreement":null},{"id":"W2151471947","doi":"10.1093/bioinformatics/btv219","title":"ESPRESSO: taking into account assessment errors on outcome and exposures in power analysis for association studies","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"FP7 Health; Canadian Institutes of Health Research; European Commission","keywords":"Association (psychology); Outcome (game theory); Computer science; Meta-analysis; Econometrics; Statistics; Psychology; Environmental health; Medicine; Mathematics; Internal medicine","score_opus":0.2878465843490817,"score_gpt":0.4961217734300007,"score_spread":0.20827518908091897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151471947","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.736528,0.00009641394,0.2582524,0.00059732574,0.00024975216,0.0011942734,0.00003854769,0.0003331306,0.0027101468],"genre_scores_gemma":[0.7035018,0.000017281944,0.29604435,0.00022680518,0.000014144191,0.00009976722,0.000010342048,0.000012532546,0.00007292488],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984819,0.000036775084,0.00072386354,0.00012281646,0.00039524699,0.00023933947],"domain_scores_gemma":[0.99764186,0.0010601011,0.00070991623,0.00025140526,0.0002766556,0.00006003958],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014525634,0.00018564385,0.00048446943,0.00034439733,0.00006148845,0.00006488512,0.00012642972,0.00012103504,0.0000031534341],"category_scores_gemma":[0.0038711368,0.00015220162,0.00007635919,0.00030413715,0.00003071377,0.00042438105,0.00009841868,0.0001408113,0.000002292143],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007058126,0.0002514356,0.86471575,0.00072885636,0.0013131268,0.0000032354242,0.030630218,0.00096403493,0.00005047217,0.09386431,0.0040746806,0.0033332857],"study_design_scores_gemma":[0.004478033,0.0020477772,0.109171525,0.0006774482,0.0017478717,0.0000033283497,0.064871006,0.09799255,0.0018886233,0.7111907,0.0037983877,0.0021327338],"about_ca_topic_score_codex":0.000011538614,"about_ca_topic_score_gemma":0.00018345547,"teacher_disagreement_score":0.75554425,"about_ca_system_score_codex":0.000759822,"about_ca_system_score_gemma":0.000037659207,"threshold_uncertainty_score":0.62066025},"labels":[],"label_agreement":null},{"id":"W2151519751","doi":"10.1093/bioinformatics/bti781","title":"Highly consistent patterns for inherited human diseases at the molecular level","year":2005,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":53,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Medical Research Council","keywords":"Biology; Gene; Functional genomics; Genetics; Disease; Identification (biology); Genomics; Computational biology; Phenotype; Human genetics; Human genome; Molecular genetics; Genome; Medicine","score_opus":0.020930450685390543,"score_gpt":0.25592990692722045,"score_spread":0.2349994562418299,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151519751","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99239707,0.0009771221,0.0035742496,0.00070663256,0.00009570313,0.0004527255,0.0013380549,0.00001776885,0.0004406952],"genre_scores_gemma":[0.99355966,0.00007149956,0.0014614937,0.002322016,0.0001680036,0.00006375907,0.0014233659,0.000022028984,0.000908178],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992505,0.0000131454935,0.00027059685,0.00012976058,0.000107927524,0.00022811821],"domain_scores_gemma":[0.999312,0.000011654746,0.00010749395,0.0003850627,0.00008149228,0.000102313876],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000057803893,0.00015107922,0.00010852992,0.000022593582,0.0002182296,0.000047874477,0.0002058505,0.00007318814,0.000022071783],"category_scores_gemma":[0.000034757475,0.000108103886,0.0001721295,0.000030255034,0.000071590744,0.000004541184,0.00015832437,0.000030473175,0.000020855317],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00070516474,0.0013816386,0.02000586,0.0013439131,0.0016867223,0.000030177976,0.0015224597,0.0033641495,0.6265896,0.010079431,0.27231595,0.060974922],"study_design_scores_gemma":[0.002834036,0.0005241809,0.022501374,0.000046835128,0.00029296047,0.000058142476,0.00068757916,0.0031239965,0.111560404,0.00016315994,0.8572694,0.0009379461],"about_ca_topic_score_codex":0.0000053897,"about_ca_topic_score_gemma":0.00004513452,"teacher_disagreement_score":0.5849534,"about_ca_system_score_codex":0.000025384896,"about_ca_system_score_gemma":0.000047729063,"threshold_uncertainty_score":0.44083488},"labels":[],"label_agreement":null},{"id":"W2151743318","doi":"10.1093/bioinformatics/btn173","title":"Optimal pooling for genome re-sequencing with ultra-high-throughput short-read technologies","year":2008,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; BC Cancer Agency","funders":"","keywords":"Pooling; Multiplex; DNA sequencing; Computer science; Bacterial artificial chromosome; Genome; Deep sequencing; Reference genome; Computational biology; Throughput; Algorithm; Biology; Genetics; Artificial intelligence; Gene; Telecommunications","score_opus":0.037241946335152605,"score_gpt":0.24526871172737083,"score_spread":0.20802676539221823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151743318","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012742788,0.00011383435,0.9850532,0.0001452509,0.0001367679,0.0003186395,0.00003461481,0.0006233988,0.0008315054],"genre_scores_gemma":[0.13866666,0.0000891435,0.8609804,0.000091451446,0.000045768826,0.000027826925,0.000039402155,0.000011027555,0.000048349128],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99871796,0.0000059681333,0.00036766322,0.00021757376,0.00028958227,0.00040125026],"domain_scores_gemma":[0.99890584,0.00007339064,0.00013145895,0.00071964273,0.00011103868,0.000058621554],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015425218,0.00019450561,0.00022029648,0.000118928074,0.00039002293,0.00012819425,0.0009159894,0.00010769839,0.0000026823325],"category_scores_gemma":[0.00004594865,0.0001407215,0.00004812184,0.0002824495,0.0001113402,0.0014095622,0.00023608099,0.00014115752,0.000018593983],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003483387,0.0005641309,0.0011822775,0.0017725031,0.0006188939,0.00054541946,0.049404737,0.13294877,0.014814703,0.12307893,0.015557774,0.65916353],"study_design_scores_gemma":[0.00084308663,0.00066257763,0.0002789371,0.00015626903,0.000022361093,0.00045712205,0.002101063,0.9631181,0.014277406,0.00074705464,0.016526569,0.00080946763],"about_ca_topic_score_codex":0.000017300668,"about_ca_topic_score_gemma":0.0000022228649,"teacher_disagreement_score":0.8301693,"about_ca_system_score_codex":0.00008012754,"about_ca_system_score_gemma":0.00013971174,"threshold_uncertainty_score":0.5738456},"labels":[],"label_agreement":null},{"id":"W2151781607","doi":"10.1093/bioinformatics/btu463","title":"Polytomy refinement for the correction of dubious duplications in gene trees","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds de recherche du Québec – Nature et technologies; Ministero dell’Istruzione, dell’Università e della Ricerca","keywords":"Source code; Tree (set theory); Computer science; Heuristic; Ensembl; Set (abstract data type); Bounded function; Gene duplication; Graph; Feature (linguistics); Binary tree; Code (set theory); Software; Theoretical computer science; Gene; Data mining; Algorithm; Artificial intelligence; Biology; Mathematics; Combinatorics; Genetics; Genomics; Programming language; Genome","score_opus":0.008654429824636958,"score_gpt":0.23043543154066712,"score_spread":0.22178100171603016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151781607","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16938798,0.0007379217,0.81512856,0.0009647384,0.0012252952,0.0016587911,0.0000959727,0.000027123602,0.010773612],"genre_scores_gemma":[0.9860684,0.0001888682,0.01254207,0.00035691555,0.000153755,0.000078766985,0.00016726916,0.00001036756,0.000433584],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993075,0.00000850431,0.0003971264,0.00006659258,0.000069442816,0.0001507987],"domain_scores_gemma":[0.99935704,0.00004389363,0.00017885417,0.00033357667,0.000058966954,0.00002769204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003016799,0.00009039371,0.000104313556,0.00003910967,0.00006900889,0.000014492056,0.00017083345,0.00008731404,0.0000036882852],"category_scores_gemma":[0.0000583955,0.000065732755,0.00006612594,0.00008201348,0.000049885894,0.0000043308223,0.000052468873,0.000045763827,0.0000041438707],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041790341,0.00038543125,0.0036578395,0.0003880848,0.0003315875,1.261732e-7,0.0025284733,0.03292533,0.06129936,0.008699703,0.09087137,0.7984948],"study_design_scores_gemma":[0.0015076918,0.00049469527,0.004982795,0.00003162217,0.00004743079,0.000009400056,0.0005564128,0.697333,0.044213764,0.0002781458,0.25025734,0.0002877473],"about_ca_topic_score_codex":0.000016954426,"about_ca_topic_score_gemma":0.00009716926,"teacher_disagreement_score":0.81668043,"about_ca_system_score_codex":0.00001113812,"about_ca_system_score_gemma":0.00003236148,"threshold_uncertainty_score":0.26805037},"labels":[],"label_agreement":null},{"id":"W2151790371","doi":"10.1093/bioinformatics/btg447","title":"Predicting subcellular localization of proteins using machine-learned classifiers","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":334,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Subcellular localization; Computer science; Artificial intelligence; Protein subcellular localization prediction; Machine learning; Computational biology; Pattern recognition (psychology); Chemistry; Biology; Biochemistry; Cytoplasm; Gene","score_opus":0.016360328509057477,"score_gpt":0.2565539395148381,"score_spread":0.24019361100578066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151790371","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43751603,0.000117545365,0.55925953,0.00004396578,0.00014039996,0.00041456826,0.000025081523,0.00004635561,0.0024365042],"genre_scores_gemma":[0.87510884,0.000051026804,0.124206215,0.0001646685,0.00008801662,0.000006408234,0.00026997484,0.000033526787,0.00007132959],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986153,0.000029800796,0.0006653707,0.00012634824,0.00028835697,0.00027480998],"domain_scores_gemma":[0.9989064,0.0000077181685,0.0004562255,0.00041076064,0.00012781496,0.00009113401],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003133821,0.0001994204,0.00019471179,0.000103594815,0.00013169978,0.00003310751,0.00024020746,0.00021596892,0.000011209612],"category_scores_gemma":[0.00028526332,0.00018866111,0.00010003563,0.00020580238,0.00012030164,0.000023195444,0.00014186083,0.00015534481,0.000011223259],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032321858,0.00038783104,0.11869975,0.0029588009,0.00041502208,0.0000064811643,0.0060111927,0.65702313,0.20492089,0.0034793327,0.00029238296,0.0054819775],"study_design_scores_gemma":[0.0014565459,0.0004485492,0.00025551833,0.00014401674,0.000053350894,0.000050914554,0.0006580178,0.79996437,0.19169345,0.00013213114,0.0047519784,0.00039113572],"about_ca_topic_score_codex":0.00007791262,"about_ca_topic_score_gemma":0.000019871815,"teacher_disagreement_score":0.4375928,"about_ca_system_score_codex":0.000048440448,"about_ca_system_score_gemma":0.00016831791,"threshold_uncertainty_score":0.76933765},"labels":[],"label_agreement":null},{"id":"W2151908672","doi":"10.1093/bioinformatics/btv318","title":"Computer vision-based automated peak picking applied to protein NMR spectra","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Waterloo; King Abdullah University of Science and Technology","keywords":"Computer science; NMR spectra database; Identification (biology); Spectral line; Artificial intelligence; Algorithm; Pattern recognition (psychology); Automated method; Biological system; Physics; Biology","score_opus":0.008174705558512439,"score_gpt":0.24156195849310316,"score_spread":0.23338725293459073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151908672","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42858413,0.00005416821,0.55894583,0.00032384382,0.00030353037,0.0015366717,0.000046333254,0.00040667746,0.009798771],"genre_scores_gemma":[0.74697214,7.598932e-7,0.2511675,0.0012747424,0.00023322168,0.000031143187,0.00021659123,0.000023436292,0.000080438505],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989961,0.000014593419,0.00030901324,0.00017046403,0.00022412869,0.00028570555],"domain_scores_gemma":[0.9991611,0.0000049233986,0.000103629456,0.000416026,0.00010012432,0.00021418654],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017761365,0.00019244538,0.00016095757,0.00006981183,0.00006259096,0.000073590614,0.0002499103,0.00015921346,0.0000049330743],"category_scores_gemma":[0.000037689835,0.00016852884,0.000054457352,0.00014194506,0.000038451646,0.0000066746734,0.00014019774,0.00008285213,0.0000878148],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015693711,0.00052914873,0.0010282751,0.0009848898,0.00039663835,0.000049025308,0.0030903753,0.11684617,0.6347262,0.006673112,0.1336122,0.100494534],"study_design_scores_gemma":[0.0032188168,0.0020361415,0.00144518,0.00012032048,0.000036128054,0.000041919975,0.0002502913,0.75660497,0.15603787,0.00036316752,0.07854013,0.0013050484],"about_ca_topic_score_codex":0.0000057780553,"about_ca_topic_score_gemma":0.000008581934,"teacher_disagreement_score":0.6397588,"about_ca_system_score_codex":0.00003487618,"about_ca_system_score_gemma":0.00016908359,"threshold_uncertainty_score":0.6872407},"labels":[],"label_agreement":null},{"id":"W2152089378","doi":"10.1093/bioinformatics/18.10.1398","title":"Genquire: genome annotation browser/editor","year":2002,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; Plant Biotechnology Institute","funders":"Genomic Health","keywords":"Perl; Annotation; Computer science; Software; Markup language; World Wide Web; Visualization; Gene Annotation; Plug-in; Download; Genome; Programming language; Information retrieval; XML; Biology; Data mining; Artificial intelligence; Gene; Genetics","score_opus":0.014212092307792955,"score_gpt":0.21323891375709833,"score_spread":0.19902682144930536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2152089378","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97588515,0.0027541535,0.0031145085,0.00024262002,0.0017989392,0.00037555004,0.000089044996,0.000019813855,0.015720224],"genre_scores_gemma":[0.98315346,0.0012234402,0.0107512195,0.00066680205,0.0025644572,0.000025930747,0.00009836354,0.000024084231,0.0014922677],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993179,0.000009484007,0.00024164947,0.00011548902,0.00010943136,0.00020606854],"domain_scores_gemma":[0.9995156,0.0000057400953,0.000087483226,0.00025832962,0.000068930625,0.00006391676],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006902268,0.00012799974,0.00009984501,0.000030799813,0.00010072146,0.00002895609,0.00014443732,0.00009246033,0.00004218482],"category_scores_gemma":[0.00003194475,0.0001204191,0.00006181102,0.00006335437,0.000053196563,0.0000018781321,0.00008281946,0.000039070503,0.00016549505],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058565423,0.00025206088,0.004353076,0.0002407941,0.00041912677,0.000004068493,0.004155917,0.0008285678,0.69226515,0.00047660898,0.2585529,0.03839314],"study_design_scores_gemma":[0.0006752172,0.00036866384,0.009573692,0.0000062935997,0.000029025374,0.000018034341,0.0003678261,0.005506881,0.009131198,0.000064212545,0.97381413,0.00044480493],"about_ca_topic_score_codex":0.0000019404217,"about_ca_topic_score_gemma":0.0000023703765,"teacher_disagreement_score":0.7152612,"about_ca_system_score_codex":0.000010009101,"about_ca_system_score_gemma":0.000011195064,"threshold_uncertainty_score":0.49105483},"labels":[],"label_agreement":null},{"id":"W2152433810","doi":"10.1093/bioinformatics/btv126","title":"GeLL: a generalized likelihood library for phylogenetic models","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Evolution and Paleontology Studies","field":"Earth and Planetary Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Biotechnology and Biological Sciences Research Council","keywords":"Phylogenetic tree; Sequence (biology); Substitution (logic); Computer science; Java; License; Data mining; Theoretical computer science; Information retrieval; Algorithm; Artificial intelligence; Programming language; Biology","score_opus":0.0546363129713933,"score_gpt":0.23630129757967255,"score_spread":0.18166498460827926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2152433810","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2260757,0.020502543,0.069053054,0.0035363303,0.0031237742,0.0021745968,0.0015530165,0.0009411091,0.67303985],"genre_scores_gemma":[0.61038387,0.0006808469,0.38065228,0.0046094935,0.00048736238,0.00001793769,0.0007941695,0.000012926342,0.0023611472],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992523,0.000020684522,0.00024901525,0.0000810563,0.00012616058,0.00027074604],"domain_scores_gemma":[0.9995223,0.00006264753,0.00007613995,0.00013310506,0.00004028053,0.0001654728],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001322385,0.00011048431,0.00015438613,0.00005626731,0.000103864695,0.000039913783,0.00015501316,0.00007104683,0.000109446526],"category_scores_gemma":[0.000026375958,0.00008542266,0.000055931872,0.000099955505,0.00006280726,0.00036685623,0.000012412662,0.000045676585,0.00026858828],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003341921,0.00006252949,0.37083575,0.00025926344,0.00021425339,0.000005289135,0.009704323,0.018465068,0.000003312973,0.0041929246,0.5207452,0.075177886],"study_design_scores_gemma":[0.0011515255,0.00022143502,0.013825526,0.000009015181,0.000029676574,0.00001296734,0.00086610735,0.87732846,0.000022242735,0.014971376,0.09132049,0.00024117748],"about_ca_topic_score_codex":0.000042151627,"about_ca_topic_score_gemma":0.00074313255,"teacher_disagreement_score":0.8588634,"about_ca_system_score_codex":0.0000019002501,"about_ca_system_score_gemma":0.000085869164,"threshold_uncertainty_score":0.3483435},"labels":[],"label_agreement":null},{"id":"W2152852962","doi":"10.1093/bioinformatics/btt630","title":"ISCB/SPRINGER series in computational biology","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"National Institutes of Health","keywords":"Computer science; Computational genomics; Publication; Systems biology; Data science; Computational biology; Genomics; Biology; Genome; Genetics","score_opus":0.015310030544391024,"score_gpt":0.2721442721398233,"score_spread":0.2568342415954323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2152852962","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93350035,0.0004275209,0.031128708,0.0027887605,0.0006790083,0.0012635874,0.00008860375,0.00006542229,0.030058019],"genre_scores_gemma":[0.93314326,0.00039180473,0.063114345,0.0011458562,0.00021248752,0.00006543666,0.0005546489,0.00002198192,0.0013501872],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99864036,0.000028363806,0.00053393346,0.00014155118,0.00021905423,0.00043675367],"domain_scores_gemma":[0.9993025,0.000022678963,0.00009555897,0.00026426362,0.0001548642,0.00016012344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024955758,0.0001670215,0.00016828059,0.00014101515,0.000063036474,0.000068176174,0.0002997798,0.00022031675,0.00014589353],"category_scores_gemma":[0.00019934073,0.00013983356,0.00006548323,0.00014935572,0.00025257186,0.000024812318,0.00023571265,0.00013537421,0.0005244015],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004162483,0.0013033529,0.14043254,0.0020454475,0.00058824953,0.000014638466,0.0058766045,0.003348148,0.096109875,0.015330334,0.20443085,0.5301037],"study_design_scores_gemma":[0.0069644526,0.00363134,0.16701768,0.00020001447,0.00003595999,0.00017973027,0.005928616,0.14750747,0.04502369,0.01876462,0.6018241,0.0029223063],"about_ca_topic_score_codex":0.00003416665,"about_ca_topic_score_gemma":0.000026510546,"teacher_disagreement_score":0.5271814,"about_ca_system_score_codex":0.000021387503,"about_ca_system_score_gemma":0.00012483777,"threshold_uncertainty_score":0.6740295},"labels":[],"label_agreement":null},{"id":"W2153109441","doi":"10.1093/bioinformatics/btu494","title":"STAMP: statistical analysis of taxonomic and functional profiles","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4314,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Python (programming language); Computer science; Graphical user interface; Software; R package; Exploratory data analysis; Statistical analysis; Data mining; Source code; Software package; Information retrieval; Programming language; Statistics; Mathematics","score_opus":0.36813942562374635,"score_gpt":0.47157612010780703,"score_spread":0.10343669448406068,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153109441","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020434024,0.000005060273,0.9747825,0.00004313407,0.0001487401,0.00021320638,0.00039560854,0.0000402408,0.0039374745],"genre_scores_gemma":[0.0913465,0.0000081555345,0.9084182,0.000075894735,0.000056776313,0.0000125826455,0.00001701913,0.00000982947,0.000055072942],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99806935,0.00019101046,0.0011188869,0.0001334977,0.0003010637,0.00018616764],"domain_scores_gemma":[0.97442913,0.024639,0.00039371612,0.00031026552,0.00010370498,0.0001241875],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002018413,0.0001383771,0.00068917905,0.00019041382,0.000046390425,0.000027807362,0.00009878015,0.00010868012,0.00045803256],"category_scores_gemma":[0.031612284,0.00011054218,0.00010242923,0.00029736137,0.00026113464,0.00007263636,0.00008472461,0.00011977053,0.000018826244],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005949864,0.000080610975,0.0034277155,0.00032390252,0.00060715835,2.6810787e-7,0.00010386137,0.00001867224,0.000027307426,0.97087324,0.0035547158,0.020923045],"study_design_scores_gemma":[0.0008860613,0.00024512317,0.031729545,0.000038327278,0.0020599498,0.0000022257038,0.00017785763,0.24155574,0.00027330054,0.7214663,0.0012759755,0.00028961242],"about_ca_topic_score_codex":0.0000041450207,"about_ca_topic_score_gemma":0.0000028090585,"teacher_disagreement_score":0.24940696,"about_ca_system_score_codex":0.000019757708,"about_ca_system_score_gemma":0.00003331175,"threshold_uncertainty_score":0.97654486},"labels":[],"label_agreement":null},{"id":"W2153167299","doi":"10.1093/bioinformatics/btr035","title":"OrthoNets: simultaneous visual analysis of orthologs and their interaction neighborhoods across different organisms","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; Hospital for Sick Children; University of Toronto","funders":"Canadian Institutes of Health Research; Hospital for Sick Children","keywords":"Identification (biology); Plug-in; Organism; Computer science; Protein–protein interaction; Computational biology; Model organism; Protein Interaction Networks; Biology; Genetics; Programming language; Gene; Ecology","score_opus":0.012393129576010705,"score_gpt":0.2534325284217612,"score_spread":0.2410393988457505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153167299","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9457866,0.00012307632,0.05243071,0.0000074195323,0.00014092444,0.00014527424,0.00008611646,0.000015367381,0.0012645449],"genre_scores_gemma":[0.9963866,0.00022055523,0.0028296718,0.00020094239,0.00003700016,0.000004267433,0.00025449749,0.000013709621,0.000052768228],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99893486,0.00001967756,0.0005655384,0.00013704781,0.00008469232,0.0002581832],"domain_scores_gemma":[0.99915636,0.00002999287,0.00032496842,0.00030543562,0.0000882628,0.000094985226],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015133273,0.00021493954,0.0003227243,0.00009193763,0.00007901763,0.000028565326,0.00015197047,0.00020206287,0.000037789046],"category_scores_gemma":[0.00003832496,0.00015888573,0.00014060173,0.00021547666,0.00011911566,0.000014092501,0.00020984559,0.0001019683,0.0000044087533],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017529151,0.0016806453,0.11290028,0.0009571744,0.014301246,0.000016709473,0.09997808,0.003972665,0.08133408,0.0015882925,0.0012126727,0.68030524],"study_design_scores_gemma":[0.002510414,0.00315661,0.05092549,0.00008348871,0.0014287098,0.00012289474,0.026696175,0.7591202,0.14680836,0.00032436743,0.007049577,0.0017736699],"about_ca_topic_score_codex":0.000014887632,"about_ca_topic_score_gemma":0.00005688304,"teacher_disagreement_score":0.7551476,"about_ca_system_score_codex":0.000010424327,"about_ca_system_score_gemma":0.000019397845,"threshold_uncertainty_score":0.6479172},"labels":[],"label_agreement":null},{"id":"W2153369847","doi":"10.1093/bioinformatics/btq588","title":"Interactive microbial genome visualization with GView","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":400,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; Public Health Agency of Canada; University of Alberta","funders":"","keywords":"Bitmap; Computer science; Zoom; Application programming interface; Interface (matter); Java; Documentation; File format; Visualization; Context (archaeology); Source code; Scalable Vector Graphics; Programming language; Graphical user interface; MIT License; Scalability; User interface; Operating system; World Wide Web; Computer graphics (images); License; Data mining; Biology","score_opus":0.006221952275581206,"score_gpt":0.23270774913820616,"score_spread":0.22648579686262496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153369847","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9911751,0.000094719995,0.0045460146,0.000038853515,0.00021331744,0.00017988484,0.000029231322,0.0000055652895,0.0037172816],"genre_scores_gemma":[0.98770607,0.000119799595,0.011379751,0.00030881172,0.00017252611,0.00000987751,0.00010395833,0.00001444788,0.00018474089],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99953747,0.0000065965496,0.00016157435,0.00009665318,0.000058849437,0.00013886],"domain_scores_gemma":[0.9995773,0.0000047488734,0.0000896399,0.00019509386,0.00008983825,0.00004341161],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000063779145,0.00011150129,0.00009180962,0.000026361953,0.00007027725,0.000029680363,0.00011108574,0.000069304864,0.00001564241],"category_scores_gemma":[0.000020370358,0.00008809161,0.000033711858,0.000050956234,0.000059064616,0.0000016862986,0.000075559896,0.000062597486,0.000024928084],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005390959,0.00003864836,0.0014238372,0.000038408765,0.000089111665,5.6208677e-7,0.00057794113,0.000031591197,0.9942716,0.00029471767,0.00058576546,0.0025939245],"study_design_scores_gemma":[0.0018866251,0.001169452,0.028286295,0.000032769214,0.00010096623,0.0001567696,0.00092445407,0.001266443,0.26890695,0.00008944243,0.6961918,0.000988026],"about_ca_topic_score_codex":0.0000037226898,"about_ca_topic_score_gemma":0.000049714454,"teacher_disagreement_score":0.7253646,"about_ca_system_score_codex":0.000004394551,"about_ca_system_score_gemma":0.000043154774,"threshold_uncertainty_score":0.35922718},"labels":[],"label_agreement":null},{"id":"W2153508883","doi":"10.1093/bioinformatics/btp103","title":"An integrative scoring system for ranking SNPs by their potential deleterious effects","year":2009,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":96,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Single-nucleotide polymorphism; SNP genotyping; SNP; Genetics; Biology; Human genome; Computational biology; Genome-wide association study; Genotyping; Genetic association; Bioinformatics; Gene; Genome; Genotype","score_opus":0.005550570813302565,"score_gpt":0.24179419929864818,"score_spread":0.2362436284853456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153508883","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.59765613,0.00020697547,0.40103245,0.000054401666,0.00023919453,0.00036779174,0.000064176544,0.00003083853,0.00034805672],"genre_scores_gemma":[0.9748211,0.0000435101,0.024097284,0.00036846215,0.00017293224,0.000028656248,0.00042202932,0.000010984892,0.000035053465],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99912435,0.000052512703,0.00032515047,0.00014786425,0.000062555344,0.00028759422],"domain_scores_gemma":[0.99940306,0.000026848627,0.00017993042,0.00023716163,0.000079951686,0.00007307126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027736768,0.00016666083,0.00021510124,0.00003303243,0.00015447167,0.000037857448,0.00017492255,0.00017802995,7.751375e-7],"category_scores_gemma":[0.000078060504,0.00013138042,0.00010383486,0.000045475867,0.000025135005,0.000009092914,0.000023549213,0.000058692076,0.0000027786537],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023016996,0.00018810456,0.0014163036,0.0003746738,0.00029858787,0.0000022981417,0.0021102373,0.0013726209,0.72721654,0.0006106314,0.014572097,0.25160778],"study_design_scores_gemma":[0.0077424394,0.010814872,0.012684436,0.00046845363,0.00030735726,0.00018386946,0.009779486,0.3578445,0.5738135,0.001018444,0.022977429,0.0023652231],"about_ca_topic_score_codex":0.000004966272,"about_ca_topic_score_gemma":0.0000033674157,"teacher_disagreement_score":0.377165,"about_ca_system_score_codex":0.000033377513,"about_ca_system_score_gemma":0.000034329893,"threshold_uncertainty_score":0.53575385},"labels":[],"label_agreement":null},{"id":"W2153606072","doi":"10.1093/bioinformatics/bth079","title":"Automated ordering of fingerprinted clones","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Genome British Columbia","funders":"","keywords":"Contig; Computer science; Fingerprint (computing); Software; clone (Java method); Sequence assembly; In silico; Data mining; Genome; Artificial intelligence; Biology; Genetics; DNA; Programming language; Gene","score_opus":0.0059434600040913456,"score_gpt":0.22119150124769435,"score_spread":0.215248041243603,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153606072","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98622537,0.0000507289,0.011749981,0.00003376687,0.00009484289,0.00008896938,0.00001638871,0.0000483364,0.0016916109],"genre_scores_gemma":[0.9555216,0.00006905975,0.044193942,0.0000620113,0.000024297358,0.000002861502,0.00007728932,0.0000114222585,0.00003752112],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99942774,0.0000038274356,0.00028551824,0.00007033007,0.00007479914,0.0001377914],"domain_scores_gemma":[0.9995343,0.0000029455186,0.00012689191,0.0002357994,0.000062342195,0.000037740043],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006898187,0.00009437738,0.000105076804,0.00003450647,0.000033861885,0.000012040033,0.00014222895,0.00008593186,0.0000044936833],"category_scores_gemma":[0.000039761682,0.000090170484,0.000053660573,0.00007101409,0.000041745498,0.0000032497378,0.00009502113,0.000034849534,0.000012526919],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007048572,0.00027243383,0.0032693013,0.0006946458,0.00026183602,0.0000029360128,0.0016937781,0.051715154,0.93074536,0.0037546896,0.0011749029,0.006344486],"study_design_scores_gemma":[0.0035939608,0.00087767426,0.011954206,0.00020107262,0.000062588835,0.00011521497,0.0013340489,0.20007153,0.7682403,0.0007668306,0.011777443,0.0010051834],"about_ca_topic_score_codex":0.000011749472,"about_ca_topic_score_gemma":0.000011519493,"teacher_disagreement_score":0.16250509,"about_ca_system_score_codex":0.000012560467,"about_ca_system_score_gemma":0.00006997541,"threshold_uncertainty_score":0.36770457},"labels":[],"label_agreement":null},{"id":"W2154130239","doi":"10.1093/bioinformatics/btv217","title":"Genome-scale strain designs based on regulatory minimal cut sets","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Microbial Metabolic Engineering and Bioproduction","field":"Biochemistry, Genetics and Molecular Biology","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Constraint (computer-aided design); Metabolic engineering; Computer science; Range (aeronautics); Set (abstract data type); Genome; MATLAB; Flux (metallurgy); Strain (injury); Scale (ratio); Gene knockout; Simple (philosophy); Key (lock); Theoretical computer science; Mathematical optimization; Gene; Mathematics; Biology; Genetics; Physics; Chemistry; Engineering; Programming language","score_opus":0.02035519260935907,"score_gpt":0.2313966490671417,"score_spread":0.2110414564577826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154130239","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97571975,0.00014954984,0.019219398,0.00015776942,0.0005650252,0.00027222728,0.000118249685,0.00006808025,0.0037299292],"genre_scores_gemma":[0.9651859,0.000015188531,0.032898862,0.00036884355,0.00044340352,0.000008504462,0.00039618285,0.000023781557,0.00065936946],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992937,0.000018039189,0.00021208216,0.00013385335,0.00014622246,0.00019611344],"domain_scores_gemma":[0.99938506,0.0000017761092,0.000065461085,0.000356543,0.00006542857,0.00012572322],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028239284,0.00013925623,0.000107926324,0.000055242588,0.00003642058,0.000021768214,0.000120615376,0.00012899106,0.000007790968],"category_scores_gemma":[0.0000591864,0.0001254591,0.000054546297,0.00007615354,0.000039836214,0.0000053371346,0.000027562357,0.00006628153,0.000049339968],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000107323955,0.000087010696,0.0001034542,0.00007019883,0.00002467587,0.000001057636,0.00024834526,0.007692456,0.9777202,0.000026482934,0.008901115,0.0050177],"study_design_scores_gemma":[0.0020162899,0.0013845238,0.0048885713,0.000046048186,0.000052357547,0.00004930745,0.0004920764,0.025277149,0.63673633,0.000023876677,0.32814968,0.0008838147],"about_ca_topic_score_codex":0.0000016137527,"about_ca_topic_score_gemma":0.000002082775,"teacher_disagreement_score":0.34098387,"about_ca_system_score_codex":0.00002067439,"about_ca_system_score_gemma":0.0000957154,"threshold_uncertainty_score":0.51160735},"labels":[],"label_agreement":null},{"id":"W2154164391","doi":"10.1093/bioinformatics/btt610","title":"A pathway-based data integration framework for prediction of disease progression","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":86,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"BC Cancer Agency; Engineering and Physical Sciences Research Council; Medical Research Council; University of Bristol; Cancer Research UK","keywords":"Computer science; Machine learning; Feature selection; Artificial intelligence; Classifier (UML); Predictive modelling; Data mining; Data type","score_opus":0.02166951579529282,"score_gpt":0.26652677860525836,"score_spread":0.24485726280996553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154164391","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013580967,0.00015635419,0.9834097,0.00018916214,0.00023316212,0.0010164235,0.0010855012,0.000021242546,0.0003074625],"genre_scores_gemma":[0.57170177,0.00004402012,0.4185099,0.00036153698,0.0002489372,0.00014196133,0.008920222,0.000020719273,0.00005093675],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991143,0.000010690805,0.00044774174,0.00012291763,0.00013125171,0.0001730985],"domain_scores_gemma":[0.99873793,0.000023965888,0.0002619834,0.0007239203,0.00014856749,0.00010365704],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020298938,0.00012710619,0.00011693087,0.000039468716,0.000064211796,0.000042572614,0.00030571068,0.00015840723,0.000013139705],"category_scores_gemma":[0.00016930254,0.00010188364,0.000062570296,0.00006539404,0.000057504232,0.00002850211,0.00012410356,0.00006489878,0.000009921322],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008269888,0.0005638133,0.0028816748,0.0020816654,0.00020564404,2.7592935e-7,0.00063600997,0.0012874219,0.022217654,0.011469185,0.09025208,0.8675776],"study_design_scores_gemma":[0.000868695,0.00057804515,0.0014991254,0.0002594099,0.00004520204,9.548066e-7,0.00022421994,0.9613419,0.012055803,0.004159719,0.018719997,0.00024691544],"about_ca_topic_score_codex":0.0000019455447,"about_ca_topic_score_gemma":0.0000013271438,"teacher_disagreement_score":0.9600545,"about_ca_system_score_codex":0.000008456324,"about_ca_system_score_gemma":0.00014225776,"threshold_uncertainty_score":0.41546944},"labels":[],"label_agreement":null},{"id":"W2154202919","doi":"10.1093/bioinformatics/bti057","title":"PSORTb v.2.0: Expanded prediction of bacterial protein subcellular localization and insights gained from comparative proteome analysis","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":723,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Simon Fraser University; Michael Smith Health Research BC","keywords":"Proteome; Computer science; n-gram; Subsequence; Support vector machine; Computational biology; MIT License; Subcellular localization; Biology; Artificial intelligence; Software; Bioinformatics; Genetics; Mathematics; Programming language; Language model","score_opus":0.011121309572131761,"score_gpt":0.23112521259350607,"score_spread":0.22000390302137432,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154202919","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8251913,0.000059904374,0.17363714,0.000016030457,0.000048915124,0.0005405703,0.00010133965,0.000024481631,0.00038029114],"genre_scores_gemma":[0.9697294,0.00002605553,0.027267003,0.00003309084,0.0000804228,0.000028344662,0.0027909817,0.000010640787,0.00003404932],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987788,0.000043288415,0.00064279774,0.00014902459,0.00022889483,0.00015720002],"domain_scores_gemma":[0.999035,0.000008216559,0.00041219033,0.00032656203,0.00013668802,0.000081312464],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013189764,0.0001952533,0.00030729958,0.00015377488,0.00008893712,0.000042868956,0.00013161915,0.0001929874,0.000020511043],"category_scores_gemma":[0.00007239404,0.00017262559,0.00008702922,0.00029815853,0.00012018184,0.00003165229,0.00009198807,0.000090450114,0.0000056225226],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009958898,0.00048005377,0.012944383,0.000900951,0.002956508,0.0000030027736,0.03426037,0.055822358,0.88881236,0.0011789986,0.00046824614,0.0011768983],"study_design_scores_gemma":[0.0045197555,0.0012884049,0.008666976,0.00014256575,0.0006003722,0.000007425035,0.0018988013,0.25254852,0.72466385,0.0006717031,0.004361083,0.0006305194],"about_ca_topic_score_codex":0.000048811286,"about_ca_topic_score_gemma":0.000034997443,"teacher_disagreement_score":0.19672617,"about_ca_system_score_codex":0.000025329247,"about_ca_system_score_gemma":0.000073480616,"threshold_uncertainty_score":0.7039467},"labels":[],"label_agreement":null},{"id":"W2154237723","doi":"10.1093/bioinformatics/btl538","title":"PROTERAN: animated terrain evolution for visual analysis of patterns in protein folding trajectory","year":2006,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Visualization; Energy landscape; Protein folding; Folding (DSP implementation); Data mining; Biology","score_opus":0.005096344942455624,"score_gpt":0.24225487652494349,"score_spread":0.23715853158248787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154237723","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85089254,0.000048754984,0.14806908,0.000008534412,0.000018012192,0.0006887823,0.00010844658,0.000009648162,0.00015617286],"genre_scores_gemma":[0.9880226,0.0000019438485,0.011179112,0.000020491509,0.00003783593,0.00009150293,0.0006021559,0.000009934349,0.000034396253],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99913496,0.000017823348,0.0004340647,0.00011761302,0.00010305395,0.00019251251],"domain_scores_gemma":[0.99956554,0.000005735732,0.00018674468,0.00016049364,0.00005919738,0.000022297245],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016424053,0.0001226927,0.00020226347,0.00022259697,0.000030472082,0.000013575285,0.00010003322,0.00014206463,0.0000032933692],"category_scores_gemma":[0.000029506538,0.00011482189,0.00012936242,0.0002769062,0.000026911925,0.000009942952,0.000031480045,0.000042916756,3.1361785e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002801685,0.00015270685,0.045583643,0.00057637977,0.00034109998,9.955072e-7,0.00031103133,0.0039256397,0.94518214,0.0009309697,0.00007683228,0.0026384052],"study_design_scores_gemma":[0.0028250497,0.0012233307,0.14497644,0.0001443092,0.00039553683,0.00000683014,0.0005763864,0.5142935,0.33346292,0.0005605731,0.00075048325,0.00078463444],"about_ca_topic_score_codex":0.00010996504,"about_ca_topic_score_gemma":0.00047466086,"teacher_disagreement_score":0.6117192,"about_ca_system_score_codex":0.000033637654,"about_ca_system_score_gemma":0.000045093162,"threshold_uncertainty_score":0.46823007},"labels":[],"label_agreement":null},{"id":"W2154348147","doi":"10.1093/bioinformatics/bts721","title":"Fragment recruitment on metabolic pathways: comparative metabolic profiling of metagenomes and metatranscriptomes","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Leibniz-Gemeinschaft; Deutsche Forschungsgemeinschaft","keywords":"KEGG; Metagenomics; Profiling (computer programming); Perl; Metabolic pathway; Computational biology; Biology; Java; Computer science; Bioinformatics; Gene; Transcriptome; Genetics; World Wide Web; Programming language","score_opus":0.04910625613312687,"score_gpt":0.26873570459960555,"score_spread":0.2196294484664787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154348147","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96309257,0.015799226,0.009598533,0.00011339988,0.0003357658,0.0024877544,0.00013947545,0.00003292655,0.008400339],"genre_scores_gemma":[0.9406764,0.0025182064,0.055605117,0.0005555105,0.00009121895,0.00021430921,0.00015407291,0.000021064483,0.00016408619],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99851745,0.000042350453,0.00071414973,0.00017735291,0.00022129511,0.00032740337],"domain_scores_gemma":[0.999005,0.000024290292,0.00031779252,0.00040158635,0.00010952282,0.00014180344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002879516,0.0002928776,0.0005069442,0.00011001685,0.00008925864,0.000059323764,0.00020791139,0.00013439431,0.000034364744],"category_scores_gemma":[0.000013927097,0.00022574913,0.00014579466,0.00012219742,0.0001293279,0.000027751083,0.000108263244,0.00011743162,0.0000358327],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043853148,0.0011215431,0.0025253585,0.0016468558,0.0070791105,0.0000027056522,0.024366766,0.0032796925,0.502048,0.117158905,0.012320801,0.32801172],"study_design_scores_gemma":[0.0028099935,0.0013497672,0.0054051136,0.000097127886,0.0004888962,0.000024343604,0.0070630503,0.0220974,0.8361112,0.0018457143,0.12146314,0.0012442438],"about_ca_topic_score_codex":0.000010807432,"about_ca_topic_score_gemma":0.0000026275052,"teacher_disagreement_score":0.33406317,"about_ca_system_score_codex":0.0000074593113,"about_ca_system_score_gemma":0.000054147924,"threshold_uncertainty_score":0.92057824},"labels":[],"label_agreement":null},{"id":"W2154408165","doi":"10.1093/bioinformatics/17.6.557","title":"Compositional symmetries in complete genomes","year":2001,"lang":"en","type":"article","venue":"Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":69,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children","funders":"","keywords":"Genome; Oligonucleotide; Homogeneous space; Basis (linear algebra); DNA; DNA sequencing; Computer science; Computational biology; Biology; Genetics; Mathematics; Gene","score_opus":0.018670551423125827,"score_gpt":0.23666133734492908,"score_spread":0.21799078592180327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154408165","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93439275,0.0016088147,0.031261764,0.00051850645,0.0002448284,0.00043605585,0.0000758882,0.00003370766,0.031427674],"genre_scores_gemma":[0.9681935,0.00073860306,0.02904279,0.0011060057,0.00013885181,0.000022087897,0.00024465492,0.000014199031,0.0004993621],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99942297,0.000017139335,0.00021462608,0.00007708267,0.00010462685,0.00016353054],"domain_scores_gemma":[0.99969375,0.000011846683,0.00005397909,0.00016089038,0.0000381188,0.00004141854],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012745673,0.000089814996,0.00009565472,0.00006528612,0.00004917216,0.000024334096,0.00012839455,0.0000738196,0.000046960107],"category_scores_gemma":[0.000028257913,0.00008378473,0.000041663618,0.000095669915,0.00003511636,0.000005851796,0.000052663767,0.00003503252,0.00007078238],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030952934,0.00021858425,0.016937815,0.00017969852,0.00011280349,0.000024356299,0.00055925036,0.00022497837,0.8976077,0.010866844,0.0062333164,0.066725135],"study_design_scores_gemma":[0.0017815769,0.00060952664,0.009119777,0.00008694854,0.000019489193,0.00022996792,0.0007751183,0.0028045087,0.31943735,0.002191959,0.6620878,0.000855991],"about_ca_topic_score_codex":0.0000045682846,"about_ca_topic_score_gemma":0.000009493532,"teacher_disagreement_score":0.65585446,"about_ca_system_score_codex":0.000010048785,"about_ca_system_score_gemma":0.000025931464,"threshold_uncertainty_score":0.34166422},"labels":[],"label_agreement":null},{"id":"W2154518589","doi":"10.1093/bioinformatics/btu181","title":"geiger v2.0: an expanded suite of methods for fitting macroevolutionary models to phylogenetic trees","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Evolution and Paleontology Studies","field":"Earth and Planetary Sciences","cited_by":1222,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Geiger counter; Computer science; Source code; R package; Phylogenetic tree; Suite; Scope (computer science); Code (set theory); Data mining; Data science; Biology; Set (abstract data type); Programming language; Genetics; Physics; Geography","score_opus":0.06591234001703411,"score_gpt":0.3228357091837009,"score_spread":0.2569233691666668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154518589","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23055369,0.001222192,0.7470203,0.000169485,0.0005261025,0.00059525104,0.00016793815,0.000079124206,0.019665904],"genre_scores_gemma":[0.5161876,0.000029342871,0.48322794,0.00033309904,0.00006346377,0.0000045913775,0.000052377538,0.0000022544305,0.00009930427],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99903363,0.0000889884,0.00038797423,0.00009568798,0.00009639725,0.00029734752],"domain_scores_gemma":[0.99908644,0.00039131008,0.0001328467,0.0001782426,0.000079694335,0.00013148614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007351557,0.000119219185,0.00022702049,0.00010076293,0.00016627612,0.00001260207,0.00016419154,0.000070616974,0.000045908986],"category_scores_gemma":[0.00013539816,0.00009709726,0.00006584794,0.00012404557,0.00007788761,0.00024576634,0.000014515796,0.000045041696,0.000022088841],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012492172,0.000055103763,0.5246338,0.00024514424,0.00009978952,1.07995405e-7,0.010826427,0.041425444,0.00014763589,0.0024144554,0.002695173,0.417332],"study_design_scores_gemma":[0.0002582322,0.00027700895,0.23302695,0.000014086854,0.000021287047,0.000004726368,0.0009139593,0.75885373,0.000097684904,0.0015844214,0.004788543,0.00015933633],"about_ca_topic_score_codex":0.00009194097,"about_ca_topic_score_gemma":0.0013871515,"teacher_disagreement_score":0.7174283,"about_ca_system_score_codex":0.0000033025767,"about_ca_system_score_gemma":0.000021886344,"threshold_uncertainty_score":0.39595112},"labels":[],"label_agreement":null},{"id":"W2154722286","doi":"10.1093/bioinformatics/btr556","title":"miREnvironment Database: providing a bridge for microRNAs, environmental factors and phenotypes","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"MicroRNA in disease regulation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":74,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Research Council Canada","keywords":"Phenotype; microRNA; Biology; Computational biology; Organism; Database; Bioinformatics; Genetics; Computer science; Gene","score_opus":0.023721835275175473,"score_gpt":0.22199157430721708,"score_spread":0.19826973903204162,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154722286","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98755276,0.00042447553,0.011053004,0.0000068473573,0.000053012816,0.00042613075,0.00035617806,0.000009946437,0.00011766522],"genre_scores_gemma":[0.9787949,0.00011522553,0.019664615,0.00006244779,0.000045215183,0.000022639408,0.0012156138,0.000017837172,0.0000615582],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99942195,0.000008157119,0.00019414819,0.00013884254,0.00006988492,0.00016698749],"domain_scores_gemma":[0.9995918,0.0000061645082,0.00009952387,0.00022031451,0.0000047732306,0.00007741817],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000068858964,0.00013727261,0.000085333006,0.000024945484,0.00007556499,0.000015372578,0.00008875142,0.00006955758,0.000019425557],"category_scores_gemma":[0.000017190278,0.00012272096,0.000046149242,0.000013407709,0.000072029194,0.000013932803,0.00010858077,0.000025267726,0.0000063975285],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011383443,0.00013302563,0.021608924,0.0002121776,0.00010241505,4.8924846e-7,0.0010921151,0.0000017868294,0.969245,0.00010241994,0.0021602763,0.0052275197],"study_design_scores_gemma":[0.0009940504,0.00027084522,0.11698019,0.000028280438,0.000089799905,0.000013561468,0.0004375555,0.0015072973,0.8381187,0.000040537518,0.041048255,0.0004709584],"about_ca_topic_score_codex":0.0000038157054,"about_ca_topic_score_gemma":0.000002177177,"teacher_disagreement_score":0.13112634,"about_ca_system_score_codex":0.000020490243,"about_ca_system_score_gemma":0.000016246611,"threshold_uncertainty_score":0.50044155},"labels":[],"label_agreement":null},{"id":"W2154865814","doi":"10.1093/bioinformatics/btr649","title":"Identifying quantitative trait loci via group-sparse multitask regression and feature selection: an imaging genetics study of the ADNI cohort","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":181,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Aging; University of California, San Diego; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; University of California, Los Angeles; Genentech; National Institutes of Health; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; Alzheimer's Association; Amorfix Life Sciences; Dana Foundation; Bayer HealthCare; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; National Center for Research Resources; F. Hoffmann-La Roche; Medpace; Bristol-Myers Squibb; Eli Lilly and Company; AstraZeneca; Novartis Pharmaceuticals Corporation; Synarc; Foundation for the National Institutes of Health; National Science Foundation","keywords":"Feature selection; Single-nucleotide polymorphism; Imaging genetics; Artificial intelligence; Computer science; Regression; Pairwise comparison; Computational biology; Interpretability; Neuroimaging; Machine learning; Pattern recognition (psychology); Biology; Genetics; Statistics; Mathematics; Genotype; Neuroscience","score_opus":0.03403405047364537,"score_gpt":0.29344337596239134,"score_spread":0.25940932548874596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154865814","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99002606,0.0002489198,0.0089164125,0.00002299781,0.00013305814,0.00040464787,0.000015269292,0.000009703603,0.0002229537],"genre_scores_gemma":[0.9554154,0.00008979601,0.044245876,0.000085649626,0.00003694283,0.000015101803,0.00004229675,0.000012945069,0.00005596767],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989952,0.00013865704,0.00036426843,0.00017762797,0.00013153195,0.00019275874],"domain_scores_gemma":[0.99915683,0.000016373144,0.0003375695,0.0002925085,0.00013625257,0.000060466973],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038426428,0.00015405871,0.0001904985,0.000042678537,0.00019368593,0.000015649535,0.00018785849,0.00012932961,0.0000068036225],"category_scores_gemma":[0.000085808686,0.00010997301,0.000054929595,0.00012135334,0.00010062211,0.000014759157,0.00014175876,0.000117023665,0.000001273005],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005259898,0.0002913851,0.9698684,0.000048482052,0.00016646646,5.1150823e-7,0.0072350674,0.0000918009,0.014607657,0.000054726348,0.0010542708,0.006528624],"study_design_scores_gemma":[0.0007424724,0.0006527403,0.96618533,0.000018968107,0.00013078387,0.000022475719,0.01006454,0.017542921,0.003966825,0.0001243915,0.00033099117,0.00021758527],"about_ca_topic_score_codex":0.000083533414,"about_ca_topic_score_gemma":0.00023345387,"teacher_disagreement_score":0.03532946,"about_ca_system_score_codex":0.000013558011,"about_ca_system_score_gemma":0.000026939211,"threshold_uncertainty_score":0.4484569},"labels":[],"label_agreement":null},{"id":"W2155201678","doi":"10.1093/bioinformatics/btt092","title":"EBARDenovo: highly accurate <i>de novo</i> assembly of RNA-Seq with efficient chimera-detection","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"De Bruijn graph; Sequence assembly; De Bruijn sequence; Computer science; Computational biology; De novo transcriptome assembly; Amplicon; RNA-Seq; Software; RNA; Chimera (genetics); Biology; Graph; Genetics; Gene; Transcriptome; Theoretical computer science; Mathematics; Programming language; Gene expression; Combinatorics; Polymerase chain reaction","score_opus":0.0070750471589631535,"score_gpt":0.20596737948605845,"score_spread":0.1988923323270953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155201678","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.988909,0.00020277462,0.006558338,0.000061335835,0.00011239389,0.00026582857,0.00001997381,0.000006766706,0.0038635996],"genre_scores_gemma":[0.993927,0.00012483925,0.0055105696,0.00014415133,0.000074170355,0.000026229141,0.000014390923,0.00001551346,0.0001631304],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991952,0.000013950822,0.00029918263,0.00011908896,0.0001278693,0.00024469232],"domain_scores_gemma":[0.9993027,0.000010552079,0.00018216103,0.0002774265,0.00015858079,0.00006857855],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010891363,0.0001568039,0.00015859763,0.000039081006,0.00007665656,0.00003046196,0.00014922077,0.00009092838,0.000006458084],"category_scores_gemma":[0.00002411851,0.0001222059,0.000059920803,0.00008813078,0.00007254727,0.0000020011453,0.00008631963,0.000055193246,0.00002621081],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004481894,0.000058173802,0.0003831601,0.0000758538,0.00012197878,4.1171606e-7,0.00036348333,0.0034130581,0.9904772,0.000040665876,0.00046981487,0.0045513627],"study_design_scores_gemma":[0.00088256726,0.0008061447,0.008170051,0.000024397168,0.000048935603,0.000036472422,0.00049490796,0.008267589,0.97391593,0.000022912298,0.0069898874,0.00034017238],"about_ca_topic_score_codex":0.000040911345,"about_ca_topic_score_gemma":0.000014449503,"teacher_disagreement_score":0.016561255,"about_ca_system_score_codex":0.000013640701,"about_ca_system_score_gemma":0.00006280403,"threshold_uncertainty_score":0.49834126},"labels":[],"label_agreement":null},{"id":"W2155886619","doi":"10.1093/bioinformatics/btv065","title":"Where are we at regarding species translation? A review of the sbv IMPROVER challenge","year":2015,"lang":"en","type":"review","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Translation (biology); Computer science; Biology","score_opus":0.07257934998167527,"score_gpt":0.2985734266777903,"score_spread":0.22599407669611504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155886619","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000040697796,0.9913205,0.000014429187,0.00020734245,0.00027723343,0.000813564,0.00030737492,0.0000028080128,0.0070526586],"genre_scores_gemma":[0.0000041375233,0.99785566,0.00053576543,0.00007490121,0.00018520046,0.00003196344,0.00007129795,0.000029571991,0.001211496],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99855494,0.00006237857,0.00077736634,0.00017617921,0.00022786912,0.0002012456],"domain_scores_gemma":[0.9981886,0.000020872825,0.0008459971,0.00073222595,0.00015711358,0.00005518106],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031399232,0.00033386648,0.00096436724,0.000029714009,0.00008426164,0.000011805635,0.0004227556,0.00027735656,0.0000138577525],"category_scores_gemma":[0.000048775062,0.00020492684,0.00059426104,0.00011351342,0.00009196968,0.0000013796313,0.00035596025,0.00013105739,0.0000130733015],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000063359566,0.000031647036,0.000009438336,0.34936488,0.0005333721,5.1201516e-7,0.0003487153,0.0000013447848,0.000024918723,0.000056618523,0.060320638,0.5893016],"study_design_scores_gemma":[0.00012337163,0.00004929808,0.000001843244,0.030532256,0.00039322648,0.000012843189,0.00008496985,0.0000042747124,0.00001783226,0.000006429429,0.9685415,0.00023217249],"about_ca_topic_score_codex":9.1649093e-7,"about_ca_topic_score_gemma":0.000021417529,"teacher_disagreement_score":0.9082208,"about_ca_system_score_codex":0.00004440011,"about_ca_system_score_gemma":0.00018894074,"threshold_uncertainty_score":0.8356674},"labels":[],"label_agreement":null},{"id":"W2156124616","doi":"10.1093/bioinformatics/btm452","title":"Leveraging the structure of the Semantic Web to enhance information retrieval for proteomics","year":2007,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institutes of Health; National Institute of General Medical Sciences; McGill University","keywords":"Computer science; Information retrieval; Graph; Leverage (statistics); SPARQL; RDF; Subgraph isomorphism problem; Semantic Web; Artificial intelligence; Theoretical computer science","score_opus":0.009301903491705083,"score_gpt":0.26632088811460186,"score_spread":0.2570189846228968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156124616","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85702074,0.000038687605,0.14118546,0.000618278,0.0002909339,0.0005967266,0.00004403594,0.000010781362,0.00019433026],"genre_scores_gemma":[0.9691372,0.000008122308,0.029764218,0.000906106,0.00008631632,0.00000234766,0.000023878003,0.0000046063783,0.00006719178],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992741,0.000009278537,0.00032790875,0.00005380419,0.00015120351,0.00018371249],"domain_scores_gemma":[0.99937147,0.00003449891,0.0001720707,0.00028429378,0.00010307791,0.000034593373],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035322897,0.000086996704,0.00008684798,0.00002671034,0.00011047252,0.000020933436,0.00030085188,0.00012143861,0.0000016481033],"category_scores_gemma":[0.00055930414,0.00004714064,0.00006175328,0.00013840811,0.00009430789,0.0000070947376,0.000113738555,0.000078002086,0.0000021719115],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00058828486,0.000033017826,0.0013634198,0.00067480217,0.00012150659,1.5089059e-7,0.007123276,0.00030698633,0.84145904,0.00038663842,0.017067222,0.13087565],"study_design_scores_gemma":[0.000253139,0.00018035044,0.0016068527,0.000041382507,0.000016547927,0.000008379809,0.0012438152,0.0020408109,0.91356814,0.00010964524,0.08080287,0.00012808134],"about_ca_topic_score_codex":0.0000021298304,"about_ca_topic_score_gemma":0.000010020105,"teacher_disagreement_score":0.13074757,"about_ca_system_score_codex":0.00001134614,"about_ca_system_score_gemma":0.00007864265,"threshold_uncertainty_score":0.19223393},"labels":[],"label_agreement":null},{"id":"W2156216305","doi":"10.1093/bioinformatics/bts109","title":"Mirroring co-evolving trees in the light of their topologies","year":2012,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Network topology; Heuristics; Similarity (geometry); Computer science; Mirroring; Domain (mathematical analysis); Tree (set theory); Phylogenetic tree; Maximization; Distance matrix; Enhanced Data Rates for GSM Evolution; Theoretical computer science; Algorithm; Mathematics; Mathematical optimization; Artificial intelligence; Combinatorics; Biology","score_opus":0.019062205201531856,"score_gpt":0.25261054783164744,"score_spread":0.2335483426301156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156216305","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89268434,0.0035047268,0.0041584526,0.0004290535,0.00047384622,0.00048328453,0.000037119153,0.000021980293,0.098207206],"genre_scores_gemma":[0.99625325,0.00015262498,0.0030771033,0.00025461713,0.0001265631,0.000008793792,0.00003859351,0.000006950087,0.000081473445],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99914527,0.000024233721,0.00038443186,0.000049047543,0.00009996008,0.0002970546],"domain_scores_gemma":[0.9994272,0.000026534593,0.00015573384,0.00032867686,0.000026134374,0.00003571531],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052014453,0.0001246429,0.00013688761,0.00004623641,0.000054782093,0.000022272776,0.00030182398,0.00012075113,0.000010088577],"category_scores_gemma":[0.000038387963,0.00007818302,0.00007297453,0.000087059445,0.00006768942,0.000019533543,0.000087272354,0.00009375692,0.000009679741],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003842702,0.0013846213,0.25501874,0.0013164707,0.0007603271,0.0000042745364,0.16739385,0.0011173992,0.19768621,0.04811577,0.12023303,0.20658505],"study_design_scores_gemma":[0.0023618168,0.00083106617,0.06962829,0.00021712534,0.00007531128,0.0001367519,0.0692934,0.011950268,0.2158629,0.00089447614,0.62729543,0.0014531882],"about_ca_topic_score_codex":0.000005368625,"about_ca_topic_score_gemma":0.000014151817,"teacher_disagreement_score":0.5070624,"about_ca_system_score_codex":0.0000088000525,"about_ca_system_score_gemma":0.000023058574,"threshold_uncertainty_score":0.31882107},"labels":[],"label_agreement":null},{"id":"W2156553312","doi":"10.1093/bioinformatics/btp028","title":"Gene network reconstruction from transcriptional dynamics under kinetic model uncertainty: a case for the second derivative","year":2009,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; ENCODE; Bayesian probability; Expression (computer science); Bayesian network; Gene; Gene regulatory network; Representation (politics); Transcription (linguistics); Computational biology; Gene expression; Theoretical computer science; Data mining; Algorithm; Biology; Artificial intelligence; Genetics","score_opus":0.013357795792574708,"score_gpt":0.2265834792411285,"score_spread":0.2132256834485538,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156553312","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36767134,0.0006267772,0.6304889,0.0002926193,0.00015207575,0.00031995366,0.0002555591,0.000015475649,0.00017732392],"genre_scores_gemma":[0.93332154,0.000069625276,0.06393857,0.0010323172,0.00041752303,0.000027693153,0.0008572733,0.00001592328,0.00031951393],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99903846,0.000022926348,0.00037331504,0.00017840676,0.000115383606,0.00027151898],"domain_scores_gemma":[0.9992561,0.000036767804,0.00016111886,0.00035377458,0.000121528465,0.00007072684],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015298385,0.00018991032,0.00016742038,0.000029010325,0.00024552908,0.00004670739,0.00015854377,0.00016725564,0.000026274138],"category_scores_gemma":[0.000013205883,0.00015121003,0.00018652774,0.00012365801,0.00008323311,0.000011201434,0.000023010445,0.00008125738,0.000002496291],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010049478,0.000025018951,0.00006224523,0.000014642957,0.000337953,0.0000019586614,0.0001684332,0.96515346,0.004599501,0.001039603,0.0025181333,0.025978547],"study_design_scores_gemma":[0.0004846176,0.000098789584,0.00025706756,0.000007885941,0.00014270662,0.00017848487,0.00035679663,0.9906154,0.001377099,0.0047967816,0.0014755228,0.00020879095],"about_ca_topic_score_codex":0.000008325633,"about_ca_topic_score_gemma":0.0004350932,"teacher_disagreement_score":0.5665503,"about_ca_system_score_codex":0.00005423914,"about_ca_system_score_gemma":0.000091009715,"threshold_uncertainty_score":0.6166166},"labels":[],"label_agreement":null},{"id":"W2156733952","doi":"10.1093/bioinformatics/btn444","title":"Seeder: discriminative seeding DNA motif discovery","year":2008,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Centre Sève; Fonds Québécois de la Recherche sur la Nature et les Technologies; Norges Teknisk-Naturvitenskapelige Universitet","keywords":"Discriminative model; Computational biology; Computer science; DNA binding site; Promoter; Benchmark (surveying); Transcription factor; Biology; Data mining; Artificial intelligence; Genetics; Gene; Gene expression","score_opus":0.012101206424195807,"score_gpt":0.2174705794309284,"score_spread":0.20536937300673258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156733952","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97437394,0.00008331547,0.014728743,0.000064780186,0.0002063639,0.00014168106,0.00005615839,0.000020817612,0.010324183],"genre_scores_gemma":[0.9883147,0.00028673784,0.009056673,0.00022121237,0.00014234801,0.000008048788,0.00020527291,0.000022189983,0.0017428144],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99914306,0.000010605825,0.00029652266,0.0001424174,0.00014563816,0.00026175988],"domain_scores_gemma":[0.9994291,0.0000088038005,0.00013029517,0.00029525827,0.00005839521,0.000078138924],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008361337,0.00017525704,0.00014228762,0.000042701475,0.00018847802,0.00004929094,0.00021301494,0.00011445626,0.000007130156],"category_scores_gemma":[0.000037262624,0.0001579107,0.000099665405,0.00007142079,0.00011118148,0.000021308271,0.0001792844,0.000075863005,0.000026642916],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002933031,0.0008527333,0.061200276,0.0011172404,0.0010518063,0.00008439025,0.020619089,0.0036288882,0.8125288,0.010041775,0.06821712,0.020364609],"study_design_scores_gemma":[0.007770184,0.0030154332,0.16044414,0.00029662668,0.0003264665,0.0020908145,0.01928551,0.24782528,0.39867046,0.0018206507,0.15244879,0.006005629],"about_ca_topic_score_codex":0.000005488548,"about_ca_topic_score_gemma":0.000006385831,"teacher_disagreement_score":0.4138583,"about_ca_system_score_codex":0.00002592574,"about_ca_system_score_gemma":0.00007527308,"threshold_uncertainty_score":0.64394116},"labels":[],"label_agreement":null},{"id":"W2156847802","doi":"10.1093/bioinformatics/btl094","title":"Combining multi-species genomic data for microRNA identification using a Naïve Bayes classifier","year":2006,"lang":"en","type":"article","venue":"Bioinformatics","topic":"MicroRNA in disease regulation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":181,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"National Cancer Institute; National Center for Research Resources; Natural Sciences and Engineering Research Council of Canada; Pennsylvania Department of Health; National Science Foundation","keywords":"False positive paradox; Bayes' theorem; Naive Bayes classifier; Classifier (UML); Computer science; Artificial intelligence; Gene prediction; Genome; Computational biology; Machine learning; Data mining; Gene; Biology; Support vector machine; Bayesian probability; Genetics","score_opus":0.05732768182420857,"score_gpt":0.29172140772989985,"score_spread":0.2343937259056913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156847802","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.63745666,0.0004609545,0.3604721,0.00003725807,0.00022429168,0.0005007974,0.0006593167,0.000025922835,0.00016270122],"genre_scores_gemma":[0.85173744,0.000030176696,0.13905042,0.000088370885,0.00033404864,0.00001852108,0.00809124,0.000037125308,0.00061264576],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99903345,0.000015192859,0.00044868575,0.0002042564,0.00009367065,0.00020476563],"domain_scores_gemma":[0.99887115,0.000012709618,0.00027357545,0.0006952747,0.00010802204,0.00003925031],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000206664,0.0001394404,0.000114915514,0.000056089422,0.00014490713,0.00010195408,0.00033710254,0.00012278819,0.000005905808],"category_scores_gemma":[0.00006733067,0.00014449694,0.000061747465,0.00006125173,0.000067243374,0.000027312173,0.000204239,0.000036157995,0.000012708208],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023209026,0.000043959095,0.0006460162,0.00008935116,0.000032575146,1.464014e-7,0.00004258045,0.00033249147,0.9924705,0.00013298594,0.005618883,0.0005673015],"study_design_scores_gemma":[0.0021058184,0.00006481558,0.041177265,0.00006071142,0.00015456606,0.000025739844,0.00045025753,0.55989903,0.28536838,0.0001287631,0.109892674,0.0006719816],"about_ca_topic_score_codex":0.000010994856,"about_ca_topic_score_gemma":0.000028310484,"teacher_disagreement_score":0.7071021,"about_ca_system_score_codex":0.000041464664,"about_ca_system_score_gemma":0.00008576682,"threshold_uncertainty_score":0.5892414},"labels":[],"label_agreement":null},{"id":"W2156923845","doi":"10.1093/bioinformatics/btn146","title":"Guided genome halving: hardness, heuristics and the history of the Hemiascomycetes","year":2008,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Canada Research Chairs","keywords":"Genome; Ancestor; Heuristics; Computer science; Event (particle physics); Genome evolution; Heuristic; Biology; Evolutionary biology; Computational biology; Genetics; Gene; Artificial intelligence; Physics","score_opus":0.018734386632463865,"score_gpt":0.20116576835242958,"score_spread":0.1824313817199657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156923845","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93188536,0.021207806,0.004393684,0.0011094318,0.0024325156,0.0015760984,0.00008205777,0.000047264315,0.03726578],"genre_scores_gemma":[0.975642,0.0028086335,0.009267862,0.0007933566,0.00021021854,0.000024655032,0.00005219569,0.000031369866,0.011169674],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992376,0.000031492436,0.00031634522,0.00008591053,0.00017426285,0.00015438754],"domain_scores_gemma":[0.9991925,0.000016789005,0.00019415513,0.0004739988,0.0000858456,0.000036757672],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021734736,0.000121023986,0.0001495068,0.000020727364,0.000096153926,0.0000074508625,0.00030895093,0.000073219104,0.000009945221],"category_scores_gemma":[0.0001476332,0.00007071679,0.00008977245,0.000052131727,0.00060204224,0.0000045913434,0.0002475285,0.000071430186,0.000005170099],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005071972,0.00045603502,0.0473452,0.0021729898,0.001545904,0.000013981118,0.032368153,0.00061022013,0.22976711,0.0049841595,0.67213523,0.008093805],"study_design_scores_gemma":[0.004496999,0.00016082021,0.020932203,0.00004168945,0.00015250567,0.00028623396,0.0006772723,0.0064851693,0.013320609,0.0002273591,0.9526491,0.0005700146],"about_ca_topic_score_codex":0.000009417969,"about_ca_topic_score_gemma":0.0000016169425,"teacher_disagreement_score":0.28051388,"about_ca_system_score_codex":0.000035301447,"about_ca_system_score_gemma":0.00013601745,"threshold_uncertainty_score":0.2883747},"labels":[],"label_agreement":null},{"id":"W2157460239","doi":"10.1093/bioinformatics/btt178","title":"Assembling the 20 Gb white spruce (<i>Picea glauca</i>) genome from whole-genome shotgun sequencing data","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":393,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ministry of Forests; Government of British Columbia; Simon Fraser University; University of British Columbia","funders":"BC Cancer Agency; Canada's Michael Smith Genome Sciences Centre","keywords":"Shotgun sequencing; Sequence assembly; Genome; Shotgun; Hybrid genome assembly; Biology; Computational biology; Whole genome sequencing; Illumina dye sequencing; Genomics; DNA sequencing; Reference genome; Genome project; Genetics; Gene; Transcriptome","score_opus":0.03217634457678138,"score_gpt":0.2396316445186623,"score_spread":0.20745529994188094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157460239","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9866604,0.0026649705,0.0044562053,0.0007907371,0.00037886683,0.00058436574,0.0011809851,0.000018215796,0.0032652046],"genre_scores_gemma":[0.9621523,0.0008878522,0.029129963,0.0024939047,0.0010661139,0.000050860996,0.0031912953,0.000061925784,0.00096578634],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99837124,0.000038702157,0.00055299985,0.0003457967,0.00022368426,0.00046758278],"domain_scores_gemma":[0.9978464,0.00003626559,0.00023919207,0.0016118496,0.0001408532,0.00012540497],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031669874,0.0003006603,0.00024913682,0.00004094138,0.00029980432,0.00022025913,0.001212028,0.00016213735,0.000051597046],"category_scores_gemma":[0.00007446704,0.00022425126,0.00008923375,0.00012518256,0.00011153545,0.000014790992,0.0011389119,0.00016311152,0.00027341046],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010974377,0.000020540703,0.0026867038,0.000038856208,0.00025519868,0.0000012808432,0.0011774345,0.00084936444,0.9897457,0.00001562106,0.0034173117,0.0017810581],"study_design_scores_gemma":[0.0018704368,0.00043689783,0.073961966,0.000068711815,0.00036118276,0.00006265592,0.008522984,0.042222816,0.014282234,0.00073799695,0.8552854,0.0021867263],"about_ca_topic_score_codex":0.00014408557,"about_ca_topic_score_gemma":0.00008331267,"teacher_disagreement_score":0.97546345,"about_ca_system_score_codex":0.000033973673,"about_ca_system_score_gemma":0.000133954,"threshold_uncertainty_score":0.9144701},"labels":[],"label_agreement":null},{"id":"W2157673856","doi":"10.1093/bioinformatics/btu677","title":"flowDensity: reproducing manual gating of flow cytometry data by automated density-based cell population identification","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":139,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institute of Allergy and Infectious Diseases; National Institutes of Health","keywords":"Bioconductor; Computer science; Bivariate analysis; Gating; Source code; Data set; Identification (biology); Population; Data mining; Set (abstract data type); Code (set theory); Artificial intelligence; Programming language; Machine learning; Biology","score_opus":0.014861539705209686,"score_gpt":0.2517141235168281,"score_spread":0.23685258381161842,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157673856","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.855257,0.00003897964,0.14397874,0.000029090043,0.0002189281,0.00015210017,0.000111715286,0.000074953256,0.00013850458],"genre_scores_gemma":[0.9580938,0.000008939263,0.035636324,0.00014565406,0.0000943851,0.0000016844725,0.005950471,0.000018979112,0.000049757895],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986795,0.000052815412,0.0005808565,0.0002836225,0.0002220499,0.0001811508],"domain_scores_gemma":[0.998406,0.00002290515,0.0003306581,0.0010540896,0.00013051099,0.000055824843],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000707061,0.00014843185,0.00018408163,0.00007761607,0.00010502604,0.000047773345,0.00031183206,0.00020874577,0.0000027504416],"category_scores_gemma":[0.00028705157,0.00015359386,0.000050195333,0.00015577306,0.00003818978,0.000024931755,0.000101588004,0.00010204454,0.000009538669],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047608537,0.0001014298,0.014906455,0.0004003338,0.00002553487,2.1744772e-7,0.00015182063,0.0017762604,0.9706158,0.000004283209,0.00411793,0.0078523075],"study_design_scores_gemma":[0.00033779762,0.0000595751,0.003860492,0.000023095796,0.000028741566,0.0000019259683,0.00003856815,0.56612885,0.42890337,0.0000037928658,0.00046746546,0.00014632703],"about_ca_topic_score_codex":0.000067342,"about_ca_topic_score_gemma":0.000020214515,"teacher_disagreement_score":0.5643526,"about_ca_system_score_codex":0.000018168848,"about_ca_system_score_gemma":0.000034083187,"threshold_uncertainty_score":0.6263376},"labels":[],"label_agreement":null},{"id":"W2157748357","doi":"10.1093/bioinformatics/bti054","title":"Circular genome visualization and exploration using CGView","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1122,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Genome Prairie; Genome Canada","keywords":"Scalable Vector Graphics; Visualization; Computer science; Java applet; Genome; Graphics; Documentation; Sample (material); World Wide Web; XML; Computer graphics; Computer graphics (images); Java; Information retrieval; Data mining; Biology; Programming language; Genetics","score_opus":0.029482022421761275,"score_gpt":0.26261835932282573,"score_spread":0.23313633690106444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157748357","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9013913,0.0017274993,0.09631797,0.000031364616,0.00006952013,0.00015439409,0.000008907173,0.0000043256628,0.00029471543],"genre_scores_gemma":[0.98737776,0.0014915387,0.010750545,0.00020699679,0.00008442295,0.000005078862,0.000061348415,0.000010850382,0.000011453372],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995604,0.0000069653893,0.00017570546,0.00008573439,0.00006229462,0.000108913446],"domain_scores_gemma":[0.99972,0.0000014676442,0.000067876405,0.00012534163,0.000047826743,0.000037526403],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007673155,0.00008825802,0.00007885734,0.000027286433,0.000092513175,0.000028175406,0.000046410834,0.0000573768,0.0000012454748],"category_scores_gemma":[0.000017606864,0.00008524041,0.000025328993,0.0000518023,0.000034908422,0.0000033627675,0.00006105581,0.000017835018,0.0000044926496],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020851436,0.000065651504,0.0013007232,0.0003090952,0.00014898418,0.0000014953657,0.0032889936,0.009551961,0.97625357,0.0049130227,0.000046723606,0.00409894],"study_design_scores_gemma":[0.013863985,0.0035352649,0.04029803,0.00041115322,0.0007867994,0.00057685474,0.015308934,0.0742966,0.4994317,0.018309921,0.32743138,0.0057493793],"about_ca_topic_score_codex":0.0000057724606,"about_ca_topic_score_gemma":0.0000030653307,"teacher_disagreement_score":0.47682187,"about_ca_system_score_codex":0.000012831263,"about_ca_system_score_gemma":0.00003612517,"threshold_uncertainty_score":0.3476003},"labels":[],"label_agreement":null},{"id":"W2158026707","doi":"10.1093/bioinformatics/btt348","title":"PING 2.0: an R/Bioconductor package for nucleosome positioning using next-generation sequencing data","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Clinical Research Institute","funders":"National Human Genome Research Institute","keywords":"Bioconductor; R package; Computer science; DNA sequencing; Nucleosome; Ping (video games); Software; Software package; Computational biology; Data mining; Biology; Computational science; Programming language; Genetics; Computer network; DNA; Histone","score_opus":0.10728624577053644,"score_gpt":0.2843603002387506,"score_spread":0.17707405446821414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2158026707","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91183054,0.00006105468,0.08718347,0.000038639966,0.00018201765,0.00042919235,0.00015241305,0.000020014179,0.00010268379],"genre_scores_gemma":[0.71750873,0.000023432205,0.27757886,0.0003233785,0.00041956973,0.000015957077,0.0040699746,0.00003098639,0.00002912863],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990532,0.000016809878,0.00036521212,0.00021241851,0.000091122674,0.00026128333],"domain_scores_gemma":[0.9986363,0.0000071025097,0.0001807128,0.00095779356,0.00012512639,0.0000929655],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018708622,0.00015585015,0.00012395762,0.000042575695,0.00023648591,0.00029036263,0.0004777493,0.00013287521,0.000013756989],"category_scores_gemma":[0.000081385406,0.00015796011,0.000043649903,0.000051293937,0.000033210254,0.00011304778,0.00026805175,0.0000528292,0.0000130662365],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002440222,0.000012083788,0.000050005627,0.000054582346,0.000024325886,1.3481754e-7,0.00015944429,0.0005034269,0.9970558,0.00012653496,0.00054678577,0.0014644332],"study_design_scores_gemma":[0.00028925372,0.000121148056,0.000057014786,0.000019243793,0.000025284566,0.000021450896,0.0007119201,0.93974257,0.057969186,0.00012277243,0.0006530997,0.0002670603],"about_ca_topic_score_codex":0.000038005637,"about_ca_topic_score_gemma":0.000017740227,"teacher_disagreement_score":0.93923914,"about_ca_system_score_codex":0.00004842216,"about_ca_system_score_gemma":0.0001142202,"threshold_uncertainty_score":0.6441426},"labels":[],"label_agreement":null},{"id":"W2158376448","doi":"10.1093/bioinformatics/btp045","title":"QMSim: a large-scale genome simulator for livestock","year":2009,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic and phenotypic traits in livestock","field":"Biochemistry, Genetics and Molecular Biology","cited_by":399,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Executable; Computer science; Population; Scale (ratio); Pedigree chart; Programming language; Biology; Genetics; Cartography; Geography","score_opus":0.010195448025228832,"score_gpt":0.2439689393708104,"score_spread":0.23377349134558156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2158376448","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3587419,0.0005807659,0.63148266,0.0002076596,0.00029945996,0.0009780258,0.00023755354,0.000060857816,0.007411097],"genre_scores_gemma":[0.6381629,0.000023651803,0.3572983,0.0017656956,0.0004907499,0.00002769484,0.00032573772,0.00002306085,0.0018821708],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99903965,0.0000099002245,0.00030788776,0.00016815595,0.00011324124,0.00036115476],"domain_scores_gemma":[0.99930584,0.000012718784,0.00009832815,0.0003748001,0.000080871134,0.00012745561],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011958168,0.00017763942,0.00015376508,0.000034371416,0.000120195284,0.00003052772,0.0002385243,0.00016831637,0.000018848677],"category_scores_gemma":[0.000047189686,0.00016483525,0.00011517675,0.00006227917,0.000035853176,0.000006398104,0.00004643592,0.0000602082,0.000035727266],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003693771,0.0057689794,0.005653778,0.002237606,0.0014548386,0.0000043152427,0.03380809,0.11258033,0.27108666,0.1561797,0.21456528,0.19296667],"study_design_scores_gemma":[0.005398133,0.006797223,0.07562892,0.000046939593,0.0001483942,0.00003969522,0.0015389882,0.016641906,0.013489027,0.009627755,0.8690333,0.001609714],"about_ca_topic_score_codex":3.6349059e-7,"about_ca_topic_score_gemma":0.00000194729,"teacher_disagreement_score":0.654468,"about_ca_system_score_codex":0.000009222652,"about_ca_system_score_gemma":0.00006829609,"threshold_uncertainty_score":0.6721787},"labels":[],"label_agreement":null},{"id":"W2158404603","doi":"10.1093/bioinformatics/bts082","title":"Early immunologic correlates of HIV protection can be identified from computational analysis of complex multivariate T-cell flow cytometry assays","year":2012,"lang":"en","type":"article","venue":"Bioinformatics","topic":"HIV Research and Treatment","field":"Immunology and Microbiology","cited_by":72,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Michael Smith Health Research BC; University of British Columbia; BC Cancer Agency","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada; Walter Reed National Military Medical Center; National Institute of Biomedical Imaging and Bioengineering; Michael Smith Health Research BC; U.S. Public Health Service; Compute Canada; Canadian Institutes of Health Research; Uniformed Services University of the Health Sciences; Vaccine Research Center; National Institute of Allergy and Infectious Diseases; Terry Fox Research Institute; Western Canada Research Grid; National Institutes of Health; U.S. Department of Health and Human Services","keywords":"Bioconductor; Multivariate statistics; Multivariate analysis; Flow cytometry; Identification (biology); Computer science; Computational biology; Documentation; Biology; Data mining; Immunology; Machine learning; Genetics","score_opus":0.035279313773383635,"score_gpt":0.2667180177372091,"score_spread":0.23143870396382546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2158404603","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9765528,0.00030130145,0.019188767,0.000031146898,0.00015944743,0.00034805314,0.002811211,0.000033024833,0.0005742689],"genre_scores_gemma":[0.9906253,0.000013077011,0.005477552,0.000013081416,0.000006200649,0.00001557743,0.0036258728,0.0000060787697,0.00021724688],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988258,0.0001303558,0.0005581071,0.00009058166,0.000103950144,0.00029120577],"domain_scores_gemma":[0.99896187,0.00023502868,0.00038474836,0.00022270222,0.00016132984,0.000034324716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025962,0.00014179335,0.00039620014,0.00045759382,0.000104836174,0.000011633174,0.00015686588,0.00018249106,0.00047603654],"category_scores_gemma":[0.0000737492,0.000114883216,0.00016488369,0.00055367366,0.00017645153,0.00015115667,0.00008335,0.00017234642,0.0002879473],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00096086215,0.0038680306,0.4557109,0.000397415,0.02608025,0.00000406767,0.023752244,0.010100083,0.453543,0.00045646506,0.0021807777,0.022945903],"study_design_scores_gemma":[0.0032092882,0.00030466638,0.9304981,0.000023754877,0.00084175525,0.0000035211842,0.0011253051,0.03425103,0.029142475,0.000054427543,0.00033169752,0.0002139475],"about_ca_topic_score_codex":0.0006439914,"about_ca_topic_score_gemma":0.0000134206475,"teacher_disagreement_score":0.47478724,"about_ca_system_score_codex":0.00005780264,"about_ca_system_score_gemma":0.000046103774,"threshold_uncertainty_score":0.52122664},"labels":[],"label_agreement":null},{"id":"W2158576281","doi":"10.1093/bioinformatics/bti829","title":"Quality classification of tandem mass spectrometry data","year":2005,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institute for Theoretical Astrophysics","keywords":"Mascot; Identification (biology); Computer science; Bottleneck; Tandem mass spectrometry; Process (computing); Data mining; Replicate; Quality (philosophy); Mass spectrometry; Artificial intelligence; Information retrieval; Chemistry; Chromatography; Mathematics; Biology; Statistics","score_opus":0.0656602963842446,"score_gpt":0.34696959766278473,"score_spread":0.28130930127854015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2158576281","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027491214,0.000058291625,0.8567832,0.00039652735,0.000012529307,0.00014130758,0.00035354582,0.00018873002,0.11457461],"genre_scores_gemma":[0.32696941,0.00007906086,0.672326,0.000033817243,0.0000621594,0.00001080943,0.00028413752,0.000007173056,0.00022742397],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99914175,0.0000031493,0.00048634483,0.000100086814,0.00015167428,0.0001170028],"domain_scores_gemma":[0.9985254,0.000039263974,0.0003252402,0.0010239239,0.00004679633,0.000039373397],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019341131,0.000079707715,0.00012474896,0.00003210988,0.000044600092,0.000013641555,0.0004700772,0.00008148352,0.0001686294],"category_scores_gemma":[0.000057264755,0.00007660992,0.00002865412,0.00012279932,0.00004685287,0.00026911072,0.000099325545,0.00010741829,0.0000333924],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021291075,0.0002425453,0.006298449,0.0005540263,0.000057624413,1.5924215e-7,0.00030577907,0.000052869982,0.7458137,0.113736674,0.005941709,0.12697512],"study_design_scores_gemma":[0.0006644401,0.000023190205,0.002317916,0.000066426444,0.000038636488,0.0000075012035,0.0007196927,0.14771181,0.69583416,0.012762168,0.13929851,0.00055551744],"about_ca_topic_score_codex":0.0000027228891,"about_ca_topic_score_gemma":0.000002041432,"teacher_disagreement_score":0.2994782,"about_ca_system_score_codex":0.000053363266,"about_ca_system_score_gemma":0.000030390094,"threshold_uncertainty_score":0.31240618},"labels":[],"label_agreement":null},{"id":"W2158957954","doi":"10.1093/bioinformatics/bts395","title":"Side-chain rotamer changes upon ligand binding: common, crucial, correlate with entropy and rearrange hydrogen bonding","year":2012,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":83,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Hydrogen bond; Conformational isomerism; Chemistry; Conformational entropy; Ligand (biochemistry); Entropy (arrow of time); Computational chemistry; Thermodynamics; Biochemistry; Physics; Molecule; Organic chemistry","score_opus":0.008453271641621773,"score_gpt":0.2213110976668868,"score_spread":0.21285782602526504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2158957954","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99565315,0.0011489611,0.0011513828,0.00013999759,0.00013083332,0.00031403537,0.000036540365,0.000025706944,0.0013993663],"genre_scores_gemma":[0.99396205,0.00032697865,0.004640935,0.00030120404,0.00023534053,0.000017200378,0.0001484736,0.00002764276,0.0003401815],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991088,0.000019703239,0.00021506466,0.00012346011,0.00014480598,0.0003881819],"domain_scores_gemma":[0.99936104,0.000011513162,0.00016694858,0.00026474384,0.00003204093,0.00016372369],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001849948,0.00020790874,0.00019402588,0.0000662155,0.00014345639,0.00004692545,0.00011352359,0.00019341301,0.0000040546543],"category_scores_gemma":[0.000028422604,0.00016389739,0.000035258872,0.00008894316,0.00008288229,0.000021797541,0.00012370896,0.000112914524,0.000011956028],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00089862244,0.000192625,0.10011658,0.0007465502,0.00079725473,0.000022454586,0.008407145,0.00009795458,0.8298535,0.006496462,0.0047640903,0.047606803],"study_design_scores_gemma":[0.005309829,0.002475174,0.00942795,0.0003889695,0.00047306772,0.0011152859,0.0028665352,0.009621141,0.708504,0.00045040686,0.25659752,0.0027700625],"about_ca_topic_score_codex":0.000013081575,"about_ca_topic_score_gemma":0.00004581074,"teacher_disagreement_score":0.25183344,"about_ca_system_score_codex":0.0000158504,"about_ca_system_score_gemma":0.000024832227,"threshold_uncertainty_score":0.66835415},"labels":[],"label_agreement":null},{"id":"W2159227212","doi":"10.1093/bioinformatics/16.10.899","title":"USAGE: a web-based approach towards the analysis of SAGE data","year":2000,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Pediatric Oncology Group","funders":"","keywords":"Computer science; Flexibility (engineering); SAGE; Relational database; The Internet; Web application; Software; Set (abstract data type); Database; Data sharing; World Wide Web; Data science; Information retrieval; Data mining","score_opus":0.0382471465092211,"score_gpt":0.2795155096130832,"score_spread":0.2412683631038621,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159227212","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55759853,0.0022838598,0.22595158,0.0013379725,0.0002817014,0.0012635802,0.0018209856,0.00009284863,0.20936896],"genre_scores_gemma":[0.9898752,0.00022807423,0.0066977697,0.0004321795,0.000039994506,0.000013655578,0.0015888928,0.00000676943,0.0011174553],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993177,0.000031692674,0.00025360947,0.00012504021,0.00016612213,0.00010582984],"domain_scores_gemma":[0.9986983,0.000005918451,0.00010687911,0.001120141,0.000032591248,0.000036149773],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025511225,0.00008261817,0.00011516022,0.00006150213,0.000051758398,0.000021847058,0.00053574156,0.000072173025,0.00015985638],"category_scores_gemma":[0.000025281352,0.00005384689,0.00007934201,0.00041064774,0.0000667912,0.0000060130133,0.00007331317,0.000043388067,0.0000070014635],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024817148,0.00041581644,0.0021411958,0.0002083128,0.0014221349,3.8997413e-7,0.0007912419,0.016341444,0.08198306,0.000121023455,0.06271623,0.833611],"study_design_scores_gemma":[0.0005747626,0.00005711494,0.0074279564,0.000008802471,0.00045112325,0.0000011961583,0.00027924712,0.5984905,0.017426193,0.0000058677533,0.37509125,0.00018601122],"about_ca_topic_score_codex":0.000007872111,"about_ca_topic_score_gemma":0.00000567471,"teacher_disagreement_score":0.833425,"about_ca_system_score_codex":0.0000051551688,"about_ca_system_score_gemma":0.00011513993,"threshold_uncertainty_score":0.21958123},"labels":[],"label_agreement":null},{"id":"W2159531362","doi":"10.1093/bioinformatics/bts658","title":"A system for exact and approximate genetic linkage analysis of SNP data in large pedigrees","year":2012,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"National Institute of General Medical Sciences; National Human Genome Research Institute","keywords":"Tag SNP; Computer science; SNP; Markov chain Monte Carlo; Workflow; Linkage (software); Data mining; Pedigree chart; Theoretical computer science; Haplotype; Single-nucleotide polymorphism; Bayesian probability; Genetics; Artificial intelligence; Database; Biology","score_opus":0.031441021981738086,"score_gpt":0.2962077704679798,"score_spread":0.2647667484862417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159531362","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92742926,0.0009806507,0.07039643,0.000019420291,0.00006967919,0.00024063654,0.0005863185,0.000005867178,0.00027174805],"genre_scores_gemma":[0.9636802,0.00017961932,0.035040706,0.00004280267,0.00006330756,0.000016664622,0.0009421934,0.000007083809,0.000027388372],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990482,0.000035665213,0.0004534358,0.00011733568,0.0000633094,0.00028206827],"domain_scores_gemma":[0.99915445,0.00004681017,0.0002261687,0.00047040748,0.00004261477,0.000059550955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008024924,0.00009832323,0.00028020164,0.000119812954,0.00003594989,0.000007702093,0.00018342235,0.00014147532,0.0000023838145],"category_scores_gemma":[0.00020185972,0.00008667938,0.000058139387,0.00016763227,0.000028416236,0.000008761858,0.00019620244,0.000033136133,0.0000010990086],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002281705,0.00009744119,0.9935618,0.00048740755,0.00057273573,1.4762949e-7,0.00069800706,0.00032605944,0.0011549448,0.00022283626,0.0006209898,0.0022348287],"study_design_scores_gemma":[0.0008195338,0.00011705603,0.64448935,0.000020748406,0.0006087336,0.000005558985,0.0018815298,0.34739918,0.0005689483,0.000009318937,0.003848625,0.00023138481],"about_ca_topic_score_codex":0.000015084283,"about_ca_topic_score_gemma":0.000060082464,"teacher_disagreement_score":0.3490724,"about_ca_system_score_codex":0.000010299537,"about_ca_system_score_gemma":0.00002459825,"threshold_uncertainty_score":0.35346824},"labels":[],"label_agreement":null},{"id":"W2159640103","doi":"10.1093/bioinformatics/btq216","title":"Next-generation VariationHunter: combinatorial algorithms for transposon insertion discovery","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":221,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; Genome British Columbia; National Human Genome Research Institute; Howard Hughes Medical Institute","keywords":"Transposable element; Algorithm; Genome; Computer science; Human genome; Structural variation; Scope (computer science); Computational biology; Biology; Genetics; Gene","score_opus":0.024851415321221256,"score_gpt":0.2506231169510057,"score_spread":0.22577170162978444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159640103","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6862942,0.000044049226,0.30817923,0.00019845906,0.0036910304,0.000875853,0.0001296174,0.000037469228,0.00055009907],"genre_scores_gemma":[0.9315189,0.000059063208,0.06319182,0.00018876688,0.0019714218,0.00011805253,0.0025868993,0.000032864846,0.00033222075],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991543,0.00001245638,0.00031887094,0.00015278762,0.00015473395,0.0002068474],"domain_scores_gemma":[0.999423,0.000009249713,0.00011967257,0.0002692263,0.00011948934,0.000059325837],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000225154,0.00014859656,0.00011270105,0.000053566455,0.00012232494,0.00014493855,0.00015503042,0.00019695537,0.000010043165],"category_scores_gemma":[0.00005894599,0.00014376262,0.00009757781,0.00006896388,0.00003207286,0.00005474866,0.000026925161,0.00008631478,0.0000135245045],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058232275,0.00009757836,0.00022278483,0.00006135858,0.000056353052,1.560039e-7,0.00025427394,0.00004919974,0.98207414,0.002122373,0.0015224547,0.013481094],"study_design_scores_gemma":[0.007180573,0.001607073,0.0026688483,0.00002164735,0.00016831185,0.000022571485,0.00032742452,0.20518202,0.59175277,0.0011256066,0.18875588,0.0011872663],"about_ca_topic_score_codex":0.000005654709,"about_ca_topic_score_gemma":0.000023711727,"teacher_disagreement_score":0.39032137,"about_ca_system_score_codex":0.000014393964,"about_ca_system_score_gemma":0.00006668355,"threshold_uncertainty_score":0.58624697},"labels":[],"label_agreement":null},{"id":"W2159739447","doi":"10.1093/bioinformatics/btv341","title":"JSBML 1.0: providing a smorgasbord of options to encode systems biology models","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Institute of Allergy and Infectious Diseases; Biotechnology and Biological Sciences Research Council; Seventh Framework Programme; Danmarks Tekniske Universitet; National Institute of General Medical Sciences; Novo Nordisk; Bundesministerium für Bildung und Forschung; European Commission; Deutsche Forschungsgemeinschaft; Novo Nordisk Fonden; National Science Foundation; Google; National Institutes of Health","keywords":"ENCODE; Computer science; Computational biology; Systems biology; Biology; Data science; Genetics; Gene","score_opus":0.034921473298470486,"score_gpt":0.2662321145306797,"score_spread":0.2313106412322092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159739447","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66432583,0.0014898892,0.32857257,0.00010846702,0.00037488865,0.0005908896,0.00007417381,0.000040913164,0.004422385],"genre_scores_gemma":[0.97562087,0.000055375916,0.023738965,0.000074073796,0.00010561054,0.000027790556,0.00011115159,0.000015577767,0.00025061038],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998987,0.000042257485,0.00045128667,0.000141012,0.00013749489,0.00024090939],"domain_scores_gemma":[0.99893147,0.0000072593593,0.00017549662,0.0004575203,0.00023571283,0.0001925666],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033244738,0.0001403809,0.00023010606,0.00011469974,0.000039936327,0.00001945255,0.00024253072,0.00014604702,0.0000017805905],"category_scores_gemma":[0.00007212662,0.00012748303,0.00008728563,0.00023109461,0.00004887586,0.000009468577,0.00016364305,0.000033208733,0.000020465413],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000111044734,0.000141973,0.0038733613,0.0002607653,0.000514836,0.0000012578773,0.0017466666,0.8491206,0.1121288,0.008363136,0.02010082,0.0036367115],"study_design_scores_gemma":[0.0014813764,0.0012570249,0.00018148783,0.00010343661,0.00025151874,0.000053556396,0.003408398,0.8794369,0.045816567,0.0009738862,0.06607674,0.00095911755],"about_ca_topic_score_codex":0.00003414459,"about_ca_topic_score_gemma":0.000013622758,"teacher_disagreement_score":0.31129503,"about_ca_system_score_codex":0.000030168057,"about_ca_system_score_gemma":0.00016186733,"threshold_uncertainty_score":0.5198607},"labels":[],"label_agreement":null},{"id":"W2160004708","doi":"10.1093/bioinformatics/btl259","title":"Distance based algorithms for small biomolecule classification and structural similarity search","year":2006,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"","keywords":"Minkowski distance; Classifier (UML); Nearest neighbor search; Computer science; Similarity (geometry); Artificial intelligence; Pruning; Pattern recognition (psychology); Data mining; Focus (optics); k-nearest neighbors algorithm; Machine learning; Algorithm; Mathematics; Euclidean distance","score_opus":0.054116687373180636,"score_gpt":0.31771800108442666,"score_spread":0.263601313711246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160004708","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020818233,0.000034157212,0.9776439,0.000607679,0.00012610483,0.00028702777,0.000041591076,0.00007708635,0.0003642233],"genre_scores_gemma":[0.21897957,9.0160927e-7,0.7807397,0.00014579113,0.000035770718,0.000012969185,0.000056688787,0.0000049617684,0.000023604096],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99909014,0.000039772593,0.0002838513,0.00016342392,0.00021659328,0.00020624611],"domain_scores_gemma":[0.9991735,0.00027750316,0.000093239636,0.00026713696,0.00013407106,0.000054500568],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036433275,0.00011147913,0.00010700101,0.00008529763,0.0001522643,0.0002528877,0.00032641736,0.000047167676,0.000001015231],"category_scores_gemma":[0.000046662997,0.00010303375,0.000042900363,0.00024432244,0.00006412629,0.00041258358,0.000090437126,0.00006224575,0.0000028047364],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000465671,0.00011463179,0.0033150436,0.00065452827,0.000028808088,0.000003329649,0.00093944964,0.05260537,0.0009124733,0.6359591,0.0013339528,0.30408674],"study_design_scores_gemma":[0.0003207018,0.000032743937,0.022500094,0.000007966499,0.0000034345187,0.0000034506213,0.00002097662,0.96597534,0.0010548888,0.009119399,0.0008279893,0.00013300187],"about_ca_topic_score_codex":0.000020460508,"about_ca_topic_score_gemma":0.00000958295,"teacher_disagreement_score":0.91336995,"about_ca_system_score_codex":0.00005368164,"about_ca_system_score_gemma":0.00010730738,"threshold_uncertainty_score":0.42015943},"labels":[],"label_agreement":null},{"id":"W2160265768","doi":"10.1093/bioinformatics/btr208","title":"Error correction of high-throughput sequencing datasets with non-uniform coverage","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":123,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"National Center for Research Resources; National Institutes of Health","keywords":"Computer science; Error detection and correction; Throughput; Simple (philosophy); Hamming graph; Algorithm; Hamming distance; Hamming code; Data mining; Decoding methods; Telecommunications","score_opus":0.015894315644210757,"score_gpt":0.22750690572631177,"score_spread":0.211612590082101,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160265768","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8953339,0.000057530273,0.086353965,0.000009181289,0.00067633024,0.00032416542,0.00086522003,0.000015985992,0.016363742],"genre_scores_gemma":[0.97594416,0.00017122454,0.022495283,0.00019827111,0.000072909665,0.000007662407,0.0010218607,0.000015811573,0.0000728445],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993517,0.000004987769,0.00026749584,0.00010763602,0.000102293074,0.00016592244],"domain_scores_gemma":[0.9992975,0.0000103060975,0.00019433004,0.00037340296,0.000065262015,0.000059178623],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008746421,0.00012513332,0.00013575918,0.000036417583,0.00004877072,0.0000126597315,0.0001372476,0.00009790095,0.000021729988],"category_scores_gemma":[0.000035019177,0.00010719419,0.00003149331,0.00007139005,0.00006515519,0.000013749037,0.0000854094,0.000061377476,0.000013422534],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00661101,0.001955601,0.024713814,0.0034983773,0.002573905,0.00012835332,0.027806537,0.041468628,0.30918542,0.008419677,0.4039861,0.16965261],"study_design_scores_gemma":[0.0038367403,0.004013209,0.0069308504,0.00020086949,0.00022374216,0.00016813457,0.002512089,0.027364077,0.9080794,0.00025739308,0.045218226,0.0011952937],"about_ca_topic_score_codex":0.0003243094,"about_ca_topic_score_gemma":0.000139042,"teacher_disagreement_score":0.598894,"about_ca_system_score_codex":0.00003236432,"about_ca_system_score_gemma":0.00016351338,"threshold_uncertainty_score":0.4371252},"labels":[],"label_agreement":null},{"id":"W2160615485","doi":"10.1093/bioinformatics/bti120","title":"A Java tool for dynamic web-based 3D visualization of anatomy and overlapping gene or protein expression patterns","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Java; Visualization; Computer science; Computational biology; Expression (computer science); Web application; Gene expression; Computer graphics (images); Gene; Biology; Anatomy; Programming language; World Wide Web; Data mining; Genetics","score_opus":0.011974473710474309,"score_gpt":0.2844673868023079,"score_spread":0.27249291309183354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160615485","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7342718,0.00008158858,0.26520568,0.000036057725,0.000030185542,0.00028986507,0.00005281016,0.000016539292,0.000015458845],"genre_scores_gemma":[0.8955738,0.00004290052,0.1039892,0.00010848083,0.000019978528,0.000040500396,0.00018684022,0.0000095092655,0.000028791253],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99938285,0.000009946829,0.00026800827,0.000102047874,0.00009876511,0.00013840284],"domain_scores_gemma":[0.9996427,0.000012286097,0.0001075166,0.00014759999,0.000052956762,0.00003690011],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011511807,0.000101276186,0.00012463039,0.000045256475,0.000048090096,0.000014759789,0.00007878344,0.00015254015,0.0000033087824],"category_scores_gemma":[0.00014613646,0.00007595257,0.00003643129,0.000054371332,0.000063130334,0.0000056810977,0.00004631397,0.000027481787,5.442144e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022126996,0.00008278267,0.0009949012,0.00089509255,0.000028908638,9.937385e-7,0.00025041896,0.00008696125,0.9767658,0.00005304846,0.00011324229,0.020506574],"study_design_scores_gemma":[0.00563388,0.0015397408,0.0023930247,0.0006191714,0.000036079164,0.000013566892,0.00047087486,0.048422538,0.9331043,0.0000787009,0.0072437986,0.00044437012],"about_ca_topic_score_codex":0.0000031932084,"about_ca_topic_score_gemma":0.000008141296,"teacher_disagreement_score":0.161302,"about_ca_system_score_codex":0.000012457633,"about_ca_system_score_gemma":0.00010818371,"threshold_uncertainty_score":0.3097256},"labels":[],"label_agreement":null},{"id":"W2160972508","doi":"10.1093/bioinformatics/bts411","title":"From phenotype to genotype: an association study of longitudinal phenotypic markers to Alzheimer's disease relevant SNPs","year":2012,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":71,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"U.S. National Library of Medicine; National Institute on Aging; Genentech; National Institutes of Health; Canadian Institutes of Health Research; University of California, Los Angeles; Servier; Eisai; Northern California Institute for Research and Education; University of California, San Diego; Pfizer; Biogen; BioClinica; Amorfix Life Sciences; Dana Foundation; Bayer HealthCare; Meso Scale Diagnostics; National Center for Research Resources; F. Hoffmann-La Roche; Medpace; Bristol-Myers Squibb; Eli Lilly and Company; AstraZeneca; Novartis Pharmaceuticals Corporation; Synarc; Foundation for the National Institutes of Health; National Science Foundation","keywords":"Single-nucleotide polymorphism; SNP; Genetic association; Genotype; Computational biology; Biology; Imaging genetics; Phenotype; Genetics; Genome-wide association study; Longitudinal study; Neuroimaging; Medicine; Pathology; Neuroscience; Gene","score_opus":0.022760359593949547,"score_gpt":0.2850777229348396,"score_spread":0.26231736334089,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160972508","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9950129,0.00021388607,0.0032235812,0.00018390398,0.00038562916,0.0005395011,0.00011736159,0.000014844799,0.00030843893],"genre_scores_gemma":[0.981706,0.000014674849,0.01706098,0.00043000214,0.00039815108,0.000034432695,0.0002498918,0.000019374542,0.00008647551],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9985207,0.00012096309,0.0005234433,0.0001903976,0.00023561218,0.00040888667],"domain_scores_gemma":[0.99859613,0.000048589143,0.00027994072,0.0004959754,0.00017013025,0.00040920632],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006118443,0.00017615594,0.0002508044,0.000070697955,0.000096322816,0.000016979577,0.0002279543,0.00013683001,0.000040733994],"category_scores_gemma":[0.00054682343,0.00016827264,0.00006313208,0.00015791651,0.000012835042,0.000016858716,0.00016302716,0.00006935839,0.00011769373],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034854034,0.0007132876,0.9722939,0.000013668755,0.00045766242,3.79898e-7,0.0037613453,0.0013273645,0.0019364355,0.00003268909,0.0127342725,0.0063804537],"study_design_scores_gemma":[0.00045731943,0.00073184876,0.991367,0.0000069701837,0.00021802563,2.133476e-7,0.0018041048,0.0005238834,0.00027372132,0.00003953795,0.004324397,0.00025298988],"about_ca_topic_score_codex":0.00020233887,"about_ca_topic_score_gemma":0.00012371787,"teacher_disagreement_score":0.019073088,"about_ca_system_score_codex":0.00006169618,"about_ca_system_score_gemma":0.00006717441,"threshold_uncertainty_score":0.6861959},"labels":[],"label_agreement":null},{"id":"W2161186860","doi":"10.1093/bioinformatics/bth148","title":"Haplotypes histories as pathways of recombinations","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Neurodegenerative Diseases","field":"Neuroscience","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier Universitaire Sainte-Justine; Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Haplotype; Biology; Recombination; Genetics; Genome; Evolutionary biology; Sequence (biology); Computational biology; Gene; Allele","score_opus":0.03892729957076401,"score_gpt":0.25214078638459925,"score_spread":0.21321348681383523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161186860","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9776054,0.000028832806,0.0014591562,0.00027638976,0.00039781784,0.0001980125,0.000056008903,0.00008953362,0.019888857],"genre_scores_gemma":[0.99484456,0.000027537133,0.0045168702,0.00038370094,0.000012454069,0.000009662811,0.000003880314,0.000009407442,0.00019191563],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999247,0.000018619457,0.0002759561,0.000091353475,0.00023376691,0.0001332778],"domain_scores_gemma":[0.9994456,0.00006206825,0.00013514193,0.00022611672,0.00006713438,0.000063943444],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000039853556,0.00009302586,0.00010510436,0.00008073453,0.00009746454,0.00002115223,0.0001823568,0.000027367989,0.000039060866],"category_scores_gemma":[0.000778243,0.00008540862,0.000049526454,0.00019549382,0.00013045284,0.0001825906,0.000047216225,0.000045843397,0.00016405433],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026792919,0.00052367407,0.00030660746,0.00019428195,0.00000925366,0.000007516627,0.009327754,0.002171804,0.4398272,0.54184824,0.0013038424,0.004453025],"study_design_scores_gemma":[0.0003087488,0.00014461622,0.0003931026,0.0000116837855,0.000008446356,0.000006793185,0.00021277557,0.00018102411,0.98740876,0.009341558,0.0018779865,0.000104503255],"about_ca_topic_score_codex":0.000006160371,"about_ca_topic_score_gemma":0.0000023397477,"teacher_disagreement_score":0.54758155,"about_ca_system_score_codex":0.00004272892,"about_ca_system_score_gemma":0.00015369472,"threshold_uncertainty_score":0.3482862},"labels":[],"label_agreement":null},{"id":"W2161241698","doi":"10.1093/bioinformatics/bts060","title":"Predicting kinase substrates using conservation of local motif density","year":2012,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Kinase; Computer science; Motif (music); Computational biology; Training set; Artificial intelligence; Biology; Machine learning; Genetics; Physics","score_opus":0.018419556843068275,"score_gpt":0.23568615793772005,"score_spread":0.21726660109465176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161241698","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8877548,0.000220993,0.110933825,0.000011797148,0.00018824617,0.00012199332,0.000017806318,0.00001011503,0.00074040296],"genre_scores_gemma":[0.98135567,0.000027387301,0.018158488,0.00016321994,0.00015436065,0.0000015991179,0.00010808489,0.0000101305595,0.000021049842],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990718,0.000014772021,0.00045829234,0.00005930857,0.00012034533,0.00027551388],"domain_scores_gemma":[0.9992882,0.00001317305,0.00026666062,0.00023398151,0.00009948916,0.000098524106],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032079982,0.00012810134,0.00014074701,0.000035539513,0.00007556781,0.000016221687,0.00010767458,0.00016156762,0.000007105199],"category_scores_gemma":[0.000029877707,0.000120153556,0.00006564093,0.00008132205,0.000107831846,0.000024829194,0.00009119278,0.000073675335,0.000006869238],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033176542,0.0005369151,0.69556963,0.0017433198,0.0005695702,0.0000018970217,0.005099587,0.009626519,0.22411877,0.004933796,0.0063008037,0.051167414],"study_design_scores_gemma":[0.0011012414,0.00025968617,0.02408954,0.00011160807,0.000118852644,0.00008990145,0.003784149,0.57485455,0.39158612,0.00015693092,0.0032290057,0.0006184386],"about_ca_topic_score_codex":0.00003216196,"about_ca_topic_score_gemma":0.0000126914,"teacher_disagreement_score":0.6714801,"about_ca_system_score_codex":0.000016981832,"about_ca_system_score_gemma":0.000059092818,"threshold_uncertainty_score":0.489972},"labels":[],"label_agreement":null},{"id":"W2161481677","doi":"10.1093/bioinformatics/btq255","title":"Pathgroups, a dynamic data structure for genome reconstruction problems","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Computer Research Institute of Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Heuristics; Computer science; Heuristic; Greedy algorithm; Genome; Set (abstract data type); Data structure; Sequence (biology); Algorithm; Scheme (mathematics); Theoretical computer science; Data mining; Computational biology; Gene; Artificial intelligence; Biology; Mathematics; Genetics","score_opus":0.012882705248054703,"score_gpt":0.24099728298190282,"score_spread":0.2281145777338481,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161481677","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9100072,0.00029570682,0.08266717,0.00017085036,0.0015938501,0.001747681,0.0026209194,0.000068235124,0.0008283978],"genre_scores_gemma":[0.5644222,0.00019472347,0.42221504,0.00017647745,0.00060823024,0.00005799195,0.011741981,0.0000619678,0.0005213859],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991396,0.0000065538215,0.00028599487,0.0002148789,0.00010613901,0.00024685165],"domain_scores_gemma":[0.99882245,0.0000055484625,0.00014618742,0.0008710044,0.000084605264,0.00007019028],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018202586,0.00015168008,0.00011681339,0.000049192087,0.00009165758,0.0000550873,0.00046116317,0.00019134463,0.000029222227],"category_scores_gemma":[0.00006392669,0.00013796492,0.00004513282,0.00006469738,0.000060205344,0.000019620393,0.00020739011,0.00011787576,0.00001271148],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022236325,0.000029407982,0.0003564784,0.00024587958,0.00009904806,2.463367e-7,0.00017293055,0.00004792817,0.9078903,0.00007107865,0.00081164984,0.09025277],"study_design_scores_gemma":[0.004048096,0.0009177964,0.0046396875,0.00004321941,0.00019973193,0.0004988504,0.00079568423,0.20712677,0.020097518,0.0019474493,0.75799763,0.0016875432],"about_ca_topic_score_codex":0.0000022438408,"about_ca_topic_score_gemma":0.00009542309,"teacher_disagreement_score":0.8877928,"about_ca_system_score_codex":0.00000990373,"about_ca_system_score_gemma":0.00006355299,"threshold_uncertainty_score":0.5626046},"labels":[],"label_agreement":null},{"id":"W2161666955","doi":"10.1093/bioinformatics/btm489","title":"BiasViz: visualization of amino acid biased regions in protein alignments","year":2007,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Biotechnology and Biological Sciences Research Council","keywords":"Sequence (biology); Source code; Computer science; Visualization; Java; Java applet; Protein sequencing; Sequence alignment; Protein superfamily; Computational biology; Amino acid; Peptide sequence; Code (set theory); Amino acid residue; Programming language; Biology; Data mining; Set (abstract data type); Genetics","score_opus":0.019369109772539153,"score_gpt":0.2649673212057758,"score_spread":0.24559821143323668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161666955","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98570514,0.00017493311,0.010970288,0.00001913051,0.000060323593,0.0002872107,0.000015464135,0.0000028379795,0.0027646816],"genre_scores_gemma":[0.99432564,0.00010960263,0.005275177,0.00008435343,0.00003328554,0.000008281787,0.000053788957,0.000008892218,0.00010097558],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999235,0.000011453654,0.00038533393,0.00008556443,0.000105482824,0.00017721188],"domain_scores_gemma":[0.9995554,0.000006462756,0.00014793496,0.00019649656,0.000055548222,0.000038120736],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024614052,0.00009732526,0.00011344585,0.00008156741,0.000030580424,0.0000063634443,0.000104592866,0.00008882174,0.0000021536982],"category_scores_gemma":[0.000063120795,0.00009276713,0.000041393716,0.00013109931,0.00004916625,0.0000013832391,0.000069280046,0.000024725512,0.000003886798],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005587633,0.00010258326,0.011464002,0.00008586736,0.00004205463,0.0000010247138,0.00065801886,0.00004534707,0.9825463,0.000912743,0.0004025666,0.0036835806],"study_design_scores_gemma":[0.00080733077,0.00029336193,0.023172243,0.000044853474,0.000011109628,0.0000033401716,0.0006565083,0.00042332965,0.96548116,0.00013873512,0.008761886,0.000206117],"about_ca_topic_score_codex":0.000013130746,"about_ca_topic_score_gemma":0.00005153959,"teacher_disagreement_score":0.01706515,"about_ca_system_score_codex":0.000012391005,"about_ca_system_score_gemma":0.00003109371,"threshold_uncertainty_score":0.37829337},"labels":[],"label_agreement":null},{"id":"W2161722223","doi":"10.1093/bioinformatics/btv541","title":"markophylo: Markov chain analysis on phylogenetic trees","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Innovative Research Group Project of the National Natural Science Foundation of China","keywords":"Markov chain; R package; Phylogenetic tree; Computer science; Tree (set theory); Markov chain Monte Carlo; Markov model; Data mining; Theoretical computer science; Bayesian probability; Mathematics; Artificial intelligence; Biology; Machine learning; Combinatorics; Genetics; Programming language; Gene","score_opus":0.015612745329582954,"score_gpt":0.2358507888474713,"score_spread":0.22023804351788834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161722223","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9744325,0.0008122236,0.0016296674,0.00014051289,0.00024434202,0.00022635018,0.00008123578,0.000010784833,0.022422355],"genre_scores_gemma":[0.9910478,0.000193181,0.0070059025,0.000555001,0.00019416185,0.000019882087,0.00010160437,0.000018570601,0.0008639045],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99889994,0.00003547225,0.00033435138,0.00021117543,0.00021853032,0.0003005167],"domain_scores_gemma":[0.9990348,0.0000149942825,0.00012749138,0.00053801236,0.000107921966,0.00017674486],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025986184,0.00022414558,0.00025048605,0.00014829697,0.000075713826,0.000038737115,0.00025392408,0.00012223123,0.000010657554],"category_scores_gemma":[0.00008295745,0.00019500256,0.0001786355,0.00030108923,0.00007490513,9.83545e-7,0.00015007533,0.000059204598,0.000057642457],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021193142,0.0014865502,0.3991807,0.00032384368,0.015702188,0.000037877882,0.007051944,0.06454833,0.17526399,0.0027941847,0.1333105,0.19818059],"study_design_scores_gemma":[0.0072874753,0.0067170765,0.36285368,0.00005007884,0.0023230612,0.000050861137,0.0042476873,0.055400908,0.07207122,0.0010473015,0.4841001,0.0038505464],"about_ca_topic_score_codex":0.000011305224,"about_ca_topic_score_gemma":0.00005089176,"teacher_disagreement_score":0.3507896,"about_ca_system_score_codex":0.00002095681,"about_ca_system_score_gemma":0.00006596506,"threshold_uncertainty_score":0.79519737},"labels":[],"label_agreement":null},{"id":"W2161724277","doi":"10.1093/bioinformatics/btq040","title":"SNVMix: predicting single nucleotide variants from next-generation sequencing of tumors","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":218,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Provincial Health Services Authority; BC Cancer Agency","funders":"Canadian Institutes of Health Research; Michael Smith Health Research BC","keywords":"Genome; Computational biology; Computer science; Probabilistic logic; Biology; Inference; DNA sequencing; Software; Exome sequencing; Data mining; Genetics; Artificial intelligence; Mutation; Gene","score_opus":0.02670086111264113,"score_gpt":0.2255201977902274,"score_spread":0.19881933667758625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161724277","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9930502,0.000077876895,0.0037259783,0.0000228802,0.0006775669,0.000121301055,0.0001428748,0.000012244392,0.0021690414],"genre_scores_gemma":[0.97337943,0.000047737216,0.025307462,0.00017983819,0.0007037581,0.0000040222803,0.00033231665,0.000016628977,0.000028784503],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991965,0.000008466062,0.0003901254,0.00012213197,0.000115865376,0.000166906],"domain_scores_gemma":[0.99926597,0.000025478726,0.00022164822,0.00032119057,0.00009276713,0.00007296852],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012955646,0.0001170829,0.0001281055,0.000034736422,0.000064759275,0.000052931184,0.0001519091,0.00012293816,0.000023984594],"category_scores_gemma":[0.00025431003,0.00011950346,0.000056393834,0.00005725946,0.000051097602,0.000014946041,0.00009287722,0.00009589796,0.000009404785],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008870825,0.000021972306,0.0017840435,0.00001694106,0.000020554668,6.949993e-7,0.00025423523,0.00016646038,0.9932063,0.00008538318,0.0007592489,0.00367525],"study_design_scores_gemma":[0.0005072379,0.00021534348,0.0016267782,0.000033570144,0.0000357311,0.00001046076,0.00045663203,0.055580035,0.9357753,0.00011231306,0.0053816205,0.00026499253],"about_ca_topic_score_codex":0.0001581532,"about_ca_topic_score_gemma":0.0002802799,"teacher_disagreement_score":0.05743106,"about_ca_system_score_codex":0.000019104873,"about_ca_system_score_gemma":0.00014591886,"threshold_uncertainty_score":0.48732096},"labels":[],"label_agreement":null},{"id":"W2161921787","doi":"10.1093/bioinformatics/btv630","title":"Fast Optimized Cluster Algorithm for Localizations (FOCAL): a spatial cluster analysis for super-resolved microscopy","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Advanced Fluorescence Microscopy Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"DBSCAN; Focus (optics); Cluster analysis; Computer science; Scaling; Algorithm; Cluster (spacecraft); Software; Microscopy; Artificial intelligence; Cardinal point; Pattern recognition (psychology); Mathematics; Physics; Optics; Geometry; Fuzzy clustering","score_opus":0.015587870179144573,"score_gpt":0.298134211063087,"score_spread":0.2825463408839424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161921787","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00071481266,0.000092199334,0.996508,0.00016150236,0.00017209117,0.0014997125,0.00069794385,0.00006766787,0.00008606641],"genre_scores_gemma":[0.0019936142,0.00003219163,0.9927287,0.001147868,0.00019038517,0.0003929977,0.0029712329,0.00004713978,0.0004958399],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99850327,0.000026597834,0.0005900477,0.00028406075,0.00015666867,0.00043935183],"domain_scores_gemma":[0.99857634,0.00003741899,0.00019285889,0.00050905586,0.0005008126,0.00018352513],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003052925,0.00028112586,0.0003623361,0.00016044111,0.00016136027,0.00009022632,0.00031952126,0.00029203907,0.0000055072583],"category_scores_gemma":[0.00019486471,0.0002615399,0.00030456204,0.0002465203,0.00014271397,0.000027280848,0.00016105542,0.00006956933,0.0000061426626],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0059018964,0.0016318467,0.002853815,0.0010031045,0.005040297,0.000002830109,0.0062529068,0.08879191,0.2647346,0.00029859977,0.41095868,0.21252953],"study_design_scores_gemma":[0.0032149297,0.00055985874,0.000008210294,0.000017462664,0.0003217688,0.000004289178,0.00031963596,0.7309953,0.20379956,0.00008096788,0.06024548,0.0004325325],"about_ca_topic_score_codex":0.000019912368,"about_ca_topic_score_gemma":0.0000543015,"teacher_disagreement_score":0.6422034,"about_ca_system_score_codex":0.00006181719,"about_ca_system_score_gemma":0.00015929184,"threshold_uncertainty_score":0.99998367},"labels":[],"label_agreement":null},{"id":"W2161938868","doi":"10.1093/bioinformatics/btv192","title":"Gene selection for the reconstruction of stem cell differentiation trees: a linear programming approach","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University; Ottawa Hospital; University of Ottawa","funders":"","keywords":"Hierarchy; Hierarchical clustering; Gene; Computational biology; Metric (unit); Tree (set theory); Euclidean distance; Cluster analysis; Biology; Computer science; Mathematics; Genetics; Artificial intelligence; Combinatorics","score_opus":0.03283974096337588,"score_gpt":0.25013622598395635,"score_spread":0.21729648502058047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161938868","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20517838,0.00026037733,0.7930123,0.000036050787,0.00026917554,0.0006222394,0.000011487269,0.000017648495,0.00059230713],"genre_scores_gemma":[0.9432503,0.000067048306,0.05587963,0.00002381912,0.00016352584,0.0001136521,0.00014571003,0.000009943551,0.00034637307],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99947774,0.0000165669,0.00023246846,0.00008254596,0.00010019098,0.00009045709],"domain_scores_gemma":[0.99942595,0.000006412544,0.00021457531,0.00015440857,0.00016277871,0.000035851055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016810009,0.00007156777,0.00006816736,0.000033205426,0.000059788126,0.000016333779,0.00008449481,0.000084559,7.317754e-7],"category_scores_gemma":[0.000012276595,0.00005056781,0.00005237982,0.00009179896,0.000026172602,0.000008211523,0.000018717114,0.000031937885,9.968057e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031088182,0.00019977152,0.002792396,0.000294657,0.000088744455,8.77541e-9,0.0017087609,0.0032474452,0.36323625,0.00013312996,0.004648749,0.6233392],"study_design_scores_gemma":[0.0010495691,0.00034961308,0.0004353195,0.000011519627,0.000054651668,0.000009694934,0.0031056805,0.23549296,0.73572505,0.000022573931,0.023595138,0.00014826733],"about_ca_topic_score_codex":0.0000027268018,"about_ca_topic_score_gemma":0.0000027071765,"teacher_disagreement_score":0.7380719,"about_ca_system_score_codex":0.000016457456,"about_ca_system_score_gemma":0.00006928889,"threshold_uncertainty_score":0.20620956},"labels":[],"label_agreement":null},{"id":"W2162156442","doi":"10.1093/bioinformatics/btg378","title":"GRIL: genome rearrangement and inversion locator","year":2003,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"U.S. National Library of Medicine; National Institute of General Medical Sciences; National Institutes of Health; Groupe de recherche interuniversitaire en limnologie; Mashhad University of Medical Sciences","keywords":"Correctness; Computer science; Genome; Sequence (biology); Basis (linear algebra); Set (abstract data type); Data mining; Computational biology; Algorithm; Theoretical computer science; Biology; Genetics; Mathematics; Programming language; Gene","score_opus":0.010679139315246573,"score_gpt":0.20592708579076494,"score_spread":0.19524794647551835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162156442","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98901904,0.0014720109,0.000754488,0.00004894046,0.00011238907,0.0001374745,0.00001181316,0.0000032792204,0.008440566],"genre_scores_gemma":[0.9895466,0.0012402842,0.0084252795,0.0004063405,0.000046631598,0.0000064390924,0.000019168363,0.000009036085,0.00030023907],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.999558,0.000010770355,0.00014083176,0.00009059143,0.000061495724,0.00013831715],"domain_scores_gemma":[0.99969494,0.0000032729347,0.000044831086,0.00016653197,0.000030740597,0.00005969655],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010396331,0.0000915636,0.000076211654,0.000022172537,0.0000757852,0.000016179016,0.00005603479,0.000054876968,0.0000062858803],"category_scores_gemma":[0.000026154337,0.00008123188,0.000026189606,0.000033524793,0.000045957026,8.1832655e-7,0.00006783759,0.000025272848,0.000016393988],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008680377,0.00013766986,0.021653479,0.00038965914,0.00042421988,0.0000034740547,0.0026169862,0.00023496857,0.9390258,0.0046190675,0.017195355,0.0136125],"study_design_scores_gemma":[0.0008375659,0.00034595642,0.0081926165,0.000008438812,0.000032161915,0.00001989524,0.0011246962,0.00027736253,0.056983944,0.00019301819,0.9316272,0.00035715682],"about_ca_topic_score_codex":0.0000023176146,"about_ca_topic_score_gemma":0.0000032988055,"teacher_disagreement_score":0.9144318,"about_ca_system_score_codex":0.0000066349626,"about_ca_system_score_gemma":0.000022555758,"threshold_uncertainty_score":0.331254},"labels":[],"label_agreement":null},{"id":"W2162350421","doi":"10.1093/bioinformatics/btt707","title":"A phylogenetic Kalman filter for ancestral trait reconstruction using molecular data","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Phylogenetic tree; Trait; Bayesian probability; Regression; Biology; Phylogenetics; Evolutionary biology; Algorithm; Computer science; Statistics; Mathematics; Genetics; Gene","score_opus":0.04485866981425683,"score_gpt":0.26827159190331573,"score_spread":0.22341292208905889,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162350421","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9753027,0.00047966448,0.022593813,0.000060301754,0.00024952114,0.0005584523,0.00024093656,0.00000546157,0.0005091733],"genre_scores_gemma":[0.8239845,0.00008855284,0.17504416,0.00027664978,0.00021086297,0.00004391453,0.00026706362,0.000022491517,0.00006178487],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991009,0.000011828562,0.00031544155,0.00021603807,0.00007804193,0.00027773192],"domain_scores_gemma":[0.9991416,0.000008341647,0.0001250686,0.0005616101,0.000094844065,0.00006858011],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009845965,0.00016389733,0.0001458339,0.000034529447,0.000099771365,0.00005311106,0.00032582623,0.00010531829,0.000015182072],"category_scores_gemma":[0.000038421975,0.0001537884,0.00006880884,0.000050090446,0.00008007678,0.0000057217394,0.00017911312,0.00003884334,0.000008497079],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002106358,0.000033108725,0.001522008,0.00011642303,0.00017755297,3.4574774e-7,0.00010844336,0.00052329083,0.93488586,0.00006669025,0.0027806591,0.05976457],"study_design_scores_gemma":[0.0057007005,0.0020349107,0.03403404,0.00015368071,0.00053724786,0.0005182335,0.0025372559,0.43644065,0.4090702,0.003885959,0.10191964,0.0031674993],"about_ca_topic_score_codex":0.000021091892,"about_ca_topic_score_gemma":0.000008175598,"teacher_disagreement_score":0.52581567,"about_ca_system_score_codex":0.000009193584,"about_ca_system_score_gemma":0.00005751049,"threshold_uncertainty_score":0.62713087},"labels":[],"label_agreement":null},{"id":"W2162473677","doi":"10.1093/bioinformatics/btv361","title":"MetaPathways v2.5: quantitative functional, taxonomic and usability improvements","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":53,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Genome British Columbia; University of British Columbia","funders":"Pacific Northwest National Laboratory; Natural Sciences and Engineering Research Council of Canada; Genome Alberta; University of British Columbia; Genome British Columbia; Genome Canada; Tula Foundation; Canadian Institute for Advanced Research; Western Canada Research Grid; Compute Canada","keywords":"Computer science; Usability; Pipeline (software); Annotation; Software; Data mining; Information retrieval; Artificial intelligence; Human–computer interaction; Programming language","score_opus":0.056242950902730474,"score_gpt":0.25802429057536885,"score_spread":0.2017813396726384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162473677","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.991015,0.0008242881,0.004329653,0.000052510277,0.00023413033,0.00020073554,0.00005869461,0.000004653869,0.0032803242],"genre_scores_gemma":[0.97713095,0.0001360012,0.022221673,0.00023263182,0.00006276442,0.000020787558,0.000043038563,0.000008457166,0.00014371176],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993942,0.000014944633,0.00022656313,0.00013178261,0.00008516635,0.00014736752],"domain_scores_gemma":[0.9995097,0.000011256281,0.00008889704,0.00019349085,0.00009939122,0.00009728154],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023917355,0.000118870725,0.000120895995,0.000022673024,0.000065375425,0.000025244099,0.00007240461,0.000058449445,0.0000030609226],"category_scores_gemma":[0.00010079985,0.000103633814,0.000039382612,0.000033714277,0.00009716531,0.0000026477446,0.00015583943,0.000034887686,0.000018927489],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014526215,0.0008347189,0.1430353,0.0006582336,0.002618554,0.000004684364,0.0079181325,0.0014615428,0.6546769,0.02393529,0.10294043,0.060463604],"study_design_scores_gemma":[0.010505681,0.0069508534,0.123504974,0.00004281801,0.0003850057,0.000101815334,0.022148572,0.032602232,0.14034419,0.0081180865,0.65239215,0.0029035958],"about_ca_topic_score_codex":0.000014693397,"about_ca_topic_score_gemma":0.000014565869,"teacher_disagreement_score":0.54945177,"about_ca_system_score_codex":0.000015823356,"about_ca_system_score_gemma":0.00007224907,"threshold_uncertainty_score":0.42260644},"labels":[],"label_agreement":null},{"id":"W2162671544","doi":"10.1093/bioinformatics/btt261","title":"pyGenClean: efficient tool for genetic data clean up before association testing","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Montreal Heart Institute","funders":"","keywords":"Python (programming language); Computer science; Genotyping; Data mining; Software; Source code; Pipeline (software); Documentation; Data quality; Operating system; Genotype; Biology; Engineering","score_opus":0.029356549159342018,"score_gpt":0.2703399993806277,"score_spread":0.24098345022128567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162671544","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97009367,0.000051708757,0.027499681,0.0002470144,0.000418121,0.0008024877,0.00014415006,0.0000296308,0.00071356364],"genre_scores_gemma":[0.7048787,0.00002432254,0.29068127,0.00073387445,0.00041627992,0.000094631134,0.0014086129,0.000033963526,0.0017283324],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99865365,0.000033876902,0.00052817067,0.00023263985,0.00014577631,0.00040590297],"domain_scores_gemma":[0.99855226,0.000086541404,0.00036881183,0.00064882665,0.00027146473,0.00007207255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005536553,0.0001536634,0.00018221216,0.000036961792,0.00013796744,0.000054778244,0.00037879669,0.00022753094,0.000037309135],"category_scores_gemma":[0.0012814847,0.00014207259,0.000064338274,0.00010178941,0.000022672555,0.000009707781,0.00026078537,0.00006802764,0.000164643],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024816576,0.0001464516,0.458538,0.00024438926,0.00033291752,2.494423e-7,0.0005491565,0.0042126137,0.009440255,0.00011647695,0.17733403,0.34906068],"study_design_scores_gemma":[0.000965426,0.00047404642,0.29260975,0.000020412694,0.000067701694,0.000008376878,0.00056023005,0.67751014,0.0005231877,0.00031650387,0.026508309,0.00043589962],"about_ca_topic_score_codex":0.000027923004,"about_ca_topic_score_gemma":0.00001606082,"teacher_disagreement_score":0.6732975,"about_ca_system_score_codex":0.000055087374,"about_ca_system_score_gemma":0.00008212116,"threshold_uncertainty_score":0.5793552},"labels":[],"label_agreement":null},{"id":"W2162792752","doi":"10.1093/bioinformatics/btq249","title":"PSORTb 3.0: improved protein subcellular localization prediction with refined localization subcategories and predictive capabilities for all prokaryotes","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2574,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Simon Fraser University; Michael Smith Health Research BC; Cystic Fibrosis Foundation","keywords":"Proteome; Protein subcellular localization prediction; Archaea; Computer science; Subcellular localization; Precision and recall; Computational biology; Interface (matter); Proteomics; Software; Metagenomics; Biology; Bioinformatics; Data mining; Artificial intelligence; Bacteria; Cytoplasm; Genetics; Gene; Programming language","score_opus":0.004537457218943714,"score_gpt":0.21131141928287536,"score_spread":0.20677396206393164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162792752","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20389883,0.00005149547,0.793013,0.0001379432,0.00016743001,0.002012748,0.0001692798,0.000103973194,0.0004453416],"genre_scores_gemma":[0.94022065,0.000039052196,0.054412335,0.00025347195,0.00023500156,0.00038630088,0.0039393017,0.000059685957,0.0004542051],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987406,0.000025894076,0.00051799323,0.00021743518,0.00020065831,0.00029740835],"domain_scores_gemma":[0.99882627,0.00002327812,0.00031139882,0.00038056474,0.00035394225,0.00010454052],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035361285,0.00027151554,0.00019396249,0.0000853086,0.00021817478,0.00011970151,0.00014287488,0.000296555,0.000005827842],"category_scores_gemma":[0.0003992946,0.0002218342,0.000045013177,0.000116596515,0.00026205412,0.00006983665,0.00007385167,0.000177672,0.0000019325232],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0108821,0.0014487416,0.18593249,0.02424354,0.0024434004,0.0000047876574,0.040350202,0.044028547,0.5986182,0.037291355,0.020594282,0.034162354],"study_design_scores_gemma":[0.00146458,0.002060263,0.0006911913,0.000047483525,0.000089913134,0.000031479238,0.0008106132,0.8975166,0.06320073,0.00037323957,0.033293076,0.00042081557],"about_ca_topic_score_codex":0.00001718558,"about_ca_topic_score_gemma":0.000073836636,"teacher_disagreement_score":0.8534881,"about_ca_system_score_codex":0.000019894875,"about_ca_system_score_gemma":0.00011452962,"threshold_uncertainty_score":0.9046136},"labels":[],"label_agreement":null},{"id":"W2162797435","doi":"10.1093/bioinformatics/btl233","title":"BNTagger: improved tagging SNP selection using Bayesian networks","year":2006,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":56,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Selection (genetic algorithm); Computer science; SNP; Bayesian probability; Artificial intelligence; Biology; Genetics; Single-nucleotide polymorphism","score_opus":0.006642357560736971,"score_gpt":0.24105347208302355,"score_spread":0.23441111452228658,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162797435","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1078939,0.00013792295,0.8787523,0.000068497895,0.00043418416,0.0003909075,0.000012296893,0.00014092476,0.012169069],"genre_scores_gemma":[0.8054537,0.000034597047,0.191711,0.00069604156,0.0009052273,0.000011149431,0.0004429747,0.000057683803,0.00068758643],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99854976,0.000031329713,0.0006166138,0.00015907401,0.00017712863,0.00046609118],"domain_scores_gemma":[0.9991205,0.000012918876,0.0003494141,0.00033321313,0.000098871926,0.00008510421],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00028810126,0.0002631205,0.00018804893,0.000100494886,0.00024713806,0.00011979011,0.00021947561,0.00026717407,0.000026717988],"category_scores_gemma":[0.000060914663,0.0002576138,0.00011516621,0.00021816725,0.00006553656,0.000027430344,0.00013086418,0.00021958149,0.000015824799],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033903192,0.00040290807,0.05698962,0.0010034824,0.00042895123,0.0000065859062,0.0007882767,0.6457323,0.19676629,0.0032371248,0.04973551,0.044569924],"study_design_scores_gemma":[0.00042963863,0.00011620223,0.00053653977,0.00002186886,0.000027796117,0.00007114213,0.0000745039,0.96416914,0.0057455325,0.000023937975,0.028437395,0.00034631573],"about_ca_topic_score_codex":0.00008476362,"about_ca_topic_score_gemma":0.000039942595,"teacher_disagreement_score":0.69755983,"about_ca_system_score_codex":0.00005395166,"about_ca_system_score_gemma":0.00008073329,"threshold_uncertainty_score":0.9999876},"labels":[],"label_agreement":null},{"id":"W2163059805","doi":"10.1093/bioinformatics/btv047","title":"KAPPA, a simple algorithm for discovery and clustering of proteins defined by a key amino acid pattern: a case study of the cysteine-rich proteins","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Executable; Computer science; Cluster analysis; Computational biology; Kappa; Data mining; Pairwise comparison; Cysteine; Set (abstract data type); Sequence (biology); Protein superfamily; Protein sequencing; Peptide sequence; Bioinformatics; Theoretical computer science; Artificial intelligence; Biology; Mathematics; Genetics; Biochemistry; Programming language","score_opus":0.014589410809665969,"score_gpt":0.25502361307559557,"score_spread":0.2404342022659296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163059805","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8042692,0.00007843689,0.19308405,0.00002703837,0.000062553685,0.0021051546,0.00024805567,0.000011196401,0.00011431408],"genre_scores_gemma":[0.94893134,0.000005164145,0.050547518,0.000070663824,0.000045021483,0.00017097859,0.00008964364,0.000025096966,0.00011457751],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99852914,0.00005409553,0.0007462081,0.00014318667,0.00027554986,0.00025181685],"domain_scores_gemma":[0.99855185,0.000024977515,0.00059252104,0.0005583876,0.0001835604,0.00008871478],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039453886,0.00023310415,0.00030380028,0.000053533426,0.00009493789,0.000049158843,0.00027716206,0.00013191694,7.2687493e-7],"category_scores_gemma":[0.00027332798,0.00016699814,0.00007724257,0.00013344544,0.000097102675,0.000033209253,0.00046020898,0.00011335858,5.7491565e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014139822,0.00858556,0.1344132,0.019750183,0.0033780376,0.00010609759,0.181422,0.005351408,0.16155183,0.00012177972,0.023767553,0.46013838],"study_design_scores_gemma":[0.015657293,0.016062291,0.00095953443,0.00029628552,0.00035036984,0.0018531225,0.053616524,0.77848697,0.12370194,0.000053469983,0.007508221,0.0014539686],"about_ca_topic_score_codex":0.00025595044,"about_ca_topic_score_gemma":0.00021566435,"teacher_disagreement_score":0.7731356,"about_ca_system_score_codex":0.00001956105,"about_ca_system_score_gemma":0.00010216637,"threshold_uncertainty_score":0.6809987},"labels":[],"label_agreement":null},{"id":"W2163262592","doi":"10.1093/bioinformatics/btp701","title":"Pandora, a PAthway and Network DiscOveRy Approach based on common biological evidence","year":2009,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Ontario Institute for Cancer Research","funders":"Michael Smith Health Research BC; Canadian Institutes of Health Research; Government of Ontario; Ontario Institute for Cancer Research","keywords":"Biological network; Biological pathway; KEGG; Computer science; Computational biology; Biological data; Systems biology; Biological database; Perl; Gene ontology; Ontology; UniProt; Domain (mathematical analysis); Biology; Bioinformatics; Gene; Genetics; World Wide Web","score_opus":0.021563019755216208,"score_gpt":0.2361732331037945,"score_spread":0.2146102133485783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163262592","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5653009,0.0048426087,0.37322184,0.001473442,0.0007123022,0.0022686126,0.0001497374,0.000191006,0.051839575],"genre_scores_gemma":[0.96883893,0.00034703742,0.024938148,0.0052976934,0.00026668826,0.000011435966,0.00019454444,0.000009765432,0.00009573831],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99881923,0.00003640999,0.00043023037,0.00018788248,0.00015062056,0.00037562192],"domain_scores_gemma":[0.9991911,0.00004400613,0.0001652239,0.00043645702,0.000039665596,0.00012351744],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041290143,0.00023828268,0.0002455729,0.000034394983,0.00014840397,0.00013199497,0.00022612694,0.00024552472,0.0000030089434],"category_scores_gemma":[0.000066847795,0.00017767806,0.00009204745,0.000106439365,0.00009823951,0.000023069366,0.000090290276,0.0001597605,0.0000095233145],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0038159287,0.0014491894,0.01944856,0.0008001237,0.0003309213,0.000022691293,0.0013498667,0.085209906,0.010054531,0.026768258,0.11773341,0.7330166],"study_design_scores_gemma":[0.0033524993,0.006890371,0.020557292,0.00051478925,0.000068813664,0.00010305094,0.00049343,0.9038707,0.002323571,0.003074034,0.05673192,0.0020195232],"about_ca_topic_score_codex":0.0000016433735,"about_ca_topic_score_gemma":0.0000013644908,"teacher_disagreement_score":0.8186608,"about_ca_system_score_codex":0.000013853836,"about_ca_system_score_gemma":0.000055376033,"threshold_uncertainty_score":0.72455007},"labels":[],"label_agreement":null},{"id":"W2163587256","doi":"10.1093/bioinformatics/btr079","title":"Automated workflows for accurate mass-based putative metabolite identification in LC/MS-derived metabolomic datasets","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":193,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Biotechnology and Biological Sciences Research Council; Directorate for Biological Sciences; National Institute for Health and Care Research; Cancer Research UK; Wellcome Trust","keywords":"Metabolomics; Workflow; Computer science; Identification (biology); Matching (statistics); Metabolite; Annotation; Software; Artifact (error); Data mining; False positive paradox; Limiting; Computational biology; Chemistry; Database; Artificial intelligence; Chromatography; Biology; Mathematics","score_opus":0.030480199805048347,"score_gpt":0.28736586061543684,"score_spread":0.2568856608103885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163587256","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6825063,0.0035786333,0.2982742,0.00025909668,0.0014206799,0.0036930747,0.0076274252,0.00033889606,0.00230168],"genre_scores_gemma":[0.82621306,0.000596234,0.16513817,0.00042673486,0.00009190443,0.0003293889,0.0070440513,0.00004681897,0.00011363729],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983586,0.000058078273,0.00073241396,0.00029540906,0.00014207435,0.00041340178],"domain_scores_gemma":[0.9988561,0.000034260178,0.00039480216,0.0004953275,0.0001345748,0.000084919855],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005517408,0.00027739597,0.0003732909,0.00021748611,0.00010783916,0.000053935106,0.00032461158,0.00015700478,0.000016068037],"category_scores_gemma":[0.0002868743,0.00025137037,0.00013163406,0.0002977819,0.00009199632,0.0000346694,0.000090061716,0.000086407,0.000025809908],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010215547,0.00039976783,0.0012725422,0.00035093984,0.00077244214,0.000004576625,0.0014428038,0.0006112392,0.97863084,0.0027395235,0.006337856,0.0064159073],"study_design_scores_gemma":[0.0031059799,0.0002549745,0.020339135,0.000019352445,0.0002196772,0.0000036547438,0.0006394792,0.086519375,0.8620716,0.00079271104,0.025270892,0.0007631765],"about_ca_topic_score_codex":0.000018759192,"about_ca_topic_score_gemma":0.000021965176,"teacher_disagreement_score":0.14370674,"about_ca_system_score_codex":0.000024219446,"about_ca_system_score_gemma":0.00009461383,"threshold_uncertainty_score":0.99999386},"labels":[],"label_agreement":null},{"id":"W2163649997","doi":"10.1093/bioinformatics/btl080","title":"MACGT: multi-dimensional automated clustering genotyping tool for analysis of microarray-based mini-sequencing data","year":2006,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Paul's Hospital; University of British Columbia","funders":"Heart and Stroke Foundation of British Columbia and Yukon; National Sanitarium Association; Heart and Stroke Foundation of Canada","keywords":"Genotyping; Cluster analysis; SNP; SNP genotyping; Computer science; DNA microarray; Single-nucleotide polymorphism; Computational biology; Genotype; SNP array; Data mining; Biology; Artificial intelligence; Genetics","score_opus":0.04516803501496724,"score_gpt":0.3026467413629859,"score_spread":0.25747870634801867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163649997","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36403814,0.00023285406,0.6342893,0.000060007438,0.00016593834,0.00038666843,0.0006169101,0.0000663988,0.00014378189],"genre_scores_gemma":[0.723919,0.00000639551,0.26984552,0.00020688007,0.000058070484,0.000019444671,0.0058126845,0.000014778855,0.00011727386],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99902505,0.000015713604,0.00047795605,0.00019221728,0.00012083608,0.0001682227],"domain_scores_gemma":[0.99892396,0.000016854709,0.00027513114,0.00062684156,0.00012654353,0.000030685278],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022199228,0.00011998779,0.00017385912,0.00015956396,0.0000741553,0.00002339931,0.00026848848,0.00011087923,0.000008461213],"category_scores_gemma":[0.00005207255,0.0001134064,0.00010068436,0.00024190181,0.000036531826,0.000010627378,0.00010907494,0.00002975966,0.0000018848583],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057600722,0.00003879381,0.00080222124,0.0001255885,0.00016708524,1.4775026e-7,0.000038162667,0.04083039,0.95223176,0.000010383681,0.0043861326,0.0013117447],"study_design_scores_gemma":[0.0005376775,0.000026940685,0.002313673,0.000020152542,0.0001668903,8.2624257e-7,0.00004748212,0.85315603,0.13943255,0.0000013014372,0.0041596475,0.00013681053],"about_ca_topic_score_codex":0.000022585862,"about_ca_topic_score_gemma":0.00004862924,"teacher_disagreement_score":0.8127992,"about_ca_system_score_codex":0.000027799815,"about_ca_system_score_gemma":0.00015077849,"threshold_uncertainty_score":0.4624579},"labels":[],"label_agreement":null},{"id":"W2163822209","doi":"10.1093/bioinformatics/bth913","title":"Striped sheets and protein contact prediction","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":89,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Knut och Alice Wallenbergs Stiftelse; Stiftelsen för Strategisk Forskning; Physicians' Services Incorporated Foundation","keywords":"Genetic programming; Sequence (biology); Computer science; Set (abstract data type); Source code; Algorithm; Protein methods; Sequence analysis; Artificial intelligence; Data mining; Biology; Genetics","score_opus":0.004783633876989148,"score_gpt":0.20641157875567803,"score_spread":0.20162794487868888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163822209","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9598767,0.0002023053,0.034841802,0.00008646739,0.000093357026,0.0004424421,0.00006243463,0.000032087042,0.004362402],"genre_scores_gemma":[0.98482406,0.000050687697,0.014621848,0.00016275734,0.000088201814,0.000014847278,0.00013429191,0.000008277074,0.000095006166],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995121,0.000005500599,0.00017322678,0.00009006337,0.000084457555,0.0001346503],"domain_scores_gemma":[0.9996707,0.000001374071,0.00006253366,0.00017120483,0.000032808057,0.000061389364],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006213429,0.00009912214,0.00007606214,0.000024540652,0.000059144724,0.000028277182,0.00006662027,0.0001237496,0.0000035236735],"category_scores_gemma":[0.00003613305,0.00008613086,0.000026879068,0.000038442122,0.000033033426,0.000009350576,0.000052581883,0.000056237895,0.000005034217],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003872152,0.00013688658,0.0031510324,0.0005344194,0.00024058035,0.000010296583,0.0011091869,0.0006571313,0.9116478,0.01530101,0.0015660364,0.06525839],"study_design_scores_gemma":[0.013411671,0.0049091442,0.037976872,0.00032934846,0.0001405705,0.00046943227,0.0011219801,0.010724254,0.82429713,0.009903297,0.09479944,0.0019168383],"about_ca_topic_score_codex":0.0000067181954,"about_ca_topic_score_gemma":0.000006776936,"teacher_disagreement_score":0.0932334,"about_ca_system_score_codex":0.00001302966,"about_ca_system_score_gemma":0.000056627694,"threshold_uncertainty_score":0.35123143},"labels":[],"label_agreement":null},{"id":"W2163980860","doi":"10.1093/bioinformatics/bti493","title":"Discovering patterns to extract protein–protein interactions from the literature: Part II","year":2005,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":96,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Killam Trusts","keywords":"Merge (version control); Computer science; Recall; Protein–protein interaction; Generalization; Precision and recall; Protein expression; Artificial intelligence; Task (project management); Machine learning; Data mining; Computational biology; Information retrieval; Biology; Genetics; Mathematics","score_opus":0.015103357633382478,"score_gpt":0.26207536494041134,"score_spread":0.24697200730702887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163980860","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98238164,0.00032706192,0.012723828,0.0031870094,0.00019966491,0.0003282842,0.00019804039,0.000039423303,0.0006150477],"genre_scores_gemma":[0.97521764,0.00003512518,0.020450693,0.0013236878,0.00089875294,0.00008539109,0.0002559127,0.000014143774,0.0017186832],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99919075,0.000021908634,0.00027811495,0.00014209974,0.00013916694,0.00022796322],"domain_scores_gemma":[0.9993762,0.000017520788,0.00008451651,0.00039601087,0.000034397788,0.00009139125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000114372044,0.00014761514,0.00010432578,0.000022678563,0.00018136113,0.000098904646,0.00028061264,0.0001121609,0.00004768446],"category_scores_gemma":[0.00017826105,0.00009549084,0.0000761675,0.000086560234,0.000045957033,0.000015460002,0.00023148785,0.000166243,0.000061373015],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001640045,0.00025310792,0.0012569418,0.00009029135,0.00021294689,0.0000054293682,0.008323615,0.000116543146,0.12408887,0.0001943241,0.048208397,0.8170855],"study_design_scores_gemma":[0.00023749286,0.00019216591,0.0010242099,0.00027039472,0.000010882058,0.00000884368,0.00064620544,0.0004111945,0.061442386,0.000031516796,0.93549883,0.0002258789],"about_ca_topic_score_codex":0.000022048627,"about_ca_topic_score_gemma":0.000112027774,"teacher_disagreement_score":0.8872904,"about_ca_system_score_codex":0.000016093296,"about_ca_system_score_gemma":0.00003039732,"threshold_uncertainty_score":0.38940033},"labels":[],"label_agreement":null},{"id":"W2163982822","doi":"10.1093/bioinformatics/btu198","title":"Inferring rare disease risk variants based on exact probabilities of sharing by multiple affected relatives","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut Universitaire en Santé Mentale de Québec","funders":"National Institute of Dental and Craniofacial Research; National Institute of General Medical Sciences; National Human Genome Research Institute","keywords":"Kinship; Genetics; Exome sequencing; Population; Biology; Computer science; Mutation; Medicine; Gene","score_opus":0.010034335280250776,"score_gpt":0.2302433048776615,"score_spread":0.22020896959741074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163982822","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9622345,0.00004984041,0.0355259,0.00004831108,0.00006911418,0.0002365029,0.00016480866,0.000019362129,0.0016516634],"genre_scores_gemma":[0.9905182,0.000027374084,0.008859804,0.0001020592,0.00003573757,0.000019274794,0.00029642176,0.000012033944,0.00012908291],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990672,0.00010565696,0.000363956,0.00015771977,0.00010137318,0.0002041239],"domain_scores_gemma":[0.9990287,0.00013714826,0.00029228575,0.0003836688,0.00006850356,0.00008969213],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042511686,0.00013886952,0.00018400619,0.00004448102,0.000090583904,0.000012179008,0.00014874319,0.00012160464,0.000011268691],"category_scores_gemma":[0.0027505402,0.00012145722,0.00008308572,0.00006168715,0.00006199948,0.0000069772673,0.000076985125,0.00008217566,0.0000068359336],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014245887,0.00022395795,0.9602288,0.00029360948,0.00010732668,2.0104686e-7,0.00048211563,0.02442749,0.00721485,0.00026041496,0.0029163293,0.0037024731],"study_design_scores_gemma":[0.0009634571,0.00038190844,0.53751796,0.00006243739,0.00003735342,3.3275916e-7,0.00013966327,0.45659477,0.0022207547,0.00031013106,0.0015264408,0.00024481086],"about_ca_topic_score_codex":0.000018973577,"about_ca_topic_score_gemma":0.0000060391694,"teacher_disagreement_score":0.4321673,"about_ca_system_score_codex":0.000016639347,"about_ca_system_score_gemma":0.000042504045,"threshold_uncertainty_score":0.49528816},"labels":[],"label_agreement":null},{"id":"W2164555431","doi":"10.1093/bioinformatics/btm532","title":"Uniformization for sampling realizations of Markov processes: applications to Bayesian implementations of codon substitution models","year":2007,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":70,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Canadian Institute for Advanced Research","funders":"Canadian Institutes of Health Research; Centre National de la Recherche Scientifique; Canadian Institute for Advanced Research","keywords":"Computer science; Markov chain Monte Carlo; Uniformization (probability theory); Substitution (logic); Tree (set theory); Bayesian probability; Algorithm; Probabilistic logic; Theoretical computer science; Pruning; Range (aeronautics); Markov chain; Markov model; Mathematics; Artificial intelligence; Variable-order Markov model; Machine learning; Combinatorics; Programming language","score_opus":0.033327972746494273,"score_gpt":0.31336914141959965,"score_spread":0.28004116867310536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164555431","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04414651,0.00007989769,0.9539565,0.000024924482,0.000025650215,0.00074492244,0.00034482073,0.0000029315781,0.00067384087],"genre_scores_gemma":[0.79617363,0.00013423685,0.20290679,0.00004090946,0.00003410687,0.000077948374,0.0006013788,0.000008416386,0.000022573211],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992632,0.000003363625,0.0004526461,0.00008020353,0.00007460237,0.0001259464],"domain_scores_gemma":[0.9991224,0.000026321624,0.00019955247,0.00016623188,0.00044223652,0.000043297794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020148208,0.00007647565,0.00009997913,0.000083052175,0.00009205285,0.000006306105,0.00009553463,0.000054018055,0.000001166393],"category_scores_gemma":[0.000063131454,0.00007835842,0.000036445075,0.00022431553,0.000034360288,0.0000038362928,0.000035828856,0.000012692083,2.7382566e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005436469,0.00066400645,0.013065635,0.005157477,0.00063457777,8.2787274e-8,0.009701732,0.25998968,0.44582278,0.20046133,0.0021978116,0.06176126],"study_design_scores_gemma":[0.0037124166,0.0017724446,0.0086833425,0.0002150095,0.00046001934,0.000011633036,0.013065659,0.061701547,0.7950776,0.013926696,0.10001207,0.0013615269],"about_ca_topic_score_codex":0.0000132533205,"about_ca_topic_score_gemma":0.00015232032,"teacher_disagreement_score":0.75202715,"about_ca_system_score_codex":0.00001199706,"about_ca_system_score_gemma":0.00010768265,"threshold_uncertainty_score":0.31953636},"labels":[],"label_agreement":null},{"id":"W2164620224","doi":"10.1093/bioinformatics/btm115","title":"SherLoc: high-accuracy prediction of protein subcellular localization by integrating text and protein sequence data","year":2007,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":127,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Sequence (biology); Protein sequencing; Artificial intelligence; Computational biology; Protein subcellular localization prediction; Data mining; Pattern recognition (psychology); Peptide sequence; Biology; Genetics; Gene","score_opus":0.015547919242480267,"score_gpt":0.25874349043564987,"score_spread":0.2431955711931696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164620224","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38257584,0.00023908865,0.6151128,0.000044819608,0.000060389924,0.00077998673,0.00026986407,0.000040745395,0.0008764815],"genre_scores_gemma":[0.8742926,0.00006316589,0.12141255,0.00009452315,0.00008244013,0.000013389549,0.0037496327,0.000026960572,0.000264728],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984665,0.00004297691,0.0007794937,0.0001846281,0.00027056353,0.00025586432],"domain_scores_gemma":[0.99857014,0.000025763728,0.00049333984,0.00068632246,0.00013498166,0.000089418434],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010705179,0.0001998337,0.00017492117,0.000068753965,0.00012548722,0.000052645682,0.00037838033,0.00021365016,0.000010492874],"category_scores_gemma":[0.0009825751,0.00018046323,0.000025486963,0.00016855,0.00015045887,0.00006826115,0.00030902374,0.0001992147,0.0000043106284],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015093177,0.0001200351,0.0053537823,0.0017474294,0.00010816486,0.00000183296,0.001376343,0.0002810404,0.9125117,0.0011455219,0.0043785847,0.07282461],"study_design_scores_gemma":[0.0011256167,0.0008396425,0.00044120042,0.00037127847,0.00004562359,0.00003975186,0.0012179912,0.49340394,0.43114367,0.00007527509,0.07076634,0.00052966736],"about_ca_topic_score_codex":0.000067496956,"about_ca_topic_score_gemma":0.000015104466,"teacher_disagreement_score":0.4937002,"about_ca_system_score_codex":0.000023107337,"about_ca_system_score_gemma":0.000071843235,"threshold_uncertainty_score":0.73590773},"labels":[],"label_agreement":null},{"id":"W2164803230","doi":"10.1093/bioinformatics/bth142","title":"Fuzzy J-Means and VNS methods for clustering genes from microarray data","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":70,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"Université de Moncton","keywords":"Cluster analysis; Microarray analysis techniques; Computer science; Fuzzy logic; Data mining; Microarray; Computational biology; Gene; Artificial intelligence; Biology; Genetics; Gene expression","score_opus":0.048461004433985974,"score_gpt":0.3445911649265163,"score_spread":0.2961301604925303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164803230","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01715452,0.0015258506,0.9795038,0.00029112402,0.00024914017,0.00023051775,0.00020033498,0.000016386031,0.0008283369],"genre_scores_gemma":[0.03163173,0.0008202141,0.96525097,0.00050668186,0.00022308406,0.000026304991,0.0013752665,0.00001753657,0.00014822133],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994278,0.000014055465,0.00020539985,0.0001768159,0.000046309346,0.00012962487],"domain_scores_gemma":[0.99925953,0.000011741136,0.00008725695,0.00054491963,0.000035460445,0.00006108212],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016770496,0.00009957904,0.00009120529,0.000025861167,0.00007855876,0.000043523476,0.00024382726,0.000096739364,0.0000026241232],"category_scores_gemma":[0.00005170316,0.00008867576,0.000026956126,0.000036241247,0.00003623607,0.000011844995,0.0002026082,0.00003133615,0.0000031898567],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003706783,0.000018106115,0.00007252038,0.000056030247,0.000036084228,6.766599e-8,0.00029192562,0.00011977319,0.84629166,0.00008540897,0.0024564164,0.15053496],"study_design_scores_gemma":[0.0014662808,0.00011888866,0.0004718811,0.000038515773,0.00004660676,0.0000082511615,0.00077151303,0.009619386,0.4483841,0.00093283824,0.53781605,0.00032571732],"about_ca_topic_score_codex":0.000012076907,"about_ca_topic_score_gemma":0.000022162823,"teacher_disagreement_score":0.5353596,"about_ca_system_score_codex":0.000009555399,"about_ca_system_score_gemma":0.000057095465,"threshold_uncertainty_score":0.36160925},"labels":[],"label_agreement":null},{"id":"W2165260680","doi":"10.1093/bioinformatics/bts228","title":"Identifying disease sensitive and quantitative trait-relevant biomarkers from multidimensional heterogeneous imaging genetics data via sparse multimodal multitask learning","year":2012,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":159,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Aging; University of California, San Diego; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; University of California, Los Angeles; Genentech; National Institutes of Health; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; Alzheimer's Association; Amorfix Life Sciences; Dana Foundation; Bayer HealthCare; Alzheimer's Disease Neuroimaging Initiative; National Center for Advancing Translational Sciences; Meso Scale Diagnostics; National Center for Research Resources; F. Hoffmann-La Roche; Medpace; Bristol-Myers Squibb; Eli Lilly and Company; AstraZeneca; Novartis Pharmaceuticals Corporation; Synarc; Foundation for the National Institutes of Health; National Science Foundation","keywords":"Imaging genetics; Neuroimaging; Cognition; Computer science; Machine learning; Artificial intelligence; Alzheimer's Disease Neuroimaging Initiative; Pairwise comparison; Multi-task learning; Psychology; Neuroscience; Cognitive impairment; Task (project management)","score_opus":0.0339192501247622,"score_gpt":0.2984632222230629,"score_spread":0.26454397209830066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2165260680","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90936834,0.0023248878,0.08692321,0.000091385766,0.00030723948,0.00025446046,0.0006744946,0.000025309515,0.000030655618],"genre_scores_gemma":[0.80058813,0.00033278528,0.19611719,0.0002172134,0.00013328172,0.0000068233153,0.0025614449,0.000026555623,0.000016599908],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982435,0.00018328261,0.0005189295,0.00034744877,0.00018741554,0.0005194255],"domain_scores_gemma":[0.99861,0.00016922594,0.00030508722,0.00047643803,0.00011070445,0.0003284993],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000529885,0.00027605591,0.00025725533,0.00007030579,0.00025666892,0.00003703009,0.00019133644,0.00013365809,0.000010295973],"category_scores_gemma":[0.0005939311,0.00026758577,0.00007859675,0.000066287,0.00017926609,0.000039836254,0.0005696849,0.00014736956,0.000031337637],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006696581,0.0005729509,0.6457614,0.0002056089,0.0021508457,0.00004150227,0.0066616656,0.012565645,0.25026014,0.000080531376,0.0029465207,0.07808352],"study_design_scores_gemma":[0.0010155414,0.000071235256,0.18078628,0.0000370529,0.00019155418,0.00003564879,0.0019802733,0.8101308,0.0028835398,0.000035590536,0.0022983863,0.0005340977],"about_ca_topic_score_codex":0.00011596036,"about_ca_topic_score_gemma":0.000027161848,"teacher_disagreement_score":0.79756516,"about_ca_system_score_codex":0.000028788756,"about_ca_system_score_gemma":0.00006029127,"threshold_uncertainty_score":0.99997765},"labels":[],"label_agreement":null},{"id":"W2165474022","doi":"10.1093/bioinformatics/btn165","title":"Designing succinct structural alphabets","year":2008,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Chinese Government Scholarship; Natural Sciences and Engineering Research Council of Canada; Mitacs; National Natural Science Foundation of China","keywords":"Sequence (biology); Computer science; Construct (python library); State (computer science); Algorithm; Programming language; Chemistry","score_opus":0.009531432337122883,"score_gpt":0.22692665459427547,"score_spread":0.21739522225715258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2165474022","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9543168,0.00029268084,0.04023724,0.000027997212,0.00021438286,0.00018519102,0.000017831917,0.000038583537,0.004669298],"genre_scores_gemma":[0.93100053,0.000065299435,0.06796081,0.00035046693,0.00016410419,0.0000049819278,0.00013211143,0.0000140139155,0.00030766692],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992879,0.00001227327,0.00022634663,0.00010796889,0.00013075053,0.00023475564],"domain_scores_gemma":[0.99950117,0.0000056758267,0.000085960506,0.00027689556,0.000051940802,0.00007837287],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000060841496,0.00014240386,0.00011259817,0.00003372025,0.00016476067,0.000015996664,0.00017414469,0.0001271339,0.000014661536],"category_scores_gemma":[0.000045569403,0.00012149248,0.00006621549,0.00006621029,0.000073689116,0.000009653985,0.00008642616,0.00007185483,0.000023790364],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006025727,0.00009872367,0.10189925,0.0005419242,0.00070759706,0.00013872531,0.004950825,0.0028890122,0.7147737,0.0031315235,0.053380918,0.11688524],"study_design_scores_gemma":[0.004164941,0.0013837917,0.050907865,0.000061551495,0.000088889785,0.0026841399,0.000839115,0.036949236,0.83110774,0.0014192311,0.06796985,0.0024236522],"about_ca_topic_score_codex":0.0000053042877,"about_ca_topic_score_gemma":0.00000532144,"teacher_disagreement_score":0.11633404,"about_ca_system_score_codex":0.000010764753,"about_ca_system_score_gemma":0.00007021765,"threshold_uncertainty_score":0.49543196},"labels":[],"label_agreement":null},{"id":"W2165567081","doi":"10.1093/bioinformatics/16.5.484","title":"Viral Genome DataBase: storing and analyzing genes and proteins from complete viral genomes","year":2000,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Animal Virus Infections Studies","field":"Agricultural and Biological Sciences","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"GenBank; Genome; Gene; Biology; Database; Codon usage bias; Genetics; DNA sequencing; Computational biology; Computer science","score_opus":0.03443914197597459,"score_gpt":0.22560039761033884,"score_spread":0.19116125563436426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2165567081","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9956224,0.0026660606,0.00004575926,0.0000772145,0.000026114216,0.00018339613,0.00034934844,0.00006340116,0.00096627965],"genre_scores_gemma":[0.98769045,0.003531345,0.008029745,0.00013625773,0.0002825371,0.000016432128,0.00013720946,0.0000016241371,0.00017438465],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9993081,0.000017005179,0.00022512737,0.00013557705,0.00010589142,0.00020827867],"domain_scores_gemma":[0.9997421,0.00005467643,0.00006237858,0.000051772808,0.000019823965,0.000069250666],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009020359,0.00013734902,0.0001724457,0.000014235523,0.00047479538,0.000106835854,0.000092397626,0.000041957348,0.0002172078],"category_scores_gemma":[0.000009399326,0.000060104172,0.000029118795,0.00009954673,0.00010713961,0.00033251735,0.0001308355,0.0000768921,0.00004559097],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005552233,0.000058636117,0.058033746,0.000077499404,0.00013893771,0.000004599272,0.0017832378,0.000017568691,0.19257814,0.00039498846,0.0001167796,0.74674034],"study_design_scores_gemma":[0.00057427783,0.00073625566,0.69340813,0.000085205415,0.00011752383,0.000030712272,0.0022954487,0.0071238913,0.0013515976,0.00046060333,0.29276896,0.0010473971],"about_ca_topic_score_codex":0.00046451972,"about_ca_topic_score_gemma":0.00026235648,"teacher_disagreement_score":0.74569297,"about_ca_system_score_codex":0.000020190439,"about_ca_system_score_gemma":0.000003028501,"threshold_uncertainty_score":0.36517903},"labels":[],"label_agreement":null},{"id":"W2166098531","doi":"10.1093/bioinformatics/bts701","title":"Characterization of disordered proteins with ENSEMBLE","year":2012,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":157,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Perl; Computer science; Characterization (materials science); Interface (matter); Set (abstract data type); Ensemble learning; Intrinsically disordered proteins; Data mining; Programming language; Artificial intelligence; Physics; Operating system; Nanotechnology; Materials science","score_opus":0.005304317679989394,"score_gpt":0.2036163241529141,"score_spread":0.1983120064729247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166098531","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88490844,0.000038736474,0.11294835,0.000014525178,0.000042342803,0.00023168558,0.000021722513,0.000007819535,0.0017863915],"genre_scores_gemma":[0.9816095,0.000024245486,0.017819561,0.00005917118,0.00006644451,0.000012510064,0.00027480794,0.000008717079,0.0001250258],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995744,0.0000067889127,0.00015181555,0.00004182358,0.00008268515,0.0001424464],"domain_scores_gemma":[0.99960965,0.0000013854583,0.00011843078,0.00018388499,0.000044548262,0.000042110176],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000053853328,0.000077965844,0.00007802816,0.000020963747,0.00002606659,0.000006346706,0.00006801338,0.00007056083,0.000004492936],"category_scores_gemma":[0.000013386275,0.000058516765,0.00002262985,0.000057036013,0.000033178,0.00001207299,0.000033871118,0.000027833059,0.00000391719],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006693109,0.00004428566,0.0073660826,0.00010629037,0.00003102355,6.9755984e-8,0.0003768375,0.000006867241,0.9841229,0.00062863354,0.000033376113,0.0072167194],"study_design_scores_gemma":[0.0005737568,0.00037783902,0.016225822,0.000025402205,0.000022653287,0.000020568377,0.00014302671,0.0005538811,0.9689374,0.000039923358,0.012834703,0.00024505125],"about_ca_topic_score_codex":0.0000019274107,"about_ca_topic_score_gemma":0.0000033731005,"teacher_disagreement_score":0.09670109,"about_ca_system_score_codex":0.000003528403,"about_ca_system_score_gemma":0.00002799378,"threshold_uncertainty_score":0.23862444},"labels":[],"label_agreement":null},{"id":"W2166268906","doi":"10.1093/bioinformatics/btp212","title":"A partition function algorithm for interacting nucleic acid strands","year":2009,"lang":"en","type":"article","venue":"Bioinformatics","topic":"DNA and Nucleic Acid Chemistry","field":"Biochemistry, Genetics and Molecular Biology","cited_by":104,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Algorithm; Nucleic acid; Partition (number theory); Computer science; Function (biology); Mathematics; Combinatorics; Chemistry; Biology; Biochemistry; Genetics","score_opus":0.00877055586134036,"score_gpt":0.24114521534579478,"score_spread":0.2323746594844544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166268906","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4548822,0.00016857318,0.53401655,0.00022235888,0.00050608645,0.00036511547,0.00007664307,0.000086968306,0.009675497],"genre_scores_gemma":[0.95811874,0.000037700043,0.039943714,0.0006053665,0.0004083769,0.000013617637,0.00054016616,0.000012999127,0.00031933002],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999378,0.0000043463288,0.0002363715,0.000109301065,0.0000810417,0.00019088898],"domain_scores_gemma":[0.999591,0.0000057835614,0.00010481535,0.00017636264,0.00006193498,0.000060139304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009370809,0.00011635191,0.00009162328,0.000020925754,0.00008737863,0.000040820516,0.000091270354,0.00012482656,0.000017242517],"category_scores_gemma":[0.000039122646,0.0001114545,0.00008908402,0.000043103002,0.000018779197,0.000016082453,0.000018001349,0.000057476012,0.000013952371],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000109430446,0.000072511975,0.000031914245,0.00005191802,0.000042494947,4.4841696e-7,0.00013698115,0.000013111264,0.5230513,0.000058757298,0.009858636,0.4665725],"study_design_scores_gemma":[0.0016901535,0.0012185035,0.00034796336,0.000049373553,0.000069150636,0.00003634911,0.00073025527,0.047203418,0.85125124,0.00037073207,0.09659115,0.00044170718],"about_ca_topic_score_codex":3.1690996e-7,"about_ca_topic_score_gemma":3.995432e-7,"teacher_disagreement_score":0.50323653,"about_ca_system_score_codex":0.000012435996,"about_ca_system_score_gemma":0.000022059023,"threshold_uncertainty_score":0.45449826},"labels":[],"label_agreement":null},{"id":"W2166281646","doi":"10.1093/bioinformatics/bth019","title":"Transposable element annotation of the rice genome","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Chromosomal and Genetic Variations","field":"Agricultural and Biological Sciences","cited_by":62,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Annotation; Transposable element; Genome; Computer science; Perl; Set (abstract data type); Computational biology; Biology; Sequence alignment; Genetics; Programming language; Gene","score_opus":0.013399751487314138,"score_gpt":0.19352560113012673,"score_spread":0.18012584964281259,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166281646","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9962152,0.000023359666,0.00012155698,0.0011948223,0.00005967889,0.00015329134,0.000065767395,0.0000126459,0.0021536273],"genre_scores_gemma":[0.99815804,0.000012267842,0.0015772391,0.00013708045,0.000032191376,0.0000035722135,0.000027161215,1.7292616e-7,0.000052269967],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.999595,0.000005326623,0.00017161945,0.000032268777,0.000115643255,0.000080129816],"domain_scores_gemma":[0.9998296,0.000013862176,0.00007030928,0.00003408182,0.000032480566,0.000019701016],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000049371665,0.000040771592,0.000046057557,0.000002873867,0.00009295878,0.000010496514,0.000119238364,0.00002282544,0.000068294365],"category_scores_gemma":[0.000006835981,0.000012125824,0.00004269042,0.00018566765,0.000018909703,0.00005557679,0.000015499862,0.00002382173,0.000020465339],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026318392,0.0005274212,0.0072863596,0.00015893363,0.00007031273,5.523289e-7,0.009454585,0.008377065,0.9050654,0.021998622,0.00017846066,0.046855934],"study_design_scores_gemma":[0.00068963424,0.00037518825,0.908693,0.000043975684,0.000047451922,0.000009726362,0.0015604171,0.0014875064,0.04756225,0.007183745,0.032073323,0.000273778],"about_ca_topic_score_codex":0.00003731806,"about_ca_topic_score_gemma":0.00010951889,"teacher_disagreement_score":0.90140665,"about_ca_system_score_codex":0.000013405689,"about_ca_system_score_gemma":0.000009750713,"threshold_uncertainty_score":0.07477754},"labels":[],"label_agreement":null},{"id":"W2166335393","doi":"10.1093/bioinformatics/btp222","title":"Constrained mixture estimation for analysis and robust classification of clinical time series","year":2009,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Division of Mathematical Sciences; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Computer science; Robustness (evolution); Personalized medicine; Machine learning; Data mining; Artificial intelligence; Missing data; Pattern recognition (psychology); Bioinformatics; Gene; Biology","score_opus":0.04136910599703127,"score_gpt":0.29435331925133573,"score_spread":0.2529842132543045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166335393","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0074028275,0.00001630591,0.9909421,0.00055257836,0.00002553594,0.00011453253,0.000012726301,0.000039035618,0.00089432555],"genre_scores_gemma":[0.21952489,0.000010224909,0.78024083,0.00006100429,0.000018651228,0.0000016891124,0.000047918733,0.0000016156398,0.000093159324],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99896455,0.000015715063,0.0006861193,0.000105161635,0.00012194108,0.00010650097],"domain_scores_gemma":[0.9990228,0.00009936196,0.00044464107,0.00024128375,0.00014087491,0.000051055416],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050261326,0.00008054101,0.00029506805,0.00013156088,0.00007683633,0.0000891183,0.0001723182,0.000072401686,0.0000060194075],"category_scores_gemma":[0.00017486735,0.00006639231,0.0001421625,0.0005170763,0.0000629709,0.0006106784,0.00002640898,0.000042807478,0.0000028180734],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039109458,0.000120315286,0.0015962396,0.000102981896,0.0004275344,3.688288e-7,0.001341394,0.0077392203,0.00018911279,0.07146712,0.0007998961,0.91617674],"study_design_scores_gemma":[0.00016978986,0.00017622903,0.013874382,0.000008037382,0.00014941914,0.0000023054495,0.00006504225,0.9845954,0.00008294448,0.0006067014,0.00019365487,0.00007606259],"about_ca_topic_score_codex":0.000001182643,"about_ca_topic_score_gemma":0.000002024118,"teacher_disagreement_score":0.97685623,"about_ca_system_score_codex":0.0000057187913,"about_ca_system_score_gemma":0.000032000964,"threshold_uncertainty_score":0.27073997},"labels":[],"label_agreement":null},{"id":"W2166372712","doi":"10.1093/bioinformatics/btu544","title":"Figmop: a profile HMM to identify genes and bypass troublesome gene models in draft genomes","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Gene; Genome; Computational biology; Hidden Markov model; Biology; Genetics; Computer science; Artificial intelligence","score_opus":0.0148272516669068,"score_gpt":0.2479729135171589,"score_spread":0.2331456618502521,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166372712","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9902991,0.002345947,0.004694732,0.00012985397,0.00011058731,0.00035228042,0.00005726648,0.00000656207,0.0020036483],"genre_scores_gemma":[0.9708518,0.001142412,0.026951047,0.00048760563,0.00014101467,0.000059822047,0.000056462566,0.00002142746,0.00028843872],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99902815,0.00002094596,0.0003404725,0.00020221478,0.00010812206,0.00030007263],"domain_scores_gemma":[0.9994471,0.000012422942,0.00007604545,0.00030088858,0.000055163906,0.00010838407],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020370864,0.0001824762,0.00020565388,0.00008695588,0.000074947566,0.000053520176,0.0001787778,0.00010858621,0.000004715268],"category_scores_gemma":[0.000026038293,0.00016955847,0.00004683008,0.00009043492,0.000044824053,0.000004100488,0.0002714207,0.00004763079,0.000020637654],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015485038,0.00014549153,0.015663015,0.00044090307,0.00024719557,0.0000031996385,0.0042497017,0.0060739433,0.88430995,0.0014706332,0.0046642665,0.08257687],"study_design_scores_gemma":[0.00746984,0.0025958444,0.088943444,0.00016751945,0.00017851715,0.00012568582,0.0028364945,0.16601177,0.40553358,0.0057518743,0.3166074,0.00377804],"about_ca_topic_score_codex":0.00001649265,"about_ca_topic_score_gemma":0.000048242844,"teacher_disagreement_score":0.47877634,"about_ca_system_score_codex":0.000012718012,"about_ca_system_score_gemma":0.000033129127,"threshold_uncertainty_score":0.69143933},"labels":[],"label_agreement":null},{"id":"W2166393666","doi":"10.1093/bioinformatics/btm145","title":"An efficient method for the detection and elimination of systematic error in high-throughput screening","year":2007,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":98,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University and Génome Québec Innovation Centre; Université du Québec à Montréal","funders":"","keywords":"Throughput; Computer science; Error detection and correction; Systematic error; High-throughput screening; Statistics; Algorithm; Mathematics; Biology; Bioinformatics; Operating system","score_opus":0.03858466843007075,"score_gpt":0.34658664766903596,"score_spread":0.3080019792389652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166393666","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021573488,0.00006737121,0.97735834,0.00008186477,0.00016812426,0.0006958808,0.0000025098177,0.000027722128,0.00002470628],"genre_scores_gemma":[0.45154458,0.0000010686387,0.5483957,0.000031182888,0.000009963919,0.000012670215,0.0000010337525,0.0000026238806,0.0000011670592],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99880826,0.00010288703,0.00056693965,0.000104807325,0.000268052,0.00014907197],"domain_scores_gemma":[0.9972931,0.0019936564,0.0002856565,0.00027665237,0.00011886885,0.000032023006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044681304,0.00008629349,0.00017109142,0.00019212707,0.000088574685,0.00007259738,0.00029601122,0.000041422794,2.1666892e-7],"category_scores_gemma":[0.00032696014,0.00006243267,0.000034587378,0.00038480436,0.000026309724,0.00040713375,0.00007384294,0.00005749558,5.429577e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038892093,0.00008065776,0.000052823947,0.0052267266,0.000023372088,5.8894335e-7,0.010309302,0.6408103,0.00040264335,0.07553052,0.0000028119593,0.26752132],"study_design_scores_gemma":[0.00026958785,0.000084369436,0.009112533,0.00021628223,0.000014099351,0.000009227282,0.0008599348,0.9866844,0.0018250046,0.00084703026,0.000004722277,0.00007281084],"about_ca_topic_score_codex":0.000030897423,"about_ca_topic_score_gemma":0.000029034212,"teacher_disagreement_score":0.4299711,"about_ca_system_score_codex":0.000043215085,"about_ca_system_score_gemma":0.000025527188,"threshold_uncertainty_score":0.25459304},"labels":[],"label_agreement":null},{"id":"W2166542841","doi":"10.1093/bioinformatics/btq562","title":"GeneMANIA Cytoscape plugin: fast gene function predictions on the desktop","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":661,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Ontario Genomics; Ontario Genomics Institute; Genome Canada","keywords":"Plug-in; Computer science; Function (biology); Complement (music); Java; Set (abstract data type); Gene; Programming language; Biology; Genetics","score_opus":0.007931295299022024,"score_gpt":0.20052849950022197,"score_spread":0.19259720420119994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166542841","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77842146,0.00015705891,0.12878567,0.0012266727,0.003715359,0.0011634701,0.00021971292,0.00013999098,0.08617061],"genre_scores_gemma":[0.989897,0.000095827556,0.0055461423,0.0022644806,0.00093377195,0.000048787653,0.00030308397,0.000028495117,0.00088240346],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989569,0.00001530693,0.0003933179,0.00013815606,0.00018768464,0.00030863527],"domain_scores_gemma":[0.9989277,0.000021980546,0.00016911095,0.0006888948,0.00008313894,0.00010916874],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029977574,0.00020587609,0.00011689386,0.000047536956,0.00033079952,0.00009308058,0.000309788,0.0002503232,0.00011746],"category_scores_gemma":[0.000045600722,0.00014365473,0.00011265363,0.00011326043,0.000112194415,0.0000117827,0.000120754696,0.00030942255,0.00022629432],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00059431954,0.0005268953,0.0018358541,0.00022645557,0.0009387692,0.0000038760204,0.002136505,0.00543018,0.47899333,0.04733384,0.3281898,0.1337902],"study_design_scores_gemma":[0.0018539608,0.001533643,0.008589058,0.00004320667,0.00018788231,0.00018673406,0.0012799014,0.13747431,0.0751906,0.0013450634,0.77103585,0.0012797853],"about_ca_topic_score_codex":0.0000035304686,"about_ca_topic_score_gemma":0.000038478123,"teacher_disagreement_score":0.44284606,"about_ca_system_score_codex":0.000011038209,"about_ca_system_score_gemma":0.00007561409,"threshold_uncertainty_score":0.58580697},"labels":[],"label_agreement":null},{"id":"W2166603052","doi":"10.1093/bioinformatics/btl513","title":"THOR: targeted high-throughput ortholog reconstructor","year":2006,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency","funders":"Michael Smith Health Research BC; Genome Canada","keywords":"Sequence (biology); Genome; Computational biology; Throughput; Biology; Set (abstract data type); Whole genome sequencing; Computer science; Genetics; Gene","score_opus":0.0070013370118372584,"score_gpt":0.20645833400386795,"score_spread":0.1994569969920307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166603052","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9865454,0.0006258707,0.0014991638,0.0000871156,0.0004401523,0.00016631596,0.00010233624,0.000013655579,0.010520016],"genre_scores_gemma":[0.95637435,0.00020080831,0.041882128,0.00023218372,0.0003447506,0.000012279959,0.00019284981,0.000017459584,0.00074317335],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99913234,0.00001498141,0.0003408206,0.00015414442,0.0000926909,0.000265021],"domain_scores_gemma":[0.99942905,0.000008477493,0.00012395576,0.00032304387,0.000071533024,0.000043938326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009748796,0.0001676129,0.00015666026,0.00003407308,0.000110869434,0.000028585979,0.00015620342,0.00013313684,0.000022433838],"category_scores_gemma":[0.000026216614,0.00014929443,0.00007873777,0.000068477035,0.00010616947,0.0000015840037,0.00012372725,0.000054432563,0.0000519945],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016872429,0.000256822,0.08179639,0.00022938036,0.00048421932,0.000012566856,0.00051163853,0.0010050386,0.7199848,0.01105939,0.13992006,0.04457092],"study_design_scores_gemma":[0.0025599594,0.0010798494,0.14165843,0.00002787081,0.00011803959,0.00016321977,0.00069468375,0.0009280509,0.28804803,0.0040653795,0.5590311,0.0016253979],"about_ca_topic_score_codex":0.00003647073,"about_ca_topic_score_gemma":0.00003933179,"teacher_disagreement_score":0.43193683,"about_ca_system_score_codex":0.000010467243,"about_ca_system_score_gemma":0.00004899303,"threshold_uncertainty_score":0.608805},"labels":[],"label_agreement":null},{"id":"W2166815431","doi":"10.1093/bioinformatics/btu284","title":"A combinatorial approach for analyzing intra-tumor heterogeneity from high-throughput sequencing data","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":124,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Burroughs Wellcome Fund; National Human Genome Research Institute; Natural Sciences and Engineering Research Council of Canada; National Cancer Institute; National Institutes of Health; National Science Foundation","keywords":"Cluster analysis; Python (programming language); Tumor heterogeneity; Population; DNA sequencing; Computer science; Biology; Computational biology; Single cell sequencing; Mutation; Algorithm; Genetics; Gene; Machine learning; Cancer; Exome sequencing","score_opus":0.026978806483223386,"score_gpt":0.2588377383390367,"score_spread":0.23185893185581335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166815431","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40061074,0.00020988168,0.59590626,0.000039532006,0.0008931149,0.00039845562,0.0012970761,0.000025691501,0.000619246],"genre_scores_gemma":[0.83076936,0.00006431893,0.16206585,0.0005488889,0.0012595493,0.000025283798,0.0052337823,0.000028016797,0.000004969966],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99884766,0.000022789327,0.0003982037,0.0003175575,0.00012268069,0.00029109645],"domain_scores_gemma":[0.9984774,0.00006592401,0.00019694067,0.0010686732,0.00008352948,0.00010753156],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003532325,0.00018983315,0.00023344009,0.000030824278,0.0001278272,0.00010117567,0.00055054354,0.0001293634,0.0000028190168],"category_scores_gemma":[0.00040547657,0.00018750361,0.000073756775,0.00006300902,0.000058719135,0.000016826985,0.0004149487,0.00007639481,0.000005813183],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00332257,0.0020534026,0.03394762,0.0039401334,0.004939488,0.000014087485,0.0039393725,0.033769067,0.4525575,0.10201472,0.20772709,0.15177494],"study_design_scores_gemma":[0.0074195783,0.0011457006,0.0007335123,0.0000654739,0.0004129717,0.000022913222,0.0005031457,0.66352296,0.18259363,0.0048184698,0.13701102,0.001750607],"about_ca_topic_score_codex":0.0001279319,"about_ca_topic_score_gemma":0.00003954494,"teacher_disagreement_score":0.6297539,"about_ca_system_score_codex":0.00004752775,"about_ca_system_score_gemma":0.0001456434,"threshold_uncertainty_score":0.7646175},"labels":[],"label_agreement":null},{"id":"W2167050411","doi":"10.1093/bioinformatics/btp532","title":"Predicting homologous signaling pathways using machine learning","year":2009,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Homologous chromosome; Artificial intelligence; Computational biology; Signal transduction; Machine learning; Biology; Cell biology; Genetics; Gene","score_opus":0.014601779393406436,"score_gpt":0.223485171631814,"score_spread":0.20888339223840757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167050411","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9217654,0.0008297583,0.07046514,0.000046053425,0.000248806,0.0002650305,0.000025843834,0.000089223664,0.0062647834],"genre_scores_gemma":[0.95623726,0.00009814732,0.042426363,0.0005797954,0.00030442834,0.0000020594127,0.00019434765,0.00001860674,0.00013896916],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99876124,0.000024572795,0.0005140699,0.0001383655,0.00015689926,0.0004048399],"domain_scores_gemma":[0.9992795,0.000012119547,0.00025695268,0.00026959262,0.00006570312,0.00011611342],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034004627,0.00021556963,0.00018681864,0.000064376094,0.0002631938,0.00007756528,0.00021750384,0.00021298116,0.000013260198],"category_scores_gemma":[0.00006382979,0.00020168067,0.000108006076,0.00011231382,0.000042926997,0.00001618915,0.00009908948,0.0002329483,0.000016481223],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032746076,0.00032165615,0.01883714,0.00038417953,0.00041729526,0.00003501653,0.005519112,0.12082158,0.659201,0.0022320652,0.0019885604,0.18991488],"study_design_scores_gemma":[0.0008556058,0.00075958687,0.0002473413,0.00006702811,0.000049852286,0.00019973719,0.00059804996,0.9542172,0.034356005,0.00046023086,0.0075879376,0.00060143485],"about_ca_topic_score_codex":0.000007192153,"about_ca_topic_score_gemma":0.000003698429,"teacher_disagreement_score":0.8333956,"about_ca_system_score_codex":0.00002457925,"about_ca_system_score_gemma":0.00006797936,"threshold_uncertainty_score":0.8224299},"labels":[],"label_agreement":null},{"id":"W2167226024","doi":"10.1093/bioinformatics/btl292","title":"Analysis of binding site similarity, small-molecule similarity and experimental binding profiles in the human cytosolic sulfotransferase family","year":2007,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Monoclonal and Polyclonal Antibodies Research","field":"Medicine","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Structural Genomics Consortium; University of Toronto","funders":"Canadian Institutes of Health Research; Wellcome Trust; Ontario Genomics Institute; Genome Canada","keywords":"Small molecule; Structural similarity; Binding site; Similarity (geometry); Sulfotransferase; Molecule; Plasma protein binding; Computational biology; Function (biology); Chemistry; Biology; Biochemistry; Genetics; Sulfation; Computer science","score_opus":0.053375137443588294,"score_gpt":0.34374316574124353,"score_spread":0.29036802829765523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167226024","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9947462,0.00021399031,0.0001307352,0.00018040434,0.000018970255,0.0003333962,0.00013021634,0.000016462447,0.004229645],"genre_scores_gemma":[0.99795425,0.00008201642,0.0011913076,0.0003492486,0.0000335291,0.0000069806183,0.00028468718,0.0000095871,0.00008836792],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99828374,0.0000455568,0.00062672904,0.00014221597,0.00050315465,0.00039862184],"domain_scores_gemma":[0.9992897,0.00018630094,0.000096856405,0.00023544864,0.000060882314,0.00013079875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010629687,0.00018329131,0.00042388274,0.00071890955,0.0001840272,0.00004697425,0.00016906818,0.00011204549,0.000031493248],"category_scores_gemma":[0.00004022334,0.00012622897,0.00016396052,0.0010028513,0.00020232238,0.00011202607,0.00010041498,0.00030888515,0.0000074421782],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038688278,0.00065054215,0.5939044,0.00082270853,0.00070655753,0.00016249498,0.015942033,0.000020895677,0.38511282,0.00079381006,0.0001874664,0.0013093761],"study_design_scores_gemma":[0.003435384,0.0010723555,0.68657756,0.00033172825,0.0010282658,0.00008347171,0.015785588,0.020626206,0.2693368,0.000016062495,0.0010506874,0.00065587455],"about_ca_topic_score_codex":0.00031838444,"about_ca_topic_score_gemma":0.00021618704,"teacher_disagreement_score":0.11577603,"about_ca_system_score_codex":0.000047988302,"about_ca_system_score_gemma":0.000044081902,"threshold_uncertainty_score":0.51474684},"labels":[],"label_agreement":null},{"id":"W2167272772","doi":"10.1093/bioinformatics/btm248","title":"Nucleotide composition string selection in HIV-1 subtyping using whole genomes","year":2007,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Subtyping; Phylogenetic tree; Genome; String (physics); Computational biology; Biology; Selection (genetic algorithm); Executable; Composition (language); Computer science; Genetics; Programming language; Gene; Artificial intelligence; Mathematics","score_opus":0.0150696711811774,"score_gpt":0.24437248272364961,"score_spread":0.22930281154247223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167272772","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9683692,0.00037573779,0.03028026,0.000014509679,0.00007941861,0.000121178746,0.0000087153185,0.0000050331696,0.0007459339],"genre_scores_gemma":[0.97416073,0.00009492179,0.02547605,0.000083820094,0.00011424821,0.0000013308907,0.000031095482,0.000010794528,0.000027012613],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993013,0.000008895855,0.00028749133,0.00009870542,0.00006916238,0.00023444428],"domain_scores_gemma":[0.9997374,0.000007812133,0.000089835616,0.00008576405,0.000040811618,0.00003842045],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002334911,0.00010414677,0.00009885516,0.00008419969,0.00009515644,0.000023444338,0.00007212359,0.000075072836,0.0000019692511],"category_scores_gemma":[0.000009535689,0.000111175585,0.000038276346,0.00010974789,0.000025902273,0.00000285778,0.00006597728,0.00005657383,0.000008360756],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036700963,0.00002740471,0.043050714,0.000048987888,0.00002916475,0.0000010158589,0.0003945584,0.0037280053,0.94853,0.000112793816,0.00008048376,0.003960143],"study_design_scores_gemma":[0.0027829863,0.00044677188,0.24997354,0.00018052093,0.000075132026,0.00011086351,0.0040189438,0.07825736,0.6303759,0.00027554328,0.03213746,0.0013649547],"about_ca_topic_score_codex":0.000013652865,"about_ca_topic_score_gemma":0.000050294868,"teacher_disagreement_score":0.3181541,"about_ca_system_score_codex":0.000043306456,"about_ca_system_score_gemma":0.00002748139,"threshold_uncertainty_score":0.4533609},"labels":[],"label_agreement":null},{"id":"W2167540852","doi":"10.1093/bioinformatics/btq418","title":"MetPA: a web-based metabolomics tool for pathway analysis and visualization","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":785,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Institute for Nanotechnology; University of Alberta","funders":"","keywords":"Visualization; Computer science; Metabolomics; Context (archaeology); Data visualization; Zoom; Metabolic network; Metabolic pathway; Data mining; Computational biology; Bioinformatics; Biology","score_opus":0.007518783320624244,"score_gpt":0.24923714496547042,"score_spread":0.24171836164484617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167540852","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77935255,0.00024255471,0.21911961,0.00008866658,0.0002239947,0.0003491479,0.000198397,0.00002387431,0.00040122957],"genre_scores_gemma":[0.8798808,0.00023076066,0.11851622,0.00044271653,0.00013668484,0.00006413615,0.0005085133,0.00001915816,0.00020101361],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99922806,0.000011967292,0.00030226968,0.00016232228,0.00009668825,0.00019870092],"domain_scores_gemma":[0.99935436,0.000028115814,0.00015187502,0.00027735476,0.00013153795,0.00005672735],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034263637,0.00015372664,0.00024934707,0.000180199,0.00011965826,0.00005595655,0.000104924955,0.00013481115,0.0000112225825],"category_scores_gemma":[0.00026472964,0.00013192791,0.00015010935,0.00028944478,0.000062029765,0.000007934496,0.00006426852,0.00005727168,0.0000019357904],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016840537,0.00015760605,0.025065206,0.00022639858,0.0020566918,4.2649876e-7,0.00017027845,0.00010311773,0.93122226,0.022269724,0.002479382,0.016080528],"study_design_scores_gemma":[0.00280151,0.0004142781,0.010153951,0.000004359781,0.0014006203,0.000004732698,0.00016174179,0.121269114,0.38105053,0.00027151,0.48168904,0.0007786328],"about_ca_topic_score_codex":0.0000025583315,"about_ca_topic_score_gemma":0.0000816983,"teacher_disagreement_score":0.55017173,"about_ca_system_score_codex":0.0000039437627,"about_ca_system_score_gemma":0.00006484742,"threshold_uncertainty_score":0.5379864},"labels":[],"label_agreement":null},{"id":"W2167566248","doi":"10.1093/bioinformatics/btp595","title":"NAViGaTOR: Network Analysis, Visualization and Graphing Toronto","year":2009,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":273,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"University of Toronto; Ontario Genomics; Ontario Genomics Institute; Genome Canada","keywords":"Visualization; Computer science; Computer graphics (images); Data mining","score_opus":0.00527186983615427,"score_gpt":0.24303482373120608,"score_spread":0.2377629538950518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167566248","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42972437,0.009155989,0.5338241,0.00019799836,0.0005803625,0.0008022827,0.000048110644,0.00014487687,0.025521927],"genre_scores_gemma":[0.98496276,0.0010479754,0.011625717,0.001498717,0.00029520795,0.000003454195,0.00044270387,0.000010047313,0.0001134127],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99909425,0.000014157638,0.00038330894,0.0001201449,0.000118516225,0.0002696441],"domain_scores_gemma":[0.9993915,0.000006010058,0.00015870453,0.0002802621,0.00004800096,0.00011555597],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024585534,0.00015810317,0.00017920631,0.000035176585,0.00013932068,0.000084646505,0.0001242578,0.00015685186,0.000010808194],"category_scores_gemma":[0.000012140974,0.00014611856,0.00009837194,0.00020378633,0.000035581845,0.00002311196,0.000058932455,0.00005243389,0.000003989163],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00058225484,0.00050701643,0.039143026,0.000538672,0.0058095097,0.000008805345,0.013446291,0.026536431,0.009371577,0.19914217,0.18321903,0.5216952],"study_design_scores_gemma":[0.0026292524,0.0017951928,0.03547393,0.0001199261,0.001402245,0.00007736993,0.0027460149,0.73250103,0.0019781743,0.005209165,0.21362482,0.0024428882],"about_ca_topic_score_codex":0.000010891648,"about_ca_topic_score_gemma":0.00008210929,"teacher_disagreement_score":0.70596457,"about_ca_system_score_codex":0.000015075898,"about_ca_system_score_gemma":0.000021460175,"threshold_uncertainty_score":0.5958542},"labels":[],"label_agreement":null},{"id":"W2167846577","doi":"10.1093/bioinformatics/btl356","title":"GenePro: a cytoscape plug-in for advanced visualization and analysis of interaction networks","year":2006,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Hospital for Sick Children","funders":"Canadian Institutes of Health Research; Hospital for Sick Children","keywords":"Plug-in; Computer science; Visualization; Parsing; Software; Set (abstract data type); Domain (mathematical analysis); Software engineering; Data science; Data mining; Programming language","score_opus":0.006255042208858774,"score_gpt":0.2517326425909427,"score_spread":0.2454776003820839,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167846577","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4544365,0.00033988216,0.5440535,0.000010758161,0.000093071125,0.000328145,0.000036336314,0.000007743691,0.00069405383],"genre_scores_gemma":[0.98715657,0.0001720255,0.011421586,0.000082229126,0.000061164304,0.000023515491,0.0010099676,0.000010204705,0.0000627314],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991843,0.0000085935735,0.0004927367,0.000096669966,0.00006036961,0.00015733887],"domain_scores_gemma":[0.99948514,0.000018037845,0.00024330702,0.00016168863,0.00006514774,0.000026690152],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001690134,0.00010764738,0.00019341336,0.00015614826,0.00003281288,0.000021018424,0.00006675829,0.00012735125,0.0000025390923],"category_scores_gemma":[0.000015985232,0.00010423431,0.000084116036,0.00026268544,0.000031285457,0.000013993552,0.000041722516,0.000034552002,2.7837504e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012925945,0.00046615742,0.06566333,0.00094337267,0.0017677431,9.046275e-7,0.001315595,0.7327884,0.030336762,0.017348872,0.005030746,0.14304554],"study_design_scores_gemma":[0.0006275453,0.00012277754,0.004699604,0.0000148437975,0.00012950615,0.0000015790641,0.00014787613,0.98827523,0.0026958508,0.00008502607,0.0030568386,0.00014332893],"about_ca_topic_score_codex":0.000011769797,"about_ca_topic_score_gemma":0.000120996476,"teacher_disagreement_score":0.5327201,"about_ca_system_score_codex":0.000012714086,"about_ca_system_score_gemma":0.000017175471,"threshold_uncertainty_score":0.42505518},"labels":[],"label_agreement":null},{"id":"W2168047871","doi":"10.1093/bioinformatics/btq355","title":"TreesimJ: a flexible, forward time population genetic simulator","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic diversity and population structure","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of General Medical Sciences; McGill University; National Science Foundation","keywords":"Computer science; Population; Simulation; Genetic algorithm; Machine learning; Demography","score_opus":0.006045611241174022,"score_gpt":0.22176551904386307,"score_spread":0.21571990780268904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168047871","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99261373,0.000025507883,0.0038559085,0.000048062844,0.00034987228,0.00020046599,0.0000492469,0.000041875577,0.0028153271],"genre_scores_gemma":[0.96838033,0.000009012935,0.028609354,0.0003302529,0.0002469443,0.000002955736,0.00046255643,0.00001484596,0.0019437481],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9992009,0.000012266561,0.00026494273,0.00013912679,0.00017802144,0.00020479127],"domain_scores_gemma":[0.9993185,0.0000068485783,0.000118050695,0.00036898645,0.00007233067,0.00011532107],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000078386365,0.00015034404,0.000120495795,0.0000627783,0.00011946202,0.00004886586,0.00019052907,0.00023877108,0.00021447182],"category_scores_gemma":[0.000057952304,0.00014440529,0.000089092035,0.00009703553,0.000039352286,0.000010076777,0.00008957525,0.00010502846,0.00022643912],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004801006,0.00027678997,0.31532106,0.00041687288,0.00047737354,0.000009351365,0.0016291479,0.030646529,0.39564905,0.0020646912,0.078296795,0.17473225],"study_design_scores_gemma":[0.0025831743,0.0004915023,0.49403802,0.000020358631,0.00014599951,0.0000997735,0.0001617474,0.06675063,0.03274441,0.0010028549,0.40065703,0.0013045067],"about_ca_topic_score_codex":0.000010623644,"about_ca_topic_score_gemma":0.000017495699,"teacher_disagreement_score":0.36290464,"about_ca_system_score_codex":0.0000056796202,"about_ca_system_score_gemma":0.00003351093,"threshold_uncertainty_score":0.58886766},"labels":[],"label_agreement":null},{"id":"W2168220711","doi":"10.1093/bioinformatics/bts209","title":"MoRFpred, a computational tool for sequence-based prediction and characterization of short disorder-to-order transitioning binding regions in proteins","year":2012,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":369,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"U.S. National Library of Medicine; Natural Sciences and Engineering Research Council of Canada; Killam Trusts; Russian Academy of Sciences; National Institutes of Health; National Science Foundation","keywords":"Sequence (biology); Support vector machine; Computer science; Computational biology; Intrinsically disordered proteins; Artificial intelligence; Chemistry; Biology; Biochemistry","score_opus":0.012483846323756513,"score_gpt":0.2417982339169962,"score_spread":0.2293143875932397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168220711","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5558724,0.0000075342996,0.44345257,0.000034912333,0.000023503404,0.00041459815,0.00017471741,0.0000047898625,0.0000149952],"genre_scores_gemma":[0.9065661,0.00000846668,0.09137856,0.00009008312,0.0000386523,0.00009005075,0.0018145276,0.000007608282,0.000005974091],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994707,0.000009784936,0.00024332624,0.0000689135,0.00007548504,0.00013177516],"domain_scores_gemma":[0.9997504,0.000007597586,0.000060364477,0.00007870535,0.00006633567,0.000036592475],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000114775474,0.00007834074,0.000084129606,0.000076843506,0.00005221009,0.000011742268,0.00003807508,0.00008414896,6.398659e-7],"category_scores_gemma":[0.000033484972,0.00007825989,0.000024089302,0.00010709681,0.000027371027,0.000023973093,0.000014013066,0.00003214348,2.3390577e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025838797,0.00013910464,0.05389807,0.0005417717,0.000052606836,1.4767775e-7,0.0018335714,0.0280237,0.89114213,0.001223988,0.000022217471,0.022864321],"study_design_scores_gemma":[0.0028187276,0.0008595354,0.12316089,0.00033308548,0.0000667421,0.000022745675,0.0004572383,0.77989507,0.08960784,0.00028376043,0.0017765026,0.00071787444],"about_ca_topic_score_codex":0.0000017193594,"about_ca_topic_score_gemma":0.0000037643135,"teacher_disagreement_score":0.8015343,"about_ca_system_score_codex":0.000012920915,"about_ca_system_score_gemma":0.000048909584,"threshold_uncertainty_score":0.31913456},"labels":[],"label_agreement":null},{"id":"W2168361262","doi":"10.1093/bioinformatics/btp525","title":"A report on the 2009 SIG on short read sequencing and algorithms (Short-SIG)","year":2009,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Algorithm; Software; Programming language","score_opus":0.02606938456688283,"score_gpt":0.2555712443093973,"score_spread":0.2295018597425145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168361262","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9695795,0.0004666201,0.0007360181,0.0006617704,0.00016771184,0.0003586159,0.000028608894,0.000011039047,0.02799007],"genre_scores_gemma":[0.9932114,0.0004921319,0.0034027726,0.0021590241,0.00020380582,0.000011111737,0.00004092774,0.000012253637,0.00046656662],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.999082,0.000016962269,0.00032486345,0.00018147618,0.00015884882,0.00023584615],"domain_scores_gemma":[0.99932677,0.00002559507,0.00007100357,0.00045310945,0.000056606386,0.00006692737],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030373692,0.00018657571,0.00015373205,0.000031233987,0.00016739964,0.00004403301,0.00013992052,0.00010590045,0.0000034532231],"category_scores_gemma":[0.00009966208,0.0001265612,0.00006383807,0.00005690972,0.00006296033,0.000001494237,0.000060564493,0.00009879084,0.00000786197],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038264107,0.00037056595,0.0072251502,0.00014381154,0.0007823661,0.0002046284,0.0033009858,0.0011453491,0.35124713,0.0057278583,0.0605782,0.5688913],"study_design_scores_gemma":[0.0014948098,0.009720077,0.07946997,0.00031862356,0.0002875768,0.0015469198,0.0035990123,0.019286096,0.40356517,0.0025181244,0.4751599,0.0030337055],"about_ca_topic_score_codex":0.000004959736,"about_ca_topic_score_gemma":0.000004361475,"teacher_disagreement_score":0.5658576,"about_ca_system_score_codex":0.00001869808,"about_ca_system_score_gemma":0.00004854879,"threshold_uncertainty_score":0.51610154},"labels":[],"label_agreement":null},{"id":"W2168443777","doi":"10.1093/bioinformatics/btt599","title":"A probabilistic approach to explore human miRNA targetome by integrating miRNA-overexpression data and sequence information","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"MicroRNA in disease regulation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Bioconductor; microRNA; Computational biology; Probabilistic logic; Computer science; Data mining; Gene; Biology; Artificial intelligence; Genetics","score_opus":0.03972558507809203,"score_gpt":0.27838884180424195,"score_spread":0.2386632567261499,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168443777","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.962013,0.00010929191,0.03384689,0.00008796552,0.000047947055,0.0012140826,0.0002686322,0.000045348603,0.0023668292],"genre_scores_gemma":[0.9288303,0.000017453822,0.063047476,0.00039226763,0.00006568428,0.00012242424,0.007421846,0.000018337685,0.00008417662],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989129,0.000026798538,0.000448885,0.00018996424,0.0001936843,0.00022780275],"domain_scores_gemma":[0.9988361,0.000008646297,0.00019835081,0.0006654739,0.00012653157,0.00016490156],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017885247,0.00018556576,0.00012922796,0.000060479444,0.00013232145,0.0001803547,0.00038964627,0.00012865946,0.000014180632],"category_scores_gemma":[0.00023768049,0.00015874785,0.000024026955,0.00009947655,0.000062178195,0.00017082905,0.00046941967,0.00007956604,0.00004573081],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024796429,0.00009299664,0.0004700201,0.0006716576,0.00004192407,1.0772687e-7,0.0021807863,0.00013022416,0.8556451,0.00021933755,0.12978843,0.010734575],"study_design_scores_gemma":[0.0035572613,0.0009691159,0.008472905,0.0009988176,0.00014253396,0.00012183506,0.010372534,0.63417155,0.15444306,0.0012815689,0.18226644,0.0032023552],"about_ca_topic_score_codex":0.000030698404,"about_ca_topic_score_gemma":0.0000011540658,"teacher_disagreement_score":0.7012021,"about_ca_system_score_codex":0.000032132695,"about_ca_system_score_gemma":0.000045773864,"threshold_uncertainty_score":0.64735496},"labels":[],"label_agreement":null},{"id":"W2168546919","doi":"10.1093/bioinformatics/btu023","title":"Exploring genome characteristics and sequence quality without a reference","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":162,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"Government of Ontario; Ontario Institute for Cancer Research; Wellcome Trust","keywords":"Sequence assembly; Reference genome; Software; Genome; Computer science; Sequence (biology); DNA sequencing; Loss of heterozygosity; Computational biology; Key (lock); Data mining; Biology; Genetics; DNA; Gene; Programming language","score_opus":0.1222213845852358,"score_gpt":0.2881844902889477,"score_spread":0.16596310570371192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168546919","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9950552,0.000095451935,0.0022045313,0.000036224526,0.00008083667,0.000089758745,0.000040976058,0.000006373282,0.0023906196],"genre_scores_gemma":[0.9903928,0.00093583565,0.008204524,0.00021830531,0.000109435445,0.000016745971,0.000044389904,0.000009636237,0.00006834394],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9993004,0.000023206405,0.00027455357,0.00013557839,0.00008271039,0.00018351345],"domain_scores_gemma":[0.9994633,0.000012982933,0.00011531408,0.00027171514,0.00006240346,0.000074243006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024778373,0.00012874728,0.00015462805,0.000021269105,0.00009507976,0.00003419119,0.00011636832,0.000053474552,0.0000017437139],"category_scores_gemma":[0.0001040307,0.00011640477,0.00002463505,0.00003132597,0.000080257465,0.0000029662908,0.00015496003,0.000053092514,0.000011144188],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008673645,0.000046919577,0.05920249,0.00040889333,0.00013521768,6.814261e-7,0.0019967523,0.000024237235,0.8684438,0.004220478,0.00007028098,0.06536354],"study_design_scores_gemma":[0.0011538898,0.0007384588,0.75051063,0.000051047056,0.000058785496,0.00004462777,0.0010126046,0.002923947,0.01901889,0.0003933192,0.2228901,0.001203731],"about_ca_topic_score_codex":0.000009159186,"about_ca_topic_score_gemma":0.0000059369017,"teacher_disagreement_score":0.8494249,"about_ca_system_score_codex":0.0000066661755,"about_ca_system_score_gemma":0.000021305934,"threshold_uncertainty_score":0.47468486},"labels":[],"label_agreement":null},{"id":"W2168859815","doi":"10.1093/bioinformatics/bts340","title":"ChromoHub: a data hub for navigators of chromatin-mediated signalling","year":2012,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":90,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Structural Genomics Consortium; University of Toronto","funders":"Ministero dello Sviluppo Economico; Ontario Ministry of Economic Development and Innovation; Canadian Institutes of Health Research; Genome Canada; Wellcome Trust; Eli Lilly Canada; GlaxoSmithKline; Pfizer; Eli Lilly and Company","keywords":"Chromatin; Histone; Computational biology; Resource (disambiguation); Epigenetics; Biology; Bromodomain; Relevance (law); Chromatin remodeling; Signalling; Nucleosome; Data science; Computer science; Genetics; Gene; Cell biology","score_opus":0.02208753217242906,"score_gpt":0.26162781869681123,"score_spread":0.23954028652438217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168859815","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9610373,0.00055777526,0.035942744,0.00002994689,0.00027847043,0.0004317172,0.0009048994,0.000020219148,0.00079696934],"genre_scores_gemma":[0.93318516,0.000101832156,0.062601596,0.00011122882,0.00022516715,0.000014773351,0.0036837151,0.000028466597,0.000048035454],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989172,0.000011684195,0.0004887189,0.00012239744,0.00013035025,0.0003296149],"domain_scores_gemma":[0.99883735,0.00003499102,0.0002943768,0.0006317951,0.000084323096,0.000117172014],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039749464,0.00015741735,0.00019178276,0.00003615997,0.000063901105,0.000018062863,0.00048047912,0.00015096889,0.000010608189],"category_scores_gemma":[0.0001731203,0.0001474689,0.0000734605,0.00007839346,0.000061547944,0.00001923013,0.00027705712,0.00005168801,0.000013656449],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012503106,0.00053287495,0.007004412,0.0019952646,0.00059243845,5.4813876e-7,0.0017958614,0.00047925356,0.95747596,0.0014064967,0.018545885,0.010046001],"study_design_scores_gemma":[0.0044659455,0.0012609703,0.0029647895,0.0002720962,0.00033231862,0.000079937236,0.0026796968,0.49340054,0.3157931,0.00020485876,0.17671303,0.0018327011],"about_ca_topic_score_codex":0.0000042023785,"about_ca_topic_score_gemma":0.0000034037678,"teacher_disagreement_score":0.64168286,"about_ca_system_score_codex":0.000013158738,"about_ca_system_score_gemma":0.00008831169,"threshold_uncertainty_score":0.60136074},"labels":[],"label_agreement":null},{"id":"W2168872202","doi":"10.1093/bioinformatics/bth196","title":"Identifying multiple alignment regions satisfying simple formulas and patterns","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Institutes of Health","keywords":"Simple (philosophy); Documentation; Set (abstract data type); Computer science; Software; Data mining; Theoretical computer science; Algorithm; Programming language","score_opus":0.022933498496123354,"score_gpt":0.25007345929627206,"score_spread":0.2271399608001487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168872202","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.965106,0.00043435086,0.033667713,0.00008507735,0.00009477593,0.00018347215,0.00004342189,0.000006580732,0.0003786168],"genre_scores_gemma":[0.9860878,0.0007401473,0.012742589,0.00024938345,0.00007019704,0.000014137176,0.00005121595,0.000012512707,0.00003200734],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993317,0.0000057853454,0.00023416939,0.00012431192,0.00008977906,0.00021424699],"domain_scores_gemma":[0.9995933,0.000008875522,0.00008227241,0.00021525986,0.000029563302,0.00007070673],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000076996315,0.00012919126,0.000107421074,0.000030220961,0.00016730992,0.000043721742,0.000089564564,0.000064858745,0.0000018412627],"category_scores_gemma":[0.000030036772,0.00012063675,0.00004850372,0.00003259906,0.000038251837,0.0000026408663,0.00018771492,0.000037590544,0.0000061928195],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011169935,0.00027489418,0.3157621,0.0010195719,0.0009455206,0.00001602594,0.014852431,0.0035265991,0.60195774,0.008221234,0.0033654352,0.04994675],"study_design_scores_gemma":[0.012601431,0.0016867204,0.35052723,0.0003397038,0.00030533015,0.0003342282,0.017961934,0.0049491604,0.46192834,0.016056132,0.13012,0.00318981],"about_ca_topic_score_codex":0.00004882735,"about_ca_topic_score_gemma":0.00012898828,"teacher_disagreement_score":0.14002939,"about_ca_system_score_codex":0.000017215501,"about_ca_system_score_gemma":0.000024886705,"threshold_uncertainty_score":0.4919424},"labels":[],"label_agreement":null},{"id":"W2168950020","doi":"10.1093/bioinformatics/btq184","title":"VARiD: A variation detection framework for color-space and letter-space platforms","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Variation (astronomy); Space (punctuation); Computer science; Color space; Computer vision; Artificial intelligence; Computer graphics (images); Image (mathematics); Operating system; Physics; Astronomy","score_opus":0.007877595987041856,"score_gpt":0.2256863102814138,"score_spread":0.21780871429437196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168950020","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75788265,0.000070008966,0.2406336,0.00026393452,0.0004893209,0.00032355727,0.000032282467,0.0000074263353,0.00029717773],"genre_scores_gemma":[0.87433875,0.000074989955,0.12475166,0.00035902596,0.00032960347,0.00004382189,0.00001934661,0.000013526154,0.0000692842],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99943745,0.00000318951,0.00018048158,0.00012742668,0.00006713027,0.00018433023],"domain_scores_gemma":[0.9995117,0.000036853602,0.00011846117,0.00020721655,0.00007024743,0.00005552049],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015555041,0.0001286824,0.00010959894,0.0000313312,0.00015457935,0.00004511582,0.00008172584,0.0002121025,0.0000022555826],"category_scores_gemma":[0.00015103504,0.000114344344,0.000044903278,0.00004600531,0.000050421335,0.0000030878725,0.000074749376,0.000098312245,0.0000037398695],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000119906574,0.000036408543,0.0008125962,0.00011551672,0.00012007596,1.9042456e-7,0.0011619466,0.00006885355,0.9692306,0.017541897,0.0009512307,0.0098407855],"study_design_scores_gemma":[0.0032966647,0.002341979,0.033849508,0.000038506234,0.00021849481,0.000087945555,0.0010722348,0.051888198,0.57059556,0.04000441,0.29505235,0.0015541145],"about_ca_topic_score_codex":0.000007075501,"about_ca_topic_score_gemma":0.000034435303,"teacher_disagreement_score":0.398635,"about_ca_system_score_codex":0.0000061219203,"about_ca_system_score_gemma":0.000022282644,"threshold_uncertainty_score":0.4662827},"labels":[],"label_agreement":null},{"id":"W2168951863","doi":"10.1093/bioinformatics/btu669","title":"GeneNet Toolbox for MATLAB: a flexible platform for the analysis of gene connectivity in biological networks","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; European Commission; Natural Sciences and Engineering Research Council of Canada; Wellcome Trust","keywords":"Toolbox; Subnetwork; Computer science; Graphical user interface; MATLAB; Set (abstract data type); Permutation (music); Visualization; Data mining; Gene regulatory network; Biological network; Software; Interface (matter); Bioinformatics; Gene; Programming language; Computer network; Operating system; Biology","score_opus":0.02391273013113176,"score_gpt":0.25529952655803784,"score_spread":0.23138679642690607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168951863","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13669565,0.0003279458,0.86141163,0.000060158054,0.00016789019,0.0008144285,0.0001671465,0.000011841704,0.00034328597],"genre_scores_gemma":[0.96090806,0.00019606834,0.037055437,0.00057983026,0.00021948869,0.00016874493,0.000792477,0.000016821277,0.00006307481],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987004,0.000016719048,0.0006635595,0.00015590401,0.00008931764,0.00037410387],"domain_scores_gemma":[0.9987693,0.00028572648,0.0003129524,0.00046370467,0.000108787324,0.000059516784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009837816,0.00019185843,0.00039017183,0.000110987494,0.00010873588,0.00003698418,0.00033805222,0.00028214062,0.000004949823],"category_scores_gemma":[0.00014906676,0.00013124998,0.00031038912,0.0003100335,0.00010096838,0.000010460911,0.00007555462,0.00007955954,9.937571e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022423433,0.00044604842,0.012652023,0.00059782324,0.005185212,3.1442465e-7,0.0014801114,0.64133805,0.011886702,0.022890573,0.014334345,0.28694645],"study_design_scores_gemma":[0.0009793256,0.00036097705,0.003525636,0.000008160888,0.00022812438,0.0000019294114,0.0001815489,0.96761817,0.0038212233,0.00031874023,0.022726258,0.00022988072],"about_ca_topic_score_codex":0.0000130076605,"about_ca_topic_score_gemma":0.00009604596,"teacher_disagreement_score":0.8243562,"about_ca_system_score_codex":0.000018111534,"about_ca_system_score_gemma":0.00004231347,"threshold_uncertainty_score":0.5352219},"labels":[],"label_agreement":null},{"id":"W2168980979","doi":"10.1093/bioinformatics/btq498","title":"Model-based clustering of microarray expression data via latent Gaussian mixture models","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":226,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mixture model; Bayesian information criterion; Cluster analysis; Covariance; Expectation–maximization algorithm; Computer science; Model selection; Gene chip analysis; Data mining; Gaussian; Statistical model; Bayesian probability; Artificial intelligence; Mathematics; Statistics; DNA microarray; Gene expression; Biology; Gene; Genetics; Maximum likelihood","score_opus":0.03102465879333444,"score_gpt":0.266033582338828,"score_spread":0.23500892354549358,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168980979","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.053852774,0.000083370884,0.9435609,0.00012991049,0.00027122983,0.00019259578,0.000100860816,0.00001892604,0.0017894221],"genre_scores_gemma":[0.8817456,0.000028960796,0.11715265,0.00018547762,0.000066463086,0.000008997255,0.00066191587,0.000015294665,0.00013464398],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999155,0.000012499693,0.0003293416,0.00018790444,0.00015683495,0.00015840991],"domain_scores_gemma":[0.99850756,0.0000036316749,0.00020009156,0.001128451,0.000073699695,0.00008659292],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015171248,0.00013395265,0.00011731662,0.000053078915,0.000057393747,0.000020608319,0.0004979389,0.00020585096,0.000013686606],"category_scores_gemma":[0.000018972565,0.00011062285,0.000048469403,0.000061971834,0.000052521653,0.000020514872,0.0002249605,0.00012085082,0.0000038153994],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003755903,0.00003565833,0.000041714142,0.00007162154,0.000006419621,8.6950884e-8,0.000085994376,0.011711262,0.98079973,0.000018863064,0.0039151195,0.0032759898],"study_design_scores_gemma":[0.0002527685,0.00002231182,0.000029132885,0.00002145014,0.0000069206612,0.0000018202685,0.000021230493,0.613032,0.38336116,0.000045626726,0.0031052579,0.00010033723],"about_ca_topic_score_codex":0.000002577998,"about_ca_topic_score_gemma":0.000013679556,"teacher_disagreement_score":0.82789284,"about_ca_system_score_codex":0.0000052733367,"about_ca_system_score_gemma":0.000102391685,"threshold_uncertainty_score":0.4511069},"labels":[],"label_agreement":null},{"id":"W2169224664","doi":"10.1093/bioinformatics/18.1.215","title":"Symmetry observations in long nucleotide sequences: a commentary on the Discovery Note of Qi and Cuticchia","year":2002,"lang":"en","type":"letter","venue":"Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Genome; DNA; Oligonucleotide; Genetics; Biology; Combinatorics; Computational biology; Mathematics; Gene","score_opus":0.023355846145395025,"score_gpt":0.23210959057574332,"score_spread":0.2087537444303483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169224664","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30187434,0.0018017017,0.008294634,0.67730606,0.0009889071,0.002935584,0.0013845302,0.000039639235,0.0053746155],"genre_scores_gemma":[0.091526985,0.0013662478,0.009609689,0.89443743,0.0009796239,0.00009030288,0.0010897384,0.000075430995,0.0008245765],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99892133,0.0000767245,0.00044644118,0.00015047549,0.00020613422,0.00019888945],"domain_scores_gemma":[0.99908006,0.00011648514,0.00027075966,0.00048254617,0.000026469042,0.000023655779],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020876064,0.00022773996,0.00023589234,0.00007749204,0.00006865748,0.00005402275,0.0003117461,0.0003869697,0.00001016652],"category_scores_gemma":[0.00008667049,0.00016146967,0.00009023339,0.00009492412,0.00012077615,0.000014485593,0.00012319688,0.00034694932,0.0000063480084],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046952264,0.00009238872,0.0020701813,0.0011406207,0.00021508368,0.000032869837,0.00045894587,0.000037265574,0.0099310875,0.00085862353,0.98143476,0.0036812127],"study_design_scores_gemma":[0.0020148421,0.0018506123,0.004185147,0.0037394082,0.00040774292,0.00008792287,0.0013108723,0.005682345,0.1815995,0.003921057,0.79234165,0.002858916],"about_ca_topic_score_codex":0.000047918795,"about_ca_topic_score_gemma":0.000021889073,"teacher_disagreement_score":0.21713135,"about_ca_system_score_codex":0.000021052054,"about_ca_system_score_gemma":0.000032813565,"threshold_uncertainty_score":0.65845424},"labels":[],"label_agreement":null},{"id":"W2169558190","doi":"10.1093/bioinformatics/btl326","title":"Difference detection in LC-MS data for protein biomarker discovery","year":2007,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":91,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Biomarker discovery; Computer science; Task (project management); SIGNAL (programming language); Biomarker; Class (philosophy); Data mining; Artificial intelligence; Pattern recognition (psychology); Proteomics; Chemistry","score_opus":0.0337800281231293,"score_gpt":0.30226955595067095,"score_spread":0.26848952782754165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169558190","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14629664,0.000014264111,0.85017776,0.000028920384,0.000015383186,0.0004531214,0.0002073629,0.000089965106,0.0027165888],"genre_scores_gemma":[0.7033265,0.000016901386,0.2953038,0.00003791573,0.00005601695,0.00022646718,0.00036040603,0.00001800749,0.0006539463],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991904,0.0000014229199,0.0003683982,0.00013334994,0.0000897209,0.00021671789],"domain_scores_gemma":[0.9991021,0.000042131942,0.00014197319,0.00065124035,0.000024907162,0.000037624795],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022541205,0.00010585842,0.00010142155,0.000051945328,0.00006576702,0.000043369793,0.0003453937,0.00010285647,0.000011355444],"category_scores_gemma":[0.00008052863,0.00009687888,0.000026091748,0.00012210598,0.0000343288,0.00036659534,0.00014292642,0.000104091305,0.000004800387],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014066923,0.00013841417,0.0005259476,0.00063672435,0.000015860056,9.2992843e-7,0.00013838963,0.0000057060743,0.65970707,0.0032760731,0.00022545736,0.33518875],"study_design_scores_gemma":[0.00058275886,0.000026378237,0.0006671163,0.00013119334,0.000010452788,0.0000062042263,0.00021859976,0.071178526,0.89820844,0.005799949,0.0228221,0.00034830303],"about_ca_topic_score_codex":0.000019757623,"about_ca_topic_score_gemma":0.000066283355,"teacher_disagreement_score":0.5570299,"about_ca_system_score_codex":0.00006546731,"about_ca_system_score_gemma":0.000021393576,"threshold_uncertainty_score":0.3950606},"labels":[],"label_agreement":null},{"id":"W2169802764","doi":"10.1093/bioinformatics/btq373","title":"Improved sequence-based prediction of disordered regions with multilayer fusion of multiple information sources","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":201,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Fusion; Artificial intelligence; Data mining; Sequence (biology); Dihedral angle; Classifier (UML); Similarity (geometry); Pattern recognition (psychology); Machine learning; Chemistry; Biology; Genetics","score_opus":0.006990120934709545,"score_gpt":0.2063050445354069,"score_spread":0.19931492360069736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169802764","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9045844,0.000010543471,0.094510816,0.000025253123,0.00008292741,0.0003162211,0.00021264194,0.000015001956,0.00024218671],"genre_scores_gemma":[0.9530727,0.000011821149,0.046270948,0.000041969477,0.000023435578,0.000012310524,0.00054916943,0.0000064880946,0.000011121423],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993116,0.00000797536,0.00036703606,0.00006293006,0.00013336379,0.00011706703],"domain_scores_gemma":[0.999079,0.000011531755,0.0003570516,0.00031189714,0.00019828836,0.000042232146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000868992,0.000112088965,0.000120353056,0.00006733493,0.00004962047,0.000012593395,0.00012708838,0.0001694417,0.0000036347576],"category_scores_gemma":[0.00010535424,0.00008500634,0.00005206778,0.00009339818,0.00012659993,0.000030448062,0.000039329425,0.00009026931,6.9782334e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003106743,0.000053337284,0.012426552,0.00023738052,0.000038502138,7.799408e-8,0.00065828674,0.0011150438,0.9744254,0.00013924771,0.000089098416,0.010506442],"study_design_scores_gemma":[0.0024918532,0.00084166817,0.0059619807,0.000053952783,0.000041711606,0.000010082808,0.00059103244,0.36645517,0.6175452,0.000046054323,0.0057244166,0.0002368802],"about_ca_topic_score_codex":0.000049714694,"about_ca_topic_score_gemma":0.00010467755,"teacher_disagreement_score":0.36534014,"about_ca_system_score_codex":0.0000043798577,"about_ca_system_score_gemma":0.000106538784,"threshold_uncertainty_score":0.3466458},"labels":[],"label_agreement":null},{"id":"W2170080415","doi":"10.1093/bioinformatics/btu292","title":"Probabilistic method for detecting copy number variation in a fetal genome using maternal plasma sequencing","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Prenatal Screening and Diagnostics","field":"Medicine","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Copy-number variation; Biology; Genome; Genetics; Single-nucleotide polymorphism; DNA sequencing; Chromosome; Computational biology; SNP; Genomics; SNP array; Genotype; Gene","score_opus":0.034628178887073716,"score_gpt":0.30348910164582593,"score_spread":0.26886092275875223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170080415","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46541658,0.0000024854874,0.53345644,0.000016318307,0.00007818617,0.0003163326,0.00001113643,0.000042098356,0.00066041766],"genre_scores_gemma":[0.5164525,6.2631057e-7,0.48333675,0.00007484876,0.00008331871,0.000011439577,0.000014495717,0.000010870048,0.000015160541],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99895215,0.0000304386,0.0004588811,0.00010605914,0.00017746688,0.00027501222],"domain_scores_gemma":[0.99901015,0.00043708042,0.00022600839,0.00015404701,0.00008039091,0.00009233269],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007229797,0.0001283465,0.0002384079,0.00008518063,0.000076380704,0.000045860186,0.00006610411,0.00010478197,0.00001179186],"category_scores_gemma":[0.0021141008,0.00011496708,0.00005406271,0.00013511023,0.000016991418,0.00015934996,0.000041068855,0.0001313337,0.000020398082],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0032076933,0.0005751875,0.21238847,0.01874727,0.00066405896,0.00010234266,0.0360209,0.21044192,0.0655825,0.0139464615,0.00016096704,0.43816224],"study_design_scores_gemma":[0.0013626709,0.00011904857,0.006276897,0.000243231,0.00007327353,0.00019304722,0.00015517871,0.9892429,0.0016533759,0.00044540982,0.000094587194,0.00014039116],"about_ca_topic_score_codex":0.00023951885,"about_ca_topic_score_gemma":0.000028313723,"teacher_disagreement_score":0.77880096,"about_ca_system_score_codex":0.0002469708,"about_ca_system_score_gemma":0.00009741924,"threshold_uncertainty_score":0.46882215},"labels":[],"label_agreement":null},{"id":"W2170123419","doi":"10.1093/bioinformatics/bts491","title":"Intensity quantile estimation and mapping—a novel algorithm for the correction of image non-uniformity bias in HCS data","year":2012,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University and Génome Québec Innovation Centre","funders":"Centre National de la Recherche Scientifique; Fonds Québécois de la Recherche sur la Nature et les Technologies; Infrastructures en Biologie Santé et Agronomie","keywords":"Quantile; Image (mathematics); Pixel; Algorithm; Computer science; MATLAB; Intensity (physics); Function (biology); Image processing; Field (mathematics); Artificial intelligence; Pattern recognition (psychology); Statistics; Mathematics; Physics; Optics","score_opus":0.037872389847886434,"score_gpt":0.29891965728376513,"score_spread":0.2610472674358787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170123419","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0670685,0.0000798817,0.93215734,0.000020658816,0.000070621776,0.0003018036,0.000042841733,0.000009066183,0.00024931098],"genre_scores_gemma":[0.6116464,0.00016751784,0.38728514,0.00009014383,0.00006136416,0.000013822155,0.00067599094,0.000009113616,0.000050469975],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994063,0.000006839048,0.00029337325,0.000083479514,0.00007566368,0.00013436872],"domain_scores_gemma":[0.9991807,0.000039223443,0.0001845912,0.00046425778,0.00010484943,0.000026406506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006765743,0.000086964836,0.00012732783,0.000057613157,0.00005768791,0.000026870875,0.00017611975,0.00007825457,0.0000011725386],"category_scores_gemma":[0.000277875,0.0000665918,0.000034915705,0.00010236753,0.00008901189,0.00004938471,0.00023214002,0.000055802124,0.0000011232602],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000086761844,0.00041396718,0.010047556,0.00037716536,0.0002007707,2.1748139e-7,0.0018031262,0.00008844652,0.1280454,0.000025605501,0.035714388,0.8231966],"study_design_scores_gemma":[0.00021089613,0.000043247834,0.0042732153,0.000016103704,0.000033729368,0.000009005367,0.00049301324,0.89612967,0.09508968,0.000006753483,0.003606698,0.00008797503],"about_ca_topic_score_codex":0.000089252404,"about_ca_topic_score_gemma":0.000039491806,"teacher_disagreement_score":0.8960412,"about_ca_system_score_codex":0.000010111537,"about_ca_system_score_gemma":0.000025062078,"threshold_uncertainty_score":0.27155346},"labels":[],"label_agreement":null},{"id":"W2170192148","doi":"10.1093/bioinformatics/18.suppl_1.s111","title":"Binary tree-structured vector quantization approach toclustering and visualizing microarray data","year":2002,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":73,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"National Cancer Institute","keywords":"Cluster analysis; Computer science; Vector quantization; Data mining; Binary tree; Binary data; Tree (set theory); k-d tree; Artificial intelligence; Pattern recognition (psychology); Binary number; Mathematics; Algorithm; Tree traversal","score_opus":0.05006105434218325,"score_gpt":0.27732884328221424,"score_spread":0.227267788940031,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170192148","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6877412,0.0045883884,0.29311177,0.00046725138,0.0008183751,0.0010049961,0.00016226133,0.00014081894,0.01196491],"genre_scores_gemma":[0.96726793,0.0005005395,0.03067993,0.00022273284,0.00014354585,0.000009614843,0.0008364529,0.000017602111,0.00032166808],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99934554,0.00001972612,0.00021677253,0.0001884503,0.00009666475,0.00013284708],"domain_scores_gemma":[0.9993109,0.000003288168,0.000106275475,0.0004939352,0.00002774847,0.00005786025],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008732194,0.000107048625,0.00008631058,0.000048562815,0.00009130995,0.000057345485,0.00021170013,0.00010332732,0.000011992761],"category_scores_gemma":[0.000033247215,0.00010005704,0.000018228266,0.00008958488,0.000037780854,0.000021070593,0.00019941169,0.000045395616,0.000005727556],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033973465,0.000052844745,0.0005698298,0.00021159434,0.00003688774,3.588099e-7,0.0010214596,0.000097754026,0.9317357,0.00015063911,0.019024583,0.047064397],"study_design_scores_gemma":[0.0017456636,0.00027902587,0.0077476758,0.00007336276,0.000060001832,0.00007912307,0.0014947434,0.67905825,0.1160536,0.000022126109,0.19257343,0.0008129943],"about_ca_topic_score_codex":0.0000019276638,"about_ca_topic_score_gemma":0.0000024076862,"teacher_disagreement_score":0.81568205,"about_ca_system_score_codex":0.000008242831,"about_ca_system_score_gemma":0.000012046152,"threshold_uncertainty_score":0.40802076},"labels":[],"label_agreement":null},{"id":"W2170330565","doi":"10.1093/bioinformatics/btr353","title":"A tree-based approach for motif discovery and sequence classification","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network; University of Toronto; Ontario Institute for Cancer Research","funders":"Canadian Institutes of Health Research","keywords":"Computer science; Multiple sequence alignment; Artificial intelligence; Pattern recognition (psychology); Parallelizable manifold; Sequence (biology); Tree (set theory); Data mining; Sequence alignment; Algorithm; Mathematics; Biology; Peptide sequence; Genetics","score_opus":0.038376186216780225,"score_gpt":0.23357254132165156,"score_spread":0.19519635510487132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170330565","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3782469,0.000049921033,0.6165149,0.00001638951,0.000045010573,0.00031777128,0.00008606643,0.000011997234,0.004711033],"genre_scores_gemma":[0.7720667,0.000030778534,0.2272374,0.00011806648,0.000027315227,0.00003594657,0.00035051024,0.000010697587,0.00012257311],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995083,0.000006349199,0.00018759852,0.000114689676,0.000049271315,0.00013378287],"domain_scores_gemma":[0.9995879,0.000005321723,0.0001000052,0.00022324017,0.000039572322,0.000043991142],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010023179,0.00009898988,0.00007951495,0.000024862831,0.000057249657,0.000035595756,0.000111275745,0.00009267332,0.0000011102973],"category_scores_gemma":[0.000024333118,0.000088794965,0.00004370089,0.0000311937,0.000062742045,0.000009486746,0.000034076016,0.00002785139,0.0000011969288],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009502728,0.0010989903,0.03596165,0.0035320958,0.00045509188,0.0000019279269,0.0043728864,0.0011114385,0.75578755,0.037357576,0.005329407,0.15404113],"study_design_scores_gemma":[0.00093717786,0.0003901421,0.0062483638,0.000012025416,0.000038465958,0.000009031803,0.0007037639,0.9652542,0.024179853,0.0003128055,0.0015673949,0.00034679382],"about_ca_topic_score_codex":0.0000033082822,"about_ca_topic_score_gemma":0.000003563741,"teacher_disagreement_score":0.96414274,"about_ca_system_score_codex":0.000008100741,"about_ca_system_score_gemma":0.00005253398,"threshold_uncertainty_score":0.36209536},"labels":[],"label_agreement":null},{"id":"W2170645625","doi":"10.1093/bioinformatics/btl346","title":"Detecting potential labeling errors in microarrays by data perturbation","year":2006,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":80,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Classifier (UML); Computation; Data mining; Support vector machine; Pattern recognition (psychology); Artificial intelligence; Algorithm; Machine learning","score_opus":0.014430927581674356,"score_gpt":0.24735452887072357,"score_spread":0.2329236012890492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170645625","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90900695,0.0011866956,0.08340363,0.00034110123,0.00041969772,0.00030061175,0.00010099143,0.00004031847,0.005200019],"genre_scores_gemma":[0.98759705,0.00006738226,0.009959436,0.00015231212,0.00012514163,0.0000065520408,0.0015348538,0.000010834113,0.00054642634],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99932957,0.00001599026,0.00026772724,0.00014481063,0.00009885131,0.00014305662],"domain_scores_gemma":[0.99946535,0.0000030535246,0.00010898514,0.00036789107,0.000030396886,0.000024342917],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015626397,0.00008371427,0.00006165787,0.00004654433,0.00005822347,0.000033390465,0.00021805559,0.00009932647,0.000007186789],"category_scores_gemma":[0.000038879152,0.00008093974,0.000018715316,0.000092009046,0.000018071723,0.000014274281,0.00009768467,0.000058026744,0.00000895846],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014637495,0.000026747131,0.00054801337,0.000020305719,0.0000038695907,2.0172084e-7,0.000051765473,0.00034857923,0.9720042,0.000014826441,0.020337744,0.0066291317],"study_design_scores_gemma":[0.0016407205,0.000102121136,0.0020493076,0.00005798754,0.00002275792,0.000018195451,0.0011502213,0.12902667,0.702279,0.0001563366,0.1629203,0.00057643134],"about_ca_topic_score_codex":0.00002820302,"about_ca_topic_score_gemma":0.000029219276,"teacher_disagreement_score":0.2697252,"about_ca_system_score_codex":0.000015947398,"about_ca_system_score_gemma":0.000036550002,"threshold_uncertainty_score":0.3300627},"labels":[],"label_agreement":null},{"id":"W2170652857","doi":"10.1093/bioinformatics/16.5.465","title":"BIND—a data specification for storing and describing biomolecular interactions, molecular complexes and pathways","year":2000,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":181,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute","funders":"","keywords":"Computer science; Computational biology; Protein–protein interaction; Function (biology); Object (grammar); Sequence (biology); Database; Theoretical computer science; Data mining; Biology; Genetics; Artificial intelligence","score_opus":0.056821403276481976,"score_gpt":0.2643492590564262,"score_spread":0.20752785577994423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170652857","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.59820855,0.0027731694,0.39426008,0.0003369481,0.00024191292,0.0009529385,0.00046192357,0.00005043442,0.0027140563],"genre_scores_gemma":[0.88553154,0.0014179415,0.1102606,0.0004721708,0.00020398053,0.000027063292,0.0018924467,0.000036022862,0.00015825279],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991147,0.000012857547,0.00035970207,0.00020442136,0.00008506361,0.00022328833],"domain_scores_gemma":[0.99919665,0.000017077438,0.00010809626,0.00053790514,0.00004436644,0.00009590431],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023872049,0.00016330334,0.00014298302,0.000049587718,0.00016553015,0.00012301632,0.00021747545,0.00009357629,0.000010468909],"category_scores_gemma":[0.000028522702,0.00016084989,0.00003227736,0.0000593917,0.00007568166,0.000037347767,0.00017626694,0.00006933979,0.000006372292],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017246784,0.000083074956,0.0003093931,0.00037118586,0.00023494687,0.0000023711445,0.001109154,0.00025566574,0.23115647,0.003068355,0.009197928,0.754039],"study_design_scores_gemma":[0.0023977405,0.00047562775,0.00057676464,0.0001736673,0.00015426561,0.00021430769,0.0015405248,0.38388708,0.03944993,0.0009757298,0.5690062,0.0011481536],"about_ca_topic_score_codex":0.0000061657097,"about_ca_topic_score_gemma":0.0000070109786,"teacher_disagreement_score":0.7528908,"about_ca_system_score_codex":0.000011618236,"about_ca_system_score_gemma":0.000028300103,"threshold_uncertainty_score":0.65592676},"labels":[],"label_agreement":null},{"id":"W2170726882","doi":"10.1093/bioinformatics/btp205","title":"Model-based clustering of array CGH data","year":2009,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomic variations and chromosomal abnormalities","field":"Biochemistry, Genetics and Molecular Biology","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"","keywords":"Cluster analysis; Comparative genomic hybridization; Computer science; Population; Computational biology; Software; Cluster (spacecraft); Data mining; Pattern recognition (psychology); Artificial intelligence; Biology; Medicine; Genetics; Chromosome","score_opus":0.028346948070858743,"score_gpt":0.25154376086899205,"score_spread":0.2231968127981333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170726882","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16428745,0.00013455408,0.8216658,0.00020432612,0.00010469297,0.00016770636,0.00030728328,0.00002103629,0.0131071275],"genre_scores_gemma":[0.9013398,0.000018822402,0.097678185,0.00029268852,0.000044817363,0.0000011094213,0.00046993434,0.000004502044,0.00015012274],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999455,0.000006117457,0.00025648862,0.00008239324,0.00007830739,0.0001217199],"domain_scores_gemma":[0.99924976,0.000003121367,0.00010068883,0.0005686962,0.00004338384,0.000034351233],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010441536,0.00008114384,0.00008961157,0.0000262344,0.000038466314,0.000014938874,0.00030151507,0.00006393876,0.000007849717],"category_scores_gemma":[0.000021952832,0.00007485332,0.000032776858,0.000037900303,0.000024110834,0.000009616607,0.000065362394,0.000029560115,0.0000047172994],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032066318,0.00060910964,0.0026041532,0.00078069343,0.00022836651,0.000002129739,0.0022683279,0.31005514,0.6157205,0.0034427505,0.018683067,0.045285087],"study_design_scores_gemma":[0.00060337654,0.00026761217,0.00054946204,0.000026796164,0.000027491926,0.000007920639,0.00026789156,0.8909636,0.09884661,0.0001708572,0.008014743,0.00025365254],"about_ca_topic_score_codex":0.0000027854896,"about_ca_topic_score_gemma":0.000005358983,"teacher_disagreement_score":0.7370524,"about_ca_system_score_codex":0.0000054013667,"about_ca_system_score_gemma":0.0000857567,"threshold_uncertainty_score":0.305243},"labels":[],"label_agreement":null},{"id":"W2171154262","doi":"10.1093/bioinformatics/btv232","title":"Cypiripi: exact genotyping of <i>CYP2D6</i> using high-throughput sequencing data","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Pharmacogenetics and Drug Metabolism","field":"Pharmacology, Toxicology and Pharmaceutics","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Institute of General Medical Sciences; National Human Genome Research Institute","keywords":"Genotyping; Context (archaeology); Pseudogene; Biology; Computational biology; Copy-number variation; Genotype; Computer science; Genetics; Data mining; Algorithm; Gene; Genome","score_opus":0.4461480385382918,"score_gpt":0.47036580555392304,"score_spread":0.02421776701563122,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171154262","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9475899,0.0041076257,0.024247384,0.00027665656,0.0052833995,0.0007904301,0.001150897,0.0001911995,0.016362537],"genre_scores_gemma":[0.9192274,0.0005593443,0.076211825,0.0028628062,0.0007185376,0.0000067406186,0.00024901913,0.00005569594,0.00010859082],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975804,0.00019258502,0.0009801771,0.0002660928,0.00039002704,0.00059069996],"domain_scores_gemma":[0.9977531,0.00015515753,0.00054373196,0.0008490361,0.000257537,0.0004414796],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0018015897,0.0003112479,0.0004837466,0.00017055492,0.00017140544,0.00003690472,0.0010025529,0.0004149855,0.00014159031],"category_scores_gemma":[0.00022214881,0.00029636204,0.00007856668,0.00034235194,0.00022716247,0.00063697057,0.0007311639,0.0007107115,0.00013022783],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014521583,0.001365018,0.011207175,0.0024674824,0.0030137682,0.00018773299,0.04069001,0.14268935,0.41237843,0.017595107,0.08920998,0.2777438],"study_design_scores_gemma":[0.0031818727,0.00008809564,0.000109266686,0.000051343348,0.00057893613,0.00009039283,0.0014238525,0.6652908,0.09430514,0.001090946,0.23314375,0.0006456019],"about_ca_topic_score_codex":0.00011395382,"about_ca_topic_score_gemma":0.00000529394,"teacher_disagreement_score":0.5226014,"about_ca_system_score_codex":0.00014478287,"about_ca_system_score_gemma":0.0006802765,"threshold_uncertainty_score":0.99994886},"labels":[],"label_agreement":null},{"id":"W2171164011","doi":"10.1093/bioinformatics/btg406","title":"JDotter: a Java interface to multiple dotplots generated by dotter","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Poxvirus research and outbreaks","field":"Immunology and Microbiology","cited_by":129,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"National Institute of Allergy and Infectious Diseases","keywords":"Java; Interface (matter); Computer science; Software; Programming language; Computer graphics (images); Operating system","score_opus":0.015113549004505537,"score_gpt":0.2588652430169957,"score_spread":0.24375169401249017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171164011","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96603477,0.0011397729,0.022869922,0.0022637208,0.00085323903,0.0008250476,0.0005065038,0.00036580066,0.0051412433],"genre_scores_gemma":[0.98899925,0.000055598335,0.0034453473,0.0029166394,0.00003557702,0.000035125275,0.0002504329,0.000026387548,0.004235627],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987795,0.000036502002,0.0003751735,0.00014875815,0.00006452502,0.0005955605],"domain_scores_gemma":[0.9993924,0.000043866028,0.000066821536,0.00032329612,0.00007401226,0.000099589146],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00015300249,0.0001923167,0.0002121739,0.00012427924,0.00014662919,0.000052960415,0.0003413614,0.00018909344,0.00025462458],"category_scores_gemma":[0.00012623591,0.00015589054,0.000063749016,0.00018163756,0.00009649983,0.00019469154,0.00017840811,0.00025912773,0.013221125],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021835118,0.0001648448,0.00047791592,0.000047239435,0.00017037078,0.0000060019324,0.0031790216,0.00014881729,0.66887194,0.00008490004,0.3117745,0.014856141],"study_design_scores_gemma":[0.002260132,0.00025373703,0.00029030407,0.000039394617,0.0000098235105,0.00004471873,0.00022410604,0.00009828197,0.572491,0.00003616334,0.42397767,0.00027467858],"about_ca_topic_score_codex":0.00018494407,"about_ca_topic_score_gemma":0.000054849297,"teacher_disagreement_score":0.1122032,"about_ca_system_score_codex":0.00009247949,"about_ca_system_score_gemma":0.00007568161,"threshold_uncertainty_score":0.9875472},"labels":[],"label_agreement":null},{"id":"W2171259901","doi":"10.1093/bioinformatics/btu556","title":"Prediction of Indel flanking regions in protein sequences using a variable-order Markov model","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Indel; Flanking maneuver; Markov chain; Variable (mathematics); Markov model; Computer science; Markov chain Monte Carlo; Order (exchange); Genetics; Mathematics; Statistics; Artificial intelligence; Biology; Gene; Bayesian probability; Geography","score_opus":0.018877510514529117,"score_gpt":0.24661550447183547,"score_spread":0.22773799395730634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171259901","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41579968,0.00002314271,0.57516575,0.000033624994,0.00006615615,0.00034907876,0.00003157659,0.000024298404,0.008506702],"genre_scores_gemma":[0.5500876,0.000012738972,0.44944727,0.00011644319,0.000051838084,0.0000134849915,0.00011335126,0.000015535836,0.00014175363],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987376,0.000046749687,0.00063680834,0.000114173556,0.00021717789,0.0002475276],"domain_scores_gemma":[0.99911255,0.000014396311,0.0003410649,0.0003598732,0.000121295794,0.000050804258],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005815929,0.00016217513,0.00018731688,0.00013920583,0.00006746891,0.000025916741,0.00022258032,0.00021359329,0.0000055145306],"category_scores_gemma":[0.00036598914,0.00015228959,0.0000446863,0.00024848618,0.00008183409,0.00002792559,0.00012787057,0.00016642996,0.0000024119431],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019275125,0.00022669007,0.024861854,0.002132136,0.00015130074,8.8337936e-7,0.0036209219,0.7375822,0.20948188,0.012051944,0.0010234665,0.008673979],"study_design_scores_gemma":[0.0004378893,0.0001144658,0.00020264121,0.0001404205,0.00001281369,0.0000135701985,0.00013990105,0.9942845,0.0031812855,0.00045267842,0.0008684871,0.00015133894],"about_ca_topic_score_codex":0.000037229114,"about_ca_topic_score_gemma":0.000013005896,"teacher_disagreement_score":0.2567023,"about_ca_system_score_codex":0.000028442077,"about_ca_system_score_gemma":0.0001705862,"threshold_uncertainty_score":0.62101895},"labels":[],"label_agreement":null},{"id":"W2171475724","doi":"10.1093/bioinformatics/btl629","title":"Assembling millions of short DNA sequences using SSAKE","year":2006,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":506,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency","funders":"BC Cancer Agency; Michael Smith Health Research BC","keywords":"DNA sequencing; Sanger sequencing; Computational biology; Hybrid genome assembly; Biology; Sequence assembly; Genome; Software; Sequence (biology); k-mer; Leverage (statistics); Deep sequencing; Genetics; DNA; Computer science; Reference genome; Gene; Transcriptome; Artificial intelligence","score_opus":0.02626783783145639,"score_gpt":0.26256828783320746,"score_spread":0.23630045000175107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171475724","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99239093,0.00061760924,0.0030398997,0.000013529932,0.00010982096,0.00008617996,0.000034619894,0.0000028198854,0.003704592],"genre_scores_gemma":[0.9762148,0.00012282631,0.02342182,0.000034792338,0.00010984279,0.0000023101838,0.000032141335,0.000007798129,0.000053669075],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99935514,0.000007792549,0.00030647195,0.0000808422,0.00009277602,0.00015698496],"domain_scores_gemma":[0.9996264,0.000007511152,0.000084646,0.00017889852,0.00007691856,0.000025629135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010053011,0.000100626195,0.00012177437,0.0000402725,0.00007333628,0.000013231616,0.000113310234,0.00007242782,0.000002355182],"category_scores_gemma":[0.000015934264,0.00009059,0.000069024856,0.00007644943,0.00006885668,0.0000012837105,0.00007509184,0.000027137243,0.0000017301982],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005686232,0.000026005027,0.012720152,0.00004412118,0.000046644902,4.152976e-7,0.00007475852,0.00203306,0.9836224,0.0002590793,0.0004212978,0.00074640464],"study_design_scores_gemma":[0.0004580031,0.00028240986,0.023727832,0.000053006304,0.00010362766,0.000040954492,0.0010137012,0.015667245,0.9341495,0.00052260165,0.023380274,0.0006008669],"about_ca_topic_score_codex":0.000041358246,"about_ca_topic_score_gemma":0.000029542187,"teacher_disagreement_score":0.0494729,"about_ca_system_score_codex":0.0000069999505,"about_ca_system_score_gemma":0.0000508835,"threshold_uncertainty_score":0.3694153},"labels":[],"label_agreement":null},{"id":"W2171675548","doi":"10.1093/bioinformatics/btt729","title":"Site-heterogeneous mutation-selection models within the PhyloBayes-MPI package","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":89,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Software; Focus (optics); Scalability; Selection (genetic algorithm); Interface (matter); Model selection; Data mining; Mutation; Variety (cybernetics); Dirichlet process; Bayesian probability; Theoretical computer science; Machine learning; Artificial intelligence; Programming language; Biology; Genetics; Parallel computing; Database; Gene","score_opus":0.010939629712216885,"score_gpt":0.21276376770997538,"score_spread":0.2018241379977585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171675548","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98307925,0.00040214372,0.013008908,0.00014273636,0.00019964401,0.00041994205,0.000028493154,0.000011204389,0.0027076863],"genre_scores_gemma":[0.9931402,0.00009790392,0.0056350175,0.00059459155,0.00013616611,0.00008805542,0.00005026008,0.000016389848,0.0002414144],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992143,0.000023511984,0.00029896013,0.00012902413,0.00012536065,0.00020886357],"domain_scores_gemma":[0.9993776,0.000013979155,0.00014381709,0.00028247517,0.00012723335,0.000054899105],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000113219015,0.00015899746,0.000106829444,0.0000256606,0.00020128071,0.00008255983,0.00017119768,0.00009197734,0.000018153112],"category_scores_gemma":[0.000028642407,0.00011112108,0.00007941908,0.00008022047,0.000068522575,0.000004462193,0.00009630203,0.00006434058,0.000115207346],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015595133,0.0003622465,0.009327111,0.00034061947,0.0014748496,0.0000055471573,0.01461363,0.18969247,0.6695779,0.005027309,0.059435353,0.04998702],"study_design_scores_gemma":[0.0019551064,0.0013644269,0.009539639,0.000034875593,0.00017695091,0.0003172874,0.0029675954,0.6687146,0.28043404,0.010656864,0.022214126,0.0016244813],"about_ca_topic_score_codex":0.000053018666,"about_ca_topic_score_gemma":0.000052941963,"teacher_disagreement_score":0.47902215,"about_ca_system_score_codex":0.000012696378,"about_ca_system_score_gemma":0.00004165663,"threshold_uncertainty_score":0.45313862},"labels":[],"label_agreement":null},{"id":"W2171821554","doi":"10.1093/bioinformatics/btn073","title":"SubSeqer: a graph-based approach for the detection and identification of repetitive elements in low-complexity sequences","year":2008,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"Hospital for Sick Children; Heart and Stroke Foundation of Canada","keywords":"Computer science; Visualization; Identification (biology); Palette (painting); Graph; Computational biology; Matching (statistics); Computational complexity theory; Interspersed repeat; Theoretical computer science; Biology; Algorithm; Data mining; Genome; Mathematics; Genetics","score_opus":0.030244628776910823,"score_gpt":0.24561592944355418,"score_spread":0.21537130066664334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171821554","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9306857,0.00036564973,0.06835081,0.000019215442,0.00003767653,0.00039072332,0.000046735935,0.0000014035443,0.000102083446],"genre_scores_gemma":[0.9924584,0.00032746582,0.007068237,0.000033302807,0.000016585826,0.000053906264,0.000029022809,0.000003388359,0.000009710102],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994945,0.000011701141,0.0002684233,0.000081292004,0.000057908106,0.00008617872],"domain_scores_gemma":[0.9996324,0.000016629081,0.0001441127,0.00013031771,0.00006373505,0.000012772393],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000204281,0.000063254505,0.000074109725,0.00003112166,0.000096917414,0.0000061976607,0.000070709255,0.000038681537,2.9067482e-7],"category_scores_gemma":[0.00004160008,0.000047914862,0.000034202552,0.00006167216,0.0001645724,0.0000014195754,0.000023929686,0.00002151653,1.308466e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049003295,0.00033134123,0.08942766,0.0011124643,0.0002595489,4.793298e-7,0.003920261,0.0045689726,0.8787841,0.0007218567,0.0001275721,0.02025569],"study_design_scores_gemma":[0.0019577085,0.0005357001,0.29374954,0.00002469147,0.00005779388,0.00001499969,0.0024677129,0.12603317,0.573272,0.00063824275,0.00088847877,0.00035997873],"about_ca_topic_score_codex":0.000018936216,"about_ca_topic_score_gemma":0.00003711541,"teacher_disagreement_score":0.30551216,"about_ca_system_score_codex":0.000005544664,"about_ca_system_score_gemma":0.000024263962,"threshold_uncertainty_score":0.19539113},"labels":[],"label_agreement":null},{"id":"W2171832486","doi":"10.1093/bioinformatics/btl017","title":"Polynomial model approach for resynchronization analysis of cell-cycle gene expression data","year":2006,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computational biology; Microarray analysis techniques; Gene; Identification (biology); Cell cycle; Computer science; Expression (computer science); Gene expression; Biology; Functional genomics; Microarray; Gene expression profiling; Genomics; Algorithm; Genetics; Genome","score_opus":0.015229784318238205,"score_gpt":0.23799432060265668,"score_spread":0.22276453628441847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171832486","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19302158,0.00022096124,0.8055489,0.000004539834,0.000019141335,0.00017006087,0.00031259577,0.000008846683,0.00069339556],"genre_scores_gemma":[0.70538723,0.000030084557,0.28261212,0.000017054708,0.00010571449,0.00000835654,0.01163105,0.000012785594,0.00019562671],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989835,0.000016400605,0.00044662014,0.00021345499,0.0001587086,0.00018133163],"domain_scores_gemma":[0.998627,0.0000069854555,0.0002752732,0.0009496278,0.00010030358,0.00004082703],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021204202,0.00012887522,0.00022795815,0.00014582401,0.0000716502,0.000018791803,0.00036941402,0.00014516975,0.0000030993858],"category_scores_gemma":[0.000016805481,0.00012144705,0.00015078894,0.00033557252,0.00004061045,0.0000133416415,0.00020755139,0.000025958518,5.948656e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003087872,0.00006940173,0.00055121083,0.000051218944,0.00019276893,2.5077295e-8,0.000023339362,0.75206226,0.23444468,0.000004233259,0.012308094,0.0002618799],"study_design_scores_gemma":[0.00026523694,0.00002272992,0.00013999638,0.0000016179218,0.0005468875,2.6659302e-7,0.00002822673,0.80306524,0.19534497,0.0000036652552,0.0004676703,0.00011350693],"about_ca_topic_score_codex":0.000010197896,"about_ca_topic_score_gemma":0.000010747231,"teacher_disagreement_score":0.52293676,"about_ca_system_score_codex":0.000014551136,"about_ca_system_score_gemma":0.00007067981,"threshold_uncertainty_score":0.49524668},"labels":[],"label_agreement":null},{"id":"W2171977579","doi":"10.1093/bioinformatics/btt485","title":"iBMQ: a R/Bioconductor package for integrated Bayesian modeling of eQTL data","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Clinical Research Institute","funders":"National Human Genome Research Institute; National Institutes of Health","keywords":"Bioconductor; Expression quantitative trait loci; R package; Computer science; Bayesian probability; Markov chain Monte Carlo; Univariate; Data mining; Computational biology; Biology; Machine learning; Artificial intelligence; Single-nucleotide polymorphism; Gene; Genetics; Computational science","score_opus":0.04416219096831347,"score_gpt":0.28701331923114004,"score_spread":0.24285112826282657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171977579","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43249092,0.00015581009,0.56522185,0.00021437305,0.00014855489,0.00058835756,0.00038533556,0.000014302279,0.0007804961],"genre_scores_gemma":[0.86350155,0.00007078224,0.13370557,0.00023450867,0.00008446031,0.000040504605,0.0021705716,0.000015121737,0.0001769221],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990308,0.000024761428,0.0004940218,0.00015158177,0.00006467652,0.00023411709],"domain_scores_gemma":[0.9988876,0.000027603422,0.00014378777,0.0006723931,0.00020443815,0.00006415555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030248004,0.00012287342,0.0001997503,0.000039600378,0.000051086558,0.00001681465,0.00038325015,0.00017597087,0.000029203558],"category_scores_gemma":[0.00048374702,0.000102227634,0.00006389297,0.00006529855,0.00004291686,0.000013202476,0.00017652632,0.00004963114,0.000016752616],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020705984,0.0006910487,0.031506628,0.0014695027,0.0016885778,6.9687644e-7,0.0020431005,0.008450033,0.45660442,0.002260918,0.42263672,0.072441295],"study_design_scores_gemma":[0.0005713356,0.0002128088,0.00059929496,0.000018128523,0.000036660953,0.0000035853343,0.00087935664,0.9828174,0.00575721,0.0004092448,0.008465758,0.00022921104],"about_ca_topic_score_codex":0.00006405349,"about_ca_topic_score_gemma":0.000018078063,"teacher_disagreement_score":0.9743674,"about_ca_system_score_codex":0.000009252942,"about_ca_system_score_gemma":0.000094525676,"threshold_uncertainty_score":0.41687217},"labels":[],"label_agreement":null},{"id":"W2172174827","doi":"10.1093/bioinformatics/btv356","title":"EXIMS: an improved data analysis pipeline based on a new peak picking method for EXploring Imaging Mass Spectrometry data","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Mass Spectrometry Techniques and Applications","field":"Chemistry","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IONICS Mass Spectrometry (Canada)","funders":"State Government of Victoria; University of Melbourne; Vanderbilt University","keywords":"Normalization (sociology); Computer science; Cluster analysis; Mass spectrometry imaging; Data mining; Pattern recognition (psychology); Pipeline (software); Spatial analysis; Segmentation; Artificial intelligence; Mass spectrometry; Mathematics; Chemistry","score_opus":0.1579918128006178,"score_gpt":0.36703765716931597,"score_spread":0.20904584436869816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2172174827","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020607695,0.000041171974,0.98974186,0.00043220926,0.00004652137,0.00025216877,0.0012946746,0.00041886058,0.0075664455],"genre_scores_gemma":[0.024566421,0.000016240354,0.96571475,0.00023670995,0.00040887884,0.000058356163,0.008725572,0.000046413974,0.00022668365],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978175,0.000021026994,0.00072410976,0.00056642806,0.00040142753,0.00046949444],"domain_scores_gemma":[0.9938393,0.0002557999,0.0003927426,0.0050396,0.00010666771,0.00036584935],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015620408,0.00030389088,0.000430699,0.00046416724,0.00013748107,0.0002671726,0.0023120886,0.000088223365,0.0003115879],"category_scores_gemma":[0.000586977,0.00029079107,0.00010714235,0.0010890859,0.000024930641,0.0011885937,0.00056191365,0.00025292972,0.000008863682],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012559239,0.0028899559,0.011784401,0.0038094386,0.003336634,0.000029456132,0.0043277633,0.0072562355,0.118658364,0.015665252,0.15073404,0.68025255],"study_design_scores_gemma":[0.00067298376,0.000040002127,0.000017599119,0.000029016148,0.00049924053,0.0000027957706,0.0010529521,0.96729696,0.008119913,0.0006269336,0.021285934,0.0003556924],"about_ca_topic_score_codex":0.00016758784,"about_ca_topic_score_gemma":0.000034737128,"teacher_disagreement_score":0.9600407,"about_ca_system_score_codex":0.00016966216,"about_ca_system_score_gemma":0.00020694018,"threshold_uncertainty_score":0.9999544},"labels":[],"label_agreement":null},{"id":"W2172269857","doi":"10.1093/bioinformatics/btl188","title":"FCP: functional coverage of the proteome by structures","year":2006,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Instituto de Salud Carlos III; International Union of Biochemistry and Molecular Biology; Universitat Pompeu Fabra","keywords":"Proteome; Computer science; Population; Computational biology; Bioinformatics; Biology","score_opus":0.0032564763635078114,"score_gpt":0.1856639181624849,"score_spread":0.18240744179897708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2172269857","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9282123,0.00040167733,0.05612803,0.00012589672,0.0003915453,0.0005827097,0.00035278418,0.000017975159,0.013787069],"genre_scores_gemma":[0.9956854,0.000013227813,0.0028111897,0.00022425159,0.00012362706,0.0000083022,0.00027692007,0.000008240338,0.00084886944],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99943763,0.000010001758,0.00022056403,0.000066803506,0.00014950658,0.000115503775],"domain_scores_gemma":[0.9995447,0.0000035232079,0.00013775808,0.0002494204,0.0000463268,0.000018276214],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000045640627,0.00009365288,0.00007565258,0.000012898372,0.000060747207,0.000013382952,0.00014820062,0.00010401368,0.000016623066],"category_scores_gemma":[0.000021170254,0.00006131205,0.000070802445,0.0000593694,0.00007593743,0.0000045641896,0.00007943366,0.000056926565,0.0000020755551],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001505706,0.00007847645,0.0086999405,0.00027233487,0.000113144386,4.845842e-7,0.00008053312,0.0029648573,0.83814967,0.010088247,0.13186695,0.007534791],"study_design_scores_gemma":[0.0012400005,0.00021781081,0.034055263,0.000019672734,0.000037001268,0.000047324374,0.000050084287,0.00193704,0.779218,0.010469108,0.1722623,0.00044638265],"about_ca_topic_score_codex":0.000014053464,"about_ca_topic_score_gemma":0.000009432753,"teacher_disagreement_score":0.067473054,"about_ca_system_score_codex":0.0000074450777,"about_ca_system_score_gemma":0.000048993275,"threshold_uncertainty_score":0.25002328},"labels":[],"label_agreement":null},{"id":"W2172358623","doi":"10.1093/bioinformatics/btv693","title":"Genefu: an R/Bioconductor package for computation of gene expression-based signatures in breast cancer","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":410,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"National Cancer Institute; Cancer Research Society; Canadian Institutes of Health Research; Instituto de Salud Carlos III; Banco Bilbao Vizcaya Argentaria; Fondation Brain Canada","keywords":"Bioconductor; Compendium; Subtyping; Computer science; R package; Breast cancer; Source code; Computational biology; Data mining; Bioinformatics; Cancer; Gene; Biology; Programming language; Genetics","score_opus":0.031093044095763682,"score_gpt":0.30028275011701877,"score_spread":0.2691897060212551,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2172358623","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9067128,0.0005773257,0.09103753,0.00020651279,0.00034700293,0.00055976375,0.00033964863,0.000018446195,0.00020097468],"genre_scores_gemma":[0.9769823,0.000024972871,0.02213881,0.00028081497,0.00011014479,0.00007907332,0.00034298713,0.000013990681,0.000026890199],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999271,0.000027012957,0.00029528726,0.00013440764,0.00013897716,0.00013331864],"domain_scores_gemma":[0.9992787,0.000006888278,0.00018731013,0.0002278529,0.00020228875,0.00009695611],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015583093,0.000107760956,0.00011759496,0.00007902699,0.000024424846,0.00001468943,0.00014234925,0.00018260797,0.000006923643],"category_scores_gemma":[0.000029458615,0.00009307463,0.000043278167,0.00009124016,0.00003488061,0.000014146855,0.00001936066,0.000051096235,8.628346e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021694039,0.00009806028,0.0020801178,0.00010393844,0.000007863956,1.172976e-7,0.00020867818,0.0074750907,0.980761,0.00002771325,0.006252501,0.0027680001],"study_design_scores_gemma":[0.0013860131,0.00014380128,0.0033856372,0.000043352222,0.000008304053,8.906378e-7,0.00036416648,0.026041804,0.9663185,0.00004919209,0.0020936667,0.00016466051],"about_ca_topic_score_codex":0.000008336536,"about_ca_topic_score_gemma":0.000007978995,"teacher_disagreement_score":0.07026952,"about_ca_system_score_codex":0.000025710542,"about_ca_system_score_gemma":0.00023654859,"threshold_uncertainty_score":0.37954733},"labels":[],"label_agreement":null},{"id":"W2176522635","doi":"10.1093/bioinformatics/btv616","title":"IsoMIF Finder: online detection of binding site molecular interaction field similarities","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; Québec Consortium for Drug Discovery","keywords":"Plug-in; Identification (biology); Computer science; Java; Session (web analytics); Benchmark (surveying); Interface (matter); Function (biology); Field (mathematics); Protein Data Bank (RCSB PDB); Computational biology; Data mining; World Wide Web; Operating system; Biology; Genetics; Cartography","score_opus":0.040824633121552156,"score_gpt":0.3105782690473786,"score_spread":0.26975363592582646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2176522635","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21369088,0.000027755534,0.78478277,0.0002239111,0.00045247425,0.000072513976,0.000009044908,0.00005452551,0.0006861028],"genre_scores_gemma":[0.69665843,0.0000068517634,0.30290776,0.0003338499,0.000036400023,0.0000025845811,0.00002042626,0.000005361674,0.000028325092],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990862,0.000049320242,0.00035645225,0.000087441585,0.00029751429,0.00012307831],"domain_scores_gemma":[0.9991444,0.00021264341,0.00019167397,0.00024102145,0.0001494,0.000060906215],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030488757,0.00009319458,0.00012483727,0.00019269074,0.000035066376,0.00008137145,0.00025918125,0.00005611699,0.0000025207696],"category_scores_gemma":[0.0002869674,0.000092455084,0.000058417365,0.00028775973,0.000017407014,0.0010045242,0.00018439413,0.00011342323,0.000025163072],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012363427,0.0003972806,0.00075726205,0.0005264618,0.00015093353,0.000018201848,0.018498354,0.32107836,0.015062747,0.01768605,0.0030676846,0.62263304],"study_design_scores_gemma":[0.0002327802,0.00013510184,0.00015785248,0.000034916626,0.000005626268,0.000018058468,0.000420308,0.9554549,0.040355217,0.0017399642,0.0013316079,0.00011369175],"about_ca_topic_score_codex":0.00002289246,"about_ca_topic_score_gemma":0.0000092285945,"teacher_disagreement_score":0.6343765,"about_ca_system_score_codex":0.0000640095,"about_ca_system_score_gemma":0.00008407234,"threshold_uncertainty_score":0.3770209},"labels":[],"label_agreement":null},{"id":"W2177550115","doi":"10.1093/bioinformatics/btv597","title":"PDID: database of molecular-level putative protein–drug interactions in the structural human proteome","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Institutes of Health; U.S. National Library of Medicine; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Proteome; Human proteome project; Computational biology; Drug; Computer science; Database; Bioinformatics; Biology; Proteomics; Genetics; Pharmacology; Gene","score_opus":0.03435201254339759,"score_gpt":0.2947702654347224,"score_spread":0.2604182528913248,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2177550115","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9790606,0.00013780693,0.01327348,0.00023830231,0.00012881395,0.0011963822,0.0002441825,0.000010287793,0.00571014],"genre_scores_gemma":[0.9813906,0.000003760537,0.017508326,0.00025073392,0.00006474659,0.0000597567,0.0005440523,0.000011657204,0.0001663534],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988289,0.000054521108,0.0005511605,0.00010499944,0.00022810762,0.00023230191],"domain_scores_gemma":[0.9990784,0.000010529224,0.0002822159,0.000439336,0.000112947826,0.000076568096],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004721743,0.0001695115,0.00016116987,0.00007444989,0.00006439214,0.000041288564,0.00038708354,0.00004872708,0.000005956805],"category_scores_gemma":[0.00006935063,0.00012124749,0.00007053541,0.0001604008,0.00011548452,0.000029675764,0.00017129023,0.00019357272,0.00000957365],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010988148,0.0010199292,0.004174334,0.002528844,0.0010076689,0.00006246281,0.084015675,0.009930238,0.76665384,0.04255238,0.053824734,0.033131074],"study_design_scores_gemma":[0.013543864,0.0022660503,0.0072382293,0.00092753646,0.0002646569,0.00057232584,0.06460623,0.11163237,0.7282877,0.022505507,0.044450346,0.003705205],"about_ca_topic_score_codex":0.00006682926,"about_ca_topic_score_gemma":0.00011197491,"teacher_disagreement_score":0.10170213,"about_ca_system_score_codex":0.00002287223,"about_ca_system_score_gemma":0.000114403745,"threshold_uncertainty_score":0.4944329},"labels":[],"label_agreement":null},{"id":"W2177764460","doi":"10.1093/bioinformatics/btv619","title":"ancGWAS: a post genome-wide association study method for interaction, pathway and ancestry analysis in homogeneous and admixed populations","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Common Fund; National Eye Institute; National Human Genome Research Institute; African Institute for Mathematical Sciences; Division of Mathematical Sciences; Government of Canada; National Institutes of Health; University of Cape Town; International Development Research Centre","keywords":"Genome-wide association study; Linkage disequilibrium; Genetic association; Interactome; Biology; Computational biology; Breast cancer; Genetics; Single-nucleotide polymorphism; Gene; Cancer; Genotype","score_opus":0.044067027943376816,"score_gpt":0.33288749626912667,"score_spread":0.28882046832574987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2177764460","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95056003,0.00021320592,0.04826283,0.00029133965,0.0000851092,0.00039765207,0.00008361089,0.000007958749,0.000098286786],"genre_scores_gemma":[0.93955874,0.00004919272,0.05948836,0.00028853273,0.0000507323,0.000056900913,0.00037505783,0.000008073552,0.00012438888],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99901825,0.000106166866,0.00043372865,0.00016825582,0.000083421626,0.00019015925],"domain_scores_gemma":[0.99914104,0.00011764257,0.0002804677,0.0001620814,0.00020871987,0.00009003491],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000906536,0.00011681299,0.0002481453,0.00014594341,0.000077194796,0.000034544366,0.000060380542,0.00014792546,0.0000015651323],"category_scores_gemma":[0.001524608,0.000112943904,0.000053404456,0.00021037021,0.000013102692,0.000012966277,0.00006378896,0.0000643677,0.0000011382605],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031471245,0.00009111918,0.99416715,0.000012755935,0.00024076083,3.4826277e-7,0.0010899747,0.0020960278,0.00017613366,0.0000109726425,0.00033364716,0.0017496112],"study_design_scores_gemma":[0.0012559507,0.0006952231,0.95518595,0.000003819813,0.0002691336,0.0000048310703,0.006806199,0.03181761,0.00006295898,0.000255141,0.0034033065,0.00023986322],"about_ca_topic_score_codex":0.00010939518,"about_ca_topic_score_gemma":0.0014726776,"teacher_disagreement_score":0.038981218,"about_ca_system_score_codex":0.00006625041,"about_ca_system_score_gemma":0.000075692544,"threshold_uncertainty_score":0.46057186},"labels":[],"label_agreement":null},{"id":"W2179127114","doi":"10.1093/bioinformatics/btv557","title":"Cytoscape.js: a graph theory library for visualisation and analysis","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":721,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Institute of General Medical Sciences; National Human Genome Research Institute; National Institutes of Health; National Institute for Health and Care Research","keywords":"Computer science; JavaScript; Visualization; Documentation; Source code; Graph; Programming language; Software; Web application; Graph drawing; World Wide Web; Information retrieval; Data mining; Theoretical computer science","score_opus":0.014564893441759852,"score_gpt":0.24308882647624352,"score_spread":0.22852393303448368,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2179127114","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.107104205,0.0011839733,0.8820716,0.00019469715,0.00024918435,0.0006765217,0.0002823124,0.00007123374,0.008166251],"genre_scores_gemma":[0.85866964,0.0004930671,0.13151462,0.0027683196,0.0004922834,0.00009016221,0.0043606493,0.000058462447,0.0015527618],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992323,0.000021623788,0.0003400983,0.0001109016,0.00009602912,0.00019905454],"domain_scores_gemma":[0.9993608,0.000025158834,0.0001514231,0.00025549135,0.000056337303,0.00015076001],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038696371,0.00014136478,0.00016951759,0.00011930024,0.00007060402,0.000089789,0.00013077883,0.00015293606,0.0000064219425],"category_scores_gemma":[0.000050579496,0.00012243334,0.00011878914,0.00020370625,0.00006706235,0.000028846544,0.000105344356,0.000043914857,0.000006037057],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003055116,0.0005244962,0.027388044,0.0012152601,0.009371289,0.000003681989,0.019403078,0.004485482,0.004858342,0.14141972,0.4149057,0.37336978],"study_design_scores_gemma":[0.007263586,0.002478407,0.0035740053,0.00006291592,0.0023155173,0.000060957576,0.009468464,0.46831217,0.017478654,0.054427933,0.4322098,0.0023475839],"about_ca_topic_score_codex":9.677408e-7,"about_ca_topic_score_gemma":0.0000027275264,"teacher_disagreement_score":0.75156546,"about_ca_system_score_codex":0.0000057226616,"about_ca_system_score_gemma":0.000064935644,"threshold_uncertainty_score":0.49926868},"labels":[],"label_agreement":null},{"id":"W2180318265","doi":"10.1093/bioinformatics/btv487","title":"EPGA2: memory-efficient <i>de novo</i> assembler","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Program for New Century Excellent Talents in University; National Natural Science Foundation of China","keywords":"Computer science; Sequence assembly; Pipeline (software); Contig; De Bruijn sequence; De Bruijn graph; Construct (python library); Parallels; Genome; Reference genome; Graph; Theoretical computer science; Parallel computing; Programming language; Biology; Genetics; Gene","score_opus":0.022655545222036964,"score_gpt":0.24651608930198826,"score_spread":0.2238605440799513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2180318265","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95587665,0.0006309239,0.004079744,0.00013967471,0.00034801307,0.00015790701,0.000023706982,0.000009450143,0.038733933],"genre_scores_gemma":[0.9871924,0.000086975626,0.011109938,0.0007231058,0.00021132859,0.000012783807,0.000026688871,0.000016099035,0.000620674],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992434,0.000015489813,0.00022454312,0.000111128604,0.00013618932,0.00026926733],"domain_scores_gemma":[0.99936765,0.00000695491,0.000074203075,0.00029374028,0.0001086261,0.00014881305],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002779989,0.00013295106,0.0001157558,0.00002688156,0.000059733255,0.000029766123,0.00017305155,0.00009314036,0.000004236164],"category_scores_gemma":[0.000082832135,0.00011782286,0.000060160997,0.00006229376,0.000048146332,7.176154e-7,0.00015499574,0.00004926132,0.00007173882],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042030323,0.0008012185,0.015998013,0.00032954814,0.00076190376,0.000025196328,0.011537965,0.03563156,0.63695335,0.0021935615,0.24543887,0.049908523],"study_design_scores_gemma":[0.003960087,0.0011228318,0.007374978,0.00003404777,0.00011168751,0.00024704222,0.006837869,0.03278482,0.20687199,0.0003435634,0.73890126,0.0014098416],"about_ca_topic_score_codex":0.0000062708596,"about_ca_topic_score_gemma":0.000004920037,"teacher_disagreement_score":0.49346235,"about_ca_system_score_codex":0.000022603183,"about_ca_system_score_gemma":0.00013567405,"threshold_uncertainty_score":0.48046768},"labels":[],"label_agreement":null},{"id":"W2180921306","doi":"10.1093/bioinformatics/btv587","title":"CSSSCL: a python package that uses combined sequence similarity scores for accurate taxonomic classification of long and short sequence reads","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"Government of Ontario; Ontario Institute for Cancer Research","keywords":"Python (programming language); Sequence (biology); Computer science; Similarity (geometry); R package; Computational biology; Artificial intelligence; Biology; Programming language; Genetics","score_opus":0.14316428405831452,"score_gpt":0.3136729286223924,"score_spread":0.17050864456407785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2180921306","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9899694,0.00034890798,0.008465943,0.00008322561,0.00011152837,0.0004497073,0.00022243337,0.000006751851,0.0003421119],"genre_scores_gemma":[0.98781157,0.0004661827,0.0113678565,0.00008259815,0.000038764378,0.000038498245,0.0001466477,0.0000128892925,0.000034989134],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99923295,0.000019425355,0.00031179248,0.00015889984,0.00009355003,0.0001833984],"domain_scores_gemma":[0.99922734,0.000030143066,0.00018015417,0.0003113628,0.00016429384,0.00008670757],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002739556,0.00015331016,0.00019303695,0.000034098688,0.00006529775,0.000033901808,0.00016034713,0.00011282283,5.059967e-7],"category_scores_gemma":[0.00014184022,0.00013822156,0.00005005261,0.000045137174,0.00017973728,0.000007260145,0.00012063785,0.000041500814,0.000001094205],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005429211,0.00012608024,0.21472144,0.0007422511,0.00028452915,0.0000020895209,0.0014950208,0.00026281597,0.7599082,0.0013475576,0.004774486,0.015792606],"study_design_scores_gemma":[0.003035057,0.0024116833,0.21493989,0.00015903686,0.00023877212,0.0000607145,0.0032540527,0.035849273,0.7262693,0.0012969376,0.011174888,0.0013103923],"about_ca_topic_score_codex":0.000016049848,"about_ca_topic_score_gemma":0.000050830586,"teacher_disagreement_score":0.035586458,"about_ca_system_score_codex":0.000020165575,"about_ca_system_score_gemma":0.00011325478,"threshold_uncertainty_score":0.56365114},"labels":[],"label_agreement":null},{"id":"W2191136822","doi":"10.1093/bioinformatics/btv662","title":"rHAT: fast alignment of noisy long reads with regional hashing","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National High-tech Research and Development Program; University of Toronto; National Natural Science Foundation of China","keywords":"Computer science; Hash function; Bottleneck; Hash table; Source code; Theoretical computer science; Data mining; Computational biology; Algorithm; Biology; Programming language","score_opus":0.024469740640056834,"score_gpt":0.23372364095691464,"score_spread":0.2092539003168578,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2191136822","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9850854,0.00061504886,0.0067251767,0.00015745485,0.000105653475,0.00016296815,0.000024248786,0.0000041136063,0.007119928],"genre_scores_gemma":[0.9826417,0.000116059884,0.016652891,0.00018250206,0.00008720318,0.000007000122,0.00004826498,0.000011102877,0.00025328321],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993469,0.000008849406,0.00023093043,0.00009008797,0.00016939714,0.00015382042],"domain_scores_gemma":[0.99941957,0.0000054618818,0.00013432396,0.0002406895,0.00011978506,0.000080148755],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013685341,0.00011329345,0.0001271591,0.00002506483,0.00003620521,0.000013896669,0.00012930788,0.000059951086,0.0000015735184],"category_scores_gemma":[0.000017773045,0.00008817019,0.00003846472,0.000047095913,0.0000831902,0.0000016933304,0.00009921657,0.00003146753,0.0000056544477],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002351165,0.0012418943,0.31049696,0.0014765941,0.003463596,0.000036352358,0.038891666,0.0166543,0.39026317,0.0072618993,0.14230391,0.085558504],"study_design_scores_gemma":[0.010112594,0.0076596877,0.0613416,0.00038747798,0.00037378405,0.00042061912,0.021533703,0.0067065493,0.4611396,0.000625865,0.4270233,0.0026752425],"about_ca_topic_score_codex":0.000012516582,"about_ca_topic_score_gemma":0.00002048386,"teacher_disagreement_score":0.28471938,"about_ca_system_score_codex":0.000012070488,"about_ca_system_score_gemma":0.000088731715,"threshold_uncertainty_score":0.35954762},"labels":[],"label_agreement":null},{"id":"W2206213513","doi":"10.1093/bioinformatics/btx215","title":"A Bayesian group sparse multi-task regression model for imaging genetics","year":2017,"lang":"en","type":"preprint","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of Victoria","funders":"National Institute on Aging; National Institutes of Health","keywords":"Imaging genetics; Computer science; Bayesian probability; Neuroimaging; Estimator; Inference; Bayesian inference; Artificial intelligence; Bayesian hierarchical modeling; Point estimation; Machine learning; Pattern recognition (psychology); Statistics; Mathematics; Biology","score_opus":0.04123079165782697,"score_gpt":0.31617125678560093,"score_spread":0.274940465127774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2206213513","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016578069,0.0015453743,0.97863334,0.0003124699,0.0007471184,0.0009446825,0.0006256617,0.00003440124,0.0005788784],"genre_scores_gemma":[0.40117636,0.0017015077,0.5914337,0.0005445028,0.0004611717,0.00022745637,0.0030949863,0.00007493238,0.0012853777],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980347,0.00004844642,0.0007699031,0.0004457135,0.00015652968,0.0005446661],"domain_scores_gemma":[0.99717903,0.000026877547,0.0010387823,0.0013672527,0.0002253481,0.000162713],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006045176,0.00044386357,0.0004921998,0.00008696965,0.0003548487,0.00011781609,0.0007282348,0.00074797374,0.0000027972535],"category_scores_gemma":[0.00046916518,0.00040596194,0.0003524773,0.000020526844,0.00012681955,0.000006443584,0.0010633157,0.00028008258,0.000009637052],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005217896,0.0011261363,0.08304188,0.0046167537,0.0017583641,0.000011995157,0.0047796257,0.29604083,0.023416866,0.00044646586,0.32760918,0.25663012],"study_design_scores_gemma":[0.0007657929,0.000057751997,0.0013410775,0.00010313593,0.00010057865,0.0000067917586,0.00008463234,0.986483,0.0002533265,0.00095675443,0.009351361,0.00049581856],"about_ca_topic_score_codex":0.000015300782,"about_ca_topic_score_gemma":0.00005488355,"teacher_disagreement_score":0.69044214,"about_ca_system_score_codex":0.000053384967,"about_ca_system_score_gemma":0.00027204058,"threshold_uncertainty_score":0.99983925},"labels":[],"label_agreement":null},{"id":"W2215244420","doi":"10.1093/bioinformatics/btv430","title":"Statistically identifying tumor suppressors and oncogenes from pan-cancer genome-sequencing data","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Ferroptosis and cancer prognosis","field":"Medicine","cited_by":67,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Cancer Institute; National Institutes of Health; Canadian Institutes of Health Research; Alvin J. Siteman Cancer Center","keywords":"Gene; Cancer; Biology; Genome; Suppressor; Genetics; Computational biology; Function (biology); Mutation","score_opus":0.15881024992191645,"score_gpt":0.3492056189539231,"score_spread":0.19039536903200666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2215244420","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9705674,0.0060451133,0.0166053,0.0006732978,0.0005339368,0.0006245761,0.0020794747,0.00013951627,0.002731372],"genre_scores_gemma":[0.83934265,0.0012780617,0.15610987,0.0017097152,0.00041190334,0.00004363084,0.0008993201,0.000043200926,0.0001616598],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99875027,0.000015875401,0.00042588662,0.00019006588,0.00037384478,0.00024404701],"domain_scores_gemma":[0.9988936,0.00005634407,0.00013726314,0.0005278223,0.00012317779,0.0002617592],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025032295,0.00015120964,0.0002934417,0.00005784463,0.00006211875,0.00010775357,0.00021337673,0.000052400766,0.000147841],"category_scores_gemma":[0.0001919394,0.00012270281,0.000024300987,0.00010493925,0.00008465669,0.0004079475,0.0002906795,0.00011556244,0.000057168625],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012111586,0.000496695,0.26296774,0.0051788324,0.0020956984,0.00031501523,0.042515755,0.00014861915,0.022598326,0.0011051188,0.105400555,0.5559665],"study_design_scores_gemma":[0.015566178,0.0015486312,0.23162057,0.0029806802,0.0037452271,0.00031306277,0.045031536,0.4408302,0.02030179,0.0017587848,0.23336953,0.002933811],"about_ca_topic_score_codex":0.00045233342,"about_ca_topic_score_gemma":0.00007352772,"teacher_disagreement_score":0.5530327,"about_ca_system_score_codex":0.000119091594,"about_ca_system_score_gemma":0.00032046787,"threshold_uncertainty_score":0.5003675},"labels":[],"label_agreement":null},{"id":"W2227918652","doi":"10.1093/bioinformatics/btv724","title":"Sequence database versioning for command line and Galaxy bioinformatics servers","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Agency of Canada; University of British Columbia","funders":"Genome Canada","keywords":"Computer science; Server; Sequence (biology); Sequence database; Database; Line (geometry); Software versioning; Software; Computational biology; Programming language; Operating system; Biology; Genetics; Gene; Mathematics","score_opus":0.052223927870846086,"score_gpt":0.27682404881970574,"score_spread":0.22460012094885964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2227918652","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95699745,0.0015942801,0.036151048,0.00031603032,0.00058174407,0.00079060206,0.000681169,0.000021690905,0.0028659885],"genre_scores_gemma":[0.75066406,0.0009571937,0.24630779,0.00078791816,0.00022134584,0.000031869728,0.0007383906,0.000029331395,0.00026211393],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992409,0.000008683982,0.0002968776,0.000110887326,0.000111137095,0.00023152314],"domain_scores_gemma":[0.99926984,0.00002284543,0.0001251285,0.0002808952,0.00014606165,0.00015522397],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028357946,0.0001580231,0.00015069376,0.000039511186,0.00015275046,0.000047768044,0.00015139773,0.000085826825,0.0000011007121],"category_scores_gemma":[0.00014414854,0.00014202275,0.000044141645,0.00005538552,0.00009595943,0.000007244482,0.000244594,0.000048768485,0.000007190737],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0037431102,0.0007361183,0.07662441,0.008853536,0.003284586,0.000025378531,0.040233254,0.013687738,0.27039993,0.008704277,0.35905227,0.2146554],"study_design_scores_gemma":[0.01093917,0.0036329567,0.00198781,0.00021190303,0.00030544345,0.00018782822,0.01381371,0.2063477,0.08171674,0.00073259906,0.6780138,0.002110335],"about_ca_topic_score_codex":0.000009725325,"about_ca_topic_score_gemma":0.0000148885965,"teacher_disagreement_score":0.31896153,"about_ca_system_score_codex":0.00001530484,"about_ca_system_score_gemma":0.00007585616,"threshold_uncertainty_score":0.5791519},"labels":[],"label_agreement":null},{"id":"W2232721574","doi":"10.1093/bioinformatics/btv504","title":"JBASE: Joint Bayesian Analysis of Subphenotypes and Epistasis","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Hospital for Sick Children; University of Toronto","funders":"Canadian Institutes of Health Research; Sickkids Research Institute; Hospital for Sick Children; Natural Sciences and Engineering Research Council of Canada; Instituto Mexicano del Seguro Social; Instituto de Seguriidad y Servicios Sociales de los Trabadores del Estado; Consejo Nacional de Ciencia y Tecnología","keywords":"Epistasis; Heritability; Genome-wide association study; Genotyping; Bayesian probability; Biology; Sample size determination; Genetic association; Computational biology; Genetics; Genotype; Missing heritability problem; Penetrance; Evolutionary biology; Phenotype; Genetic variants; Computer science; Statistics; Gene; Artificial intelligence; Mathematics; Single-nucleotide polymorphism","score_opus":0.024990506030581467,"score_gpt":0.26428429347428606,"score_spread":0.23929378744370458,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2232721574","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95080876,0.000480977,0.045645215,0.00021083571,0.00006101031,0.00008626744,0.000071880466,0.000007354672,0.0026276996],"genre_scores_gemma":[0.9705375,0.00011006285,0.028864142,0.00017242495,0.000025189436,0.000003157781,0.00017867597,0.000004727621,0.000104146406],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.999346,0.000032818367,0.00032966552,0.00008362284,0.000078377416,0.00012949409],"domain_scores_gemma":[0.9994029,0.000013963468,0.00017232569,0.00021229334,0.00010671387,0.000091824164],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003757631,0.000078854566,0.0002191405,0.0000976719,0.00002672553,0.000007229169,0.000063260086,0.000099152574,0.000008819971],"category_scores_gemma":[0.00029244454,0.000068965914,0.000073776006,0.00018735015,0.000064212385,0.0000027889935,0.00006501226,0.000027803273,0.0000032634427],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012633261,0.00024216816,0.89437705,0.00021836761,0.0051935455,0.0000019454967,0.004492567,0.0075420435,0.010259493,0.0025837326,0.03319975,0.041762974],"study_design_scores_gemma":[0.0019051156,0.0011000094,0.7569336,0.00002142683,0.0022987158,0.000016186268,0.0043536164,0.17397052,0.007533313,0.001151179,0.049843043,0.0008732305],"about_ca_topic_score_codex":0.000037933343,"about_ca_topic_score_gemma":0.00005501589,"teacher_disagreement_score":0.16642848,"about_ca_system_score_codex":0.000009299786,"about_ca_system_score_gemma":0.000052457373,"threshold_uncertainty_score":0.28123483},"labels":[],"label_agreement":null},{"id":"W2235818404","doi":"10.1093/bioinformatics/btv535","title":"Group and sparse group partial least square approaches applied in genomics context","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Context (archaeology); Multivariate statistics; Computational biology; Relevance (law); Computer science; Genomics; SNP; Multivariate analysis; Omics; Data mining; Biology; Bioinformatics; Machine learning; Gene; Genome; Genetics; Single-nucleotide polymorphism; Genotype","score_opus":0.05526268856140494,"score_gpt":0.2367565548618991,"score_spread":0.18149386630049413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2235818404","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9731976,0.0008482833,0.015589117,0.0001676203,0.00024429618,0.0005456776,0.000023839815,0.000027384925,0.009356192],"genre_scores_gemma":[0.99634284,0.00008516733,0.0029257478,0.00023263643,0.000105936306,0.000044408716,0.00018955095,0.000011656627,0.00006204424],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99929756,0.000017875404,0.00026276082,0.00014934695,0.00010382423,0.00016865741],"domain_scores_gemma":[0.9995276,0.0000033897695,0.000099108314,0.00023074586,0.000018336728,0.00012082191],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018936231,0.00012219134,0.00011696394,0.0000475841,0.000033866334,0.000038307116,0.00010825314,0.00013116731,0.0000029380078],"category_scores_gemma":[0.000015682504,0.0001122956,0.000024972254,0.0000676061,0.00006439744,0.000008901417,0.00008963562,0.00006543956,0.000013702852],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019423079,0.0008327207,0.018479327,0.00059690815,0.0001458706,0.000004994169,0.013868959,0.0007656208,0.30125085,0.02908114,0.036032517,0.5969988],"study_design_scores_gemma":[0.009512837,0.000955536,0.010268421,0.00008431087,0.00006081441,0.000056342968,0.038997006,0.032891404,0.12210867,0.0008982089,0.78253967,0.0016267971],"about_ca_topic_score_codex":0.000006248353,"about_ca_topic_score_gemma":0.000039889157,"teacher_disagreement_score":0.7465071,"about_ca_system_score_codex":0.000025795818,"about_ca_system_score_gemma":0.000049388014,"threshold_uncertainty_score":0.45792818},"labels":[],"label_agreement":null},{"id":"W2256500242","doi":"10.1093/bioinformatics/btv763","title":"Sampletrees and Rsampletrees: sampling gene genealogies conditional on SNP genotype data","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Michael Smith Health Research BC","keywords":"R package; Computer science; Documentation; Markov chain Monte Carlo; Source code; Code (set theory); SNP; Genotype; Markov chain; Data mining; Monte Carlo method; Programming language; Statistics; Biology; Genetics; Gene; Single-nucleotide polymorphism; Mathematics","score_opus":0.09098278476994492,"score_gpt":0.3176090273950153,"score_spread":0.22662624262507036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2256500242","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.680143,0.00068229303,0.31316042,0.0014577076,0.00028253978,0.0002787414,0.0028364623,0.00004927048,0.0011095745],"genre_scores_gemma":[0.85264635,0.0016908539,0.13993335,0.0016064051,0.00043877406,0.000016002574,0.0033781806,0.000025524192,0.0002645351],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99895954,0.000036527603,0.00034448403,0.00025332885,0.00012315653,0.00028293525],"domain_scores_gemma":[0.99889016,0.00016220052,0.00015757473,0.00063724455,0.00006943199,0.00008337852],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032951476,0.00015867734,0.00016964655,0.00005333906,0.00013952133,0.000024194043,0.00030648697,0.00015647932,0.00003493796],"category_scores_gemma":[0.00076803914,0.00011052325,0.00003572114,0.000048060145,0.00013106847,0.000011366111,0.00034122873,0.000046329445,0.000053585158],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034539145,0.00033966303,0.23889537,0.00020409709,0.0012352178,0.0000054791176,0.00052322034,0.0009510468,0.2014864,0.010627539,0.18375117,0.36163542],"study_design_scores_gemma":[0.0027344627,0.0012111192,0.4859733,0.0000655457,0.00010822198,0.000090096975,0.00048296546,0.0039462056,0.007918033,0.0056725754,0.4905693,0.0012281928],"about_ca_topic_score_codex":0.000012879548,"about_ca_topic_score_gemma":0.00003527189,"teacher_disagreement_score":0.36040723,"about_ca_system_score_codex":0.00001790268,"about_ca_system_score_gemma":0.00006524144,"threshold_uncertainty_score":0.45070076},"labels":[],"label_agreement":null},{"id":"W2256795974","doi":"10.1093/bioinformatics/btw045","title":"Predicting physiologically relevant SH3 domain mediated protein–protein interactions in yeast","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Institute of General Medical Sciences; Canadian Institutes of Health Research","keywords":"Computational biology; Protein–protein interaction; Protein sequencing; Computer science; Peptide library; SH3 domain; Biology; Peptide sequence; Genetics; Signal transduction; Gene","score_opus":0.009898811290404376,"score_gpt":0.22567551340616274,"score_spread":0.21577670211575836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2256795974","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9708821,0.000057295365,0.022165446,0.0004357794,0.00015434688,0.00070998014,0.00009406884,0.00004752136,0.0054534497],"genre_scores_gemma":[0.9861957,0.00004577972,0.012337461,0.00023630055,0.00019000501,0.000088589535,0.00011277729,0.000020016074,0.00077341555],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99856937,0.000030162477,0.00066757953,0.00017504735,0.00015287321,0.00040497797],"domain_scores_gemma":[0.99915797,0.00002145476,0.00025856783,0.00038111323,0.00006626916,0.000114638],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030821704,0.00021320672,0.00019813313,0.00007768518,0.00008127894,0.000035382516,0.00026707308,0.00016658413,0.000044688164],"category_scores_gemma":[0.00015974071,0.00014095899,0.000089932095,0.00013167092,0.00010089059,0.000026999607,0.0002013753,0.00015500467,0.00013509838],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020058051,0.00012424805,0.0014957961,0.000104663326,0.00007316175,0.0000041543126,0.0004140495,0.00004541154,0.96812606,0.001411454,0.0013735933,0.02662681],"study_design_scores_gemma":[0.024733733,0.0052084695,0.040855132,0.0056502605,0.00012165599,0.0003358755,0.0062368265,0.06627662,0.29974478,0.04277927,0.50074303,0.007314356],"about_ca_topic_score_codex":0.000008610773,"about_ca_topic_score_gemma":0.00006467367,"teacher_disagreement_score":0.6683813,"about_ca_system_score_codex":0.000046852183,"about_ca_system_score_gemma":0.00006904193,"threshold_uncertainty_score":0.5748141},"labels":[],"label_agreement":null},{"id":"W2261245081","doi":"10.1093/bioinformatics/btv755","title":"simDEF: definition-based semantic similarity measure of gene ontology terms for functional similarity analysis of genes","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Semantic similarity; Computer science; Similarity (geometry); Similarity measure; Cosine similarity; Correlation; Measure (data warehouse); Data mining; Artificial intelligence; Natural language processing; Information retrieval; Theoretical computer science; Mathematics; Pattern recognition (psychology); Image (mathematics)","score_opus":0.04728626949081537,"score_gpt":0.2517290138241195,"score_spread":0.20444274433330412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2261245081","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22752929,0.00059895887,0.7673666,0.00015112365,0.0003789771,0.00059978175,0.0011206886,0.000021575786,0.0022329993],"genre_scores_gemma":[0.93754554,0.00002863725,0.059564434,0.0003965758,0.00008855989,0.000022843671,0.002317514,0.000014688629,0.000021225123],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984478,0.000031945743,0.0008429365,0.00015164142,0.0002613074,0.00026438636],"domain_scores_gemma":[0.9982621,0.00006400994,0.000534795,0.0004718512,0.0005394865,0.00012774381],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005992992,0.00020639633,0.00048124912,0.00019499465,0.000064202446,0.000015162665,0.00022279937,0.00032580455,0.000011333434],"category_scores_gemma":[0.00016385895,0.0001894559,0.0003618332,0.00029889334,0.00016427154,0.000012095424,0.000060926934,0.00008059691,0.0000019159636],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0068341955,0.003330583,0.27180913,0.0057400037,0.023580017,0.0000061833443,0.003987197,0.45661053,0.11447909,0.013265626,0.051538415,0.048819043],"study_design_scores_gemma":[0.004748265,0.0013385367,0.011852194,0.00005194057,0.0029706236,0.000013007392,0.0006538444,0.8950941,0.072453976,0.0018416748,0.0080776485,0.0009042017],"about_ca_topic_score_codex":0.000018903884,"about_ca_topic_score_gemma":0.00014959146,"teacher_disagreement_score":0.71001625,"about_ca_system_score_codex":0.000024307465,"about_ca_system_score_gemma":0.00028191326,"threshold_uncertainty_score":0.7725787},"labels":[],"label_agreement":null},{"id":"W2261944919","doi":"10.1093/bioinformatics/btv723","title":"PharmacoGx: an R package for analysis of large pharmacogenomic datasets","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":299,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children; Montreal Clinical Research Institute; Institute of Cancer Research; Ontario Institute for Cancer Research; University Health Network; University of Toronto; Princess Margaret Cancer Centre","funders":"Ontario Institute for Cancer Research; Fondation Brain Canada; Canadian Institutes of Health Research; Cancer Research Society","keywords":"Pharmacogenomics; Computer science; R package; Drug response; Source code; Cancer cell lines; Data science; Data mining; Open source; Realization (probability); Precision medicine; Software; Drug; Bioinformatics; Cancer; Medicine; Biology; Pharmacology; Programming language","score_opus":0.04707972317749436,"score_gpt":0.36029830260763024,"score_spread":0.31321857943013587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2261944919","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89407325,0.00020579433,0.09776591,0.00006122491,0.00017836082,0.00028754785,0.006977583,0.000011621516,0.00043871222],"genre_scores_gemma":[0.95900995,0.00007711874,0.02461462,0.0006035496,0.000104800114,0.0000221899,0.015478039,0.000011759214,0.00007799462],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990977,0.000045617737,0.00040902695,0.00012578307,0.00008365092,0.00023819318],"domain_scores_gemma":[0.9991306,0.00002146604,0.0002471565,0.00032915917,0.00012932399,0.00014231443],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00071364443,0.00010914452,0.00024391963,0.000103843,0.000044351527,0.000008585373,0.00020865338,0.000098810895,0.00001770974],"category_scores_gemma":[0.00016327204,0.000101406855,0.00013095929,0.0001760232,0.000031776504,0.00000838564,0.0000780322,0.00003259439,0.000008143728],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007280416,0.0012966198,0.124609016,0.00027866405,0.010288923,0.0000020067653,0.0032787153,0.007189533,0.2668337,0.0008099534,0.5643791,0.020305734],"study_design_scores_gemma":[0.007038737,0.0013606397,0.017496262,0.0000072105354,0.0041747196,0.00000814817,0.0026863213,0.37803674,0.08469236,0.00018839313,0.5033684,0.0009420743],"about_ca_topic_score_codex":0.0000076634515,"about_ca_topic_score_gemma":0.000019138013,"teacher_disagreement_score":0.3708472,"about_ca_system_score_codex":0.000014299566,"about_ca_system_score_gemma":0.00008459596,"threshold_uncertainty_score":0.41352516},"labels":[],"label_agreement":null},{"id":"W2269649163","doi":"10.1093/bioinformatics/btw252","title":"Classifying and segmenting microscopy images with deep multiple instance learning","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":449,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Nvidia","keywords":"Pooling; Artificial intelligence; Convolutional neural network; Computer science; Pattern recognition (psychology); Segmentation; Deep learning; Feature (linguistics); Microscopy; Pixel; Contextual image classification; Machine learning; Computer vision; Image (mathematics)","score_opus":0.005466362266401763,"score_gpt":0.23233109526310197,"score_spread":0.2268647329967002,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2269649163","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6323153,0.00043037458,0.36278808,0.00005139917,0.000010344776,0.00014523634,0.000002717309,0.000068395,0.004188184],"genre_scores_gemma":[0.8870393,0.00050139206,0.11151325,0.00013556979,0.000034915374,0.000009361403,0.000018385765,0.00001786079,0.0007299411],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993795,0.0000151203085,0.00019225261,0.00013634664,0.0000854042,0.00019137023],"domain_scores_gemma":[0.99954224,0.000019312985,0.00013501562,0.00019610382,0.00006141303,0.00004591305],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001328838,0.00012146028,0.000108811335,0.000042692234,0.00010377624,0.00005503358,0.00008999562,0.00006410146,0.0000054710335],"category_scores_gemma":[0.00010046371,0.00008007123,0.000030296602,0.000059958806,0.00009892211,0.000022183953,0.00010944265,0.000054865326,0.000005964717],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023165068,0.000010203844,0.038024336,0.000042812022,0.000037042588,0.0000013980251,0.00009950177,0.0000048661345,0.9302178,0.0000036548468,0.00067431363,0.030860906],"study_design_scores_gemma":[0.00054462306,0.00014117942,0.0010653635,0.00007593694,0.000023827966,0.000018173978,0.00032723768,0.0015204509,0.97331625,0.00000513125,0.022741005,0.00022083861],"about_ca_topic_score_codex":0.0000029326868,"about_ca_topic_score_gemma":0.0000189929,"teacher_disagreement_score":0.25472406,"about_ca_system_score_codex":0.000011866026,"about_ca_system_score_gemma":0.00001841204,"threshold_uncertainty_score":0.326521},"labels":[],"label_agreement":null},{"id":"W2287141830","doi":"10.1093/bioinformatics/btw105","title":"ecceTERA: comprehensive gene tree-species tree reconciliation using parsimony","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":115,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Tree (set theory); Tree rearrangement; Phylogenetic tree; Biology; Maximum parsimony; Binary tree; Gene; Computer science; Computational biology; Phylogenetics; Genetic algorithm; Evolutionary biology; Algorithm; Genetics; Mathematics; Combinatorics; Clade","score_opus":0.0399052319189952,"score_gpt":0.24245713169802435,"score_spread":0.20255189977902915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2287141830","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98719305,0.00060217513,0.008404658,0.00013549556,0.0003078442,0.00017291658,0.00006911287,0.000007916696,0.003106818],"genre_scores_gemma":[0.9819666,0.0010499349,0.015720315,0.00031317936,0.00028494315,0.000008395049,0.000036194542,0.000017602495,0.00060280546],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991495,0.000019370245,0.00032706073,0.00015072996,0.00011188197,0.00024143074],"domain_scores_gemma":[0.9993232,0.000021767059,0.00015373933,0.00029909998,0.00013942148,0.00006276413],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000683837,0.00017092291,0.00016745749,0.000041040967,0.000107607564,0.000025121833,0.00014446839,0.000104304585,0.000011555883],"category_scores_gemma":[0.000038365266,0.0001228791,0.00009211883,0.00005278572,0.000085832486,0.000003499525,0.00012250927,0.000028051747,0.000026176438],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003652081,0.000018282639,0.003152181,0.000020727133,0.000099835954,7.077641e-7,0.00022268832,0.00006270185,0.96678126,0.00006934911,0.0018794881,0.027656239],"study_design_scores_gemma":[0.002499849,0.0005937617,0.04877183,0.00006104968,0.00009363087,0.000041700336,0.0008076269,0.0037790874,0.7100931,0.00027118812,0.23208313,0.0009040552],"about_ca_topic_score_codex":0.0000049216646,"about_ca_topic_score_gemma":0.000028303164,"teacher_disagreement_score":0.25668818,"about_ca_system_score_codex":0.000032767068,"about_ca_system_score_gemma":0.00004925936,"threshold_uncertainty_score":0.5010864},"labels":[],"label_agreement":null},{"id":"W2288603533","doi":"10.1093/bioinformatics/btv746","title":"Robust quantitative scratch assay","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; Princess Margaret Cancer Centre; University Health Network; University of Toronto","funders":"","keywords":"Artificial intelligence; Outlier; Computer science; Machine learning; Mathematics","score_opus":0.037231881019762096,"score_gpt":0.2895079666158675,"score_spread":0.25227608559610537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2288603533","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.086366616,0.0007372047,0.7094873,0.00036154847,0.00013025284,0.00044815117,0.000018635847,0.00018307073,0.2022672],"genre_scores_gemma":[0.35974434,0.00024087737,0.6306121,0.0022325478,0.00024837762,0.000037346326,0.0006560719,0.00005409924,0.006174238],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992778,0.000031783085,0.00024732656,0.000110257635,0.00016551247,0.00016732237],"domain_scores_gemma":[0.99920547,0.000008941902,0.00010512771,0.0003652383,0.00020880527,0.00010643758],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044255712,0.00011723241,0.00012065474,0.00005463679,0.000035257694,0.00004650443,0.00018806681,0.00010148145,0.000011224737],"category_scores_gemma":[0.00029457768,0.00010453618,0.000071103,0.00012695073,0.00006275031,0.000012216016,0.000118851625,0.000060810853,0.0001263435],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007659742,0.00013651332,0.0021440038,0.00005241024,0.00019514651,0.000006860368,0.00093127094,0.0005326641,0.040567376,0.0009781545,0.9461968,0.008182233],"study_design_scores_gemma":[0.0012663794,0.0011455258,0.00025559653,0.00003622405,0.00012703464,0.000030466212,0.0043747127,0.05760578,0.521503,0.000941982,0.4117016,0.0010117195],"about_ca_topic_score_codex":0.000014292263,"about_ca_topic_score_gemma":0.000021034557,"teacher_disagreement_score":0.5344952,"about_ca_system_score_codex":0.000018295474,"about_ca_system_score_gemma":0.00008488686,"threshold_uncertainty_score":0.42628616},"labels":[],"label_agreement":null},{"id":"W2307896283","doi":"10.1093/bioinformatics/btw031","title":"ELASPIC web-server: proteome-wide structure-based prediction of mutation effects on protein stability and binding affinity","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":82,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"UniProt; Web server; Computer science; Proteome; Computational biology; Protein domain; Domain (mathematical analysis); Homology modeling; Bioinformatics; Biology; Genetics; The Internet; World Wide Web; Mathematics","score_opus":0.007831043950518006,"score_gpt":0.1995485839587797,"score_spread":0.1917175400082617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2307896283","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9863179,0.000027289947,0.012152369,0.00008296774,0.0001084584,0.00089819846,0.00020392494,0.000021015216,0.00018788168],"genre_scores_gemma":[0.99467516,0.000012105041,0.004988982,0.00008113718,0.000060077167,0.000033443346,0.00011491,0.000012698445,0.00002147066],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989535,0.00004321406,0.00046175727,0.00014452105,0.00018425143,0.00021275767],"domain_scores_gemma":[0.99912417,0.00005520114,0.00030999872,0.00034293014,0.00008408611,0.000083643616],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003110159,0.00018081308,0.00017588792,0.0000722789,0.00007864055,0.000024187033,0.00011484608,0.00020952738,0.000011219309],"category_scores_gemma":[0.00017617372,0.00012622486,0.00005935023,0.0000860505,0.00009481771,0.000021606924,0.00006220625,0.000082827544,0.0000051363236],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000462734,0.00010307939,0.008998854,0.0014137662,0.00011033083,0.000001026262,0.0002609186,0.00009200689,0.9296103,0.0002965502,0.00044993142,0.05820047],"study_design_scores_gemma":[0.0017306375,0.0010741676,0.005707574,0.00022338677,0.000020986607,0.0000028594054,0.000055642093,0.0039865305,0.9863047,0.00021082544,0.00048866094,0.00019403447],"about_ca_topic_score_codex":0.0000020734542,"about_ca_topic_score_gemma":0.0000098785995,"teacher_disagreement_score":0.058006436,"about_ca_system_score_codex":0.000034607114,"about_ca_system_score_gemma":0.00010314635,"threshold_uncertainty_score":0.51473004},"labels":[],"label_agreement":null},{"id":"W2318488401","doi":"10.1093/bioinformatics/btw155","title":"MOLGENIS/connect: a system for semi-automatic integration of heterogeneous phenotype data with applications in biobanks","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"Terveyden ja hyvinvoinnin laitos; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; European Commission","keywords":"Computer science; Biobank; Documentation; Source code; Data integration; Data mining; Terminology; Open source; Information retrieval; Ontology; Categorical variable; Task (project management); Data source; Matching (statistics); Software; Programming language; Machine learning; Bioinformatics","score_opus":0.024251684551665875,"score_gpt":0.2718240070330186,"score_spread":0.24757232248135275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2318488401","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2698311,0.00037166092,0.7278995,0.00012228049,0.00007220838,0.0008175446,0.0004921803,0.00005636889,0.0003371864],"genre_scores_gemma":[0.94889444,0.000025802012,0.050577644,0.000022618195,0.0000355315,0.000082575876,0.00031980302,0.000010124158,0.00003145228],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992594,0.000013226142,0.00033925902,0.00014597161,0.00009069026,0.00015142784],"domain_scores_gemma":[0.9991127,0.00005481177,0.00016406146,0.00056375307,0.00006538703,0.000039257236],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016510212,0.00010863724,0.00015962348,0.00005147535,0.000030411016,0.000009565361,0.0003113419,0.00012856648,0.0000019349916],"category_scores_gemma":[0.00011493485,0.0000623649,0.000028288285,0.00009546205,0.00010022037,0.0000074328464,0.000087547174,0.0000255193,0.0000036764116],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023894943,0.00024060566,0.0014552609,0.0015984734,0.00021060699,0.0000014641854,0.00065610185,0.000029161065,0.11168959,0.0014847459,0.0014451803,0.88094985],"study_design_scores_gemma":[0.011634702,0.0066776485,0.0024632313,0.0029009727,0.0004543382,0.00017909735,0.008241173,0.17194496,0.70247144,0.0007143833,0.08998843,0.0023296333],"about_ca_topic_score_codex":0.0000073536958,"about_ca_topic_score_gemma":0.00005393237,"teacher_disagreement_score":0.8786202,"about_ca_system_score_codex":0.000017887516,"about_ca_system_score_gemma":0.00006888766,"threshold_uncertainty_score":0.2543167},"labels":[],"label_agreement":null},{"id":"W2319614057","doi":"10.1093/bioinformatics/btw096","title":"Reaction Decoder Tool (RDT): extracting features from chemical reactions","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Microbial Metabolic Engineering and Bioproduction","field":"Biochemistry, Genetics and Molecular Biology","cited_by":108,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"","keywords":"Computer science; Software; Chemical reaction; Java; Task (project management); Chemistry; Programming language; Biochemistry","score_opus":0.0072915514519623185,"score_gpt":0.221542326067819,"score_spread":0.2142507746158567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2319614057","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97835726,0.00015488986,0.01910252,0.00028695902,0.0007603318,0.000120445555,0.00004832376,0.00007495399,0.0010943023],"genre_scores_gemma":[0.9724912,0.00032037322,0.023857877,0.00010756272,0.0013070621,0.000011134581,0.0001449978,0.00002136859,0.0017383918],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993396,0.000009597731,0.0002459139,0.00015023733,0.000087659944,0.00016702256],"domain_scores_gemma":[0.99950856,0.000009479409,0.00009513535,0.00028637864,0.000054074586,0.000046363773],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000110132714,0.00012167254,0.00009153162,0.000033387612,0.000054030144,0.000021987771,0.00008474196,0.00016346893,0.000020239893],"category_scores_gemma":[0.0002502344,0.000086346576,0.00006276519,0.00005552235,0.000027490665,0.000019226423,0.000036532143,0.0000758342,0.00005311402],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021717102,0.00001643504,0.000055537133,0.000009238869,0.00002351397,1.680992e-7,0.000027175838,0.000003518746,0.9603862,0.00003193308,0.00458943,0.034835137],"study_design_scores_gemma":[0.00023961552,0.000020725993,0.0011328484,0.000028910277,0.00001593588,0.000036083722,0.00004032244,0.00003846461,0.8217174,0.000025570944,0.17654277,0.0001613768],"about_ca_topic_score_codex":0.000024927003,"about_ca_topic_score_gemma":0.0000048063825,"teacher_disagreement_score":0.17195335,"about_ca_system_score_codex":0.000021412661,"about_ca_system_score_gemma":0.000023406446,"threshold_uncertainty_score":0.3521111},"labels":[],"label_agreement":null},{"id":"W2323614149","doi":"10.1093/bioinformatics/btw129","title":"mDCC_tools: characterizing multi-modal atomic motions in molecular dynamics trajectories","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Genetics; Japan Society for the Promotion of Science; Research Organization of Information and Systems","keywords":"Modal; Molecular dynamics; Computer science; Dynamics (music); Biological system; Physics; Statistical physics; Classical mechanics; Chemistry; Biology; Acoustics; Quantum mechanics","score_opus":0.007779964906881822,"score_gpt":0.23137124298156164,"score_spread":0.22359127807467982,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2323614149","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7505145,0.00007281476,0.24820092,0.00020599163,0.00017947739,0.00023777531,0.00014593665,0.000029309464,0.0004132612],"genre_scores_gemma":[0.96816856,0.00008871492,0.030967414,0.00023117107,0.00006419643,0.000025206948,0.00018682306,0.00002477032,0.00024313625],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99900365,0.000022843209,0.00036307558,0.00016795666,0.00011510063,0.00032734967],"domain_scores_gemma":[0.9993915,0.000008288766,0.00011794786,0.00035806096,0.000048896818,0.00007529375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011954767,0.0001897599,0.00016165155,0.000081623286,0.000052986226,0.000032344964,0.00022051645,0.00020242967,0.000006849267],"category_scores_gemma":[0.00010004994,0.00014455317,0.000085684434,0.000104998595,0.00008108275,0.000022603484,0.00010974173,0.0000818281,0.000019292178],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008704481,0.00013116431,0.015350385,0.00014989782,0.00010842404,0.00001868792,0.00056383864,0.00008530409,0.92312586,0.0083698435,0.00011650045,0.05189305],"study_design_scores_gemma":[0.014504732,0.0012500015,0.1435955,0.00067588175,0.00015712097,0.0004149996,0.0015782187,0.15491004,0.65076864,0.0048697456,0.022580761,0.0046943217],"about_ca_topic_score_codex":0.000009716443,"about_ca_topic_score_gemma":0.00009346734,"teacher_disagreement_score":0.2723572,"about_ca_system_score_codex":0.000090979745,"about_ca_system_score_gemma":0.00011839972,"threshold_uncertainty_score":0.58947074},"labels":[],"label_agreement":null},{"id":"W2333196156","doi":"10.1093/bioinformatics/btw178","title":"Cell-free DNA fragment-size distribution analysis for non-invasive prenatal CNV prediction","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Prenatal Screening and Diagnostics","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Hospital for Sick Children; University of Toronto","funders":"","keywords":"Copy-number variation; Single-nucleotide polymorphism; SNP; Cell-free fetal DNA; Genome; Biology; Genetics; SNP array; Human genome; Computational biology; Prenatal diagnosis; Fetus; Gene; Genotype; Pregnancy","score_opus":0.01048325492405987,"score_gpt":0.2294190667248588,"score_spread":0.2189358118007989,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2333196156","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29041323,0.00006287234,0.6976815,0.00074155827,0.00030342935,0.0010146913,0.0069142445,0.00021498471,0.0026535061],"genre_scores_gemma":[0.98171914,0.000098056786,0.015405346,0.00015100407,0.0001980227,0.00007139121,0.0017037184,0.00001383715,0.00063949643],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99873745,0.000009295448,0.0004604696,0.0001485972,0.000331258,0.00031291865],"domain_scores_gemma":[0.99825126,0.0006471153,0.00020225502,0.000511759,0.00017924131,0.0002083615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018684434,0.00017281999,0.0002874362,0.0000751112,0.0001111978,0.000030336469,0.00015495806,0.00015519922,0.000046564168],"category_scores_gemma":[0.0020032432,0.00011488553,0.00023758957,0.0003063862,0.00006382149,0.0002735974,0.00009546253,0.00007241834,0.000057263966],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003083611,0.0018486871,0.35474607,0.0053378674,0.005819598,0.00005753053,0.0032731728,0.000476012,0.0071932124,0.002226723,0.5386549,0.07728259],"study_design_scores_gemma":[0.03795755,0.005368026,0.47173542,0.0025609052,0.012610866,0.00009500809,0.0016949093,0.13194819,0.30938184,0.0012153623,0.023673683,0.0017582579],"about_ca_topic_score_codex":0.000012754371,"about_ca_topic_score_gemma":0.0000069420134,"teacher_disagreement_score":0.6913059,"about_ca_system_score_codex":0.00014231031,"about_ca_system_score_gemma":0.000102050035,"threshold_uncertainty_score":0.4684896},"labels":[],"label_agreement":null},{"id":"W2334167823","doi":"10.1093/bioinformatics/btw134","title":"GSP: a web-based platform for designing genome-specific primers in polyploids","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Agriculture and Agri-Food Canada","funders":"","keywords":"Genome; Upload; Polyploid; Primer (cosmetics); Biology; Computational biology; Sequence (biology); Web server; Computer science; Source code; World Wide Web; Genetics; The Internet; Gene; Programming language","score_opus":0.022221481360277615,"score_gpt":0.2309668739902974,"score_spread":0.2087453926300198,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2334167823","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91638553,0.0012214513,0.07970543,0.00020967046,0.00023653568,0.00073474686,0.0001489329,0.0000135952405,0.0013441268],"genre_scores_gemma":[0.9456323,0.0003886122,0.053296838,0.00026348786,0.0001208524,0.00007464428,0.000037599028,0.000025153999,0.00016055664],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990806,0.000007497031,0.00033869737,0.00015550919,0.000085401225,0.00033230602],"domain_scores_gemma":[0.9994792,0.00003973169,0.00010330929,0.0002575073,0.000055632318,0.000064670145],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020801331,0.00016393996,0.00015689559,0.00008085579,0.00007208712,0.000019560755,0.00017549837,0.00011318913,0.000006495391],"category_scores_gemma":[0.000042811716,0.00012079012,0.00008951288,0.000069861075,0.00006701642,0.0000023821951,0.00006253785,0.00003082691,0.000014108535],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015517764,0.000039359922,0.002361697,0.000053686144,0.00004713021,5.402453e-7,0.00019590626,0.00013586225,0.9799919,0.00014710636,0.0011929666,0.015678627],"study_design_scores_gemma":[0.007971303,0.0011604786,0.011089301,0.00009488558,0.00003324171,0.000008307779,0.0006612533,0.00242528,0.4324268,0.0003011723,0.54279625,0.0010316902],"about_ca_topic_score_codex":0.0000018756995,"about_ca_topic_score_gemma":0.000011801639,"teacher_disagreement_score":0.54756516,"about_ca_system_score_codex":0.00003568415,"about_ca_system_score_gemma":0.000113609756,"threshold_uncertainty_score":0.4925678},"labels":[],"label_agreement":null},{"id":"W2336321619","doi":"10.1093/bioinformatics/btw053","title":"Sprites: detection of deletions from sequencing data by re-aligning split reads","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"National Natural Science Foundation of China","keywords":"Computer science; Reference genome; DNA sequencing; Computational biology; Biology; Genetics; Gene","score_opus":0.031238478506569654,"score_gpt":0.2468003291338725,"score_spread":0.21556185062730285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2336321619","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94425386,0.00094279356,0.052376807,0.0000877383,0.00014564644,0.00011873982,0.0010526469,0.000006942304,0.0010148017],"genre_scores_gemma":[0.9844594,0.00068057113,0.014369448,0.00007734467,0.00009324394,0.000004234722,0.00021508333,0.000010822399,0.00008985222],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992894,0.000014020954,0.00031241484,0.00014821353,0.00009012229,0.00014582927],"domain_scores_gemma":[0.9991005,0.000029476105,0.00015290568,0.00061062793,0.00006564969,0.000040826955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014655948,0.00010370954,0.00011743429,0.000023796358,0.000065504115,0.00001172884,0.00025719512,0.00008861725,0.0000074310997],"category_scores_gemma":[0.000120177094,0.00007839195,0.00003531203,0.000047067577,0.000062763036,0.000003912831,0.00025444166,0.000027186425,0.00001046822],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009056773,0.000006886712,0.0007426933,0.000013268341,0.000053017546,9.665506e-8,0.00011382411,0.000003611689,0.9847389,0.000013379966,0.001796886,0.012508372],"study_design_scores_gemma":[0.0004592065,0.00015413313,0.0010741582,0.000056617377,0.00004814888,0.0000033616925,0.00061601953,0.0010547808,0.939192,0.0001540663,0.05694892,0.00023857721],"about_ca_topic_score_codex":0.000078140874,"about_ca_topic_score_gemma":0.000053532505,"teacher_disagreement_score":0.055152033,"about_ca_system_score_codex":0.000017165228,"about_ca_system_score_gemma":0.000042103537,"threshold_uncertainty_score":0.3196731},"labels":[],"label_agreement":null},{"id":"W2336477031","doi":"10.1093/bioinformatics/btw227","title":"densityCut: an efficient and versatile topological approach for automatic clustering of biological data","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Cluster analysis; Computer science; Topological data analysis; Data mining; Topology (electrical circuits); Artificial intelligence; Algorithm; Mathematics","score_opus":0.06716936385813714,"score_gpt":0.27231245685480077,"score_spread":0.2051430929966636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2336477031","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66232353,0.00004395147,0.33709002,0.000020469595,0.000055730914,0.00018748388,0.00011748652,0.000013610994,0.00014770804],"genre_scores_gemma":[0.87517405,0.000041105945,0.124443896,0.000060979357,0.000049553342,0.000005523934,0.000204198,0.0000062951053,0.00001442554],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99930465,0.000020130648,0.00026535962,0.0001728898,0.000069609414,0.00016735334],"domain_scores_gemma":[0.9993798,0.00003205053,0.00008342938,0.00039784086,0.00003962664,0.0000672168],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023377214,0.00010693004,0.00015675458,0.000023065633,0.00005250311,0.000013901569,0.00025381375,0.00013999887,0.000004497357],"category_scores_gemma":[0.00011964404,0.00006490919,0.000034151937,0.00002722444,0.00015695985,0.000008253469,0.00019041097,0.000024829273,8.112195e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00075543055,0.0010156677,0.01255522,0.0010661543,0.00023442651,0.0000016534862,0.0012472363,0.0007547042,0.8194713,0.0011437993,0.0010639156,0.1606905],"study_design_scores_gemma":[0.0020633694,0.0014640411,0.0029421286,0.000040418166,0.000046739446,0.00003483981,0.0005197798,0.95152324,0.03917689,0.000056006607,0.0017481702,0.00038438235],"about_ca_topic_score_codex":0.000003569928,"about_ca_topic_score_gemma":0.0000032555845,"teacher_disagreement_score":0.95076853,"about_ca_system_score_codex":0.0000061019086,"about_ca_system_score_gemma":0.000022745291,"threshold_uncertainty_score":0.264692},"labels":[],"label_agreement":null},{"id":"W2337408142","doi":"10.1093/bioinformatics/btw211","title":"Partitioning and correlating subgroup characteristics from Aligned Pattern Clusters","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of Waterloo","funders":"","keywords":"A priori and a posteriori; Sequence alignment; Multiple sequence alignment; Biology; Class (philosophy); Similarity (geometry); Function (biology); Computational biology; Conserved sequence; Divergence (linguistics); Sequence (biology); In silico; Protein superfamily; Structural Classification of Proteins database; Rank (graph theory); Cluster analysis; Phylogenetic tree; Computer science; Artificial intelligence; Genetics; Protein structure; Peptide sequence; Mathematics; Gene; Combinatorics","score_opus":0.006556936634770645,"score_gpt":0.2177660405102531,"score_spread":0.21120910387548247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2337408142","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8116853,0.000073333766,0.1858615,0.00027873876,0.00030564997,0.00018174858,0.00014264538,0.00005746316,0.0014136093],"genre_scores_gemma":[0.9816289,0.00018904725,0.016615467,0.00076684606,0.00021535007,0.000010412999,0.00034703006,0.000025823743,0.00020113972],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99885917,0.00003240054,0.00051271624,0.00014806983,0.0001665648,0.00028105947],"domain_scores_gemma":[0.9991183,0.000068779314,0.00030547916,0.00033178818,0.000057265635,0.00011833439],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020029156,0.00019791757,0.00017329995,0.000043156717,0.00013646537,0.000077885816,0.00015612264,0.00016253309,0.000049904782],"category_scores_gemma":[0.00028215186,0.00014756418,0.000051125902,0.000046205212,0.00010268544,0.000027915223,0.00020360641,0.00006590096,0.000085276704],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009431229,0.000054572596,0.4238164,0.00022420149,0.00020229485,0.000005192598,0.0024698577,0.00003580058,0.030488597,0.0002195528,0.0055284235,0.53686076],"study_design_scores_gemma":[0.011034799,0.0020581775,0.40025157,0.0017555119,0.00038075756,0.00028628428,0.0031354192,0.35106954,0.040839154,0.0005423028,0.18407275,0.0045737503],"about_ca_topic_score_codex":0.000020124658,"about_ca_topic_score_gemma":0.000013756615,"teacher_disagreement_score":0.532287,"about_ca_system_score_codex":0.00001830405,"about_ca_system_score_gemma":0.000027851267,"threshold_uncertainty_score":0.60174924},"labels":[],"label_agreement":null},{"id":"W2346950316","doi":"10.1093/bioinformatics/btw228","title":"Drug repositioning based on comprehensive similarity measures and Bi-Random walk algorithm","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":470,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Program for New Century Excellent Talents in University; U.S. Food and Drug Administration; National Natural Science Foundation of China; Stowers Institute for Medical Research","keywords":"Similarity (geometry); Drug repositioning; Drug; Computer science; Disease; Random walk; Machine learning; Drug development; Data mining; Artificial intelligence; Mathematics; Medicine; Statistics; Pharmacology","score_opus":0.023641085473261738,"score_gpt":0.2691134950196628,"score_spread":0.24547240954640107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2346950316","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0055372193,0.000038976636,0.99086934,0.0016059668,0.00025724483,0.00018642333,0.00001952836,0.0001400158,0.0013452731],"genre_scores_gemma":[0.10843828,0.000014843004,0.88992476,0.0014937805,0.000051785868,0.0000111386325,0.000006207491,0.000008824815,0.000050379127],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985952,0.00014481077,0.00036343894,0.0001955812,0.00048833585,0.00021265114],"domain_scores_gemma":[0.99788696,0.0012590145,0.00016122729,0.00040226863,0.00018093125,0.0001095946],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050545606,0.00016220026,0.00019151876,0.00014997125,0.00019802366,0.00021309037,0.0003238339,0.00004509043,0.000004216943],"category_scores_gemma":[0.00017348371,0.000112610396,0.00006417168,0.00020888954,0.000080366,0.00072631607,0.00016746078,0.000089403824,0.00002620953],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004480107,0.00008355886,0.00024022572,0.00007579318,0.00004051007,0.000016628548,0.0013263888,0.009048631,0.0001354261,0.011154486,0.002175495,0.97565806],"study_design_scores_gemma":[0.0011462421,0.0000559922,0.002661139,0.00011450917,0.000007127051,0.000019669706,0.000032140393,0.9879351,0.0012377942,0.0042780344,0.002313572,0.00019864297],"about_ca_topic_score_codex":0.00000779712,"about_ca_topic_score_gemma":0.0000012300004,"teacher_disagreement_score":0.9788865,"about_ca_system_score_codex":0.00006381188,"about_ca_system_score_gemma":0.00010192237,"threshold_uncertainty_score":0.4592119},"labels":[],"label_agreement":null},{"id":"W2395270406","doi":"10.4018/978-1-4666-3604-0.ch029","title":"Biclustering of DNA Microarray Data","year":2013,"lang":"en","type":"book-chapter","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Biclustering; Computer science; Identification (biology); Microarray analysis techniques; Data mining; Computational biology; Microarray databases; Cluster analysis; Microarray; Biological data; Gene chip analysis; Bioinformatics; Artificial intelligence; Gene; Biology; Genetics","score_opus":0.038118952466101724,"score_gpt":0.2569467814462027,"score_spread":0.21882782898010097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2395270406","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006376953,0.0013747858,0.0070472388,0.000093672046,0.00053220417,0.00045260842,0.00044528185,0.000022769633,0.9893938],"genre_scores_gemma":[0.014259156,0.0037305797,0.027611721,0.00061577,0.0007526502,0.000020653812,0.008276505,0.00013588816,0.94459707],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99911684,0.0000043276955,0.00042632484,0.00018783915,0.00014753717,0.000117113756],"domain_scores_gemma":[0.9981662,0.000003825117,0.0003883444,0.0012940562,0.000089386434,0.000058165264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008715763,0.00018418972,0.00018246165,0.00006727921,0.000028266584,0.000021073321,0.0005584882,0.0003094289,0.0002076873],"category_scores_gemma":[0.000017476734,0.00016581568,0.0000630544,0.000014271745,0.00006609419,0.0000074846284,0.0004542962,0.000083715124,0.00013034344],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004176473,0.000027054566,0.000011554525,0.00077180634,0.00021189252,5.2724926e-7,0.00015809362,0.00001137838,0.45437366,0.0028693373,0.4671374,0.07438554],"study_design_scores_gemma":[0.00017550403,0.000054856388,0.000012051775,0.00010939989,0.000028283326,0.0000054600973,0.000029553286,0.0004103223,0.03433093,0.00010282744,0.9645174,0.00022341397],"about_ca_topic_score_codex":0.0000018419128,"about_ca_topic_score_gemma":0.0000021806347,"teacher_disagreement_score":0.49738002,"about_ca_system_score_codex":0.000010021619,"about_ca_system_score_gemma":0.000098006494,"threshold_uncertainty_score":0.6761767},"labels":[],"label_agreement":null},{"id":"W2418153904","doi":"10.1093/bioinformatics/btw337","title":"CAGEd-oPOSSUM: motif enrichment analysis from CAGE-derived TSSs","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Opossum; Perl; Transcription factor; DNA binding site; Computational biology; Biology; Gene; Promoter; Binding site; Motif (music); Computer science; Genetics; World Wide Web; Gene expression","score_opus":0.005895834575798081,"score_gpt":0.2108232657155318,"score_spread":0.20492743113973372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2418153904","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9270307,0.00013923543,0.0704527,0.00014031705,0.0001618947,0.00013873573,0.0002903804,0.000025267178,0.0016207771],"genre_scores_gemma":[0.98355925,0.00033565305,0.014419314,0.00024306194,0.00012069815,0.000011530964,0.000459094,0.000019805824,0.0008315763],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988741,0.000024518262,0.00042175862,0.00021179847,0.0001744708,0.00029330983],"domain_scores_gemma":[0.9989442,0.000020470516,0.00019382304,0.0006387297,0.00007503746,0.0001276928],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013032212,0.00020587909,0.00022795578,0.00008357989,0.000094218914,0.000051038267,0.00030470785,0.00016322984,0.000103949846],"category_scores_gemma":[0.000042853735,0.00014807173,0.00019994119,0.00015870544,0.00006709277,0.000008304289,0.00018194321,0.000047736063,0.00011088972],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000843344,0.00021081606,0.030478634,0.000070861126,0.0033482264,0.000009145567,0.0013386887,0.0010375984,0.92078084,0.0002724571,0.007935936,0.034432463],"study_design_scores_gemma":[0.0088533545,0.0012951049,0.14929974,0.00014627224,0.0034215215,0.000034736368,0.0033163773,0.090959154,0.59695995,0.0015628497,0.13974479,0.0044061844],"about_ca_topic_score_codex":0.00006041104,"about_ca_topic_score_gemma":0.00012572754,"teacher_disagreement_score":0.32382092,"about_ca_system_score_codex":0.000043974014,"about_ca_system_score_gemma":0.000061089624,"threshold_uncertainty_score":0.603819},"labels":[],"label_agreement":null},{"id":"W2420922808","doi":"10.1093/bioinformatics/btw280","title":"DFLpred: High-throughput prediction of disordered flexible linker regions in protein sequences","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":92,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Proteome; Linker; Computer science; Human proteome project; Sequence (biology); Intrinsically disordered proteins; Throughput; Domain (mathematical analysis); Computational biology; Protein domain; Biological system; Chemistry; Biology; Bioinformatics; Proteomics; Mathematics; Biochemistry","score_opus":0.010321845923509628,"score_gpt":0.22764567802067875,"score_spread":0.21732383209716913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2420922808","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8365309,0.00026617342,0.1588262,0.0005128076,0.00020563924,0.00080101955,0.00031876485,0.000052923875,0.0024855298],"genre_scores_gemma":[0.9786438,0.00021270073,0.020108318,0.00005646039,0.00007698707,0.00004095246,0.00011246111,0.000011802184,0.00073655625],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991229,0.00002055812,0.0003981413,0.0001307927,0.00013394721,0.0001936629],"domain_scores_gemma":[0.99937785,0.000007944979,0.00016758859,0.00034121802,0.00006326034,0.000042138996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011410316,0.00012633012,0.00014307753,0.00006286555,0.00003487147,0.000009973288,0.00016968788,0.00019580811,0.000009953663],"category_scores_gemma":[0.00008793424,0.000086700704,0.000052248113,0.0001215236,0.00012250847,0.000022045535,0.000083252504,0.000054760672,0.000006791903],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028106142,0.00015831256,0.0090435175,0.000414113,0.00012183007,0.0000024658202,0.0007070508,0.00025355403,0.916633,0.015021438,0.0023937586,0.05496991],"study_design_scores_gemma":[0.004213653,0.0015385622,0.0121695865,0.0006261717,0.000045251378,0.000034690762,0.0005865584,0.00342706,0.91761035,0.0237678,0.03519609,0.0007842189],"about_ca_topic_score_codex":0.000038105758,"about_ca_topic_score_gemma":0.00003920468,"teacher_disagreement_score":0.14211282,"about_ca_system_score_codex":0.000019792344,"about_ca_system_score_gemma":0.00009678954,"threshold_uncertainty_score":0.3535552},"labels":[],"label_agreement":null},{"id":"W2463091895","doi":"10.1093/bioinformatics/btw397","title":"ntHash: recursive nucleotide hashing","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":98,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"National Human Genome Research Institute; National Institutes of Health","keywords":"Hash function; Computer science; Expediting; Software; Data mining; Sequence (biology); Universal hashing; Theoretical computer science; Hash table; Biology; Genetics; Programming language","score_opus":0.017284746271392315,"score_gpt":0.23445768803110562,"score_spread":0.2171729417597133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2463091895","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015926304,0.000026099506,0.9890481,0.0009836768,0.00045979844,0.00007877625,0.000012463001,0.00017987547,0.007618563],"genre_scores_gemma":[0.03550022,0.00007414471,0.96289504,0.00075176725,0.00013476009,0.00000601741,0.000005565042,0.000010314966,0.00062217243],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99917096,0.000012976666,0.00024183227,0.000114817674,0.00022883376,0.00023057612],"domain_scores_gemma":[0.9990648,0.00009126456,0.000118412136,0.0005725132,0.000054478096,0.000098535136],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016575723,0.0000985333,0.00009833964,0.000062517436,0.00011874747,0.0001519373,0.0007825424,0.000043603373,0.000027330629],"category_scores_gemma":[0.000077744575,0.000057420526,0.00003933795,0.00013324399,0.000033271026,0.0019409138,0.00041764978,0.000051667583,0.0006562853],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034440766,0.000028368417,0.00014733238,0.00002059234,0.000011591921,0.00000807387,0.0013092723,0.0000054659067,0.0003509413,0.090192944,0.04403867,0.8638833],"study_design_scores_gemma":[0.0019866305,0.00030190515,0.002878503,0.0007247524,0.000014834663,0.0000920765,0.00034515947,0.31087983,0.009551945,0.025545554,0.64654464,0.0011341504],"about_ca_topic_score_codex":0.0000043204604,"about_ca_topic_score_gemma":7.269779e-7,"teacher_disagreement_score":0.86274916,"about_ca_system_score_codex":0.00003346915,"about_ca_system_score_gemma":0.000039511564,"threshold_uncertainty_score":0.84354395},"labels":[],"label_agreement":null},{"id":"W2467728588","doi":"10.1093/bioinformatics/btw382","title":"ChAsE: chromatin analysis and exploration tool","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; Canada's Michael Smith Genome Sciences Centre; Simon Fraser University; University of British Columbia","funders":"Canadian Institutes of Health Research","keywords":"Chromatin; Computer science; Computational biology; Biology; Genetics; DNA","score_opus":0.007374422358469707,"score_gpt":0.21430018004961965,"score_spread":0.20692575769114993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2467728588","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86290807,0.00006693907,0.13591908,0.00017131148,0.000043461332,0.00010046187,0.000045734672,0.000014032431,0.000730889],"genre_scores_gemma":[0.98309964,0.00033160075,0.015715739,0.000111942994,0.00006151866,0.000011930778,0.00012782853,0.000009617965,0.000530173],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994365,0.000009707068,0.00023586057,0.00010461689,0.000080352525,0.0001329642],"domain_scores_gemma":[0.99954957,0.000007910967,0.00010321302,0.00025258478,0.000040216564,0.000046529236],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011288767,0.0001003289,0.00010788343,0.000064927954,0.00005529549,0.00003396563,0.00008236532,0.00007983921,0.000018430575],"category_scores_gemma":[0.000041418465,0.00007024739,0.00005762242,0.000109487824,0.000042394156,0.000013016927,0.00007435301,0.00001739838,0.000021839054],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000780824,0.0001262008,0.021254834,0.0001941827,0.0016010521,0.0000028085951,0.0010254896,0.0001863132,0.7212062,0.0031790703,0.004390471,0.24675532],"study_design_scores_gemma":[0.008712562,0.002309222,0.14222208,0.00019518308,0.0022336878,0.00012263274,0.0020125792,0.26798308,0.46229663,0.004654784,0.10318635,0.004071199],"about_ca_topic_score_codex":0.000002119003,"about_ca_topic_score_gemma":0.000019298608,"teacher_disagreement_score":0.26779678,"about_ca_system_score_codex":0.000010302682,"about_ca_system_score_gemma":0.000022498743,"threshold_uncertainty_score":0.28646055},"labels":[],"label_agreement":null},{"id":"W2474973645","doi":"10.1093/bioinformatics/btw371","title":"deBGA: read alignment with de Bruijn graph-based seed and extension","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":105,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children; University of Toronto","funders":"","keywords":"De Bruijn graph; De Bruijn sequence; Computer science; Graph; Limiting; Theoretical computer science; Mathematics","score_opus":0.00835405773695894,"score_gpt":0.20520258990491902,"score_spread":0.19684853216796008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2474973645","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98218465,0.00045454444,0.016126676,0.0003170189,0.000039698833,0.00014468504,0.000022692435,0.0000058152586,0.0007042382],"genre_scores_gemma":[0.9775221,0.0004823714,0.02126189,0.0005058313,0.000038441045,0.000011321082,0.000009218664,0.000011425811,0.00015745295],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99946564,0.00001065616,0.00014303824,0.00011503904,0.000077251,0.00018838486],"domain_scores_gemma":[0.99958265,0.000012940955,0.00006471928,0.00021983207,0.0000477012,0.00007218227],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000101506805,0.00011768093,0.00009558468,0.000025446236,0.00006805359,0.000013396387,0.000064746644,0.00006233979,0.0000027055842],"category_scores_gemma":[0.000019677314,0.000069760354,0.000027805594,0.0000307728,0.000090403904,0.000001050525,0.00005584473,0.000017735183,0.000003892737],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026821543,0.00006835002,0.041877028,0.00009100868,0.00016079162,0.000004225197,0.00030312725,0.000085933,0.9292899,0.00020856124,0.0024030264,0.02523985],"study_design_scores_gemma":[0.007060074,0.0032245165,0.25437024,0.0002712978,0.0001824718,0.00015228102,0.0007845161,0.001922244,0.61395514,0.00062644295,0.11609811,0.0013526584],"about_ca_topic_score_codex":0.0000065496815,"about_ca_topic_score_gemma":0.000013526645,"teacher_disagreement_score":0.31533474,"about_ca_system_score_codex":0.00000981208,"about_ca_system_score_gemma":0.00004731768,"threshold_uncertainty_score":0.28447446},"labels":[],"label_agreement":null},{"id":"W2479952736","doi":"10.1093/bioinformatics/btw489","title":"Motif comparison based on similarity of binding affinity profiles","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University; Canadian Institute for Advanced Research; McGill University and Génome Québec Innovation Centre; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Motif (music); Sequence motif; Computational biology; Similarity (geometry); Web server; Computer science; Transcription factor; Biology; Artificial intelligence; Genetics; Gene; The Internet; World Wide Web","score_opus":0.01486414306976094,"score_gpt":0.2435220269961427,"score_spread":0.22865788392638176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2479952736","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9834329,0.000012509383,0.013219278,0.00009426821,0.00010264543,0.00014571751,0.00017333862,0.000012635978,0.0028067348],"genre_scores_gemma":[0.98567855,0.00001906629,0.014016528,0.00008279129,0.000026685373,0.0000045748657,0.00009052661,0.000011275702,0.000069994494],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99922675,0.000018027558,0.00034743836,0.00010222896,0.0001350591,0.00017048728],"domain_scores_gemma":[0.9992849,0.000028536882,0.00021597953,0.00035146106,0.00006325578,0.00005581472],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017113048,0.00012470475,0.00015498017,0.000048379246,0.000049097154,0.000012435807,0.0001860485,0.00012450125,0.000018430286],"category_scores_gemma":[0.00008706617,0.00008772959,0.000077074204,0.000053310156,0.00006741908,0.0000039560023,0.00007131996,0.000044535474,0.000021206597],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034859174,0.00093656935,0.09177033,0.0008159103,0.00016931926,0.0000017415127,0.00035592585,0.0036579734,0.8525162,0.0024914022,0.011528828,0.035407223],"study_design_scores_gemma":[0.0017447704,0.0009997064,0.01095919,0.00016181242,0.000032126525,0.000002961689,0.0003058895,0.10607509,0.87361866,0.00011853198,0.005490524,0.0004907076],"about_ca_topic_score_codex":0.0000018304756,"about_ca_topic_score_gemma":0.0000047773365,"teacher_disagreement_score":0.10241712,"about_ca_system_score_codex":0.000018239027,"about_ca_system_score_gemma":0.00007683621,"threshold_uncertainty_score":0.35775086},"labels":[],"label_agreement":null},{"id":"W2490276334","doi":"10.4018/978-1-4666-3604-0.ch045","title":"Incorporating Correlations among Gene Ontology Terms into Predicting Protein Functions","year":2013,"lang":"en","type":"book-chapter","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; University of Toronto","funders":"","keywords":"Gene ontology; Computational biology; Computer science; Function (biology); Artificial intelligence; Biology; Gene; Evolutionary biology; Genetics; Gene expression","score_opus":0.009257427965719768,"score_gpt":0.19877013691578357,"score_spread":0.1895127089500638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2490276334","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009289885,0.0005441887,0.0902154,0.00013506437,0.0012340283,0.002431568,0.0002481677,0.00015484077,0.8957469],"genre_scores_gemma":[0.10605561,0.00016030234,0.113099314,0.00073508895,0.0027355782,0.00035649596,0.009547925,0.0003022393,0.76700747],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978229,0.000015149048,0.0012119749,0.00029806668,0.00024568546,0.0004062279],"domain_scores_gemma":[0.9976745,0.000020047668,0.0011151142,0.00077860407,0.00020224282,0.0002094416],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00024138951,0.0005354744,0.0004286199,0.00016002862,0.00038987154,0.00012933307,0.00037329833,0.0011663777,0.00016785704],"category_scores_gemma":[0.000057892874,0.00051533704,0.00023285397,0.00004679143,0.00029490024,0.0000337224,0.00038991944,0.000581476,0.000511019],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039689327,0.00045379405,0.008649625,0.0054062232,0.005909257,0.00005514745,0.007531006,0.009911999,0.02519708,0.19541875,0.34203538,0.39903483],"study_design_scores_gemma":[0.0035731534,0.0024508138,0.0007468734,0.0015128965,0.0009595144,0.0003854737,0.0010600723,0.24857357,0.002558342,0.042527534,0.68942046,0.006231275],"about_ca_topic_score_codex":0.00003240432,"about_ca_topic_score_gemma":0.0001558971,"teacher_disagreement_score":0.39280355,"about_ca_system_score_codex":0.000075199365,"about_ca_system_score_gemma":0.000206205,"threshold_uncertainty_score":0.9997298},"labels":[],"label_agreement":null},{"id":"W2491260480","doi":"10.4018/978-1-4666-3604-0.ch048","title":"Computational Sequence Design Techniques for DNA Microarray Technologies","year":2013,"lang":"en","type":"book-chapter","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"DNA microarray; Gene chip analysis; Computational biology; Microarray; Computer science; Selection (genetic algorithm); Oligonucleotide; Biology; Data mining; DNA; Gene; Genetics; Gene expression; Artificial intelligence","score_opus":0.03884519221147376,"score_gpt":0.26852966897528324,"score_spread":0.2296844767638095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2491260480","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00001798705,0.00076801743,0.8745177,0.00042752313,0.00021525488,0.00178255,0.00022813579,0.0002608119,0.12178201],"genre_scores_gemma":[0.0023685577,0.0012504463,0.77510136,0.00065363717,0.00023939309,0.0005092962,0.002207716,0.00009933155,0.21757028],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990906,0.000005540419,0.00037745564,0.00021625526,0.00014139562,0.0001687344],"domain_scores_gemma":[0.9989916,0.000018305902,0.00032837235,0.0003912716,0.00023307781,0.000037388967],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011030328,0.00025495637,0.00018423118,0.000110262576,0.000087308676,0.00005178027,0.00031287014,0.00058542297,0.00003340098],"category_scores_gemma":[0.000039855302,0.00022937989,0.00011248639,0.00001992896,0.00013664726,0.000007785143,0.00008910878,0.000107244334,0.00006516563],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007374339,0.000027441358,0.0000021901176,0.0004167852,0.00015459955,5.465534e-7,0.00008976844,0.00017190148,0.14205559,0.029709734,0.600109,0.22718874],"study_design_scores_gemma":[0.00015865524,0.000195274,0.0000010635832,0.00009609037,0.000023038743,0.000010520749,0.000045678586,0.0014642872,0.14501575,0.012312044,0.8403097,0.00036791066],"about_ca_topic_score_codex":3.3733076e-7,"about_ca_topic_score_gemma":2.5729466e-7,"teacher_disagreement_score":0.24020071,"about_ca_system_score_codex":0.00003789009,"about_ca_system_score_gemma":0.00017542903,"threshold_uncertainty_score":0.93538404},"labels":[],"label_agreement":null},{"id":"W2491870111","doi":"10.4018/978-1-4666-3604-0.ch093","title":"Use of SciDBMaker as Tool for the Design of Specialized Biological Databases","year":2013,"lang":"en","type":"book-chapter","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Biological database; Database; Computer science; Data science; Biology; Bioinformatics","score_opus":0.11169445205417258,"score_gpt":0.27260752855210474,"score_spread":0.16091307649793216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2491870111","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.075763926,0.046362285,0.59455556,0.00071630586,0.005780164,0.034024365,0.026805637,0.00006734473,0.21592441],"genre_scores_gemma":[0.04642163,0.0672747,0.6324513,0.0021895443,0.0024125197,0.0004644257,0.0031179101,0.00031863473,0.24534935],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990101,0.0000109404045,0.00056435034,0.00014000443,0.00011887336,0.00015574707],"domain_scores_gemma":[0.998552,0.00021392335,0.0004627119,0.00051493227,0.00022758568,0.000028849508],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017846677,0.00023595929,0.00035432042,0.00003454083,0.000059575825,0.000015847849,0.00023952064,0.00020580553,0.0000782097],"category_scores_gemma":[0.00018138245,0.00014775238,0.0001997725,0.000013182492,0.0002879618,0.0000016373399,0.00023006595,0.000056046458,0.000014864788],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025630337,0.00030435633,0.00047738358,0.0018686233,0.0072796224,0.0000029203209,0.0009303467,0.001703244,0.2962216,0.24240385,0.33881712,0.107427895],"study_design_scores_gemma":[0.00044220447,0.0006206757,0.00012895388,0.000057895882,0.0001738349,0.0000067305455,0.00004019234,0.00052109157,0.015261593,0.0010366666,0.98136723,0.00034296003],"about_ca_topic_score_codex":0.0000098602595,"about_ca_topic_score_gemma":0.0000022895522,"teacher_disagreement_score":0.6425501,"about_ca_system_score_codex":0.000005599183,"about_ca_system_score_gemma":0.00010140666,"threshold_uncertainty_score":0.6025167},"labels":[],"label_agreement":null},{"id":"W2493472693","doi":"10.1093/bioinformatics/btw487","title":"<i>genipe</i>: an automated genome-wide imputation pipeline with automatic reporting and statistical tools","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Montreal Heart Institute","funders":"","keywords":"Computer science; Imputation (statistics); Data mining; Python (programming language); Software; Suite; Documentation; Missing data; Machine learning; Programming language","score_opus":0.017022826343548837,"score_gpt":0.28385688207671955,"score_spread":0.2668340557331707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2493472693","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7596302,0.000035284746,0.23944278,0.000209502,0.0000363898,0.00018622933,0.00005849209,0.00009199362,0.00030910608],"genre_scores_gemma":[0.8654892,0.000052663418,0.13353202,0.0003578613,0.000060686296,0.000017293585,0.00036454722,0.000017723114,0.00010799967],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9984409,0.00006204737,0.0008936904,0.00019272021,0.00012061889,0.00029001772],"domain_scores_gemma":[0.9986262,0.000100477126,0.00073890545,0.00027150434,0.00012875747,0.00013420227],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006321857,0.00015833117,0.00022548855,0.000030521816,0.000104891136,0.00004190368,0.00008630439,0.00014060285,0.000016483624],"category_scores_gemma":[0.0015345543,0.000101441925,0.000026845819,0.00006567418,0.00009589798,0.000022274602,0.000060102633,0.00004347174,0.0000154985],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019621232,0.00028104996,0.38132626,0.0004070975,0.00042733643,0.000031860043,0.0014429142,0.0012255673,0.06811949,0.0005279362,0.01392707,0.5320872],"study_design_scores_gemma":[0.0021683548,0.0014611509,0.76521885,0.000067789784,0.00012396615,0.00028079434,0.00065517786,0.21963218,0.0024846704,0.0003970395,0.0067136222,0.00079641363],"about_ca_topic_score_codex":0.0000073278634,"about_ca_topic_score_gemma":0.000021866024,"teacher_disagreement_score":0.5312908,"about_ca_system_score_codex":0.000021266089,"about_ca_system_score_gemma":0.000084121646,"threshold_uncertainty_score":0.41366816},"labels":[],"label_agreement":null},{"id":"W2507770958","doi":"10.1093/bioinformatics/btw400","title":"LCA*: an entropy-based measure for taxonomic assignment within assembled metagenomes","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Taxonomic rank; Taxonomy (biology); Voting; Phylogenetic tree; Data mining; Information retrieval; Machine learning; Biology; Ecology; Genetics","score_opus":0.025684718457889524,"score_gpt":0.24164813046747244,"score_spread":0.2159634120095829,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2507770958","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7488962,0.00055054046,0.2474552,0.00038008834,0.00050718663,0.0010376623,0.00025501932,0.000019998273,0.00089811115],"genre_scores_gemma":[0.9505594,0.00004712846,0.04851375,0.00030381785,0.00016975551,0.00011757781,0.0000462611,0.000024360026,0.00021795914],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99898756,0.000027373946,0.00037422663,0.00020023025,0.00012185244,0.00028878983],"domain_scores_gemma":[0.99914026,0.000027255797,0.00019883488,0.00041587075,0.00010429352,0.000113506474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033032752,0.00020703203,0.00020274792,0.000042190764,0.0001172944,0.000036809775,0.00022908789,0.00011354625,0.000010140591],"category_scores_gemma":[0.00007058845,0.00013978193,0.00012779166,0.000031612413,0.00004496681,0.0000033846372,0.00006118968,0.00002655356,0.000016504431],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015373838,0.000077263554,0.0013597566,0.000050902316,0.00022801364,2.9698265e-7,0.00012021152,0.0004468536,0.98726267,0.0005507139,0.0020486081,0.0077009965],"study_design_scores_gemma":[0.0039405418,0.0015645123,0.0021012614,0.000035154793,0.00015859425,0.0000052087357,0.00036197956,0.0041841124,0.8359498,0.000303292,0.15061559,0.0007799701],"about_ca_topic_score_codex":0.0000022261227,"about_ca_topic_score_gemma":0.00001857196,"teacher_disagreement_score":0.2016632,"about_ca_system_score_codex":0.000034277436,"about_ca_system_score_gemma":0.00013764319,"threshold_uncertainty_score":0.5700142},"labels":[],"label_agreement":null},{"id":"W2508423234","doi":"10.1093/bioinformatics/btw467","title":"A program for verification of phylogenetic network models","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Phylogenetic tree; Computer science; Phylogenetic network; Biology; Genetics; Gene","score_opus":0.018765223702526555,"score_gpt":0.2517337533348999,"score_spread":0.23296852963237333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2508423234","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2526697,0.0006846046,0.74068403,0.0001586669,0.00025024926,0.0021973148,0.000110521796,0.000047962356,0.003196944],"genre_scores_gemma":[0.725163,0.00028877106,0.2735422,0.000047592293,0.0002055194,0.00022293844,0.00011554695,0.00002074305,0.00039372066],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99941665,0.0000071076597,0.00023583339,0.00008489475,0.000079047895,0.00017647947],"domain_scores_gemma":[0.9994756,0.000008084149,0.00012320271,0.00025930404,0.000098228506,0.00003557199],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012476883,0.0000810026,0.00008821221,0.000019955336,0.00002554018,0.0000068338486,0.00012672479,0.000073832525,0.0000040255113],"category_scores_gemma":[0.000020996438,0.000057804293,0.00006202833,0.00005166616,0.0000427133,0.000004563363,0.00003607839,0.000010355188,0.0000053536196],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013990926,0.00018698147,0.0009224625,0.00034176107,0.00019038195,9.9729114e-8,0.00020112436,0.0021390351,0.26676118,0.0018637285,0.009002742,0.7182506],"study_design_scores_gemma":[0.007813994,0.005751349,0.0054803314,0.0002548408,0.00023210583,0.000016488028,0.00030317478,0.14712925,0.42274964,0.009210731,0.39957023,0.0014878939],"about_ca_topic_score_codex":4.3573593e-7,"about_ca_topic_score_gemma":9.191637e-7,"teacher_disagreement_score":0.7167627,"about_ca_system_score_codex":0.000007182464,"about_ca_system_score_gemma":0.000032853273,"threshold_uncertainty_score":0.23571907},"labels":[],"label_agreement":null},{"id":"W2512452276","doi":"10.1093/bioinformatics/btw538","title":"BatchQC: interactive software for evaluating sample and batch effects in genomic data","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":67,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; Institute of Cancer Research; University of Toronto; University Health Network","funders":"National Institutes of Health","keywords":"Bioconductor; Computer science; Pipeline (software); Software; Data mining; A priori and a posteriori; Sample (material); Batch processing; Data science; Operating system","score_opus":0.04013611400870473,"score_gpt":0.3309031692002055,"score_spread":0.2907670551915008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2512452276","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49663487,0.0002551675,0.5017316,0.0002348328,0.00021683752,0.0005897471,0.00022284586,0.000014598684,0.00009953421],"genre_scores_gemma":[0.86419684,0.00019052695,0.13443805,0.00032672222,0.00011039534,0.00010077468,0.00047323314,0.000019310512,0.0001441293],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99942416,0.000021356307,0.0001923457,0.00016674372,0.000063297004,0.0001321001],"domain_scores_gemma":[0.99929434,0.00013031291,0.00009672223,0.00038572133,0.00005261919,0.00004031242],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022901144,0.00008153132,0.00008494366,0.000036693007,0.000037794307,0.00001995154,0.00018017473,0.00006848959,0.000003967655],"category_scores_gemma":[0.00095311546,0.000060306447,0.000015474568,0.00004139764,0.000025137999,0.00001747721,0.0002067226,0.000026107573,0.000004227122],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016643581,0.000022995087,0.0066036205,0.00018439049,0.000027980646,1.250236e-7,0.00037184815,0.0000069423404,0.47273785,0.00006223859,0.0050511025,0.5147645],"study_design_scores_gemma":[0.019478768,0.0029779691,0.12987112,0.0013409387,0.00017189412,0.000035580193,0.00259057,0.10476881,0.46409157,0.0049206964,0.26749602,0.0022560805],"about_ca_topic_score_codex":0.000005404174,"about_ca_topic_score_gemma":0.000016708935,"teacher_disagreement_score":0.5125084,"about_ca_system_score_codex":0.00002036475,"about_ca_system_score_gemma":0.00006993184,"threshold_uncertainty_score":0.24592255},"labels":[],"label_agreement":null},{"id":"W2514454343","doi":"10.1093/bioinformatics/btw569","title":"Nanocall: an open source basecaller for Oxford Nanopore sequencing data","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":143,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research","funders":"Canadian Institutes of Health Research; University of Nottingham; Oxford Nanopore Technologies","keywords":"Minion; Nanopore sequencing; Computer science; DNA sequencer; MIT License; DNA sequencing; Nanopore; Open source; Computational biology; Hybrid genome assembly; DNA; Biology; Reference genome; Genetics; Operating system; Software; Engineering","score_opus":0.06328263123334449,"score_gpt":0.29263038869075014,"score_spread":0.22934775745740565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2514454343","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75958705,0.00091569306,0.22337009,0.0012248602,0.0007191071,0.0021698617,0.0019704478,0.000037767397,0.01000513],"genre_scores_gemma":[0.8373792,0.0010883221,0.15315774,0.0020655312,0.0005377744,0.00010260765,0.00086790643,0.000086500826,0.0047143786],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990566,0.000015478334,0.00030501667,0.00025447403,0.00008699824,0.00028145174],"domain_scores_gemma":[0.99865186,0.000023847644,0.00012363573,0.0010133473,0.0000871471,0.00010014402],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030939936,0.00016005378,0.00015622951,0.000021528163,0.00015076358,0.00007138588,0.001104929,0.000106249616,0.000018808372],"category_scores_gemma":[0.00011468008,0.000108700195,0.000036491805,0.00003346417,0.0000674649,0.0000103252,0.0011160895,0.00002396885,0.000010079831],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020728749,0.00012235848,0.0019314091,0.00016437085,0.0003435162,0.0000012434255,0.0008414653,0.00005449914,0.6480904,0.0009973275,0.0641213,0.2831248],"study_design_scores_gemma":[0.0012193763,0.0005783745,0.00019816124,0.000029027176,0.000031264015,0.00001337421,0.00045753838,0.0057720277,0.023479395,0.00020940912,0.96762455,0.0003875345],"about_ca_topic_score_codex":0.000010799387,"about_ca_topic_score_gemma":0.00006391356,"teacher_disagreement_score":0.90350324,"about_ca_system_score_codex":0.000016240687,"about_ca_system_score_gemma":0.00008986909,"threshold_uncertainty_score":0.44326654},"labels":[],"label_agreement":null},{"id":"W2515651902","doi":"10.1093/bioinformatics/btw525","title":"Gene Slider: sequence logo interactive data-visualization for education and research","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Source code; JavaScript; Visualization; Computational biology; Biology; World Wide Web; Programming language; Artificial intelligence","score_opus":0.053187148363871645,"score_gpt":0.3748135805252692,"score_spread":0.3216264321613975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2515651902","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8380477,0.00027772159,0.15891798,0.00038570934,0.00030292996,0.0006393106,0.00049156736,0.000015200764,0.0009218927],"genre_scores_gemma":[0.9504297,0.0007617125,0.046212435,0.00016842452,0.00020215592,0.000044280434,0.0014845663,0.000019830042,0.00067691074],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993682,0.000022313869,0.00019849894,0.00015853919,0.00009183531,0.00016060856],"domain_scores_gemma":[0.9991768,0.000041368985,0.000087033295,0.0004094287,0.0002332766,0.000052110325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036703772,0.000077748555,0.00006747503,0.00005111838,0.00009330268,0.000047142305,0.00021792017,0.00008267674,0.0000033441515],"category_scores_gemma":[0.00028859943,0.000058559533,0.000015253544,0.000049918144,0.00007155647,0.00002310045,0.00023970954,0.0000291745,0.000008556452],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001234134,0.00018109643,0.0017597829,0.00030468238,0.0001028232,3.0901205e-7,0.0010396137,0.0000129499185,0.6296129,0.0051928554,0.025098963,0.3365706],"study_design_scores_gemma":[0.0033554384,0.0018169864,0.003084147,0.0003623762,0.000094614144,0.00018177569,0.0048045334,0.14814207,0.44296184,0.009716404,0.38407612,0.0014036812],"about_ca_topic_score_codex":0.000005406927,"about_ca_topic_score_gemma":0.000011353053,"teacher_disagreement_score":0.35897717,"about_ca_system_score_codex":0.000028281715,"about_ca_system_score_gemma":0.00019026845,"threshold_uncertainty_score":0.23879886},"labels":[],"label_agreement":null},{"id":"W2515980744","doi":"10.1093/bioinformatics/btw425","title":"Pathway-based approach using hierarchical components of collapsed rare variants","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Institutes of Health; Korea National Institute of Health; National Institute of Diabetes and Digestive and Kidney Diseases; Korea Health Industry Development Institute; National Science Foundation, United Arab Emirates; National Research Foundation","keywords":"KEGG; Computer science; Computational biology; Software; Exome; Data mining; Biology; Phenotype; Gene; Exome sequencing; Genetics; Transcriptome; Gene expression","score_opus":0.030695636914016593,"score_gpt":0.25354921627007143,"score_spread":0.22285357935605485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2515980744","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.687727,0.00003563319,0.31028143,0.000114061666,0.00010161447,0.00017662896,0.00014628533,0.000009271823,0.0014081112],"genre_scores_gemma":[0.8899933,0.000012742037,0.1095426,0.00015908535,0.000048975486,0.000005645921,0.00014412295,0.00001005827,0.0000834719],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990133,0.000088864945,0.000426004,0.00012239878,0.000120083336,0.00022932334],"domain_scores_gemma":[0.99925697,0.000047180514,0.0002347647,0.00029202597,0.00009476492,0.000074298616],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034256533,0.00011796604,0.00020537949,0.00005008665,0.000059940034,0.0000062718645,0.00016522023,0.00018591566,0.000011831691],"category_scores_gemma":[0.00024428684,0.00008248937,0.00008632752,0.00007836296,0.00010228911,0.0000040258274,0.00007545623,0.00004166785,0.000007214515],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024715695,0.0004859841,0.07346542,0.00025295367,0.00026935752,0.0000016745124,0.00023452807,0.00243338,0.90279305,0.00085766794,0.004099337,0.014859506],"study_design_scores_gemma":[0.015029111,0.001790322,0.22774091,0.00034617627,0.00020318035,0.000090883834,0.0006716677,0.5756302,0.13606513,0.0011496551,0.039157335,0.0021254197],"about_ca_topic_score_codex":0.000008471379,"about_ca_topic_score_gemma":0.0000013421192,"teacher_disagreement_score":0.7667279,"about_ca_system_score_codex":0.000019930854,"about_ca_system_score_gemma":0.00016018319,"threshold_uncertainty_score":0.33638188},"labels":[],"label_agreement":null},{"id":"W2517179206","doi":"10.1093/bioinformatics/btw536","title":"SiNVICT: ultra-sensitive detection of single nucleotide variants and indels in circulating tumour DNA","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":87,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"","keywords":"Indel; Computational biology; DNA sequencing; Liquid biopsy; Biology; Deep sequencing; False positive paradox; DNA; Genome; Cancer; Single-nucleotide polymorphism; Genetics; Computer science; Gene; Genotype; Artificial intelligence","score_opus":0.00948069767126719,"score_gpt":0.2085639938520451,"score_spread":0.1990832961807779,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2517179206","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99076426,0.000055948367,0.007858758,0.000036114565,0.00009772383,0.00011427985,0.000043575365,0.0000046347973,0.001024724],"genre_scores_gemma":[0.99868613,0.00013574121,0.0009872363,0.00009367174,0.00006351163,0.0000023139428,0.000008555131,0.000010078885,0.00001276057],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99937654,0.000012760604,0.00029207632,0.00010148492,0.00006938161,0.00014778032],"domain_scores_gemma":[0.99957955,0.000044338347,0.0001420511,0.00013100676,0.000056966343,0.000046077595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012264837,0.000093143244,0.000117168136,0.000054302593,0.00002725268,0.000013649994,0.0000481622,0.00008770946,0.0000013337],"category_scores_gemma":[0.00019362164,0.000077844175,0.00002935747,0.00006220277,0.000057140704,0.000010201757,0.000042570893,0.000029973613,0.0000028657537],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022590879,0.000021871974,0.0013146753,0.000027181875,0.000010721583,0.0000013710818,0.00022092517,0.00001693813,0.98280925,0.00003441976,0.000015954254,0.015504075],"study_design_scores_gemma":[0.0007679027,0.00020890647,0.018047985,0.00008187676,0.000011022964,0.000024766809,0.00026909352,0.00063107174,0.9792183,0.00011182614,0.00046554598,0.00016170883],"about_ca_topic_score_codex":0.000024279547,"about_ca_topic_score_gemma":0.00008418576,"teacher_disagreement_score":0.01673331,"about_ca_system_score_codex":0.000026889722,"about_ca_system_score_gemma":0.000036557165,"threshold_uncertainty_score":0.31743935},"labels":[],"label_agreement":null},{"id":"W2518304058","doi":"10.1093/bioinformatics/btw472","title":"On cross-conditional and fluctuation correlations in competitive RNA networks","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Ottawa Hospital","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Competing endogenous RNA; Messenger RNA; microRNA; Biology; RNA; Statistical physics; Physics; Genetics; Gene","score_opus":0.009638407625203002,"score_gpt":0.2349723969062814,"score_spread":0.2253339892810784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2518304058","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87027395,0.000044169406,0.124446236,0.00010579166,0.00018461529,0.0001379482,0.00006121347,0.000010558576,0.0047355057],"genre_scores_gemma":[0.99834746,0.000066028966,0.00086773426,0.00025945218,0.00007259531,0.00000609978,0.00017991134,0.0000062357262,0.00019449426],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9995422,0.000010514274,0.00018490612,0.00008283803,0.00006807646,0.00011149722],"domain_scores_gemma":[0.99974304,0.00003828927,0.000050465078,0.00009082947,0.000041281728,0.000036084228],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000744648,0.000078505895,0.000061886465,0.000038084414,0.000054778382,0.000022590328,0.00004706877,0.00009766648,0.000019965128],"category_scores_gemma":[0.00005542033,0.000059285612,0.00002396789,0.000037427588,0.00008733819,0.0000114041795,0.000017078723,0.000044943,0.000014463704],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016655921,0.0009606825,0.32098314,0.00022005316,0.00030391535,0.000016635244,0.0023822715,0.027778717,0.20314385,0.28302613,0.009704183,0.14981484],"study_design_scores_gemma":[0.014154205,0.0020769245,0.7056329,0.000515922,0.00005624663,0.00008109026,0.00043507607,0.17697078,0.06962496,0.010320977,0.018332895,0.001797995],"about_ca_topic_score_codex":0.0000028093962,"about_ca_topic_score_gemma":0.000021559517,"teacher_disagreement_score":0.3846498,"about_ca_system_score_codex":0.000014789178,"about_ca_system_score_gemma":0.000022792436,"threshold_uncertainty_score":0.2417597},"labels":[],"label_agreement":null},{"id":"W2518374209","doi":"10.1093/bioinformatics/btw463","title":"CoLoRMap: Correcting Long Reads by Mapping short reads","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":68,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Leverage (statistics); Sequence assembly; Source code; Reference genome; DNA sequencing; Algorithm; Data mining; Computational biology; Biology; Artificial intelligence; Genetics; Gene; Programming language","score_opus":0.014047876105899531,"score_gpt":0.22845864857618062,"score_spread":0.2144107724702811,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2518374209","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.971584,0.0005590996,0.017712317,0.000156879,0.00041224508,0.00019998186,0.00006905396,0.000016115706,0.009290313],"genre_scores_gemma":[0.9938733,0.0005472267,0.003558085,0.000280271,0.0001682786,0.000017041002,0.000046643556,0.000020441,0.0014886879],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990128,0.000015034218,0.00035860026,0.00016540673,0.00012159166,0.00032653136],"domain_scores_gemma":[0.99939156,0.000026198202,0.00009881412,0.00031440624,0.00008331114,0.00008571044],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020856781,0.00017759972,0.00016039512,0.00003503872,0.00013382961,0.00002865155,0.0001945474,0.00013262568,0.000009997895],"category_scores_gemma":[0.00007465373,0.00012941584,0.000073688454,0.00006860251,0.000079749574,0.0000029745077,0.00018741089,0.00004852492,0.000036592937],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000460852,0.000049900656,0.06803217,0.000073485346,0.00019763765,0.0000023078649,0.00054105435,0.000009362427,0.6786007,0.00004687327,0.057406597,0.1949938],"study_design_scores_gemma":[0.0014235418,0.00073266873,0.026002485,0.00016123142,0.0000680289,0.00015563713,0.0016194019,0.00052921596,0.518158,0.000083574574,0.44974488,0.0013212899],"about_ca_topic_score_codex":0.0000052326823,"about_ca_topic_score_gemma":0.000008607265,"teacher_disagreement_score":0.39233828,"about_ca_system_score_codex":0.000024207186,"about_ca_system_score_gemma":0.000041390704,"threshold_uncertainty_score":0.5277425},"labels":[],"label_agreement":null},{"id":"W2520464109","doi":"10.1093/bioinformatics/btw597","title":"BOSS: a novel scaffolding algorithm based on an optimized scaffold graph","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"National Outstanding Youth Science Fund Project of National Natural Science Foundation of China; National Natural Science Foundation of China","keywords":"Boss; Scaffold; Computer science; Contig; Algorithm; Graph; Theoretical computer science; Genome; Database; Engineering; Biology","score_opus":0.014237031693811538,"score_gpt":0.2406790377023678,"score_spread":0.22644200600855624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2520464109","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.075816534,0.00008942605,0.9179114,0.0003307593,0.00044482286,0.00068919687,0.00023522053,0.00012868496,0.0043539153],"genre_scores_gemma":[0.17942503,0.00016293791,0.8172947,0.0012690912,0.00048064627,0.00008517815,0.00034559474,0.0000958216,0.00084098254],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99856496,0.000026389604,0.00038220076,0.0002704384,0.0003187491,0.0004372742],"domain_scores_gemma":[0.99882406,0.00002216652,0.00016272081,0.000689161,0.00010342141,0.00019845915],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035151103,0.00027364917,0.0002026338,0.00016437931,0.00011333894,0.00006614591,0.00035527782,0.00018545332,0.000056463185],"category_scores_gemma":[0.000055315257,0.00019604152,0.00014671155,0.0001556295,0.00008493907,0.000023781644,0.00009051754,0.00004701662,0.00008506131],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042106595,0.0011153818,0.0006939019,0.00017062995,0.0003438146,0.000009639845,0.00033079795,0.0025200648,0.54049563,0.0003613061,0.0075224475,0.44601533],"study_design_scores_gemma":[0.024931394,0.005011867,0.0017241708,0.00049641426,0.00020587283,0.00006653381,0.0007416149,0.49538234,0.37281114,0.00020274929,0.09521796,0.003207958],"about_ca_topic_score_codex":0.0000036691151,"about_ca_topic_score_gemma":0.0000015919675,"teacher_disagreement_score":0.49286225,"about_ca_system_score_codex":0.00003617818,"about_ca_system_score_gemma":0.00008028825,"threshold_uncertainty_score":0.7994341},"labels":[],"label_agreement":null},{"id":"W2530748177","doi":"10.1093/bioinformatics/btw634","title":"ARResT/Interrogate: an interactive immunoprofiler for IG/TR NGS data","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"T-cell and B-cell Immunology","field":"Immunology and Microbiology","cited_by":106,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"OVC Pet Trust; Ministerstvo Školství, Mládeže a Tělovýchovy; Central European Institute of Technology; University of Guelph","keywords":"Computer science; Task (project management); Filter (signal processing); Interpretation (philosophy); Web application; Data science; Computational biology; World Wide Web; Biology; Programming language","score_opus":0.032016507568512785,"score_gpt":0.2756753969730611,"score_spread":0.2436588894045483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2530748177","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8854132,0.0035170657,0.05471012,0.003399788,0.023633305,0.004122377,0.0067692073,0.0014740014,0.016960876],"genre_scores_gemma":[0.9749959,0.00022053166,0.0057652188,0.0006173182,0.00014850302,0.000092829505,0.0027413033,0.000056035016,0.01536237],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983607,0.000077402125,0.0006235355,0.00031495112,0.00003999496,0.0005834369],"domain_scores_gemma":[0.99788594,0.00029120623,0.00031171695,0.001339285,0.00013368978,0.000038174294],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00032723238,0.00028797542,0.0003588309,0.00012841311,0.00021678057,0.000038906637,0.0011822621,0.00035682606,0.0008374631],"category_scores_gemma":[0.00018380712,0.00018440966,0.000095099625,0.00007921316,0.00034755337,0.0011047865,0.0005342101,0.0002246465,0.0030234002],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005419186,0.00021702544,0.0000840751,0.000048067235,0.00035058515,0.0000017568645,0.0015338393,2.2138602e-7,0.8742102,0.00085588236,0.042072505,0.08008396],"study_design_scores_gemma":[0.0052904007,0.001326357,0.00015426044,0.00016898924,0.00012206672,0.00012904062,0.0029327234,0.00031620046,0.36624372,0.00052879663,0.62212676,0.00066068623],"about_ca_topic_score_codex":0.000043147982,"about_ca_topic_score_gemma":0.000037914673,"teacher_disagreement_score":0.5800543,"about_ca_system_score_codex":0.00005888123,"about_ca_system_score_gemma":0.00009164268,"threshold_uncertainty_score":0.99775285},"labels":[],"label_agreement":null},{"id":"W2531500048","doi":"10.1093/bioinformatics/btw639","title":"LDAP: a web server for lncRNA-disease association prediction","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Cancer-related molecular mechanisms research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":213,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"National Natural Science Foundation of China","keywords":"Computer science; Lightweight Directory Access Protocol; World Wide Web; Association (psychology); Web server; Software; Database; Operating system; The Internet; Directory","score_opus":0.00993484447586988,"score_gpt":0.24962100539397397,"score_spread":0.2396861609181041,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2531500048","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15808539,0.000601551,0.8294117,0.0027721357,0.0014607771,0.0025249603,0.0020740076,0.00018044272,0.0028890409],"genre_scores_gemma":[0.97545207,0.00093436526,0.006714307,0.0009368501,0.00090560946,0.00037287478,0.00074041734,0.0000806695,0.013862835],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989951,0.000023566356,0.000252484,0.00015045959,0.00027843413,0.000299919],"domain_scores_gemma":[0.9991939,0.000021522406,0.0001293351,0.00030767033,0.00020046002,0.00014712184],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031829925,0.000117115815,0.00008935897,0.00005910958,0.00007875061,0.00003330694,0.0001436015,0.00018400412,0.00003452353],"category_scores_gemma":[0.00049341616,0.00009167338,0.00011777885,0.00007733738,0.000019014798,0.0000147872715,0.000077424695,0.00004797147,0.00006485436],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00078023074,0.00013217008,0.0009253226,0.0003025254,0.00037042898,0.000002120211,0.00009676524,0.00015695712,0.8189221,0.0015593722,0.1475719,0.029180095],"study_design_scores_gemma":[0.005044433,0.0007046398,0.0011206983,0.00012328908,0.000108681,0.000007120164,0.00006320844,0.015059235,0.32677495,0.00073766615,0.64976084,0.00049522956],"about_ca_topic_score_codex":0.000001576246,"about_ca_topic_score_gemma":0.000008656865,"teacher_disagreement_score":0.8226974,"about_ca_system_score_codex":0.00014855564,"about_ca_system_score_gemma":0.00023807104,"threshold_uncertainty_score":0.3738332},"labels":[],"label_agreement":null},{"id":"W2538873949","doi":"10.1093/bioinformatics/btw672","title":"Optimizing ChIP-seq peak detectors using visual labels and supervised machine learning","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University","funders":"Canadian Institutes of Health Research","keywords":"Computer science; ENCODE; Artificial intelligence; Set (abstract data type); Genome browser; Pattern recognition (psychology); Supervised learning; Labeled data; Machine learning; Genome; Genomics; Artificial neural network; Gene; Biology","score_opus":0.009643948078409036,"score_gpt":0.22763551240346375,"score_spread":0.2179915643250547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2538873949","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9836759,0.0002735183,0.015547775,0.000031557258,0.00008231293,0.00010641923,0.000022454768,0.000022244241,0.00023783659],"genre_scores_gemma":[0.96755177,0.00035695426,0.031707447,0.00008034097,0.00007727683,0.0000026623215,0.00004618174,0.000028551209,0.00014883248],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99918175,0.000022957154,0.0002850358,0.00014485623,0.00009980497,0.0002656276],"domain_scores_gemma":[0.9995469,0.000015899723,0.00012033982,0.00017295295,0.00004475226,0.00009919479],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015636376,0.00017472709,0.0001456968,0.00005076488,0.00014727551,0.000052423457,0.000119979464,0.0001268061,0.000014693325],"category_scores_gemma":[0.00006858945,0.0001306007,0.000054000782,0.000049008984,0.00006396918,0.000012484711,0.00019812335,0.000070113274,0.000007698011],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029950761,0.000023823439,0.006500222,0.0000828062,0.00006331924,0.0000015044063,0.000366842,0.00048170163,0.97573656,0.000042615113,0.000018247169,0.016652387],"study_design_scores_gemma":[0.0031077599,0.0008054032,0.0029504553,0.00015452573,0.00008825892,0.00012113624,0.0007926099,0.84014964,0.14455737,0.00006785169,0.0060876287,0.0011173364],"about_ca_topic_score_codex":0.00001021468,"about_ca_topic_score_gemma":0.00001166136,"teacher_disagreement_score":0.839668,"about_ca_system_score_codex":0.000022378352,"about_ca_system_score_gemma":0.000042940603,"threshold_uncertainty_score":0.5325742},"labels":[],"label_agreement":null},{"id":"W2561907498","doi":"10.1093/bioinformatics/btw802","title":"Wright–Fisher exact solver (WFES): scalable analysis of population genetic models without simulation or diffusion theory","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Evolution and Genetic Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Children's Hospital; University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation","keywords":"Computer science; Markov chain; Population; Solver; Algorithm; Theoretical computer science; Machine learning; Programming language","score_opus":0.012193583736911793,"score_gpt":0.25581529432555206,"score_spread":0.24362171058864027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2561907498","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5484662,0.00004741076,0.4505413,0.000015649217,0.00005508995,0.00014027179,0.000037846225,0.000014775243,0.0006814483],"genre_scores_gemma":[0.9852756,0.00015685565,0.011849746,0.00010102031,0.000040312218,0.0000055546993,0.00024522984,0.000016614498,0.002309028],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988467,0.00005128091,0.0005051885,0.00016809766,0.00022676916,0.00020196803],"domain_scores_gemma":[0.99904805,0.000037454913,0.00025828526,0.00044081354,0.00013990111,0.000075494325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020839622,0.00016061218,0.0002301606,0.00016794492,0.000068344176,0.000016890328,0.00014354663,0.00018439241,0.00013177253],"category_scores_gemma":[0.00007266364,0.00010025484,0.00014620164,0.00026825236,0.00006614927,0.000023060347,0.000082744824,0.00003163328,0.000010793078],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00093219447,0.0003007125,0.10437932,0.00016429673,0.0013843302,9.0628225e-7,0.00067799044,0.78028774,0.04947993,0.0012339512,0.0007992165,0.06035941],"study_design_scores_gemma":[0.00065408234,0.00015441878,0.046021312,0.000023687388,0.00033293266,0.0000014387507,0.000051226303,0.95026785,0.0009142625,0.0005621148,0.0007972245,0.00021946758],"about_ca_topic_score_codex":0.000017602735,"about_ca_topic_score_gemma":0.000070227965,"teacher_disagreement_score":0.43869156,"about_ca_system_score_codex":0.00002976888,"about_ca_system_score_gemma":0.00003878678,"threshold_uncertainty_score":0.40882736},"labels":[],"label_agreement":null},{"id":"W2562042122","doi":"10.1093/bioinformatics/btw810","title":"Defining the clonality of peripheral T cell lymphomas using RNA-seq","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Lymphoma Diagnosis and Treatment","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; Canada's Michael Smith Genome Sciences Centre; Genome British Columbia; University of British Columbia; BC Cancer Agency","funders":"Canadian Institutes of Health Research","keywords":"RNA-Seq; Computational biology; RNA; Peripheral T-cell lymphoma; Peripheral; Biology; Virology; Computer science; T cell; Transcriptome; Genetics; Gene; Gene expression; Immune system","score_opus":0.02078213201240974,"score_gpt":0.26595058587321707,"score_spread":0.24516845386080732,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2562042122","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9775171,0.0006064319,0.00078594655,0.00057281187,0.00014573029,0.00024418198,0.00004030684,0.000030682826,0.020056799],"genre_scores_gemma":[0.9881118,0.000083495666,0.011238278,0.00031868526,0.000038147475,0.000006450903,0.000005655545,0.000008460039,0.00018905614],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99912965,0.000015003366,0.00036940837,0.00006402944,0.00024058453,0.00018130224],"domain_scores_gemma":[0.9992704,0.00011179802,0.00017838931,0.00029900952,0.0000694743,0.00007095447],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015676166,0.00011405565,0.00020446652,0.000029144256,0.00007342379,0.0000129977125,0.00007613416,0.000053253745,0.00010170096],"category_scores_gemma":[0.000045088378,0.000050947983,0.000116648225,0.00008418899,0.00009685448,0.00010032461,0.00004828021,0.000023916515,0.000044922843],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042378315,0.0015556075,0.67768544,0.0011760895,0.0006180387,0.00005322083,0.0076234704,0.00007128957,0.005945957,0.031316094,0.005064078,0.26846692],"study_design_scores_gemma":[0.03341775,0.0018986057,0.47088388,0.0022107838,0.001677598,0.0007469273,0.004637301,0.030162986,0.40488395,0.0011423734,0.047146678,0.001191182],"about_ca_topic_score_codex":0.00007084876,"about_ca_topic_score_gemma":0.0000025945678,"teacher_disagreement_score":0.398938,"about_ca_system_score_codex":0.00018607175,"about_ca_system_score_gemma":0.00018702752,"threshold_uncertainty_score":0.20775984},"labels":[],"label_agreement":null},{"id":"W2562850749","doi":"10.1093/bioinformatics/btw798","title":"switchde: inference of switch-like differential expression along single-cell trajectories","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; Medical Research Council Canada; Wellcome Trust; Wellcome","keywords":"Inference; Computer science; Expression (computer science); Differential (mechanical device); Computational biology; Software; Algorithm; Artificial intelligence; Biology; Programming language; Physics","score_opus":0.01616915510125579,"score_gpt":0.2229882719119528,"score_spread":0.206819116810697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2562850749","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9186291,0.00009737018,0.0795355,0.000026717116,0.00048576976,0.00014229216,0.00005029109,0.000025507172,0.0010074297],"genre_scores_gemma":[0.9948927,0.00012577565,0.0043260744,0.00005203024,0.00013315571,0.000006653462,0.000052421696,0.00002125495,0.00038994258],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99882585,0.000022566284,0.0004969673,0.00016801052,0.00021440562,0.00027218947],"domain_scores_gemma":[0.99915236,0.000038924965,0.00021271966,0.0003848913,0.00011385377,0.00009725659],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007636395,0.00021323578,0.00021832589,0.000053589403,0.00006420721,0.000025394747,0.00026875208,0.0002055759,0.000039434235],"category_scores_gemma":[0.00006807891,0.0001433721,0.000121586025,0.0000708962,0.0001197923,0.000019999208,0.000092884075,0.00006222538,0.000013521984],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009363689,0.00013449328,0.006475259,0.00010297035,0.000016407577,4.7457772e-7,0.00025265236,0.0000034715863,0.9866458,0.000028475535,0.00050567696,0.0057406873],"study_design_scores_gemma":[0.0010383365,0.000374169,0.001163357,0.00009642605,0.000020750122,0.0000031598731,0.00010166011,0.00012232468,0.99256665,0.000035110454,0.0042247293,0.00025335254],"about_ca_topic_score_codex":0.000014448584,"about_ca_topic_score_gemma":0.000019935027,"teacher_disagreement_score":0.07626357,"about_ca_system_score_codex":0.00001507909,"about_ca_system_score_gemma":0.00007598007,"threshold_uncertainty_score":0.5846545},"labels":[],"label_agreement":null},{"id":"W2566001817","doi":"10.1093/bioinformatics/btw793","title":"A new method for decontamination of <i>de novo</i> transcriptomes using a hierarchical clustering algorithm","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Agriculture and Agri-Food Canada","funders":"Agriculture and Agri-Food Canada; U.S. Department of Agriculture","keywords":"Human decontamination; Computer science; Cluster analysis; Documentation; Sample (material); Scripting language; Identification (biology); Hierarchical clustering; Algorithm; Data mining; Biology; Artificial intelligence; Engineering; Programming language; Chemistry","score_opus":0.018058883457341895,"score_gpt":0.2906607890563882,"score_spread":0.2726019055990463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2566001817","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07541172,0.0001646658,0.9238852,0.00009148485,0.00009000124,0.0001654741,0.00007108984,0.000002382832,0.000117949836],"genre_scores_gemma":[0.094400145,0.00010937911,0.90511733,0.000096079006,0.000113001755,0.000008166478,0.000007350068,0.00001137397,0.0001371891],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99942094,0.000012757614,0.00025391235,0.00008569714,0.000058049256,0.000168635],"domain_scores_gemma":[0.99964017,0.00003336869,0.00008799362,0.00012594796,0.000058832873,0.000053699547],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018171388,0.000092639886,0.00013101732,0.000034968743,0.00003865049,0.0000087171575,0.000097124444,0.000076246906,0.0000024182443],"category_scores_gemma":[0.000041623694,0.00006936645,0.000086798886,0.00003347129,0.000025155023,0.0000020542486,0.00004155314,0.000018737537,4.1205124e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034492557,0.000010487053,0.00013276495,0.000051027575,0.000056157944,8.9072415e-8,0.00035166767,0.000044415876,0.68427014,0.0000858596,0.00014745645,0.3148154],"study_design_scores_gemma":[0.004116868,0.00085286534,0.0014329419,0.00010532063,0.0001317554,0.000079007434,0.00038856108,0.11506595,0.8317382,0.0011348139,0.04444612,0.0005076178],"about_ca_topic_score_codex":0.000010451318,"about_ca_topic_score_gemma":0.000011517787,"teacher_disagreement_score":0.31430778,"about_ca_system_score_codex":0.000014624104,"about_ca_system_score_gemma":0.00009855252,"threshold_uncertainty_score":0.28286815},"labels":[],"label_agreement":null},{"id":"W2566610827","doi":"10.1093/bioinformatics/btw811","title":"Innovations and challenges in detecting long read overlaps: an evaluation of the state-of-the-art","year":2016,"lang":"en","type":"review","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"National Human Genome Research Institute; National Institutes of Health","keywords":"State (computer science); Computer science; Software; Data science; Programming language","score_opus":0.10441053174569143,"score_gpt":0.326231336371943,"score_spread":0.2218208046262516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2566610827","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01615672,0.9825588,0.000022175698,0.000020134385,0.00014251603,0.00054055435,0.000058834717,7.3836566e-7,0.0004995465],"genre_scores_gemma":[0.0045225685,0.99512094,0.00024731824,0.0000067958117,0.000028018854,0.000025777927,0.000011050314,0.000010515737,0.000027017693],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99901736,0.00009294197,0.0005274418,0.00010056892,0.00015968076,0.0001019931],"domain_scores_gemma":[0.99884814,0.000028504772,0.00053766003,0.00040772435,0.00016508247,0.000012863213],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00066174555,0.00013708488,0.00029759484,0.000048294034,0.000044463086,0.0000062610397,0.00019807015,0.00010920425,0.0000010893563],"category_scores_gemma":[0.00019569552,0.00007455894,0.00008080776,0.000115698625,0.00008175638,0.0000018692886,0.00020930135,0.00006278312,5.460864e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001130952,0.000009298178,0.00007506414,0.0017659727,0.00004799774,9.867507e-9,0.0002072456,0.0000057911243,0.00009012199,0.000024857967,0.000008835622,0.9977637],"study_design_scores_gemma":[0.0009204873,0.000302118,0.0065759695,0.009705055,0.0006372711,0.000029129607,0.0005183031,0.00046446966,0.002222136,0.00068936846,0.97726727,0.0006684101],"about_ca_topic_score_codex":0.0000029770606,"about_ca_topic_score_gemma":0.00011855978,"teacher_disagreement_score":0.9970953,"about_ca_system_score_codex":0.000018208393,"about_ca_system_score_gemma":0.00019476358,"threshold_uncertainty_score":0.30404252},"labels":[],"label_agreement":null},{"id":"W2567489417","doi":"10.1093/bioinformatics/btw781","title":"AnglerFish: a webserver for defining the geometry of α-helices in membrane proteins","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Biotechnology and Biological Sciences Research Council; Medical Research Council; Medical Research Council Canada; Pfizer","keywords":"Perl; Crystallography; Protein Data Bank (RCSB PDB); Helix (gastropod); Transmembrane protein; Orientation (vector space); Computer science; Membrane protein; Integral membrane protein; Protein structure; Transmembrane domain; Web server; Software; Computational biology; Biology; Membrane; Chemistry; Geometry; Biochemistry; Mathematics; Programming language; World Wide Web; The Internet","score_opus":0.010021768268550921,"score_gpt":0.24895022811555564,"score_spread":0.23892845984700473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2567489417","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9635864,0.00033525444,0.02821404,0.00081548124,0.0002290867,0.001182161,0.00017059514,0.000030430532,0.0054365383],"genre_scores_gemma":[0.9513539,0.00014307191,0.04717514,0.00043998333,0.000089884285,0.00010402982,0.00007735589,0.000028574561,0.00058804126],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99887544,0.000025865782,0.00056248554,0.00009739535,0.00016953697,0.00026929664],"domain_scores_gemma":[0.9990188,0.000104135164,0.00032044857,0.00042170406,0.00009453105,0.000040404007],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060203817,0.00014983436,0.00017662004,0.00009040275,0.000058335238,0.000020707132,0.00036571166,0.0001381304,0.000019087322],"category_scores_gemma":[0.0006872924,0.000083549676,0.00009793572,0.0001698039,0.00010693145,0.000019788402,0.00014102922,0.00007263726,0.000015056479],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021375527,0.0009399798,0.2128534,0.0095284935,0.0010471748,0.0000038525427,0.010726991,0.0028793518,0.32116884,0.04123378,0.037361857,0.36011872],"study_design_scores_gemma":[0.009269469,0.0025516239,0.028386045,0.00097435724,0.000111962116,0.00006559503,0.0022790828,0.03363087,0.5848027,0.00053398707,0.33583942,0.0015549004],"about_ca_topic_score_codex":0.000010861159,"about_ca_topic_score_gemma":0.000034483342,"teacher_disagreement_score":0.3585638,"about_ca_system_score_codex":0.000014375659,"about_ca_system_score_gemma":0.000075034215,"threshold_uncertainty_score":0.3407057},"labels":[],"label_agreement":null},{"id":"W2568061956","doi":"10.1093/bioinformatics/btw815","title":"Lineage-specific mutational clustering in protein structures predicts evolutionary shifts in function","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Biology; Phylogenetic tree; Computational biology; Lineage (genetic); Genetics; Cluster analysis; Evolutionary biology; Phylogenetics; Protein family; Function (biology); Selection (genetic algorithm); Gene; Computer science","score_opus":0.009964921974192926,"score_gpt":0.20950603447699584,"score_spread":0.1995411125028029,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2568061956","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8410938,0.0005955573,0.15333126,0.00024122585,0.0004917422,0.0008560942,0.00008541052,0.000033861284,0.0032710517],"genre_scores_gemma":[0.9873199,0.000077995195,0.011842829,0.00014212632,0.0002179275,0.00003871001,0.00015996868,0.000014191909,0.00018634503],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9988607,0.00002177874,0.0005430341,0.00013813197,0.00015993544,0.00027643263],"domain_scores_gemma":[0.9995255,0.000014719525,0.00013527497,0.00022241515,0.00004247996,0.000059637227],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021417717,0.00015547383,0.00012552412,0.00013071121,0.000043309003,0.00002487658,0.00014757579,0.00019957789,0.000031425083],"category_scores_gemma":[0.00003443804,0.00011911733,0.00004551802,0.00012587185,0.000060123613,0.000030526506,0.00010894893,0.00009975367,0.00002606979],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00431252,0.0007623907,0.03243953,0.0015031269,0.00035150978,0.000057973375,0.0051296935,0.048231773,0.21299341,0.023383083,0.038636714,0.6321983],"study_design_scores_gemma":[0.018577127,0.0020073203,0.49939698,0.0014569054,0.00003664024,0.0001360032,0.0019045249,0.27953658,0.017169975,0.015999446,0.16066818,0.0031103368],"about_ca_topic_score_codex":0.0000045014303,"about_ca_topic_score_gemma":0.00006884822,"teacher_disagreement_score":0.6290879,"about_ca_system_score_codex":0.000060858853,"about_ca_system_score_gemma":0.000078726516,"threshold_uncertainty_score":0.48574638},"labels":[],"label_agreement":null},{"id":"W2570372911","doi":"10.1093/bioinformatics/btw832","title":"ntCard: a streaming algorithm for cardinality estimation in genomics data","year":2017,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":80,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"National Human Genome Research Institute; BC Cancer Agency; National Institutes of Health; Genome British Columbia; Genome Canada","keywords":"k-mer; Algorithm; Computer science; Hash function; Histogram; Cardinality (data modeling); Memory footprint; Genomics; Shotgun sequencing; Population; Hash table; Sequence assembly; Genome; Data mining; Biology; Artificial intelligence","score_opus":0.03918693709759102,"score_gpt":0.30188381076641124,"score_spread":0.2626968736688202,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2570372911","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68720454,0.0006658542,0.30638456,0.00018079544,0.00056045584,0.00089065055,0.0015510205,0.0000073055853,0.0025548004],"genre_scores_gemma":[0.6658081,0.00029783807,0.33287936,0.00007178251,0.00017629915,0.000029051333,0.00062897796,0.000016087512,0.000092520124],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993164,0.000007524257,0.000256348,0.00016690526,0.00006399116,0.00018882917],"domain_scores_gemma":[0.9986744,0.000011773772,0.00017470185,0.001052209,0.000050050454,0.00003687498],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032015055,0.00011359248,0.00014520876,0.000023653845,0.00021701201,0.0000870495,0.0005187631,0.00008255294,5.098367e-7],"category_scores_gemma":[0.00015535472,0.0001124774,0.00004464491,0.00001350442,0.00005796867,0.000005467607,0.00047736376,0.000035931407,0.0000026523667],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033674103,0.00005338876,0.007839037,0.00012695527,0.00016668803,0.0000010911158,0.00044610005,0.00049294345,0.008929187,0.000111318775,0.0015568325,0.9802428],"study_design_scores_gemma":[0.0022631306,0.00026264833,0.06300217,0.00003940008,0.000091248156,0.000015133885,0.0007640629,0.8373643,0.012103949,0.00064993877,0.08278287,0.0006611351],"about_ca_topic_score_codex":0.000052127358,"about_ca_topic_score_gemma":0.00007469689,"teacher_disagreement_score":0.97958165,"about_ca_system_score_codex":0.000019052468,"about_ca_system_score_gemma":0.00006765198,"threshold_uncertainty_score":0.4586695},"labels":[],"label_agreement":null},{"id":"W2573696390","doi":"10.1093/bioinformatics/btw773","title":"The super-n-motifs model: a novel alignment-free approach for representing and comparing RNA secondary structures","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation","keywords":"Pseudoknot; Protein secondary structure; Computer science; Adjacency list; Structural motif; Nucleic acid secondary structure; RNA; Representation (politics); Theoretical computer science; Algorithm; Computational biology; Biology","score_opus":0.023506403898645757,"score_gpt":0.23715402200358585,"score_spread":0.2136476181049401,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2573696390","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15175357,0.00038009736,0.8434153,0.00020641122,0.00009414597,0.00053909206,0.00007388665,0.00002142874,0.003516048],"genre_scores_gemma":[0.83423805,0.00014698683,0.16450652,0.0001325578,0.00014064541,0.00007450002,0.000034974673,0.00002656992,0.0006991876],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99916536,0.000012944836,0.0002776469,0.00016020304,0.00012171513,0.00026211256],"domain_scores_gemma":[0.99921703,0.000040579045,0.000115649775,0.00052072614,0.000043526154,0.0000624726],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033104356,0.00014115899,0.0001273582,0.000019372983,0.00026033493,0.00008105543,0.00033064085,0.00010337963,0.000001640912],"category_scores_gemma":[0.00018718146,0.00007995523,0.00006681409,0.00002139324,0.00008108997,0.000014162059,0.00028399605,0.000036888632,6.4105234e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011855874,0.000024197585,0.0002158667,0.00015972524,0.00012870408,1.1958903e-7,0.00032292088,0.0002505183,0.94185984,0.007933156,0.0031910616,0.04579531],"study_design_scores_gemma":[0.0022571443,0.00015581076,0.00010561917,0.000041278927,0.000045842407,0.000031626063,0.0007171789,0.14420608,0.8340715,0.006100675,0.011807901,0.00045930818],"about_ca_topic_score_codex":0.0000026486825,"about_ca_topic_score_gemma":0.0000029472249,"teacher_disagreement_score":0.6824845,"about_ca_system_score_codex":0.000008220869,"about_ca_system_score_gemma":0.000036831552,"threshold_uncertainty_score":0.32604796},"labels":[],"label_agreement":null},{"id":"W2580812863","doi":"10.1093/bioinformatics/btw813","title":"BioPAXViz: a cytoscape application for the visual exploration of metabolic pathway evolution","year":2017,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Microbial Metabolic Engineering and Bioproduction","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Visualization; Computer science; Documentation; Parsing; MIT License; Pathway analysis; Software; Metabolic pathway; Computational biology; Bioinformatics; Data mining; Biology; Programming language","score_opus":0.0147237461121498,"score_gpt":0.25835188617536103,"score_spread":0.24362814006321123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2580812863","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15922731,0.00079965993,0.8383242,0.0002429452,0.00046814827,0.0006897847,0.000048948456,0.000017324466,0.00018170333],"genre_scores_gemma":[0.99458,0.00023132587,0.0044215387,0.000019857822,0.00043297128,0.00007733051,0.0000931029,0.000008948488,0.00013494697],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994879,0.000006711849,0.00022687005,0.000094962605,0.00007492899,0.000108640364],"domain_scores_gemma":[0.9991324,0.0000036929036,0.0002620907,0.00045593214,0.0001246392,0.000021233871],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025562645,0.00008820356,0.000096166885,0.00002835921,0.0002234287,0.000032049633,0.0001935594,0.00007983189,8.6460085e-7],"category_scores_gemma":[0.0001610127,0.00006378933,0.000069290196,0.000036617133,0.00006232463,0.000026704509,0.000046468536,0.000031024814,0.0000056166923],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039307284,0.00002688394,0.00007922444,0.000056305234,0.000034576762,6.9016e-9,0.000083312785,0.00024777965,0.94877106,0.0030246768,0.00024606104,0.04739082],"study_design_scores_gemma":[0.00042320543,0.00011709121,0.0028088163,0.000010075966,0.00004892013,0.0000035661658,0.00015289015,0.017405797,0.86059666,0.000098489865,0.11819361,0.00014086631],"about_ca_topic_score_codex":0.000016921054,"about_ca_topic_score_gemma":0.000008786858,"teacher_disagreement_score":0.83535266,"about_ca_system_score_codex":0.0000042979386,"about_ca_system_score_gemma":0.000037165264,"threshold_uncertainty_score":0.26012537},"labels":[],"label_agreement":null},{"id":"W2587112482","doi":"10.1093/bioinformatics/btw826","title":"VEXOR: an integrative environment for prioritization of functional variants in fine-mapping analysis","year":2017,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Centre hospitalier universitaire de Québec","funders":"National Human Genome Research Institute; Health Canada; National Cancer Institute; National Institutes of Health; Government of Canada; Fondation du cancer du sein du Québec; Compute Canada; Canadian Institutes of Health Research; Genome Canada","keywords":"Prioritization; Computer science; Genome-wide association study; Interface (matter); Identification (biology); Genetic variants; Association (psychology); User interface; Computational biology; Data science; Data mining; Biology; Single-nucleotide polymorphism; Genetics","score_opus":0.022914732973092038,"score_gpt":0.2727190200054641,"score_spread":0.24980428703237206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2587112482","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5426202,0.000030281752,0.45645955,0.00007289479,0.00006595372,0.00017998056,0.00007763213,0.0000021328385,0.00049136026],"genre_scores_gemma":[0.95749074,0.00005387178,0.04161548,0.00003172177,0.00004688601,0.000021638652,0.00059842854,0.0000040388963,0.00013721715],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9993911,0.000022055578,0.00031913814,0.0000981964,0.000056460136,0.000113053975],"domain_scores_gemma":[0.9992995,0.000018325905,0.0003178033,0.00028637022,0.000050649433,0.000027347269],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029472102,0.00007357203,0.00016312514,0.00007488692,0.00009986446,0.000013623948,0.000118627395,0.00010380719,0.000009193253],"category_scores_gemma":[0.0002778667,0.00006657082,0.00007420012,0.000041435986,0.000045981164,0.000010527818,0.000046832378,0.000028785858,0.0000013904086],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017023612,0.00051211775,0.875122,0.00013057548,0.0014210788,5.060125e-7,0.002166248,0.04350123,0.034853775,0.0018690901,0.0024903237,0.03776278],"study_design_scores_gemma":[0.00063353573,0.00023147141,0.89969766,0.000009936198,0.00008513889,6.138965e-7,0.0004676285,0.09518421,0.0009713259,0.00030497956,0.0022759356,0.00013759092],"about_ca_topic_score_codex":0.000021939824,"about_ca_topic_score_gemma":0.00013135342,"teacher_disagreement_score":0.41487053,"about_ca_system_score_codex":0.000018357192,"about_ca_system_score_gemma":0.000037952017,"threshold_uncertainty_score":0.27146792},"labels":[],"label_agreement":null},{"id":"W2587686048","doi":"10.1093/bioinformatics/btx078","title":"Kollector: transcript-informed, targeted <i>de novo</i> assembly of gene loci","year":2017,"lang":"en","type":"erratum","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"National Human Genome Research Institute; Genome British Columbia","keywords":"Sequence assembly; Computational biology; Genome; Biology; Genomics; Pipeline (software); Caenorhabditis elegans; Gene; Homo sapiens; Computer science; Genetics; Transcriptome; Gene expression","score_opus":0.015252239868434356,"score_gpt":0.24622726838113668,"score_spread":0.23097502851270232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2587686048","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08984273,0.07090232,0.008362454,0.00059468934,0.04891129,0.0035383534,0.009423,0.00008986625,0.7683353],"genre_scores_gemma":[0.19244474,0.12099354,0.11038935,0.0034651149,0.013415975,0.00036433563,0.023904223,0.00086291635,0.5341598],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99800247,0.000023135179,0.0008206217,0.00026431846,0.00030944412,0.00057999906],"domain_scores_gemma":[0.99769163,0.000014609933,0.0007923892,0.001087741,0.00026013723,0.00015349973],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00023943133,0.00051088084,0.0006715318,0.00010862047,0.00023090141,0.00007400386,0.00088370737,0.0009037052,0.000016979388],"category_scores_gemma":[0.00018271389,0.00048309774,0.0004035215,0.00006897217,0.00021885034,0.0000033433091,0.00018618701,0.00032589905,0.00001984278],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000063323394,0.000052336032,0.00009461873,0.00075290195,0.00052668113,0.0000031483153,0.0005879952,0.000023315539,0.08719363,0.000017902175,0.90886724,0.0018169197],"study_design_scores_gemma":[0.00072085403,0.00037395334,0.00041080065,0.000076251985,0.00015610835,0.00003281761,0.00015094463,0.00025827793,0.06699225,0.000020500174,0.93022674,0.0005804697],"about_ca_topic_score_codex":0.000044900138,"about_ca_topic_score_gemma":0.00011440953,"teacher_disagreement_score":0.2341755,"about_ca_system_score_codex":0.000051928277,"about_ca_system_score_gemma":0.0011637753,"threshold_uncertainty_score":0.99976206},"labels":[],"label_agreement":null},{"id":"W2588631423","doi":"10.1093/bioinformatics/btx102","title":"<i>GARLIC</i>: Genomic Autozygosity Regions Likelihood-based Inference and Classification","year":2017,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"National Human Genome Research Institute; National Institutes of Health","keywords":"Inference; Computer science; Artificial intelligence","score_opus":0.03143508679184543,"score_gpt":0.28629253257251003,"score_spread":0.2548574457806646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2588631423","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94385767,0.00011428168,0.04766384,0.0015273179,0.00016163396,0.00020960295,0.00003707282,0.000022560454,0.006406032],"genre_scores_gemma":[0.98143286,0.00021528226,0.017431295,0.00053614256,0.000074082396,0.0000143173675,0.00010484814,0.000007776707,0.00018340678],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99931467,0.000027248954,0.00024976034,0.00014038496,0.00006170337,0.00020621142],"domain_scores_gemma":[0.9988892,0.000023264827,0.00031216472,0.000612648,0.000075156415,0.00008754438],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026978133,0.000110254754,0.00012604418,0.000027394584,0.00043413593,0.00007687078,0.0002387724,0.00017263975,0.000004296212],"category_scores_gemma":[0.00043782074,0.0001040251,0.000045831417,0.000017201239,0.00014470765,0.000008769924,0.00012936452,0.000068571615,0.000030622083],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058544312,0.00015313218,0.8452223,0.0001421113,0.00014228412,0.0000012168017,0.0004204868,0.00023312427,0.072149046,0.0036979192,0.02675394,0.05102592],"study_design_scores_gemma":[0.0004664749,0.0001156586,0.93938786,0.000010872819,0.000024710742,0.000004170301,0.000076365955,0.032049403,0.0008391202,0.0004395184,0.02637919,0.00020666994],"about_ca_topic_score_codex":0.000026089285,"about_ca_topic_score_gemma":0.00006381114,"teacher_disagreement_score":0.09416557,"about_ca_system_score_codex":0.000014969909,"about_ca_system_score_gemma":0.0001116614,"threshold_uncertainty_score":0.42420205},"labels":[],"label_agreement":null},{"id":"W2596012462","doi":"10.1093/bioinformatics/btw744","title":"node.dating: dating ancestors in phylogenetic trees in R","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Evolution and Paleontology Studies","field":"Earth and Planetary Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Western University; AIDS Vancouver; Simon Fraser University","funders":"Canadian Institutes of Health Research","keywords":"Phylogenetic tree; Node (physics); Divergence (linguistics); Tree (set theory); ENCODE; Computer science; Software; Phylogenetics; Evolutionary biology; Biology; Gene; Mathematics; Genetics; Combinatorics","score_opus":0.03289374500053088,"score_gpt":0.24061457772664732,"score_spread":0.20772083272611644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2596012462","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9449218,0.00050061883,0.00021235393,0.000259125,0.00020260671,0.00010116583,0.000026671762,0.00002605469,0.0537496],"genre_scores_gemma":[0.9947848,0.00015426347,0.004774301,0.00013554438,0.000024339899,0.0000011261338,0.000009433197,0.0000011006722,0.000115148105],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99920064,0.00003260232,0.00033175718,0.00008300574,0.00010561623,0.00024637068],"domain_scores_gemma":[0.99957204,0.00018891647,0.00008957991,0.000098944416,0.00001167321,0.000038824204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023738529,0.00008943864,0.00013608883,0.000121720375,0.000053065538,0.000011413083,0.00012687549,0.000052016097,0.00031256632],"category_scores_gemma":[0.00014364166,0.000057411915,0.000018316456,0.0001932127,0.00008540818,0.00020219079,0.0000101061,0.000059255846,0.00025086003],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000048228335,0.000004478386,0.9665914,0.000010095376,0.000002367958,0.0000021303745,0.00051500846,0.00028530337,0.000008338143,0.000026053878,0.00020942466,0.032340556],"study_design_scores_gemma":[0.00035208478,0.00003555792,0.9818392,0.0000580539,0.0000016324279,0.0000039783063,0.0005870716,0.015781624,0.0000152747,0.00008069192,0.0011419816,0.00010285293],"about_ca_topic_score_codex":0.00027381364,"about_ca_topic_score_gemma":0.052053284,"teacher_disagreement_score":0.053634454,"about_ca_system_score_codex":0.00000684152,"about_ca_system_score_gemma":0.000025444373,"threshold_uncertainty_score":0.9652443},"labels":[],"label_agreement":null},{"id":"W2604472817","doi":"10.1093/bioinformatics/btx202","title":"EzMap: a simple pipeline for reproducible analysis of the human virome","year":2017,"lang":"en","type":"article","venue":"Bioinformatics","topic":"vaccines and immunoinformatics approaches","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; Libin Cardiovascular Institute of Alberta; Alberta Children's Hospital","funders":"Alberta Children's Hospital Research Institute; Canada Foundation for Innovation","keywords":"Human virome; Computer science; Metagenomics; Computational biology; Pipeline (software); Workstation; Data mining; Biology; Programming language; Genetics","score_opus":0.030205647209669707,"score_gpt":0.28950098630569654,"score_spread":0.2592953390960268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2604472817","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9820315,0.00010423059,0.011700043,0.00024284392,0.00014713407,0.00055442355,0.00020826611,0.000010350196,0.005001165],"genre_scores_gemma":[0.9949609,0.00002831845,0.003530265,0.00011465947,0.00007783868,0.000021559039,0.0002611784,0.000011365831,0.0009938923],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990651,0.000007236618,0.00050178735,0.00012419006,0.00011822411,0.00018347152],"domain_scores_gemma":[0.9973312,0.000007855963,0.00059762696,0.0019037125,0.00012663969,0.000032978936],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038343735,0.00012662694,0.00024076288,0.00006387845,0.0004311616,0.00007653736,0.00068158074,0.000091549424,0.000009104648],"category_scores_gemma":[0.0003035705,0.00008592286,0.00031929073,0.000108812914,0.00008160288,0.00001709501,0.00032432599,0.000046926278,0.0000020550983],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047164134,0.0010808884,0.13932171,0.0027990928,0.010838094,6.021929e-7,0.005828862,0.007607363,0.64303523,0.012448385,0.11902314,0.057544976],"study_design_scores_gemma":[0.0033841454,0.00056067714,0.18239711,0.000057251284,0.002594231,0.000009549278,0.001445736,0.27669477,0.3566521,0.00086073944,0.17433049,0.0010131726],"about_ca_topic_score_codex":0.000025466365,"about_ca_topic_score_gemma":0.00003376389,"teacher_disagreement_score":0.28638312,"about_ca_system_score_codex":0.000006868907,"about_ca_system_score_gemma":0.000035825848,"threshold_uncertainty_score":0.35038325},"labels":[],"label_agreement":null},{"id":"W2607390459","doi":"10.1093/bioinformatics/btx213","title":"BioCIDER: a Contextualisation InDEx for biological Resources discovery","year":2017,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"Biotechnology and Biological Sciences Research Council; Directorate for Biological Sciences; European Commission","keywords":"Contextualization; Documentation; Computer science; World Wide Web; Source code; Index (typography); Code (set theory); Open source; Software; Open source software; Data science; Programming language","score_opus":0.046255479885533336,"score_gpt":0.30591285235299864,"score_spread":0.2596573724674653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2607390459","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87086976,0.0003793594,0.123379685,0.0009316151,0.00058536336,0.00040805707,0.00014350713,0.000054022657,0.0032486394],"genre_scores_gemma":[0.987828,0.000094369956,0.010452832,0.0004387241,0.00035331192,0.000034961322,0.00013445974,0.00000853098,0.00065479724],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99929875,0.000014215222,0.00024224413,0.00013970672,0.000092604605,0.00021250326],"domain_scores_gemma":[0.9991971,0.00003497729,0.00022021885,0.00043757525,0.00005175485,0.000058371097],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024378438,0.00012039156,0.00014206933,0.000026132066,0.00034304042,0.00018301934,0.00035902538,0.00024673788,0.0000036894173],"category_scores_gemma":[0.001038339,0.00008723673,0.00009670163,0.000015401827,0.0003592742,0.000013311298,0.0001575917,0.0000527482,0.0000081753005],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016124931,0.0003437436,0.1368059,0.0004532717,0.0005387832,0.000006320976,0.00297145,0.000023755296,0.042724404,0.0049115955,0.14328407,0.6663242],"study_design_scores_gemma":[0.002388488,0.0012166894,0.05011538,0.000060582202,0.000027525102,0.00001968066,0.0019610117,0.0037945074,0.013804774,0.0009871438,0.9250529,0.0005713639],"about_ca_topic_score_codex":0.000012083595,"about_ca_topic_score_gemma":0.000014535154,"teacher_disagreement_score":0.7817688,"about_ca_system_score_codex":0.000007333829,"about_ca_system_score_gemma":0.00003335289,"threshold_uncertainty_score":0.35574105},"labels":[],"label_agreement":null},{"id":"W2611036498","doi":"10.1093/bioinformatics/btx281","title":"Assembling draft genomes using contiBAIT","year":2017,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia; BC Cancer Agency","funders":"Canadian Institutes of Health Research; Terry Fox Foundation; Terry Fox Research Institute; Michael Smith Health Research BC; Canadian Cancer Society; National Institutes of Health","keywords":"Bioconductor; Computer science; Sequence assembly; Orientation (vector space); Massively parallel; Data mining; Computational biology; Biology; Parallel computing; Genetics; Mathematics; Gene","score_opus":0.034056591695111035,"score_gpt":0.28557123785163047,"score_spread":0.2515146461565194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2611036498","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98688304,0.00091287587,0.002259193,0.000065022665,0.00033526777,0.00012749154,0.000021060274,0.000004345642,0.009391675],"genre_scores_gemma":[0.97898555,0.0003656288,0.019931667,0.00014666756,0.0002381371,0.0000029749415,0.000012103858,0.000013851791,0.00030342766],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993708,0.000006367174,0.00021376157,0.00011109022,0.000083358624,0.00021461137],"domain_scores_gemma":[0.9991189,0.000004902397,0.00019814244,0.00054997124,0.00007076207,0.000057269124],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012850373,0.00012673646,0.00013217158,0.00002470966,0.0004666022,0.00014443295,0.00031327782,0.000085358406,0.000004737949],"category_scores_gemma":[0.00006649275,0.00011709464,0.000072977746,0.00001340493,0.00008641697,0.0000027323977,0.00028344983,0.000040957057,0.000015435311],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006392932,0.00007794884,0.11456773,0.00017001896,0.0005263578,0.00000606238,0.0010282142,0.0007460114,0.8387629,0.0009423474,0.002887262,0.040221255],"study_design_scores_gemma":[0.0034890082,0.0006343003,0.07943289,0.000100980535,0.00023325418,0.00010816695,0.0017697113,0.058744192,0.2654115,0.0007065734,0.58729595,0.0020734726],"about_ca_topic_score_codex":0.000012735054,"about_ca_topic_score_gemma":0.000013053789,"teacher_disagreement_score":0.5844087,"about_ca_system_score_codex":0.000008991634,"about_ca_system_score_gemma":0.00005105928,"threshold_uncertainty_score":0.47749808},"labels":[],"label_agreement":null},{"id":"W2617255385","doi":"10.1093/bioinformatics/btx323","title":"Structurexplor: a platform for the exploration of structural features of RNA secondary structures","year":2017,"lang":"en","type":"article","venue":"Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science; RNA; Software; Computational biology; Programming language; Biology; Genetics; Gene","score_opus":0.030411347495270892,"score_gpt":0.2749737539755978,"score_spread":0.24456240648032693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2617255385","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.926177,0.0018266892,0.063713364,0.00038247695,0.0014045805,0.0019995966,0.00080194866,0.000021225833,0.0036730964],"genre_scores_gemma":[0.9803518,0.00008722816,0.019175159,0.00004923714,0.00014540782,0.000024238338,0.000071712566,0.000012919279,0.00008226914],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992663,0.000008643617,0.00033535447,0.00009146964,0.00015322257,0.00014500263],"domain_scores_gemma":[0.9985606,0.000033099823,0.0005827455,0.0006695721,0.00012257077,0.00003138457],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015942911,0.00013939438,0.00017687674,0.000028788781,0.00027508193,0.00005109318,0.00051175314,0.00013976732,0.0000157409],"category_scores_gemma":[0.00020579764,0.00008792245,0.00012916847,0.00001734097,0.00014587089,0.000047301317,0.00010930133,0.000058538324,3.8669526e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005280187,0.000010541946,0.00010851731,0.0005487429,0.00030017822,2.1407915e-7,0.0017970378,0.00017389069,0.6671286,0.019077877,0.0020681638,0.30825818],"study_design_scores_gemma":[0.0004902742,0.00023784723,0.0027317598,0.000018481733,0.00003710668,0.0000055846644,0.00074181793,0.00036303914,0.9827727,0.010057316,0.0024121585,0.0001318909],"about_ca_topic_score_codex":0.000013245227,"about_ca_topic_score_gemma":0.000022304876,"teacher_disagreement_score":0.3156441,"about_ca_system_score_codex":0.0000043862424,"about_ca_system_score_gemma":0.000067530906,"threshold_uncertainty_score":0.35853738},"labels":[],"label_agreement":null},{"id":"W2621457453","doi":"10.1093/bioinformatics/btx367","title":"MoDMaps3D: an interactive webtool for the quantification and 3D visualization of interrelationships in a dataset of DNA sequences","year":2017,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Fractal and DNA sequence analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Visualization; Computer science; Computational biology; DNA; Interactive visualization; Computer graphics (images); Artificial intelligence; Data mining; Biology; Genetics","score_opus":0.04514148420432668,"score_gpt":0.34420197863371754,"score_spread":0.29906049442939087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2621457453","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9342237,0.00009679138,0.06457349,0.000093525836,0.000047055906,0.00026995674,0.0005800354,0.0000020420803,0.00011338074],"genre_scores_gemma":[0.99618214,0.000099489735,0.0023041265,0.000021085612,0.000012104099,0.000011832636,0.0013571272,0.0000026132,0.000009492049],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99954176,0.000015120311,0.0002711213,0.00006597039,0.00005416969,0.00005184026],"domain_scores_gemma":[0.99921757,0.000028159226,0.00036488377,0.0003020404,0.00007344219,0.000013884474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023266573,0.000051323033,0.00008171132,0.000040850995,0.00007690884,0.000029532135,0.00016719085,0.000047026064,0.0000015742652],"category_scores_gemma":[0.00027403515,0.000036346013,0.000021900403,0.000031608088,0.00011227866,0.00005689133,0.000045759894,0.000022879742,4.3904737e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012103496,0.0006472887,0.118019015,0.0012179292,0.0006081536,7.44365e-7,0.011986138,0.003576489,0.7304565,0.012020581,0.0019214166,0.1183354],"study_design_scores_gemma":[0.0008089164,0.0005716161,0.041546173,0.00011851004,0.00012698419,0.000004707452,0.0059036757,0.7328132,0.21470308,0.00078547036,0.0023697275,0.00024796135],"about_ca_topic_score_codex":0.00009981178,"about_ca_topic_score_gemma":0.00021767565,"teacher_disagreement_score":0.72923666,"about_ca_system_score_codex":0.0000041521103,"about_ca_system_score_gemma":0.000024595774,"threshold_uncertainty_score":0.14821474},"labels":[],"label_agreement":null},{"id":"W2623917105","doi":"10.1093/bioinformatics/btx347","title":"COMPASS: the COMPletely Arbitrary Sequence Simulator","year":2017,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Compass; Sequence (biology); Computer science; Computer graphics (images); Simulation; Software; Programming language; Cartography; Geography; Biology","score_opus":0.04825999946533854,"score_gpt":0.28384619722334126,"score_spread":0.2355861977580027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2623917105","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9828516,0.0004474137,0.0008750241,0.00075047545,0.00034816354,0.00023791795,0.00008276007,0.0000064765745,0.014400139],"genre_scores_gemma":[0.9956612,0.00015484249,0.003008771,0.0007901204,0.00017490749,0.00000814185,0.00001890683,0.000009369459,0.0001737362],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99939877,0.000011065646,0.00019942697,0.00009901561,0.00009968201,0.00019202435],"domain_scores_gemma":[0.9989139,0.000015219733,0.00016879744,0.00079007173,0.00006317811,0.00004885594],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013035374,0.00012298417,0.00011072262,0.000009940869,0.0006285112,0.00011857042,0.0005805846,0.000058213893,0.0000052802866],"category_scores_gemma":[0.00008025663,0.00008383653,0.00007164821,0.000013492888,0.00024053514,0.0000020481784,0.00029892943,0.00006327993,0.000038223192],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036933503,0.00036827903,0.0956177,0.00054745504,0.0018510883,0.000023620983,0.0050350423,0.003924169,0.6751674,0.027833087,0.09899592,0.090266936],"study_design_scores_gemma":[0.0014329061,0.00044587464,0.13510005,0.000037723614,0.00007549868,0.000056067995,0.00078765664,0.03237314,0.041093707,0.001636506,0.7860999,0.0008609431],"about_ca_topic_score_codex":0.0000153317,"about_ca_topic_score_gemma":0.000015717316,"teacher_disagreement_score":0.687104,"about_ca_system_score_codex":0.0000064925907,"about_ca_system_score_gemma":0.000049132395,"threshold_uncertainty_score":0.48340636},"labels":[],"label_agreement":null},{"id":"W2624426054","doi":"10.1093/bioinformatics/btx372","title":"Comparison of pre-processing methods for Infinium HumanMethylation450 BeadChip array","year":2017,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Epigenetics and DNA Methylation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network; University of Toronto; Ontario Institute for Cancer Research","funders":"Canadian Institutes of Health Research; Prostate Cancer Canada; Princess Margaret Cancer Foundation; Movember Foundation; Terry Fox Research Institute; Ontario Institute for Cancer Research","keywords":"Replicate; Computer science; Sample (material); DNA methylation; Computational biology; Data mining; Biology; Genetics; Statistics; Mathematics; Gene","score_opus":0.06380849064092295,"score_gpt":0.4320959425822919,"score_spread":0.3682874519413689,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2624426054","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16659279,0.0009553137,0.8275364,0.00004476967,0.00019925817,0.00028872734,0.000019660674,0.000009020245,0.0043540713],"genre_scores_gemma":[0.5910437,0.000038513914,0.4085579,0.000016721218,0.00009820465,0.000013738788,0.00009337984,0.000011653697,0.00012619884],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990729,0.000028210172,0.00050537725,0.000121691344,0.00010419177,0.00016760729],"domain_scores_gemma":[0.9984729,0.000036509064,0.00069782435,0.00053468946,0.00020491202,0.00005315966],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005936259,0.00012668605,0.0002167203,0.000045830802,0.00032517352,0.00008395207,0.00029947067,0.0001627627,0.000003789553],"category_scores_gemma":[0.0004939213,0.00011922346,0.000097671735,0.000026745414,0.00010438407,0.000016839038,0.00007501732,0.00005592853,0.0000015203218],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008332577,0.000073560004,0.014256278,0.0003657885,0.000050236013,1.7414717e-8,0.0011553424,0.00041122604,0.64213985,0.00032943892,0.00018684824,0.34094808],"study_design_scores_gemma":[0.0004477635,0.00027413957,0.013295836,0.000025541745,0.000034161534,2.491727e-7,0.00014827002,0.0141873425,0.93676084,0.0007189791,0.03392444,0.00018240983],"about_ca_topic_score_codex":0.0000049534256,"about_ca_topic_score_gemma":0.0000063277457,"teacher_disagreement_score":0.4244509,"about_ca_system_score_codex":0.000007233054,"about_ca_system_score_gemma":0.00006339068,"threshold_uncertainty_score":0.48617917},"labels":[],"label_agreement":null},{"id":"W2626636543","doi":"10.1093/bioinformatics/btx327","title":"Detecting and removing multiplicative spatial bias in high-throughput screening technologies","year":2017,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University and Génome Québec Innovation Centre; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; False positive paradox; Multiplicative function; Protocol (science); Throughput; Data mining; Software; Machine learning; Mathematics; Medicine","score_opus":0.024382365776163813,"score_gpt":0.28665710386941745,"score_spread":0.26227473809325363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2626636543","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88485885,0.00016014458,0.113176085,0.00014300921,0.00001684024,0.00022982813,0.0000037401753,0.00010399371,0.0013075386],"genre_scores_gemma":[0.89168626,0.00021674387,0.10794588,0.00003735255,0.000029596884,0.000012268255,0.000014754325,0.0000108984605,0.000046248286],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992286,0.000014454818,0.00028635777,0.00018304813,0.00008835006,0.00019916346],"domain_scores_gemma":[0.9988973,0.00002148171,0.0003115334,0.00069308665,0.00005255253,0.000024058834],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029412904,0.0001377846,0.00016413695,0.000091877846,0.00023597864,0.00013494291,0.00031954417,0.00016456308,0.0000010726814],"category_scores_gemma":[0.0011279673,0.00012957075,0.000041654126,0.00004667414,0.00017699723,0.000028346414,0.0006128172,0.00012792788,0.0000024477968],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045687288,0.000027025013,0.07095042,0.00009488058,0.00007776055,0.000009669957,0.0005093486,0.000035162237,0.18652639,0.00006857342,0.00032408,0.741331],"study_design_scores_gemma":[0.0006612207,0.00013220208,0.021985555,0.000097838034,0.000025185576,0.000018791958,0.0013965607,0.031137018,0.9418029,0.00014576137,0.0022115814,0.00038535235],"about_ca_topic_score_codex":0.0004163604,"about_ca_topic_score_gemma":0.00039484474,"teacher_disagreement_score":0.75527656,"about_ca_system_score_codex":0.0000132492005,"about_ca_system_score_gemma":0.000015606336,"threshold_uncertainty_score":0.5283742},"labels":[],"label_agreement":null},{"id":"W2660795308","doi":"10.1093/bioinformatics/btx388","title":"The International Society for Computational Biology and WikiProject Computational Biology: celebrating 10 years of collaboration towards open access","year":2017,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia; BC Cancer Agency","funders":"","keywords":"Biology; Computational biology; Computer science","score_opus":0.04959906079315056,"score_gpt":0.40396770862636733,"score_spread":0.35436864783321675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2660795308","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.733016,0.00079676876,0.22940354,0.012454889,0.0024618134,0.0049080327,0.0036631257,0.000050568004,0.013245225],"genre_scores_gemma":[0.8209649,0.0008844314,0.17276263,0.00083115336,0.00043113725,0.000114564486,0.0034145124,0.000024106057,0.00057258975],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99891484,0.000018826333,0.0004924339,0.00015539827,0.00019437147,0.00022415064],"domain_scores_gemma":[0.9984774,0.0001329439,0.00047849436,0.00027083344,0.0005667137,0.00007359066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008159843,0.00012101353,0.0001625863,0.00004053458,0.0005280436,0.0007608759,0.0014087374,0.00016661682,0.0000076904735],"category_scores_gemma":[0.00095808593,0.0000947868,0.0000896282,0.00005334466,0.00062868826,0.00006775144,0.0013407081,0.00007294647,0.000003020128],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00084170856,0.0002585882,0.014208786,0.0005678786,0.0013924672,4.5674992e-7,0.0021468806,0.0018388383,0.01166999,0.018297581,0.14689945,0.8018774],"study_design_scores_gemma":[0.0048578377,0.001165596,0.02008788,0.0000637474,0.000054667897,0.000011294643,0.0020444982,0.63280576,0.0064966185,0.018510282,0.31330046,0.0006013448],"about_ca_topic_score_codex":0.000032061416,"about_ca_topic_score_gemma":0.00003263305,"teacher_disagreement_score":0.801276,"about_ca_system_score_codex":0.000024020206,"about_ca_system_score_gemma":0.0006052931,"threshold_uncertainty_score":0.7337144},"labels":[],"label_agreement":null},{"id":"W2668619786","doi":"10.1093/bioinformatics/btx421","title":"CoreTracker: accurate codon reassignment prediction, applied to mitochondrial genomes","year":2017,"lang":"en","type":"article","venue":"Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université de Montréal","funders":"Fonds de recherche du Québec – Nature et technologies","keywords":"Genome; Python (programming language); Computer science; Inference; False positive paradox; Pointer (user interface); Phylogenetic tree; Source code; Set (abstract data type); Computational biology; Data mining; Biology; Artificial intelligence; Genetics; Gene; Programming language","score_opus":0.017644792153679634,"score_gpt":0.24911727965160438,"score_spread":0.23147248749792473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2668619786","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6168537,0.00047151174,0.26832318,0.0013410109,0.0054617156,0.0044083414,0.00074997393,0.00020074725,0.10218982],"genre_scores_gemma":[0.92229503,0.00041092164,0.07229234,0.0008480717,0.0013336655,0.00020379058,0.00024841662,0.000049077706,0.0023187106],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99905294,0.000012310252,0.00031119285,0.00017607653,0.00019988236,0.00024762593],"domain_scores_gemma":[0.99872744,0.0000067229244,0.00022365636,0.0008321633,0.000057840687,0.0001521689],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016310101,0.0001656259,0.00014789957,0.000033965985,0.0003650161,0.00017342165,0.00044385577,0.00016598734,0.00003632001],"category_scores_gemma":[0.00011202229,0.00014692936,0.00006391095,0.000023372555,0.00005087067,0.000011888364,0.0001870892,0.00004478497,0.00014240519],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003768171,0.0000634227,0.0005317256,0.00008566121,0.00012085162,0.0000020678006,0.0004695509,0.000089930276,0.8968526,0.0010721412,0.03986589,0.0604693],"study_design_scores_gemma":[0.0009237321,0.000437818,0.001811254,0.000036688496,0.000036257814,0.000011626061,0.00025341613,0.00041120412,0.7235601,0.00019594001,0.27190763,0.00041436474],"about_ca_topic_score_codex":0.000003482914,"about_ca_topic_score_gemma":0.000005202487,"teacher_disagreement_score":0.30544132,"about_ca_system_score_codex":0.000018684652,"about_ca_system_score_gemma":0.000055823934,"threshold_uncertainty_score":0.59916055},"labels":[],"label_agreement":null},{"id":"W2727134083","doi":"10.1093/bioinformatics/btx441","title":"Reactome enhanced pathway visualization","year":2017,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":187,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research","funders":"National Institutes of Health; National Human Genome Research Institute; University of Toronto; European Bioinformatics Institute","keywords":"Scalable Vector Graphics; Computer science; Visualization; Hierarchy; Scalability; World Wide Web; Information retrieval; Data mining; Database","score_opus":0.01236784390598909,"score_gpt":0.26033991077438523,"score_spread":0.24797206686839615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2727134083","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3928504,0.0002590966,0.38770634,0.0002885965,0.0017131276,0.00080647867,0.00009700341,0.00010288453,0.21617608],"genre_scores_gemma":[0.9920369,0.00015752247,0.0054715667,0.00044064203,0.0002989383,0.000011067456,0.0002368882,0.00001884335,0.001327675],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.999155,0.000008208051,0.00034322203,0.00011060164,0.00013326998,0.00024971197],"domain_scores_gemma":[0.9986296,0.0000045608986,0.00036079748,0.00083109736,0.000082042345,0.00009185277],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020350415,0.00015133436,0.0001296106,0.000032052973,0.0003591724,0.00020308448,0.00041638716,0.00017886091,0.000016315234],"category_scores_gemma":[0.0000985856,0.00013679698,0.00007507881,0.0000255703,0.000086971115,0.000019223073,0.0002155759,0.000067537665,0.000097909455],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030427874,0.0002779814,0.0021004125,0.00055030384,0.00040732653,0.000005669065,0.0034605619,0.0003964896,0.2825944,0.024032554,0.035413392,0.6504566],"study_design_scores_gemma":[0.0033542563,0.0008189541,0.007640689,0.00014372851,0.00005782585,0.000049860406,0.0008662701,0.05061041,0.37918195,0.0019066544,0.5536528,0.0017165735],"about_ca_topic_score_codex":0.0000062313475,"about_ca_topic_score_gemma":0.000016477155,"teacher_disagreement_score":0.64874005,"about_ca_system_score_codex":0.000012165785,"about_ca_system_score_gemma":0.00006351279,"threshold_uncertainty_score":0.5578419},"labels":[],"label_agreement":null},{"id":"W2734886065","doi":"10.1093/bioinformatics/btx254","title":"Discovery and genotyping of novel sequence insertions in many sequenced individuals","year":2017,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"Türkiye Bilimsel ve Teknolojik Araştırma Kurumu; European Molecular Biology Organization","keywords":"Structural variation; Sequence assembly; Sequence (biology); Reference genome; Genome; Computational biology; Breakpoint; Computer science; Genotyping; Biology; Zygosity; Hybrid genome assembly; DNA sequencing; Genetics; Whole genome sequencing; Algorithm; Genotype; Gene","score_opus":0.04019711173590731,"score_gpt":0.2830124640901386,"score_spread":0.24281535235423127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2734886065","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99706215,0.00027673328,0.0014293819,0.000074307034,0.000055555323,0.00011371194,0.000082380386,0.000001056655,0.00090470153],"genre_scores_gemma":[0.98860574,0.0004016347,0.010829177,0.00007306368,0.000021954718,0.000006727916,0.000012317956,0.0000051750117,0.00004420421],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9994797,0.0000048671122,0.00023644361,0.000090256435,0.00005939474,0.00012933204],"domain_scores_gemma":[0.9994436,0.0000074288682,0.0001757988,0.00031667564,0.000031785,0.000024712925],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012763611,0.000085816144,0.00011760729,0.000034385215,0.00012060899,0.000050143903,0.00018609368,0.00006414827,4.3671173e-7],"category_scores_gemma":[0.00009597315,0.00007933751,0.000026662761,0.00002091148,0.00015547275,0.0000067597603,0.00023748986,0.000037606813,6.423233e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015553036,0.000044607816,0.1086353,0.00010813555,0.000057484373,5.6457344e-7,0.0008788849,0.00012968913,0.88594717,0.001622619,0.000039781247,0.0025201973],"study_design_scores_gemma":[0.001525929,0.00021523656,0.83796877,0.00011881443,0.000030556006,0.000022601267,0.00077194563,0.0028895827,0.15375549,0.0004831751,0.0017890147,0.00042890417],"about_ca_topic_score_codex":0.000052951487,"about_ca_topic_score_gemma":0.000050527775,"teacher_disagreement_score":0.7321917,"about_ca_system_score_codex":0.0000064800915,"about_ca_system_score_gemma":0.00004812884,"threshold_uncertainty_score":0.32352895},"labels":[],"label_agreement":null},{"id":"W2735438349","doi":"10.1093/bioinformatics/btx245","title":"Identification of associations between genotypes and longitudinal phenotypes via temporally-constrained group sparse canonical correlation analysis","year":2017,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":56,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; University of California, San Diego; National Institutes of Health; H. Lundbeck A/S; Servier; Nanjing University of Aeronautics and Astronautics; National Natural Science Foundation of China; Eisai; Genentech; U.S. National Library of Medicine; IXICO; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; University of Southern California; Eli Lilly and Company; U.S. Department of Defense; National Center for Advancing Translational Sciences; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Scheme for Promotion of Academic and Research Collaboration; Novartis Pharmaceuticals Corporation; Bristol-Myers Squibb; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Imaging genetics; Neuroimaging; Alzheimer's Disease Neuroimaging Initiative; Phenotype; Correlation; Computational biology; Computer science; Artificial intelligence; Biology; Machine learning; Cognition; Genetics; Neuroscience; Gene; Mathematics; Cognitive impairment","score_opus":0.04907499561906291,"score_gpt":0.2863039771638803,"score_spread":0.23722898154481736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2735438349","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9141193,0.00003066263,0.08186585,0.0011981428,0.00026544547,0.000346598,0.000385585,0.00006896064,0.0017194289],"genre_scores_gemma":[0.9983279,0.000013558836,0.0014193954,0.00005760304,0.00005280151,0.0000062549134,0.000040726354,0.000006031337,0.00007570516],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9987298,0.000045203324,0.0005523869,0.00019113184,0.0003293764,0.00015208352],"domain_scores_gemma":[0.99726456,0.001300452,0.00089470576,0.00037224186,0.00011415885,0.00005388203],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047606617,0.00012088093,0.0002910972,0.00017385618,0.00067493564,0.00013598359,0.00020524808,0.00008174364,0.000010541385],"category_scores_gemma":[0.005399341,0.00011551145,0.00009169866,0.00023395132,0.00032471688,0.000650221,0.000120252575,0.00010102714,0.000019688901],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022925025,0.00007667919,0.976085,0.00005460973,0.0003971113,0.0000010578376,0.00091719354,0.0003681037,0.0063321106,0.009970648,0.00018362032,0.0055909073],"study_design_scores_gemma":[0.0002545545,0.00004540404,0.9621164,0.00000660688,0.00036963433,0.0000013476924,0.00005146973,0.03350202,0.0024929354,0.0009563308,0.00006952026,0.00013377488],"about_ca_topic_score_codex":0.00013562354,"about_ca_topic_score_gemma":0.00026520374,"teacher_disagreement_score":0.0842086,"about_ca_system_score_codex":0.000055472392,"about_ca_system_score_gemma":0.00004500412,"threshold_uncertainty_score":0.6463906},"labels":[],"label_agreement":null},{"id":"W2736429011","doi":"10.1093/bioinformatics/btx459","title":"Phylotyper: <i>in silico</i> predictor of gene subtypes","year":2017,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Agency of Canada","funders":"","keywords":"Subtyping; In silico; Python (programming language); Computational biology; R package; Phylogenetic tree; Whole genome sequencing; Genome; Data mining; Biology; Computer science; Gene; Genetics; Programming language","score_opus":0.011763900604948708,"score_gpt":0.23193900143405483,"score_spread":0.22017510082910613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2736429011","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9912868,0.0005604542,0.000114808434,0.00004412224,0.00014972452,0.00011246309,0.000052026513,0.0000016824675,0.0076778824],"genre_scores_gemma":[0.99523425,0.00041481268,0.0040364233,0.000058419304,0.000084991116,0.0000057038033,0.000014946283,0.000008293272,0.0001421729],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994414,0.0000061927535,0.0002408598,0.000088861896,0.000075548094,0.00014712288],"domain_scores_gemma":[0.99924356,0.000005243791,0.0001682375,0.0005018764,0.000046869885,0.000034204604],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010652974,0.00009508789,0.00013610882,0.000024388226,0.000079218684,0.000018690838,0.00027714975,0.00007538884,0.0000034466493],"category_scores_gemma":[0.00007231553,0.00008521891,0.000053441825,0.000016750553,0.00010444024,0.0000015945878,0.000129153,0.00003194009,0.0000068680065],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009340005,0.00009852732,0.31025016,0.00013963453,0.0001089993,0.000001487904,0.0005820166,0.0001256076,0.679953,0.00034723306,0.0016133896,0.006686575],"study_design_scores_gemma":[0.0013064537,0.00038414693,0.42028105,0.000029002134,0.000026052117,0.000007676481,0.00023081807,0.0010040218,0.54814017,0.00016710802,0.02809332,0.0003302153],"about_ca_topic_score_codex":0.000023037273,"about_ca_topic_score_gemma":0.000034474964,"teacher_disagreement_score":0.13181281,"about_ca_system_score_codex":0.000004406935,"about_ca_system_score_gemma":0.000038702194,"threshold_uncertainty_score":0.34751263},"labels":[],"label_agreement":null},{"id":"W2742056220","doi":"10.1093/bioinformatics/btx489","title":"LRCstats, a tool for evaluating long reads correction methods","year":2017,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Nanopore sequencing; Reference genome; Process (computing); Error detection and correction; Software; Field (mathematics); Data mining; Genome; Algorithm; Programming language; Biology; Genetics","score_opus":0.05481751731997311,"score_gpt":0.3875812066325948,"score_spread":0.33276368931262174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2742056220","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69994485,0.00043572768,0.2925367,0.000098212586,0.0018393275,0.0006289722,0.00004280503,0.000009324505,0.004464052],"genre_scores_gemma":[0.53903335,0.0002347322,0.4585625,0.00019608648,0.00034435335,0.00009140816,0.0000682,0.00002392435,0.0014454268],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993204,0.000020797375,0.00025688103,0.00012756036,0.000074644915,0.00019971946],"domain_scores_gemma":[0.99904644,0.000033997392,0.0002470108,0.00049665873,0.00013993042,0.00003592876],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062768307,0.00012150721,0.00013074394,0.000020328878,0.00049093325,0.00010225691,0.00021390978,0.000091200156,0.0000031401055],"category_scores_gemma":[0.00073700707,0.000111250236,0.00009111903,0.000014398807,0.000059809285,0.0000027820397,0.00015677484,0.000038907878,0.0000053956633],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016514155,0.00004542323,0.0126735885,0.00017819801,0.0002466393,3.8630418e-7,0.0007128653,0.000283516,0.16485108,0.0002315554,0.009973683,0.8106379],"study_design_scores_gemma":[0.0043234434,0.0028993033,0.17520154,0.000118525255,0.00034907504,0.00007274116,0.0012592071,0.16768177,0.45995945,0.0016892954,0.18476081,0.0016848663],"about_ca_topic_score_codex":0.000010448845,"about_ca_topic_score_gemma":0.00001226689,"teacher_disagreement_score":0.80895305,"about_ca_system_score_codex":0.000011706325,"about_ca_system_score_gemma":0.000055956676,"threshold_uncertainty_score":0.45366532},"labels":[],"label_agreement":null},{"id":"W2745257241","doi":"10.1093/bioinformatics/btx498","title":"Motif independent identification of potential RNA G-quadruplexes by G4RNA screener","year":2017,"lang":"en","type":"article","venue":"Bioinformatics","topic":"DNA and Nucleic Acid Chemistry","field":"Biochemistry, Genetics and Molecular Biology","cited_by":114,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"G-quadruplex; RNA; Computational biology; Nucleic acid structure; Computer science; Motif (music); Artificial intelligence; Biology; Genetics; Gene; DNA; Physics","score_opus":0.007000891683450851,"score_gpt":0.23653852590421526,"score_spread":0.2295376342207644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2745257241","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9864158,0.00012739004,0.00773848,0.00009888817,0.00018953856,0.00009716078,0.00012517968,0.000010893831,0.0051966486],"genre_scores_gemma":[0.99628985,0.00013849724,0.0011976337,0.000049297596,0.0001120116,0.000004254092,0.00024865783,0.000013101272,0.001946709],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990749,0.0000071613235,0.00040724594,0.00012973309,0.00021236193,0.00016863337],"domain_scores_gemma":[0.99858063,0.000002338181,0.0004948804,0.00075992546,0.000091513255,0.0000707361],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016564381,0.0001268103,0.00012646097,0.00001984864,0.00016589407,0.000085509964,0.0005089245,0.00017264856,0.000023956156],"category_scores_gemma":[0.00009070613,0.00011952267,0.000089969195,0.000016974613,0.0001465302,0.000020442254,0.00019946913,0.000063828884,0.000021298601],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023575392,0.000043236247,0.0006532941,0.00006116168,0.00004271594,5.048607e-7,0.000035508572,0.000016425282,0.9823726,0.00002747936,0.010118794,0.006604744],"study_design_scores_gemma":[0.00041528264,0.000044326564,0.0030843369,0.000012021061,0.000024176681,0.0000070006076,0.00012308617,0.0014679176,0.9884934,0.00003028141,0.0061425013,0.0001556799],"about_ca_topic_score_codex":0.000015978354,"about_ca_topic_score_gemma":0.0000018493686,"teacher_disagreement_score":0.009874018,"about_ca_system_score_codex":0.000008309525,"about_ca_system_score_gemma":0.00003499423,"threshold_uncertainty_score":0.4873993},"labels":[],"label_agreement":null},{"id":"W2756665674","doi":"10.1093/bioinformatics/btx613","title":"A collaborative filtering-based approach to biomedical knowledge discovery","year":2017,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"Compute Canada","keywords":"Computer science; Knowledge extraction; Strengths and weaknesses; Data science; Singular value decomposition; Graph; Knowledge graph; Data mining; Information retrieval; Machine learning; Artificial intelligence; Theoretical computer science","score_opus":0.021150662301844248,"score_gpt":0.2974989414543733,"score_spread":0.276348279152529,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2756665674","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18977705,0.00046205398,0.7345251,0.001418671,0.0012039769,0.00078352535,0.0003879973,0.0001227449,0.07131892],"genre_scores_gemma":[0.8492602,0.000023067887,0.14785707,0.0006477875,0.00034697563,0.000068676425,0.00024267846,0.000020737594,0.0015327766],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991252,0.000019621715,0.00024324407,0.00018343485,0.00015230269,0.0002762376],"domain_scores_gemma":[0.99894226,0.000016040143,0.00012673027,0.00065895176,0.00007390464,0.00018214197],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020093663,0.00016050687,0.00017641488,0.00005627862,0.00027590728,0.00019522847,0.00054754846,0.00020146977,0.0000040467567],"category_scores_gemma":[0.00057807483,0.0001252315,0.000065942026,0.00007783816,0.00034965939,0.000010669875,0.00030467086,0.00008131927,0.000055379165],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00097105565,0.002495146,0.0035818042,0.0013391332,0.00057024625,0.000020117972,0.0061081555,0.0002225844,0.09141061,0.0021001587,0.49726605,0.39391494],"study_design_scores_gemma":[0.0014722648,0.0009767852,0.0038064145,0.00009280802,0.000027017513,0.00001199048,0.001014463,0.009164039,0.027836522,0.000030117773,0.95498174,0.0005858591],"about_ca_topic_score_codex":0.000004671056,"about_ca_topic_score_gemma":0.000006489383,"teacher_disagreement_score":0.6594832,"about_ca_system_score_codex":0.000015145363,"about_ca_system_score_gemma":0.00020370792,"threshold_uncertainty_score":0.51067924},"labels":[],"label_agreement":null},{"id":"W2761940999","doi":"10.1093/bioinformatics/btx609","title":"A new haplotype block detection method for dense genome sequencing data based on interval graph modeling of clusters of highly correlated SNPs","year":2017,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":79,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sinai Health System; Lunenfeld-Tanenbaum Research Institute; Public Health Ontario; University of Toronto","funders":"National Research Foundation of Korea; Canadian Institutes of Health Research; National Research Foundation; Neurosciences Research Foundation","keywords":"Haplotype; Single-nucleotide polymorphism; Computational biology; Genetics; Graph; Interval (graph theory); Genome; Biology; Block (permutation group theory); Computer science; Gene; Combinatorics; Mathematics; Theoretical computer science; Genotype","score_opus":0.05327049569628053,"score_gpt":0.30984070304935896,"score_spread":0.25657020735307845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2761940999","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16516528,0.00003416171,0.8341016,0.000067654044,0.00014966137,0.00021081656,0.00010813665,0.000006336519,0.00015632653],"genre_scores_gemma":[0.7514218,0.000021835918,0.24819167,0.000081603685,0.000039888724,0.0000036482984,0.00019602332,0.000010692115,0.000032806962],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990341,0.000040837374,0.00051630696,0.00015396792,0.00008534313,0.00016943974],"domain_scores_gemma":[0.99829775,0.000052501102,0.00059396564,0.0008553494,0.00014593767,0.00005447538],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00066587294,0.000117850126,0.00023934794,0.000071187715,0.00012416166,0.000013764568,0.0004110968,0.00019478674,0.000001478713],"category_scores_gemma":[0.00072679814,0.000109627115,0.00009797198,0.000037453818,0.000033719924,0.000010137526,0.00015969058,0.000064614025,0.0000011827823],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00087014306,0.00008835387,0.0015194297,0.00046433558,0.00052956527,6.02916e-7,0.00064975646,0.74509746,0.22506312,0.000054531003,0.0012193457,0.02444334],"study_design_scores_gemma":[0.0007006145,0.00040430686,0.00034681032,0.000031347194,0.00007412951,0.0000029429139,0.00012245636,0.9872976,0.010640225,0.00007021625,0.00019787806,0.000111459405],"about_ca_topic_score_codex":0.00017193847,"about_ca_topic_score_gemma":0.00008878927,"teacher_disagreement_score":0.58625656,"about_ca_system_score_codex":0.00002299544,"about_ca_system_score_gemma":0.00014492428,"threshold_uncertainty_score":0.4470464},"labels":[],"label_agreement":null},{"id":"W2763456665","doi":"10.1093/bioinformatics/btx648","title":"SAGE2: parallel human genome assembly","year":2017,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Genome; Sequence assembly; Computer science; Human genome; License; Graph; MIT License; Computational biology; Biology; Theoretical computer science; Genetics; Gene","score_opus":0.022374859411655616,"score_gpt":0.2756007835409523,"score_spread":0.2532259241292967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2763456665","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87959325,0.000331208,0.013498221,0.00029693387,0.00036378717,0.0005476691,0.00005114918,0.000054787128,0.10526298],"genre_scores_gemma":[0.96660274,0.00016573368,0.027235527,0.00023309214,0.0004002107,0.000022840119,0.00027632588,0.000031504896,0.0050320094],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991649,0.000009546212,0.00024933068,0.00013621447,0.00015704571,0.00028296892],"domain_scores_gemma":[0.9986806,0.0000020990303,0.00021739105,0.00094907585,0.0000554162,0.000095402494],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017797193,0.00015318194,0.00012881018,0.00003489812,0.00044026645,0.00017961649,0.0005792519,0.000121766825,0.00003497936],"category_scores_gemma":[0.000046545225,0.00014443665,0.00008604561,0.000017600485,0.00008605978,0.000014138661,0.0002947809,0.00006661599,0.00021383252],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055913377,0.00025042475,0.00904915,0.00034129323,0.00051976385,0.000021208914,0.00089246954,0.00019552493,0.94680315,0.0016795251,0.0155043285,0.02468724],"study_design_scores_gemma":[0.004188852,0.0010597797,0.2617343,0.00004915238,0.00012033057,0.000062068146,0.00057934056,0.0027855586,0.04054151,0.00044705198,0.68664855,0.0017834844],"about_ca_topic_score_codex":0.00000958903,"about_ca_topic_score_gemma":0.000013616251,"teacher_disagreement_score":0.9062616,"about_ca_system_score_codex":0.000013776054,"about_ca_system_score_gemma":0.000031858406,"threshold_uncertainty_score":0.5889956},"labels":[],"label_agreement":null},{"id":"W2765753182","doi":"10.1093/bioinformatics/btx667","title":"DISC: DISulfide linkage Characterization from tandem mass spectra","year":2017,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bioinformatics Solutions (Canada); Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Computer science; Disulfide Linkage; Tandem mass spectrometry; Mass spectrometry; Mass spectrum; Proteome; Matching (statistics); Chemistry; Characterization (materials science); Disulfide bond; Data mining; Biological system; Materials science; Chromatography; Mathematics; Cysteine; Nanotechnology; Statistics; Biochemistry; Biology","score_opus":0.015002807750675909,"score_gpt":0.2652042303954211,"score_spread":0.2502014226447452,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2765753182","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19806845,0.00001062554,0.755066,0.00050112436,0.00007127069,0.00019920981,0.0005446675,0.00030064382,0.045238018],"genre_scores_gemma":[0.6268371,0.0002618791,0.3686773,0.00013932034,0.00044131782,0.00010165048,0.001396278,0.000038873695,0.002106307],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99931127,0.0000015716096,0.00029479596,0.00010919483,0.000117506155,0.0001656792],"domain_scores_gemma":[0.99867165,0.000017251406,0.0003851785,0.00082936557,0.000028489647,0.00006808829],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000041642426,0.00012838669,0.00013195472,0.000015355623,0.00038416105,0.00021334359,0.00042687153,0.00011191122,0.00022869666],"category_scores_gemma":[0.000042818283,0.00011823521,0.00005268094,0.000020879908,0.000060724138,0.0004375777,0.0000925617,0.00014555425,0.00009405236],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016670216,0.00008140627,0.014928544,0.00014474598,0.000051156105,0.000004156028,0.00068651186,0.000006734584,0.92011577,0.012688368,0.00036246024,0.050913475],"study_design_scores_gemma":[0.00067203824,0.000017099439,0.011254247,0.0001835603,0.00004949912,0.0000031450395,0.000189464,0.033733137,0.86178887,0.024565464,0.06685595,0.0006875131],"about_ca_topic_score_codex":0.000009810502,"about_ca_topic_score_gemma":0.0000025857717,"teacher_disagreement_score":0.42876863,"about_ca_system_score_codex":0.000043929922,"about_ca_system_score_gemma":0.00001846188,"threshold_uncertainty_score":0.4821492},"labels":[],"label_agreement":null},{"id":"W2766641567","doi":"10.1093/bioinformatics/btx701","title":"Efficient comparative phylogenetics on large trees","year":2017,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":609,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; University of British Columbia","keywords":"Phylogenetics; Computer science; Tree (set theory); Computational biology; Biology; Mathematics; Genetics; Combinatorics; Gene","score_opus":0.02820503632907191,"score_gpt":0.282642592489065,"score_spread":0.2544375561599931,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766641567","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9725388,0.0002656988,0.00068878534,0.00008564749,0.0002973097,0.00019486049,0.000111134235,0.0000046363525,0.025813105],"genre_scores_gemma":[0.99631417,0.00009961865,0.0027330974,0.00024714667,0.0001701043,0.000011565063,0.000023942666,0.000011103741,0.0003892262],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991991,0.000012651715,0.00022327674,0.00015459392,0.00013372928,0.00027667597],"domain_scores_gemma":[0.9989123,0.000010064465,0.00019564944,0.0007363105,0.00007157342,0.00007413792],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001231321,0.0001776586,0.00017112588,0.000028076836,0.0005125086,0.0000808388,0.00036939766,0.000088004905,0.000006509893],"category_scores_gemma":[0.00005156936,0.00015068053,0.00008724076,0.000017552726,0.00012229296,4.828756e-7,0.00025529685,0.000057949313,0.00007638692],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013729925,0.0032228571,0.10471504,0.0004360593,0.0027154195,0.000025945374,0.016383646,0.054472744,0.65032667,0.026074743,0.09183825,0.04841561],"study_design_scores_gemma":[0.004512767,0.002398054,0.35464838,0.000073844,0.00011117653,0.00001975401,0.002298065,0.05279286,0.19884335,0.0002466232,0.38247243,0.0015827137],"about_ca_topic_score_codex":0.0000032998987,"about_ca_topic_score_gemma":0.000029021725,"teacher_disagreement_score":0.45148337,"about_ca_system_score_codex":0.000009079636,"about_ca_system_score_gemma":0.000032324286,"threshold_uncertainty_score":0.6144573},"labels":[],"label_agreement":null},{"id":"W2766750745","doi":"10.1093/bioinformatics/btx707","title":"NanoStringNormCNV: pre-processing of NanoString CNV data","year":2017,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network; University of Toronto; Ontario Institute for Cancer Research","funders":"Canadian Institutes of Health Research; Prostate Cancer Canada; Terry Fox Research Institute; Ontario Institute for Cancer Research; Movember Foundation","keywords":"Computer science; Normalization (sociology); Visualization; Software; Copy-number variation; Data mining; Data processing; Software package; R package; Database; Computational science; Operating system; Biology; Gene","score_opus":0.03027205727068864,"score_gpt":0.2912801544147864,"score_spread":0.26100809714409773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766750745","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9725662,0.0014133531,0.011248906,0.00015089713,0.0006498715,0.00032366064,0.00058358134,0.00002212395,0.0130414255],"genre_scores_gemma":[0.9871479,0.00056211406,0.011553447,0.00008211537,0.00019217508,0.000003048702,0.00027252984,0.000016377717,0.00017025712],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99915147,0.0000045578245,0.00034449002,0.00016394297,0.00013352065,0.00020204905],"domain_scores_gemma":[0.9977429,0.000011165024,0.00042209408,0.0016690979,0.000086527325,0.00006821912],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018476744,0.00012625921,0.00014946685,0.00003163183,0.00023560664,0.00012440966,0.0010875588,0.00011033025,0.0000049605806],"category_scores_gemma":[0.00046269072,0.00012297736,0.00004373637,0.000026387244,0.00011953837,0.000027765302,0.00105771,0.000059016817,0.000005931279],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035594622,0.00029181273,0.054869596,0.0014581177,0.000290804,0.000009895968,0.0011923899,0.0004870552,0.25557533,0.00094201975,0.03217244,0.6523546],"study_design_scores_gemma":[0.0027830666,0.0006032919,0.0349231,0.00039220188,0.00015561547,0.0000523135,0.00065907795,0.028791415,0.66304326,0.00018566383,0.26728565,0.0011253306],"about_ca_topic_score_codex":0.000052069503,"about_ca_topic_score_gemma":0.000042841828,"teacher_disagreement_score":0.65122926,"about_ca_system_score_codex":0.000009399192,"about_ca_system_score_gemma":0.0001719206,"threshold_uncertainty_score":0.50148714},"labels":[],"label_agreement":null},{"id":"W2767132092","doi":"10.1093/bioinformatics/btx675","title":"ARCS: scaffolding genome drafts with linked reads","year":2017,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":234,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Human Genome Research Institute; National Institutes of Health; Genome British Columbia; Genome Canada","keywords":"Computer science; Genome; Scaffold; Computational biology; Programming language; Biology; Genetics; Gene","score_opus":0.015951966697740978,"score_gpt":0.23972494911462772,"score_spread":0.22377298241688673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2767132092","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9797939,0.00035067493,0.0011246104,0.00014095585,0.00013735193,0.00018560005,0.000028053917,0.0000072459684,0.018231614],"genre_scores_gemma":[0.9846302,0.00035960748,0.013998925,0.00017330404,0.00021365608,0.000012100371,0.00003207944,0.000018222172,0.0005618907],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992839,0.00000636465,0.00020355682,0.00014236149,0.000110381494,0.00025344116],"domain_scores_gemma":[0.99891305,0.0000050316803,0.00019585069,0.00072897883,0.000078644174,0.000078428355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012057159,0.00015881142,0.00014570313,0.000026856844,0.0004286026,0.00012747088,0.0003714755,0.00009131881,0.000005402858],"category_scores_gemma":[0.000043366414,0.0001259418,0.00005379208,0.000019224384,0.00014105855,0.0000030054491,0.00024724627,0.000048005506,0.00002766109],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039063633,0.00017894355,0.072037175,0.00039661172,0.0011003606,0.00002244123,0.0031461807,0.0006247892,0.8761645,0.0014931764,0.0038476628,0.040597517],"study_design_scores_gemma":[0.004624697,0.0021768946,0.42406476,0.00014355764,0.00021640753,0.00015784748,0.001510542,0.0026779242,0.082219794,0.00042736466,0.47963864,0.002141567],"about_ca_topic_score_codex":0.000010401017,"about_ca_topic_score_gemma":0.000022964123,"teacher_disagreement_score":0.7939447,"about_ca_system_score_codex":0.000009376103,"about_ca_system_score_gemma":0.000053007225,"threshold_uncertainty_score":0.5135758},"labels":[],"label_agreement":null},{"id":"W2768250222","doi":"10.1093/bioinformatics/bty498","title":"A descriptive marker gene approach to single-cell pseudotime inference","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Statistical Sciences Institute; Medical Research Council","keywords":"Computer science; Inference; Python (programming language); Trajectory; Bayesian probability; Artificial intelligence; Gene; Pattern recognition (psychology); Data mining; Computational biology; Biology; Genetics","score_opus":0.0261985328342391,"score_gpt":0.2282672827784173,"score_spread":0.2020687499441782,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2768250222","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6939348,0.000068706606,0.24072869,0.00003686899,0.00038924775,0.00040518484,0.000048445534,0.000049934224,0.06433812],"genre_scores_gemma":[0.8694826,0.000018903216,0.12774429,0.0009372403,0.0003234268,0.00001723211,0.00011932786,0.000029616453,0.0013274075],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988116,0.000025706962,0.0003548864,0.0002409728,0.0001817967,0.00038503116],"domain_scores_gemma":[0.9990621,0.0000098124265,0.00009269249,0.0004441169,0.00019711776,0.00019411],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015777866,0.00023605023,0.00017873489,0.00007331247,0.00012075882,0.0000806553,0.00033352058,0.00018843942,0.000023195118],"category_scores_gemma":[0.00007643733,0.00021682457,0.000088728826,0.00017516308,0.00013581719,0.000013825642,0.00013557909,0.000089943045,0.00022058768],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023389561,0.00048661913,0.002194387,0.00009513018,0.00006500189,0.0000010306478,0.002279752,0.00006230413,0.9797528,0.00010485294,0.0094214305,0.0053027915],"study_design_scores_gemma":[0.001155679,0.0015977821,0.0010991213,0.0000325148,0.000047404,0.000030466434,0.00055676623,0.011573758,0.9386188,0.00004559651,0.044435523,0.00080658734],"about_ca_topic_score_codex":0.000015100886,"about_ca_topic_score_gemma":0.000008950769,"teacher_disagreement_score":0.17554776,"about_ca_system_score_codex":0.000031156298,"about_ca_system_score_gemma":0.000087237604,"threshold_uncertainty_score":0.88418496},"labels":[],"label_agreement":null},{"id":"W2768349867","doi":"10.1093/bioinformatics/btx749","title":"glactools: a command-line toolset for the management of genotype likelihoods and allele counts","year":2017,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Max-Planck-Gesellschaft","keywords":"Computer science; Population; Workflow; Set (abstract data type); Scripting language; Source code; Software; Bespoke; Database; Programming language","score_opus":0.028889968602558148,"score_gpt":0.29922432142460437,"score_spread":0.2703343528220462,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2768349867","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5748196,0.0064085755,0.32153425,0.0052131643,0.0013649657,0.0029361572,0.0008068785,0.000035628145,0.08688078],"genre_scores_gemma":[0.9518095,0.0025898356,0.043154992,0.00037514046,0.00010676932,0.00003033431,0.00014431705,0.000009249245,0.0017798208],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9996907,0.0000048630045,0.00014138123,0.000044285844,0.00003475912,0.0000839723],"domain_scores_gemma":[0.9995281,0.000015005779,0.00013519939,0.0002678793,0.000037934864,0.000015889575],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019871123,0.000048187023,0.00007205888,0.000005836575,0.00013149071,0.000015944292,0.00014158059,0.00005294394,0.0000060492607],"category_scores_gemma":[0.000042233856,0.00003336386,0.000028773955,0.0000067115175,0.000050239483,0.0000028759616,0.00009527416,0.000019026862,0.000004908987],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002571905,0.00016357155,0.028286496,0.001070758,0.0019584408,9.708027e-7,0.0006631572,0.00026274563,0.0013472195,0.011518259,0.26607707,0.6883941],"study_design_scores_gemma":[0.0011578394,0.0002972049,0.065725915,0.00002051895,0.00013222721,0.0000048914208,0.000364245,0.017116811,0.00060578965,0.0009414442,0.91343623,0.00019689048],"about_ca_topic_score_codex":0.0000033987685,"about_ca_topic_score_gemma":0.0000052843848,"teacher_disagreement_score":0.6881972,"about_ca_system_score_codex":0.0000026279117,"about_ca_system_score_gemma":0.000010611993,"threshold_uncertainty_score":0.13605388},"labels":[],"label_agreement":null},{"id":"W2769159716","doi":"10.1093/bioinformatics/btx764","title":"CytoCtrlAnalyser: a Cytoscape app for biomolecular network controllability analysis","year":2017,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"National Natural Science Foundation of China","keywords":"Controllability; Computer science; Biological network; Upload; Network topology; Identification (biology); Network controllability; Complex network; Network analysis; Control (management); Distributed computing; Data mining; Bioinformatics; Artificial intelligence; Computer network; World Wide Web; Biology; Engineering; Mathematics","score_opus":0.011222578171884837,"score_gpt":0.261826191908094,"score_spread":0.25060361373620915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2769159716","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055428,0.0006960958,0.93215483,0.00041396116,0.0005047356,0.0014388628,0.00031717186,0.00006317478,0.008983191],"genre_scores_gemma":[0.94719994,0.00012481092,0.049861606,0.00078997226,0.000613526,0.00009807909,0.00077360583,0.00003061749,0.00050783565],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99823576,0.000023284081,0.0007069465,0.00026568942,0.00019029091,0.0005780471],"domain_scores_gemma":[0.99721617,0.000028707727,0.0006465634,0.0017213916,0.00020160545,0.00018558977],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007603956,0.00029336396,0.00048633403,0.00006541962,0.0007212272,0.00033751482,0.00078002084,0.00029343992,0.000018945495],"category_scores_gemma":[0.00019220849,0.00026132754,0.00061196694,0.00015864288,0.00017912319,0.00002174406,0.0002828251,0.00009705316,0.00002473307],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006129094,0.001328493,0.14821064,0.0025218276,0.061049376,0.000025581887,0.00225899,0.1245698,0.08040561,0.028773421,0.31047487,0.2342523],"study_design_scores_gemma":[0.005279373,0.0008301694,0.00943401,0.000035937202,0.0031120733,0.00001783203,0.00021694269,0.74625236,0.0062133796,0.0028529277,0.22412537,0.0016296438],"about_ca_topic_score_codex":0.000015232215,"about_ca_topic_score_gemma":0.000076086064,"teacher_disagreement_score":0.891772,"about_ca_system_score_codex":0.0000233809,"about_ca_system_score_gemma":0.000097910815,"threshold_uncertainty_score":0.9999839},"labels":[],"label_agreement":null},{"id":"W2770747919","doi":"10.1093/bioinformatics/btx752","title":"Reactome diagram viewer: data structures and strategies to boost performance","year":2017,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":235,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research","funders":"National Institute of General Medical Sciences; National Institutes of Health; National Human Genome Research Institute; University of Toronto; European Bioinformatics Institute","keywords":"Computer science; Visualization; Usability; Scalability; HTML5; Rendering (computer graphics); Data visualization; Data mining; Information retrieval; World Wide Web; Human–computer interaction; Database; Artificial intelligence","score_opus":0.0251877592865337,"score_gpt":0.2801560565035076,"score_spread":0.2549682972169739,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2770747919","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95880616,0.0008341098,0.013968384,0.0005326385,0.00073740806,0.0006907933,0.00035047813,0.00004404688,0.024035998],"genre_scores_gemma":[0.9824924,0.0009879869,0.015036879,0.00058621465,0.00026801325,0.000007648732,0.0003632714,0.000017293154,0.00024030895],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989936,0.0000072481535,0.00034709676,0.00019471261,0.00014332395,0.00031405594],"domain_scores_gemma":[0.9977184,0.000006757698,0.00022900639,0.0018212969,0.000057612182,0.00016693195],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026965464,0.00020536575,0.00018151519,0.000038309303,0.00040860754,0.0005434824,0.0009930113,0.00015469812,0.00000703454],"category_scores_gemma":[0.00007885131,0.00017137066,0.000029262193,0.000027421005,0.00013813401,0.00006752447,0.001185002,0.000113255024,0.000028392804],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001842808,0.000052730542,0.007082854,0.0006703253,0.00025174566,0.0000036055553,0.0017695517,0.0002598743,0.0053058746,0.0032597338,0.04370481,0.93745464],"study_design_scores_gemma":[0.0018235701,0.0010249144,0.11103188,0.0001567605,0.00011050447,0.00014358194,0.0017273667,0.06596979,0.005123677,0.0010537915,0.8101283,0.0017058639],"about_ca_topic_score_codex":0.000020489419,"about_ca_topic_score_gemma":0.00005916933,"teacher_disagreement_score":0.93574876,"about_ca_system_score_codex":0.0000072726525,"about_ca_system_score_gemma":0.000082247454,"threshold_uncertainty_score":0.69882923},"labels":[],"label_agreement":null},{"id":"W2773943265","doi":"10.1093/bioinformatics/btx807","title":"Computational identification of micro-structural variations and their proteogenomic consequences in cancer","year":2017,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"National Cancer Institute; National Institutes of Health; National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; Indiana University","keywords":"Identification (biology); Computer science; Computational biology; Proteogenomics; Artificial intelligence; Biology; Genetics; Genome; Genomics; Gene","score_opus":0.02001339280471797,"score_gpt":0.2992022984635289,"score_spread":0.27918890565881094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2773943265","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9542365,0.00006575264,0.04385004,0.00037881316,0.000019525749,0.0002769761,0.00035927357,0.000027899232,0.00078518613],"genre_scores_gemma":[0.92530775,0.00005204685,0.07445603,0.0000116205665,0.0000118092485,0.000088457804,0.000033441927,0.0000042543647,0.00003458227],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994761,0.0000023131731,0.000333535,0.00006858171,0.00004492552,0.000074561154],"domain_scores_gemma":[0.9992485,0.00002261987,0.0004368727,0.0002173986,0.00005488465,0.000019747757],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006595809,0.00006847034,0.0000943299,0.000031315536,0.00017818857,0.000052915748,0.0001750141,0.000047646387,0.00002127345],"category_scores_gemma":[0.000028847466,0.000060223385,0.00001772836,0.000024027111,0.00018693443,0.0001932305,0.000049649072,0.00006210293,0.0000012128432],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025438283,0.00004731746,0.03300836,0.00062841485,0.000049235106,3.5105373e-7,0.00358634,0.0027189574,0.87237865,0.052890938,0.000047078778,0.034618914],"study_design_scores_gemma":[0.00050048553,0.000009754301,0.017680164,0.00010817674,0.000012284458,0.000013158134,0.00038226685,0.21843448,0.68826157,0.07407603,0.00027067956,0.00025095258],"about_ca_topic_score_codex":0.00008265275,"about_ca_topic_score_gemma":0.000015610542,"teacher_disagreement_score":0.21571553,"about_ca_system_score_codex":0.000033783082,"about_ca_system_score_gemma":0.00005474181,"threshold_uncertainty_score":0.24558383},"labels":[],"label_agreement":null},{"id":"W2774750904","doi":"10.1093/bioinformatics/btx769","title":"Model-based design of bistable cell factories for metabolic engineering","year":2017,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Microbial Metabolic Engineering and Bioproduction","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Max Planck Institute for Dynamics of Complex Technical Systems Magdeburg; Ontario Ministry of Research and Innovation; Natural Sciences and Engineering Research Council of Canada","keywords":"Bistability; Metabolic engineering; Computer science; Biology; Materials science; Genetics","score_opus":0.02065703111434475,"score_gpt":0.22984291311245614,"score_spread":0.2091858819981114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2774750904","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058976706,0.00029071482,0.94003433,0.000016050713,0.00027185332,0.0002270321,0.00006342532,0.000015768686,0.00010409076],"genre_scores_gemma":[0.7784356,0.000073749296,0.22102991,0.000012831577,0.00011643263,0.0000151895,0.000041758223,0.000014609832,0.00025991863],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994983,0.000003014972,0.0001979707,0.000087939276,0.000058164045,0.00015462293],"domain_scores_gemma":[0.9992971,0.000003433627,0.00014895007,0.0004241637,0.000090457215,0.000035922676],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013298543,0.00011263269,0.00014242437,0.000037280264,0.000089384404,0.00003527219,0.00019221981,0.00008641133,9.974747e-7],"category_scores_gemma":[0.0001521906,0.00010236844,0.000064790314,0.000021384778,0.000030308693,0.00001061726,0.00003223678,0.000031383093,0.0000010850919],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024999026,0.00001681523,0.00002229024,0.00018255821,0.000015693895,2.0189956e-8,0.000035835543,0.12546197,0.8730882,0.0001041388,0.0004790655,0.00056843885],"study_design_scores_gemma":[0.00028864367,0.00005142754,0.00004726012,0.000008376563,0.000019884179,4.7221465e-7,0.000007541682,0.23892657,0.7460372,0.000005623412,0.014499325,0.00010770559],"about_ca_topic_score_codex":0.0000043582017,"about_ca_topic_score_gemma":4.87794e-7,"teacher_disagreement_score":0.7194589,"about_ca_system_score_codex":0.000003678669,"about_ca_system_score_gemma":0.000056914338,"threshold_uncertainty_score":0.41744637},"labels":[],"label_agreement":null},{"id":"W2779222065","doi":"10.1093/bioinformatics/btx821","title":"DyNetViewer: a Cytoscape app for dynamic network construction, analysis and visualization","year":2017,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Central South University; National Natural Science Foundation of China","keywords":"Visualization; Computer science; Cluster analysis; Network analysis; Data mining; Data visualization; Graph drawing; Machine learning","score_opus":0.006517248778063056,"score_gpt":0.25594796557713834,"score_spread":0.24943071679907527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2779222065","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04801135,0.0004892292,0.94823045,0.000116905176,0.00041715926,0.00055153575,0.000098320146,0.000029670404,0.0020553889],"genre_scores_gemma":[0.83795077,0.0015093832,0.15738378,0.0005774978,0.0004660108,0.000065586806,0.0013956474,0.000037305217,0.0006140112],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99906546,0.000009646946,0.00041458482,0.00014834337,0.00009056733,0.00027138225],"domain_scores_gemma":[0.99877274,0.000012755721,0.00043933457,0.00056462246,0.0001180871,0.00009246928],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002880874,0.00016851946,0.00023105492,0.00006336642,0.0005693529,0.00022732397,0.00022758482,0.00018257914,0.000006822632],"category_scores_gemma":[0.000070024435,0.00015801363,0.00013190071,0.00008978701,0.00016147818,0.000022483342,0.0001522512,0.00004865556,0.0000047492185],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00077887264,0.0002049863,0.094227746,0.0018303923,0.008446997,0.0000022469403,0.0018546071,0.01155337,0.004279469,0.042924587,0.060725313,0.7731714],"study_design_scores_gemma":[0.0016911662,0.0003370434,0.014998651,0.00004292696,0.000884578,0.000032858017,0.00031116846,0.88382244,0.0006072295,0.0023018194,0.094228804,0.0007413233],"about_ca_topic_score_codex":0.000004766182,"about_ca_topic_score_gemma":0.00007749176,"teacher_disagreement_score":0.87226903,"about_ca_system_score_codex":0.000011120173,"about_ca_system_score_gemma":0.00004147068,"threshold_uncertainty_score":0.6443609},"labels":[],"label_agreement":null},{"id":"W2780622732","doi":"10.1093/bioinformatics/btx839","title":"ChopStitch: exon annotation and splice graph construction using transcriptome assembly and whole genome sequencing data","year":2017,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"National Human Genome Research Institute; National Institutes of Health","keywords":"Annotation; splice; Sequence assembly; Exon; Computational biology; Genome; Transcriptome; Computer science; Whole genome sequencing; Genome project; Graph; RNA splicing; Genetics; Exon skipping; Gene Annotation; Biology; Alternative splicing; Gene; Theoretical computer science; RNA; Gene expression","score_opus":0.05435405250254151,"score_gpt":0.2784282938971421,"score_spread":0.22407424139460058,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2780622732","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9927856,0.0009745931,0.0053110123,0.000057779103,0.00014090243,0.00014026345,0.0001811438,0.0000035797855,0.00040517122],"genre_scores_gemma":[0.9673132,0.0011563022,0.031200208,0.000068036476,0.0001022584,0.000002244708,0.00013184916,0.000009892901,0.000016063766],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99940264,0.000009145559,0.00019716499,0.00017481692,0.00006962407,0.00014662113],"domain_scores_gemma":[0.9992245,0.0000049863092,0.00016486667,0.0005039212,0.00004645139,0.00005528817],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016256045,0.00012034375,0.00011750956,0.00003432303,0.00040618825,0.00011473789,0.00018242204,0.00008100455,5.585882e-7],"category_scores_gemma":[0.00004001517,0.000118215146,0.0000173971,0.000020307889,0.00016170584,0.000016658349,0.00021540088,0.000044385983,8.8322867e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014365366,0.0000048237225,0.004261157,0.00008975689,0.000059194594,6.2531376e-7,0.0005580008,0.000043240492,0.98802453,0.000054931967,0.000032887277,0.006856484],"study_design_scores_gemma":[0.009378003,0.0014836973,0.52545685,0.0003665824,0.0011378526,0.0014912932,0.02253035,0.21748726,0.103899814,0.002066954,0.11040158,0.0042997794],"about_ca_topic_score_codex":0.00004613426,"about_ca_topic_score_gemma":0.000030148985,"teacher_disagreement_score":0.8841247,"about_ca_system_score_codex":0.000008809567,"about_ca_system_score_gemma":0.00003454221,"threshold_uncertainty_score":0.48206738},"labels":[],"label_agreement":null},{"id":"W2784883284","doi":"10.1093/bioinformatics/bty494","title":"Deep convolutional networks for quality assessment of protein folds","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":112,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canadian Institute for Advanced Research","keywords":"Computer science; Convolutional neural network; Quality assessment; Quality (philosophy); Artificial intelligence; Reliability engineering; Evaluation methods; Engineering","score_opus":0.014708584649960195,"score_gpt":0.30088106583445734,"score_spread":0.2861724811844971,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2784883284","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06576929,0.000085114225,0.9311295,0.000028235858,0.00013588194,0.0004884713,0.000046974892,0.000008882533,0.0023076234],"genre_scores_gemma":[0.8336302,0.000008133878,0.16553524,0.00014767984,0.00026097568,0.00004246306,0.00025100686,0.000007885176,0.00011643201],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99925715,0.000016414222,0.00034816566,0.000091748625,0.000115513,0.0001709837],"domain_scores_gemma":[0.99927384,0.000010486834,0.00019851564,0.00025038264,0.0002220939,0.00004466778],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025494586,0.00009868114,0.00012895683,0.000020158404,0.000067814784,0.000010962207,0.00014008123,0.00014965136,0.000009078889],"category_scores_gemma":[0.00006253809,0.00008700234,0.000081707934,0.000047976602,0.00013613222,0.0000053916356,0.00007152009,0.000039387152,0.0000011100161],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017229967,0.0007043123,0.026772348,0.0027988367,0.0014818906,0.0000010767931,0.0008815513,0.007415176,0.40108284,0.40474784,0.0126110455,0.13978007],"study_design_scores_gemma":[0.0023982488,0.0019880407,0.01563376,0.00005285454,0.000051547857,0.000010387107,0.00019049182,0.89116776,0.050417777,0.0038605814,0.03359827,0.0006302705],"about_ca_topic_score_codex":0.0000041598764,"about_ca_topic_score_gemma":0.000019033161,"teacher_disagreement_score":0.8837526,"about_ca_system_score_codex":0.000013860845,"about_ca_system_score_gemma":0.00010288624,"threshold_uncertainty_score":0.35478526},"labels":[],"label_agreement":null},{"id":"W2788915007","doi":"10.1093/bioinformatics/bty082","title":"flowLearn: fast and precise identification and quality checking of cell populations in flow cytometry","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; Terry Fox Research Institute; University of British Columbia","funders":"National Institute of Allergy and Infectious Diseases; National Institutes of Health; Wellcome Trust; California Department of Fish and Game; National Institute of General Medical Sciences; Wellcome","keywords":"Identification (biology); Flow cytometry; Computer science; Flow (mathematics); Quality (philosophy); Computational biology; Biology; Mathematics; Molecular biology; Physics","score_opus":0.04216526388673059,"score_gpt":0.292363036621574,"score_spread":0.2501977727348434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2788915007","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9793173,0.00012999726,0.019663084,0.000014365021,0.00009368237,0.00010755337,0.000024102677,0.0000051491133,0.00064476574],"genre_scores_gemma":[0.98389715,0.00009719875,0.015769972,0.00003067837,0.000043939282,0.0000021918156,0.000072299765,0.0000061584847,0.000080400394],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99936867,0.000019204814,0.00034549183,0.00009436117,0.0000739261,0.00009834251],"domain_scores_gemma":[0.99963665,0.0000075982516,0.00010519223,0.00015500508,0.00005814324,0.000037426875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022927247,0.00007453561,0.00010143477,0.00006660988,0.000040944095,0.00002358374,0.00005830273,0.00009336425,0.0000031403692],"category_scores_gemma":[0.000055418277,0.00007376485,0.00002090018,0.00009130894,0.00008923995,0.000012425187,0.000039289574,0.000042111642,0.000001960172],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000065774584,0.00009063861,0.0668408,0.00032319277,0.000014054072,1.1381343e-7,0.0021898553,0.000040260093,0.90642273,0.00008875075,0.00007646525,0.023847384],"study_design_scores_gemma":[0.0013765513,0.00027131865,0.22545855,0.000062379186,0.000032941425,0.0000053593585,0.00093695876,0.05729798,0.71281636,0.00012236099,0.001267254,0.00035197052],"about_ca_topic_score_codex":0.000026624877,"about_ca_topic_score_gemma":0.000090057816,"teacher_disagreement_score":0.19360633,"about_ca_system_score_codex":0.00000625494,"about_ca_system_score_gemma":0.000015791584,"threshold_uncertainty_score":0.30080435},"labels":[],"label_agreement":null},{"id":"W2789853766","doi":"10.1093/bioinformatics/bty075","title":"chromswitch: a flexible method to detect chromatin state switches","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Jewish General Hospital","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Compute Canada","keywords":"Bioconductor; Epigenomics; Chromatin; Computer science; Benchmarking; Key (lock); Epigenetics; Source code; State (computer science); Data mining; Computational biology; Biology; Gene; DNA methylation; Gene expression; Programming language; Genetics; Operating system","score_opus":0.011509805674919115,"score_gpt":0.2669648109639451,"score_spread":0.255455005289026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2789853766","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5804595,0.000059049213,0.413553,0.000107268475,0.00019223135,0.00033602453,0.000055910838,0.000059072427,0.005177939],"genre_scores_gemma":[0.40232736,0.000038115373,0.5942104,0.001391384,0.00037312228,0.00003539092,0.00009161567,0.000054047265,0.0014785769],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99866074,0.000023898725,0.0004615692,0.00023447114,0.0001838189,0.00043549942],"domain_scores_gemma":[0.99890107,0.000012867345,0.00016028479,0.00058029394,0.00014905984,0.00019643946],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039284813,0.00024561907,0.00021219975,0.00009130889,0.00015663862,0.000089399415,0.00037934983,0.00013409181,0.00004621048],"category_scores_gemma":[0.000074176205,0.00022804836,0.000096210315,0.0002047993,0.00006723028,0.000009044351,0.00028891722,0.00007739342,0.00040796885],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000101111575,0.00004787262,0.00019882892,0.00015296374,0.0001485263,0.0000016135165,0.0016752126,0.0003240864,0.8879154,0.00016205452,0.0141552305,0.09511711],"study_design_scores_gemma":[0.00076535105,0.0014163235,0.0015219023,0.00004497759,0.000025943698,0.0000643548,0.00036988314,0.019170113,0.82970554,0.0009129966,0.1452796,0.0007230049],"about_ca_topic_score_codex":0.000019138766,"about_ca_topic_score_gemma":0.000065531276,"teacher_disagreement_score":0.18065739,"about_ca_system_score_codex":0.00003656887,"about_ca_system_score_gemma":0.00012973302,"threshold_uncertainty_score":0.92995423},"labels":[],"label_agreement":null},{"id":"W2790921906","doi":"10.1093/bioinformatics/bty095","title":"Improved genomic island predictions with IslandPath-DIMOB","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":223,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Computer science; Computational biology; Biology","score_opus":0.004793943520078781,"score_gpt":0.2206221854113326,"score_spread":0.21582824189125382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2790921906","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5703038,0.00010150583,0.3327569,0.00019781668,0.0006401781,0.0008310604,0.00021027433,0.00019171619,0.09476673],"genre_scores_gemma":[0.91740257,0.000067977046,0.07737092,0.000889104,0.00092073024,0.000032858177,0.00046901626,0.00005371528,0.0027931272],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989624,0.000017774615,0.00037847983,0.0001456663,0.00015950846,0.00033618626],"domain_scores_gemma":[0.9989816,0.000010189184,0.00020276953,0.0005429663,0.00015112106,0.00011134507],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017639846,0.00021662563,0.00015089716,0.000072847426,0.00021745019,0.00007373568,0.00026780958,0.00015846323,0.0000762873],"category_scores_gemma":[0.000070067355,0.00016713336,0.00005769524,0.00012655731,0.00021014981,0.000017210767,0.00014277082,0.00014394437,0.0001494319],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004113267,0.0012381069,0.1590388,0.0024420274,0.0033521003,0.000020451118,0.030997539,0.0046077752,0.23189913,0.003474673,0.48256263,0.0762535],"study_design_scores_gemma":[0.0040326705,0.0059386096,0.009427648,0.00009126384,0.0001552652,0.00043712667,0.0011096474,0.437321,0.020789977,0.000055264692,0.5192991,0.0013424163],"about_ca_topic_score_codex":0.000011678708,"about_ca_topic_score_gemma":0.00013639712,"teacher_disagreement_score":0.43271324,"about_ca_system_score_codex":0.000020334282,"about_ca_system_score_gemma":0.00012020609,"threshold_uncertainty_score":0.6815501},"labels":[],"label_agreement":null},{"id":"W2793111149","doi":"10.1093/bioinformatics/bty153","title":"Data mining of effect sizes from PubMed abstracts: a cross-study conceptual replication","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Université de Toulouse; Agence Nationale de la Recherche","keywords":"Replication (statistics); Computer science; Data mining; Computational biology; Data science; Statistics; Biology; Mathematics","score_opus":0.23823442753928825,"score_gpt":0.4248347766624087,"score_spread":0.18660034912312046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2793111149","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9859447,0.000014610926,0.0056434553,0.000039112867,0.0009867527,0.0004845979,0.00049864186,0.000057185367,0.006330962],"genre_scores_gemma":[0.98702747,5.519593e-7,0.012213109,0.000063684325,0.000142452,0.0000088014585,0.00019903615,0.0000044770054,0.00034040306],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9965344,0.00008985632,0.0013251259,0.00053029653,0.001287922,0.00023238848],"domain_scores_gemma":[0.99204135,0.0018434532,0.0008084599,0.0049349274,0.0002829438,0.00008884714],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011217741,0.00011750129,0.00025482982,0.00016236096,0.00018198777,0.00065759633,0.0025317732,0.000041858006,0.00011410435],"category_scores_gemma":[0.014449657,0.00008249444,0.000037990365,0.00061746675,0.0003822458,0.000954621,0.0014682842,0.00005624925,0.00043271357],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000947644,0.00022389738,0.113469474,0.000016795086,0.000081883045,0.0000019148008,0.0126059605,0.00007426947,0.000036687696,0.00006900149,0.13198848,0.7413369],"study_design_scores_gemma":[0.0015029702,0.00048674404,0.7482431,0.000037837268,0.00006214856,0.0000019555978,0.017812481,0.15557057,0.0009187326,0.00028944976,0.074771486,0.0003025608],"about_ca_topic_score_codex":0.00008435193,"about_ca_topic_score_gemma":0.000051460935,"teacher_disagreement_score":0.7410343,"about_ca_system_score_codex":0.00001768776,"about_ca_system_score_gemma":0.00003886366,"threshold_uncertainty_score":0.9938521},"labels":[],"label_agreement":null},{"id":"W2793136329","doi":"10.1093/bioinformatics/bty208","title":"MechRNA: prediction of lncRNA mechanisms from RNA–RNA and RNA–protein interactions","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Cancer-related molecular mechanisms research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":111,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Institute of General Medical Sciences; Deutsche Forschungsgemeinschaft; Baden-Württemberg Stiftung","keywords":"RNA; Computational biology; Non-coding RNA; Biology; RNA editing; Genetics; Gene","score_opus":0.012646024646255302,"score_gpt":0.25746365466075644,"score_spread":0.24481763001450113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2793136329","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2953131,0.00027667964,0.69690365,0.00013984597,0.00057668175,0.00057912455,0.00040293214,0.000043464777,0.005764538],"genre_scores_gemma":[0.9693462,0.0002013055,0.029257264,0.00012718087,0.0002742069,0.000031480366,0.00022015588,0.000030583888,0.00051157793],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988118,0.00003716322,0.00041481137,0.00020276624,0.00028293938,0.0002505344],"domain_scores_gemma":[0.99897516,0.00001138933,0.00019818942,0.00043898326,0.00025199697,0.00012426525],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019392313,0.00017029404,0.00016893502,0.000114648254,0.00011639663,0.00004439918,0.00020298119,0.00020917348,0.000110284134],"category_scores_gemma":[0.00013519719,0.00016693155,0.00007895475,0.00014225102,0.00012868509,0.00002414667,0.00023251494,0.00016491105,0.000034611192],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007772338,0.000029332286,0.0000019477986,0.000031501488,0.000105629144,7.858676e-7,0.0001837654,0.0000075649473,0.9877107,0.0006766861,0.0010579902,0.010116355],"study_design_scores_gemma":[0.0006167573,0.0005712584,0.000051546245,0.000073363946,0.000035125628,0.000011284588,0.00022308013,0.0067284233,0.98151743,0.001390873,0.008633792,0.000147062],"about_ca_topic_score_codex":0.000101002166,"about_ca_topic_score_gemma":0.00004918425,"teacher_disagreement_score":0.67403316,"about_ca_system_score_codex":0.000037823913,"about_ca_system_score_gemma":0.000105559164,"threshold_uncertainty_score":0.6807271},"labels":[],"label_agreement":null},{"id":"W2793622104","doi":"10.1093/bioinformatics/bty136","title":"ddPCRclust: an R package and Shiny app for automated analysis of multiplexed ddPCR data","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Innovative Microfluidic and Catalytic Techniques Innovation","field":"Engineering","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bottleneck; Digital polymerase chain reaction; Computer science; Throughput; Multiplexing; Interface (matter); Operating system; Embedded system; Polymerase chain reaction; Biology","score_opus":0.035184368106834216,"score_gpt":0.2955873917552118,"score_spread":0.2604030236483776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2793622104","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08606836,0.000043853943,0.90977,0.0000141565115,0.000114397364,0.00037993168,0.0011576407,0.0010514879,0.0014001465],"genre_scores_gemma":[0.86318684,0.000010279494,0.13401736,0.0000702895,0.00004545816,0.000010246775,0.002617777,0.000020095984,0.000021663827],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990904,0.0000051350935,0.00051653525,0.000106478336,0.00011076474,0.00017068587],"domain_scores_gemma":[0.99895424,0.00003310361,0.000115493014,0.000633333,0.0002318409,0.000031974065],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004168108,0.00013355656,0.00025092284,0.00034770003,0.000058093596,0.0000310027,0.0002964959,0.00010111961,0.000014191951],"category_scores_gemma":[0.000075057316,0.0001249229,0.000026726362,0.0010207081,0.00013130302,0.00047154372,0.00010412963,0.00005568659,0.0000035805206],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015571421,0.00024425445,0.0026909094,0.0025860853,0.0047932244,0.0000018464284,0.018236168,0.0003938421,0.5544221,0.022827052,0.15142846,0.24222036],"study_design_scores_gemma":[0.0002523839,0.00007280482,0.0014892154,0.000014487233,0.00018258335,0.0000013613123,0.00027578144,0.94073325,0.05253686,0.000045100885,0.004242724,0.00015343123],"about_ca_topic_score_codex":0.000007878283,"about_ca_topic_score_gemma":0.000004475023,"teacher_disagreement_score":0.94033945,"about_ca_system_score_codex":0.000028545715,"about_ca_system_score_gemma":0.00001760503,"threshold_uncertainty_score":0.50942075},"labels":[],"label_agreement":null},{"id":"W2793784779","doi":"10.1093/bioinformatics/bty046","title":"pymzML v2.0: introducing a highly compressed and seekable gzip format","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":90,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Jewish General Hospital","funders":"","keywords":"Computer science; Random access; Scripting language; File format; Documentation; Code (set theory); Source code; Scheme (mathematics); Field (mathematics); MIT License; Data file; Data compression; Algorithm; Software; Computational science; Computer engineering; Database; Programming language; Set (abstract data type)","score_opus":0.008613553688783167,"score_gpt":0.22951924981960134,"score_spread":0.22090569613081817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2793784779","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.955278,0.0015338627,0.017683623,0.00043091952,0.0006132162,0.00035942733,0.000050725175,0.000056193538,0.023994066],"genre_scores_gemma":[0.96428394,0.0010187447,0.032609668,0.0007125795,0.00060674024,0.000012174683,0.000067667956,0.000019628647,0.00066887937],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99911594,0.000013227808,0.00029676623,0.00016096944,0.000114020935,0.00029908319],"domain_scores_gemma":[0.9993291,0.000014343306,0.0001237643,0.00034318856,0.000106092426,0.00008349996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020676738,0.00016491028,0.00019657688,0.00006755866,0.00019852072,0.00006618213,0.00014725665,0.000091284455,0.000019484029],"category_scores_gemma":[0.0001253273,0.00013961387,0.00004474195,0.000105206804,0.0001536991,0.000014986124,0.00026704668,0.00006517971,0.000038877202],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038573606,0.00020808296,0.0073193037,0.00069833675,0.00078610936,0.000003461461,0.0035155516,0.000040135827,0.7149982,0.010202224,0.23346849,0.028374374],"study_design_scores_gemma":[0.0013776951,0.0008074517,0.0023677156,0.000029211593,0.00006221847,0.000045123088,0.0007688974,0.010498923,0.21876766,0.00033916757,0.7643825,0.00055347185],"about_ca_topic_score_codex":0.000011525369,"about_ca_topic_score_gemma":0.00001707931,"teacher_disagreement_score":0.53091395,"about_ca_system_score_codex":0.000009337475,"about_ca_system_score_gemma":0.000029269331,"threshold_uncertainty_score":0.56932884},"labels":[],"label_agreement":null},{"id":"W2796130155","doi":"10.1093/bioinformatics/bty242","title":"Accurate prediction of orthologs in the presence of divergence after duplication","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Gene duplication; Phylogenetic tree; Phylogenetics; Computational biology; Gene; Biology; Divergence (linguistics); Similarity (geometry); Function (biology); Computer science; Evolutionary biology; Genetics; Artificial intelligence","score_opus":0.015191951221622946,"score_gpt":0.2430373068675879,"score_spread":0.22784535564596495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2796130155","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99722016,0.00016945164,0.0015727155,0.000029745137,0.00006896773,0.00013012401,0.000044689423,6.914905e-7,0.00076347264],"genre_scores_gemma":[0.9981513,0.0002482501,0.0014745372,0.00004611191,0.000037591562,0.000014714305,0.000009825807,0.0000019680547,0.000015671974],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9995698,0.0000146821785,0.00022487977,0.000053691325,0.000066845416,0.000070120834],"domain_scores_gemma":[0.9995657,0.000009931443,0.00011264612,0.00021522111,0.000088148896,0.000008353207],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015890689,0.00004791925,0.000058398105,0.000019180336,0.000019319175,0.0000028485158,0.000137862,0.000041487598,0.0000029486107],"category_scores_gemma":[0.00005059418,0.000033462064,0.00002354173,0.00007381301,0.00012838213,0.0000014923716,0.000069089525,0.000019502611,0.0000022245679],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032234436,0.00026774668,0.5250026,0.00031044317,0.000105294115,5.660728e-7,0.014091489,0.00027254678,0.4451698,0.000709777,0.0026751736,0.011072206],"study_design_scores_gemma":[0.00029248474,0.0004845483,0.89386237,0.000020529991,0.00001645842,0.000004308314,0.00078079547,0.0024529796,0.09756917,0.00014093019,0.0042912783,0.00008415896],"about_ca_topic_score_codex":0.0000080383925,"about_ca_topic_score_gemma":0.000016041264,"teacher_disagreement_score":0.36885977,"about_ca_system_score_codex":0.0000017399578,"about_ca_system_score_gemma":0.000016349226,"threshold_uncertainty_score":0.13645434},"labels":[],"label_agreement":null},{"id":"W2801106948","doi":"10.1093/bioinformatics/bty368","title":"Improved enzyme annotation with EC-specific cutoffs using DETECT v2","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; Hospital for Sick Children; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; National Institute of Allergy and Infectious Diseases; Government of Ontario","keywords":"Annotation; Computer science; Enzyme; Artificial intelligence; Chemistry; Biochemistry","score_opus":0.012649891050087679,"score_gpt":0.22722516158106076,"score_spread":0.21457527053097308,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2801106948","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40886766,0.0004042791,0.5828496,0.000049823706,0.0005196584,0.00057804695,0.000048644026,0.00006285873,0.0066193826],"genre_scores_gemma":[0.853604,0.000119577286,0.14431494,0.00059376966,0.0008555389,0.000011052945,0.0001899761,0.000042789827,0.00026831313],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998877,0.000014403086,0.00042912707,0.00015856345,0.00014808401,0.0003728088],"domain_scores_gemma":[0.9989883,0.000007803872,0.00024690724,0.00045802275,0.00018868988,0.00011032633],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001939784,0.00022541858,0.00016345878,0.00006669768,0.00019666474,0.00009960379,0.00021459162,0.00019326038,0.000023761255],"category_scores_gemma":[0.000012940243,0.00018408011,0.00006465501,0.00016104555,0.00017659985,0.000024047491,0.000100363446,0.00010395047,0.000049277187],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017074259,0.00025881076,0.0010875197,0.0005521045,0.0007883311,0.000009104383,0.0056313816,0.0023877758,0.63260895,0.0013714742,0.048428193,0.3051689],"study_design_scores_gemma":[0.0023815017,0.002539301,0.0003185836,0.000093519484,0.00007501874,0.00019679723,0.0008974392,0.5850778,0.18924181,0.00019053729,0.21780685,0.0011808481],"about_ca_topic_score_codex":0.000009058133,"about_ca_topic_score_gemma":0.000030778345,"teacher_disagreement_score":0.58269,"about_ca_system_score_codex":0.000030093299,"about_ca_system_score_gemma":0.00010216143,"threshold_uncertainty_score":0.7506569},"labels":[],"label_agreement":null},{"id":"W2801288141","doi":"10.1093/bioinformatics/bty331","title":"MetaBridge: enabling network-based integrative analysis via direct protein interactors of metabolites","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Canadian Institutes of Health Research; Killam Trusts; University of British Columbia; Canada Research Chairs","keywords":"Workflow; Computer science; Source code; Computational biology; Complement (music); Systems biology; Metabolomics; Bioinformatics; Biology; Database; Biochemistry; Programming language; Mutant","score_opus":0.008295472400709979,"score_gpt":0.2388291522548754,"score_spread":0.2305336798541654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2801288141","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27713588,0.0013354075,0.7056525,0.00006919953,0.00051304203,0.00090531044,0.00016715183,0.000058627116,0.014162891],"genre_scores_gemma":[0.9506974,0.000034627003,0.04795433,0.0002706403,0.0003525451,0.000022314425,0.00037817284,0.000019774114,0.00027018064],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983274,0.00005631213,0.00083395076,0.00018210786,0.00020713337,0.0003930969],"domain_scores_gemma":[0.9982799,0.00003462463,0.00056083576,0.0005629048,0.0004473863,0.00011431925],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055190496,0.00028563364,0.00050177437,0.00020010197,0.00011076394,0.000054409706,0.00034192164,0.00018587481,0.00006129041],"category_scores_gemma":[0.00013826102,0.00022119262,0.00032968103,0.0009031995,0.00022536817,0.000022171296,0.00014994032,0.00013026712,0.000019792787],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0034848691,0.0016149291,0.03177465,0.002123901,0.042085163,0.00000884825,0.014243896,0.049999867,0.48800427,0.008016332,0.049167886,0.30947536],"study_design_scores_gemma":[0.0010455126,0.00095078634,0.0009164159,0.00012575953,0.0012749666,0.0000038193593,0.00052616297,0.35398686,0.57486767,0.0002357689,0.065171525,0.00089475507],"about_ca_topic_score_codex":0.00002845356,"about_ca_topic_score_gemma":0.00007660752,"teacher_disagreement_score":0.6735615,"about_ca_system_score_codex":0.000017786513,"about_ca_system_score_gemma":0.00011667119,"threshold_uncertainty_score":0.9019973},"labels":[],"label_agreement":null},{"id":"W2801332475","doi":"10.1093/bioinformatics/bty363","title":"NGScloud: RNA-seq analysis of non-model species using cloud computing","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Ministerio de Economía y Competitividad; Ministry of Agriculture - Saskatchewan","keywords":"Cloud computing; RNA-Seq; Computer science; Computational biology; Software; Data science; Biology; Genetics; Operating system; Gene; Transcriptome","score_opus":0.025178827820963704,"score_gpt":0.26661059269504833,"score_spread":0.24143176487408463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2801332475","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9229403,0.00010339223,0.07086571,0.000010315055,0.00016902796,0.00007875714,0.000054158958,0.0000027972847,0.0057755513],"genre_scores_gemma":[0.9474008,0.00006566282,0.051979635,0.00012566951,0.0002500568,5.789715e-7,0.00002949985,0.00000965941,0.00013845529],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999139,0.000008384499,0.00040026937,0.00012322128,0.00011911761,0.00020998214],"domain_scores_gemma":[0.99921286,0.000009843633,0.00022661545,0.00032078152,0.00018234813,0.000047542602],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016136773,0.00013857093,0.00026055035,0.000105614265,0.000115217954,0.000018471332,0.00018408378,0.00008625741,0.000010852005],"category_scores_gemma":[0.000030929838,0.00012744092,0.00015866777,0.00026778007,0.00017420061,0.0000012102935,0.00021858106,0.000035437435,0.0000040881077],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006231405,0.00008788056,0.014892317,0.00012255723,0.002928197,5.3453834e-7,0.0043160706,0.05087273,0.9202833,0.00043207203,0.0018996265,0.0041023553],"study_design_scores_gemma":[0.00023855238,0.00014728312,0.0054865982,0.000011622797,0.0004105144,0.0000017651931,0.00056992006,0.93431705,0.056519546,0.000032105618,0.0020427946,0.0002222415],"about_ca_topic_score_codex":0.000017999773,"about_ca_topic_score_gemma":0.000022627306,"teacher_disagreement_score":0.8834443,"about_ca_system_score_codex":0.000011634859,"about_ca_system_score_gemma":0.00005671851,"threshold_uncertainty_score":0.51968896},"labels":[],"label_agreement":null},{"id":"W2803639923","doi":"10.1093/bioinformatics/bty385","title":"MRMAssayDB: an integrated resource for validated targeted proteomics assays","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Jewish General Hospital; Genome British Columbia; University of Victoria","funders":"Fondation De Famille Alvin Segal; Leids Universitair Medisch Centrum; Genome British Columbia; McGill University; University of Victoria; Jewish General Hospital; Leading Edge Endowment Fund; Genome Canada","keywords":"Proteomics; UniProt; KEGG; Computational biology; Quantitative proteomics; Computer science; Resource (disambiguation); Bioinformatics; Biology; Gene ontology; Gene; Biochemistry; Gene expression","score_opus":0.021240597739801293,"score_gpt":0.2857756677972513,"score_spread":0.26453507005745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2803639923","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026255751,0.00000795591,0.9550519,0.00014571066,0.000035145462,0.00087022263,0.00051670684,0.0008572183,0.016259413],"genre_scores_gemma":[0.028724238,0.000007716745,0.9678811,0.00026052297,0.00022602608,0.00049274834,0.0014123387,0.000055250614,0.0009400847],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987611,0.000008555016,0.0005267206,0.00019594419,0.00014742179,0.00036023677],"domain_scores_gemma":[0.9985668,0.00004360983,0.0002877772,0.0006586909,0.00030080634,0.0001423389],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002361764,0.00022448052,0.00020241042,0.00006365946,0.00028709526,0.00009101316,0.0004340352,0.00023799927,0.00016710945],"category_scores_gemma":[0.00012572722,0.0002056869,0.000074917996,0.00021971506,0.00014093882,0.00030387042,0.00007743908,0.00020107249,0.000048213533],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00064921746,0.0006334985,0.00034960234,0.0009141883,0.00019540061,0.0000018325718,0.0034951395,0.00018207433,0.8300061,0.033523776,0.05335751,0.07669165],"study_design_scores_gemma":[0.00040486327,0.00010774823,0.0000023257849,0.000034555007,0.000019289146,0.000006219685,0.0003827219,0.08988183,0.6174026,0.002273745,0.28919736,0.00028672884],"about_ca_topic_score_codex":0.000009217949,"about_ca_topic_score_gemma":0.0000046286095,"teacher_disagreement_score":0.23583984,"about_ca_system_score_codex":0.00009662916,"about_ca_system_score_gemma":0.00008005246,"threshold_uncertainty_score":0.8387668},"labels":[],"label_agreement":null},{"id":"W2806701851","doi":"10.1093/bioinformatics/bty430","title":"GateFinder: projection-based gating strategy optimization for flow and mass cytometry","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Terry Fox Research Institute","funders":"National Institute of Allergy and Infectious Diseases; National Institute of General Medical Sciences; U.S. Food and Drug Administration; Cure Starts Now Foundation; National Cancer Institute; Entertainment Industry Foundation; International Society for Advancement of Cytometry; National Institutes of Health; Ovarian Cancer Research Fund; Terry Fox Foundation; Canadian Institutes of Health Research; Damon Runyon Cancer Research Foundation; Stanford Bio-X; Hamilton Health Sciences Foundation; European Commission; Stanford University; March of Dimes Foundation; California Institute for Regenerative Medicine","keywords":"Bioconductor; Computer science; Mass cytometry; R package; Projection (relational algebra); Simple (philosophy); Polygon (computer graphics); Algorithm; Data mining; Computational biology; Theoretical computer science; Biology; Computational science","score_opus":0.019318678120541957,"score_gpt":0.24989795749647944,"score_spread":0.23057927937593747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2806701851","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06937351,0.00005353586,0.92889994,0.000035199853,0.00018129549,0.0003082726,0.00004172135,0.000026748214,0.0010797615],"genre_scores_gemma":[0.5998884,0.000033005974,0.39894298,0.00033328988,0.00032269038,0.000024965606,0.00032766236,0.000023486142,0.00010355695],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99938613,0.000009886042,0.00022952571,0.000121686964,0.000077245735,0.0001755507],"domain_scores_gemma":[0.9995704,0.000014319961,0.0000864545,0.00013362664,0.00014390248,0.000051253497],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013241087,0.00011761995,0.000093322626,0.00005538604,0.00015356096,0.000065582986,0.00006866708,0.0001379909,0.000010431584],"category_scores_gemma":[0.00006272296,0.00011034442,0.000041510622,0.00009063952,0.00007610762,0.000010013407,0.000012106959,0.000039894316,0.0000025111158],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014353136,0.00043483594,0.020242939,0.0025198078,0.00039383135,0.0000015744696,0.0015925128,0.08931433,0.65718496,0.0003283472,0.0068029133,0.21974866],"study_design_scores_gemma":[0.00074062997,0.0005361901,0.000067140434,0.000016839218,0.000015979818,0.0000029037371,0.00014035201,0.91758627,0.078999445,0.000018686596,0.0017157465,0.00015983166],"about_ca_topic_score_codex":0.0000042936217,"about_ca_topic_score_gemma":0.0000072829143,"teacher_disagreement_score":0.8282719,"about_ca_system_score_codex":0.000010930427,"about_ca_system_score_gemma":0.00008171352,"threshold_uncertainty_score":0.4499715},"labels":[],"label_agreement":null},{"id":"W2807635396","doi":"10.1093/bioinformatics/bty420","title":"Knotty: efficient and accurate prediction of complex RNA pseudoknot structures","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":62,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Pseudoknot; Benchmark (surveying); Computer science; Minification; Algorithm; Space (punctuation); RNA; Biology; Genetics","score_opus":0.02181555103800082,"score_gpt":0.2504419687821222,"score_spread":0.2286264177441214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2807635396","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9666134,0.00012478836,0.028948173,0.000035689074,0.00019273402,0.00021642275,0.00009944954,0.000015427831,0.0037539303],"genre_scores_gemma":[0.9851843,0.00005187601,0.014425227,0.000092763396,0.00013314866,0.0000037757325,0.00004223631,0.000007688625,0.000058949707],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99942076,0.000017348199,0.00024263957,0.00008823462,0.00010674567,0.00012425368],"domain_scores_gemma":[0.99953204,0.000007248924,0.0001318093,0.00020623145,0.00007513159,0.000047531517],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001248611,0.0000961094,0.000102232065,0.00003357756,0.00007051724,0.000017366823,0.00009689249,0.000092632064,0.000031532938],"category_scores_gemma":[0.000046535097,0.00007877896,0.000031693908,0.0000408665,0.000120210665,0.0000037692953,0.00007557671,0.000025520207,0.00000720705],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006157096,0.000017202268,0.00010254301,0.00009090188,0.000036963098,1.4994612e-7,0.00031448965,0.000030874853,0.97972775,0.0007627386,0.0013862421,0.017468572],"study_design_scores_gemma":[0.00034062853,0.00047903837,0.0029388843,0.000018494065,0.000019304352,0.000014518,0.00018833745,0.00976866,0.97318727,0.0002465753,0.012677222,0.00012108767],"about_ca_topic_score_codex":0.000003502129,"about_ca_topic_score_gemma":0.0000011815195,"teacher_disagreement_score":0.018570948,"about_ca_system_score_codex":0.000003783956,"about_ca_system_score_gemma":0.0000228357,"threshold_uncertainty_score":0.32125127},"labels":[],"label_agreement":null},{"id":"W2807745747","doi":"10.1093/bioinformatics/bty234","title":"aliFreeFold: an alignment-free approach to predict secondary structure from homologous RNA sequences","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Université de Sherbrooke","keywords":"RNA; Computer science; Weighting; Computational biology; Sequence (biology); Sequence alignment; Set (abstract data type); Nucleic acid secondary structure; Protein secondary structure; Structural alignment; Homologous chromosome; Nucleic acid structure; Multiple sequence alignment; Algorithm; Pseudoknot; Protein superfamily; Theoretical computer science; Biology; Genetics; Peptide sequence; Physics; Gene","score_opus":0.011423693410995715,"score_gpt":0.22554404988826676,"score_spread":0.21412035647727104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2807745747","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93248993,0.00024404292,0.04380306,0.00011812609,0.0005944407,0.0006679285,0.0014456202,0.00007739181,0.020559475],"genre_scores_gemma":[0.82565683,0.0000282951,0.17081256,0.0015132426,0.0009174314,0.000032073927,0.0006963241,0.000031829204,0.00031142856],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987174,0.000056612727,0.00034758958,0.00028779302,0.00025284028,0.00033774297],"domain_scores_gemma":[0.998528,0.000009041575,0.00013489557,0.0010306285,0.000077853874,0.00021960038],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001797251,0.00024190855,0.00019700473,0.000055285676,0.00015309325,0.00008147221,0.0008288398,0.00028462708,0.00014437907],"category_scores_gemma":[0.00008085057,0.00020233812,0.0000654074,0.00008998616,0.00012505449,0.000023664565,0.000280718,0.000081651735,0.0000471872],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001381086,0.00008570536,0.0001808216,0.000056380934,0.00017827151,0.000002819693,0.001623245,0.000030607338,0.93336046,0.0005182903,0.021584773,0.042240508],"study_design_scores_gemma":[0.0005167789,0.0011153072,0.00033207276,0.000019605692,0.000036796686,0.000031306397,0.0007447766,0.00065448356,0.9667415,0.0025051786,0.026859496,0.00044272136],"about_ca_topic_score_codex":0.000061914936,"about_ca_topic_score_gemma":0.00004002615,"teacher_disagreement_score":0.12700951,"about_ca_system_score_codex":0.000017897926,"about_ca_system_score_gemma":0.00010347677,"threshold_uncertainty_score":0.8251109},"labels":[],"label_agreement":null},{"id":"W2808973977","doi":"10.1093/bioinformatics/bty466","title":"iMetaLab 1.0: a web platform for metaproteomics data analysis","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Advanced Research; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Metaproteomics; Computer science; Pipeline (software); Task (project management); Data mining; Data science; Database; World Wide Web; Metagenomics; Engineering; Biology; Systems engineering","score_opus":0.041602311727796375,"score_gpt":0.3111446754283295,"score_spread":0.26954236370053314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2808973977","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6942586,0.00043075986,0.29405114,0.00037073685,0.00058690936,0.0015302463,0.003355137,0.000075121214,0.005341399],"genre_scores_gemma":[0.5891561,0.00025713057,0.39765212,0.0017106341,0.00085340143,0.000034453664,0.008889361,0.000041780244,0.0014050537],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99901295,0.000007422587,0.0003704147,0.00021713952,0.00008626223,0.00030581522],"domain_scores_gemma":[0.9985326,0.0000103650655,0.00016212618,0.001066939,0.0001330503,0.00009493809],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039806476,0.00014567337,0.00021833615,0.00011101863,0.00014891644,0.00004884081,0.00050609006,0.00014906765,0.000030832707],"category_scores_gemma":[0.00008945808,0.00012577722,0.00012573757,0.00026035352,0.000091520014,0.000016466896,0.00028656915,0.000049678816,0.00006161081],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000727037,0.00034712302,0.0038077813,0.0007939316,0.007006507,0.0000012292446,0.0011213061,0.000047481688,0.7142974,0.0018645163,0.23978299,0.030202692],"study_design_scores_gemma":[0.0017014615,0.0008582392,0.0012991116,0.00001219588,0.00134545,0.000017958973,0.00034563823,0.12191181,0.08155029,0.000114505216,0.79021394,0.00062941073],"about_ca_topic_score_codex":0.000007954386,"about_ca_topic_score_gemma":0.00016238516,"teacher_disagreement_score":0.6327471,"about_ca_system_score_codex":0.000013363872,"about_ca_system_score_gemma":0.00018345675,"threshold_uncertainty_score":0.51290464},"labels":[],"label_agreement":null},{"id":"W2809066811","doi":"10.1093/bioinformatics/bty482","title":"Metaxa2 Database Builder: enabling taxonomic identification from metagenomic or metabarcoding data using any genetic marker","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Environmental DNA in Biodiversity Studies","field":"Environmental Science","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Food Inspection Agency","funders":"Vetenskapsrådet; Svenska Forskningsrådet Formas; Project Apis m.","keywords":"Metagenomics; Identification (biology); Biology; Amplicon; Taxonomic rank; DNA barcoding; Software; Computational biology; Genetic marker; Computer science; Data mining; Evolutionary biology; Gene; Genetics; Ecology; Taxon; Polymerase chain reaction","score_opus":0.0907229681115546,"score_gpt":0.2702370529449247,"score_spread":0.1795140848333701,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2809066811","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.960534,0.0002533696,0.036345117,0.000035538425,0.00041915782,0.00048236136,0.0012058252,0.00006925623,0.0006553903],"genre_scores_gemma":[0.33037466,0.00036350367,0.6682131,0.0002560676,0.00014102053,0.0000065252,0.00036410533,0.000024409617,0.0002565943],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980532,0.000058492133,0.00061399094,0.00046940916,0.00039940828,0.00040551616],"domain_scores_gemma":[0.99796116,0.000088117085,0.00039600726,0.0014188405,0.000007967777,0.00012788891],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005579083,0.0002690498,0.00027081385,0.0000785751,0.00056611135,0.0001505625,0.001136879,0.000070254675,0.0030398618],"category_scores_gemma":[0.00012652203,0.00023662939,0.000057988174,0.00022256545,0.0005001726,0.0016771676,0.0028660577,0.00011567109,0.0032436524],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030403183,0.0004609205,0.48447427,0.00022393944,0.0017551705,0.000048571022,0.005236142,0.001927741,0.40443724,0.000026241984,0.052372344,0.048733372],"study_design_scores_gemma":[0.0015271425,0.000110526365,0.376635,0.000083699844,0.0016719777,0.00004067176,0.004692933,0.47871843,0.039110042,0.00006366617,0.09567601,0.0016699089],"about_ca_topic_score_codex":0.00065723143,"about_ca_topic_score_gemma":0.00015106407,"teacher_disagreement_score":0.631868,"about_ca_system_score_codex":0.00032576488,"about_ca_system_score_gemma":0.00001150975,"threshold_uncertainty_score":0.9978715},"labels":[],"label_agreement":null},{"id":"W2809263774","doi":"10.1093/bioinformatics/bty475","title":"HUME: large-scale detection of causal genetic factors of adverse drug reactions","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Pharmacovigilance and Adverse Drug Reactions","field":"Pharmacology, Toxicology and Pharmaceutics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Child and Family Research Institute; Children's & Women's Health Centre of British Columbia; Simon Fraser University","funders":"Institute of Cancer Research; Canada Foundation for Innovation; Genome Canada","keywords":"Confounding; Drug reaction; Drug; Data mining; Adverse drug reaction; Computer science; Adverse effect; Medicine; Bioinformatics; Intensive care medicine; Internal medicine; Pharmacology; Biology","score_opus":0.05633522496170181,"score_gpt":0.38342296736908704,"score_spread":0.32708774240738525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2809263774","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.986614,0.000041816107,0.0030713815,0.000034557965,0.0015720886,0.00029843007,0.00031962764,0.000083238956,0.00796486],"genre_scores_gemma":[0.9978148,0.00016332822,0.0010199661,0.00015352575,0.0001884922,0.000011496721,0.00003357847,0.000015771613,0.00059906824],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99855757,0.00007910937,0.0007078401,0.00012386027,0.0001888568,0.0003427773],"domain_scores_gemma":[0.9987262,0.00015638692,0.0004838145,0.0002467749,0.00022693643,0.00015988752],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029467852,0.00018812448,0.00027212585,0.00021316344,0.0002518997,0.0000033485655,0.00019209868,0.00019065343,0.00059008505],"category_scores_gemma":[0.000060285263,0.0001768553,0.00015112344,0.00037410602,0.00032433783,0.00031905266,0.000062784566,0.0003696083,0.00016920749],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007103682,0.00232221,0.096575394,0.001304009,0.0010984514,0.000009540198,0.03470851,0.003453653,0.83578575,0.0006639174,0.010823241,0.012544951],"study_design_scores_gemma":[0.0015671314,0.00017120245,0.018048733,0.00003724356,0.00032159974,0.00001892905,0.005228158,0.035981473,0.7696897,0.000076416734,0.16856252,0.00029689426],"about_ca_topic_score_codex":0.00004369096,"about_ca_topic_score_gemma":0.00006682595,"teacher_disagreement_score":0.15773928,"about_ca_system_score_codex":0.00005890158,"about_ca_system_score_gemma":0.00009526198,"threshold_uncertainty_score":0.721195},"labels":[],"label_agreement":null},{"id":"W2809895957","doi":"10.1093/bioinformatics/bty528","title":"MetaboAnalystR: an R package for flexible and reproducible analysis of metabolomics data","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":802,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; McGill University; Chesapeake Research Consortium","keywords":"Computer science; Workflow; Flexibility (engineering); Interface (matter); Web server; Web application; World Wide Web; Database; Operating system; The Internet","score_opus":0.049798772644403,"score_gpt":0.32536535111417814,"score_spread":0.2755665784697751,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2809895957","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8609006,0.0029164143,0.1313115,0.00011961806,0.00025942718,0.00049782725,0.0020403755,0.000032975517,0.0019212523],"genre_scores_gemma":[0.765791,0.0022634214,0.22775333,0.00024926048,0.00034898784,0.000017598431,0.0029816593,0.00002675991,0.00056796806],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987965,0.000021495978,0.00046179123,0.000377327,0.000120312914,0.00022254502],"domain_scores_gemma":[0.99769735,0.000018858724,0.00026777553,0.0017066624,0.0002318211,0.000077529],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000874893,0.00015680131,0.00045555734,0.0002465266,0.00010960652,0.00003485283,0.0004093598,0.00008740869,0.000013289164],"category_scores_gemma":[0.00034857963,0.00013256792,0.000106111525,0.0005271782,0.00017859634,0.00002603138,0.000381745,0.000034707817,0.0000013560038],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008238535,0.0005735047,0.020710256,0.0005517453,0.029410956,6.143491e-7,0.001597647,0.00009311463,0.85758865,0.019525088,0.024347916,0.04477668],"study_design_scores_gemma":[0.0015490812,0.0018312592,0.010271279,0.000008790511,0.009663052,0.0000067377723,0.0017249406,0.062104158,0.67541945,0.000555169,0.23604697,0.00081911025],"about_ca_topic_score_codex":0.000018729685,"about_ca_topic_score_gemma":0.000092063885,"teacher_disagreement_score":0.21169905,"about_ca_system_score_codex":0.0000035988785,"about_ca_system_score_gemma":0.00004517109,"threshold_uncertainty_score":0.54059625},"labels":[],"label_agreement":null},{"id":"W2809990446","doi":"10.1093/bioinformatics/bty537","title":"Multiomics modeling of the immunome, transcriptome, microbiome, proteome and metabolome adaptations during human pregnancy","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Pregnancy and preeclampsia studies","field":"Medicine","cited_by":197,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal; Group for Research in Decision Analysis; Transport Canada","funders":"U.S. National Library of Medicine; National Institute of General Medical Sciences; National Institute of Diabetes and Digestive and Kidney Diseases; National Heart, Lung, and Blood Institute; Canadian Institutes of Health Research; National Institutes of Health; NOMIS Stiftung; Wellcome Trust; Ovarian Cancer Research Fund; National Institute of Allergy and Infectious Diseases; Bill and Melinda Gates Foundation","keywords":"Metabolome; Transcriptome; Proteome; Biology; Computational biology; Microbiome; Pregnancy; Bioinformatics; Physiology; Metabolomics; Genetics; Gene; Gene expression","score_opus":0.029459298037730824,"score_gpt":0.26237827660429675,"score_spread":0.23291897856656593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2809990446","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98997355,0.0023808468,0.0032147772,0.00012593671,0.00014079022,0.0009625108,0.000054633463,0.00005483725,0.0030920936],"genre_scores_gemma":[0.9785922,0.0003110604,0.020721192,0.000042587395,0.0000359814,0.00003462646,0.0000066366283,0.00001377616,0.0002419102],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.998976,0.000016941265,0.000549195,0.000099481644,0.0001474078,0.00021099998],"domain_scores_gemma":[0.9992794,0.000014010774,0.00016801035,0.00034441272,0.00014954836,0.000044637087],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008896226,0.00015271161,0.0002825029,0.000117168725,0.00036340917,0.00001657161,0.00013330723,0.00007743014,0.000009031999],"category_scores_gemma":[0.00003892795,0.00010571258,0.00009685992,0.0002523895,0.0002817993,0.00021655754,0.00008718354,0.00013449625,0.000005051552],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033467473,0.0005720853,0.028606093,0.008674548,0.0016552118,0.0000048087722,0.10449116,0.0002757809,0.8430883,0.0034688956,0.00011616565,0.008712227],"study_design_scores_gemma":[0.016694766,0.0012045462,0.64778847,0.013860281,0.0018538829,0.00038998458,0.009290691,0.1902314,0.11383359,0.001440166,0.0018107943,0.0016014089],"about_ca_topic_score_codex":0.000018669944,"about_ca_topic_score_gemma":0.000015725393,"teacher_disagreement_score":0.7292548,"about_ca_system_score_codex":0.000021758795,"about_ca_system_score_gemma":0.000044225424,"threshold_uncertainty_score":0.43108338},"labels":[],"label_agreement":null},{"id":"W2810425915","doi":"10.1093/bioinformatics/bty544","title":"lordFAST: sensitive and Fast Alignment Search Tool for LOng noisy Read sequencing Data","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"National Institute of General Medical Sciences; National Institutes of Health; National Science Foundation","keywords":"Nanopore sequencing; Computer science; Reference genome; Genomics; DNA sequencing; Throughput; Genome; Data mining; Computational biology; Biology; Wireless; Genetics; Gene; Telecommunications","score_opus":0.0409620581989204,"score_gpt":0.28350774083588093,"score_spread":0.24254568263696052,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2810425915","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9520771,0.00021112397,0.045184426,0.000121139106,0.00017622788,0.0004598322,0.0004466558,0.0000055036435,0.0013179928],"genre_scores_gemma":[0.96277994,0.0002731879,0.03546972,0.0003892908,0.00043582666,0.000010843272,0.00032417738,0.00001738203,0.00029963785],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992017,0.000012480548,0.00022662652,0.00020608155,0.00009810798,0.0002550105],"domain_scores_gemma":[0.9992358,0.000020766716,0.000064781285,0.00048394085,0.00013836111,0.000056368703],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002941894,0.00013479783,0.00012621262,0.000025059231,0.00017794946,0.000044305343,0.00017921264,0.00007564044,0.0000025937643],"category_scores_gemma":[0.0000568009,0.00012114782,0.000027188766,0.000036552236,0.00015785564,0.0000035597654,0.0005208442,0.0000338867,0.000009412205],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005480583,0.00011776781,0.010817725,0.000866245,0.0012664272,0.000009130438,0.011364801,0.00014395856,0.72719735,0.0010673798,0.020597287,0.2260039],"study_design_scores_gemma":[0.0039687017,0.0035214839,0.020636525,0.00017423218,0.00029404517,0.0002523596,0.012089752,0.093264714,0.71915376,0.00026115528,0.14440712,0.0019761475],"about_ca_topic_score_codex":0.000012063226,"about_ca_topic_score_gemma":0.000038178605,"teacher_disagreement_score":0.22402775,"about_ca_system_score_codex":0.000017301138,"about_ca_system_score_gemma":0.00007448524,"threshold_uncertainty_score":0.49402648},"labels":[],"label_agreement":null},{"id":"W2810570362","doi":"10.1093/bioinformatics/bty586","title":"Fast characterization of segmental duplications in genome assemblies","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":107,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institute of General Medical Sciences; National Institutes of Health","keywords":"Genome; Structural variation; Computer science; Sequence assembly; Computational biology; Segmental duplication; Gene duplication; Jaccard index; Biology; Genetics; Artificial intelligence; Pattern recognition (psychology); Gene","score_opus":0.010153928465806603,"score_gpt":0.23674114807972357,"score_spread":0.22658721961391698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2810570362","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9865226,0.000017101094,0.010504161,0.000034871675,0.000057167228,0.00018902165,0.000049432078,0.0000066527914,0.0026189568],"genre_scores_gemma":[0.9916752,0.00007475698,0.007141993,0.000063844374,0.00010160398,0.000014517245,0.0006480937,0.0000087659955,0.00027125646],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994848,0.0000075193993,0.00024319586,0.000070013455,0.00008050336,0.00011399006],"domain_scores_gemma":[0.9996065,0.0000016691097,0.00010548475,0.00019457797,0.00006646597,0.000025297664],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000082018814,0.00006927014,0.00007426847,0.000073917356,0.000026725063,0.0000112648995,0.00011227345,0.00005634182,0.00002449434],"category_scores_gemma":[0.000011335133,0.0000692621,0.000024808141,0.00012331057,0.000059110593,0.000008758772,0.00006690378,0.00002236286,0.00004173902],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000063387934,0.000036453486,0.0025904896,0.000025516209,0.000012490566,5.8490347e-8,0.00043343354,0.0000037410384,0.9945099,0.00003889292,0.00003136827,0.0023113384],"study_design_scores_gemma":[0.0011035833,0.0006223602,0.29457408,0.00003141913,0.000021355823,0.0000112033595,0.0010815022,0.005281434,0.67387444,0.000027274875,0.022965536,0.00040583877],"about_ca_topic_score_codex":0.0000021635378,"about_ca_topic_score_gemma":0.00000734173,"teacher_disagreement_score":0.32063547,"about_ca_system_score_codex":0.000012549221,"about_ca_system_score_gemma":0.000026996862,"threshold_uncertainty_score":0.28244266},"labels":[],"label_agreement":null},{"id":"W2810954907","doi":"10.1093/bioinformatics/bty538","title":"Differential coexpression in human tissues and the confounding effect of mean expression levels","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"National Institute of Mental Health; National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada","keywords":"Confounding; Biology; Differential (mechanical device); Gene expression; Gene; Expression (computer science); Differential diagnosis; Gene expression profiling; Computational biology; Genetics; Internal medicine; Computer science; Pathology; Medicine","score_opus":0.011072941190757163,"score_gpt":0.2735351256649175,"score_spread":0.26246218447416036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2810954907","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.991545,0.00013199593,0.005374585,0.00001720747,0.00015062783,0.00031142827,0.000009602543,0.000006081905,0.0024534436],"genre_scores_gemma":[0.9988473,0.00003863613,0.0007889947,0.00004335313,0.00015152982,0.000007889085,0.000028175382,0.000008365257,0.00008576052],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991543,0.00005938067,0.00040877098,0.000085225154,0.00011802446,0.00017424086],"domain_scores_gemma":[0.999424,0.000041599375,0.0001978928,0.00026037398,0.000034549816,0.000041617976],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039331673,0.00013762893,0.00021635652,0.000042978194,0.0001206623,0.00003469465,0.00017053485,0.00013231163,0.000021236021],"category_scores_gemma":[0.000036988255,0.00008143559,0.00004744227,0.000047438945,0.00035696788,0.000010233466,0.00021440456,0.0000824281,0.000002946859],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012934206,0.00005795036,0.004237672,0.0006972475,0.000106828724,8.893872e-7,0.0101138055,0.000034054607,0.9482015,0.0031749064,0.0037671663,0.028314559],"study_design_scores_gemma":[0.0056285574,0.0008451685,0.001312742,0.00030119857,0.000034125715,0.000011328082,0.00046977028,0.01242469,0.9755169,0.00035482107,0.0028194906,0.0002811922],"about_ca_topic_score_codex":0.000011156482,"about_ca_topic_score_gemma":0.000013755901,"teacher_disagreement_score":0.028033366,"about_ca_system_score_codex":0.0000060214984,"about_ca_system_score_gemma":0.000011388746,"threshold_uncertainty_score":0.3320847},"labels":[],"label_agreement":null},{"id":"W2884325264","doi":"10.1093/bioinformatics/bty621","title":"MAVIS: merging, annotation, validation, and illustration of structural variants","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of British Columbia; Canada's Michael Smith Genome Sciences Centre","funders":"Genome British Columbia; BC Cancer Foundation; Genome Canada","keywords":"Annotation; Context (archaeology); Computer science; Key (lock); Computational biology; Process (computing); Genome; Data mining; Data science; Artificial intelligence; Biology; Genetics; Programming language; Gene","score_opus":0.009028182947586842,"score_gpt":0.24153045101335732,"score_spread":0.23250226806577048,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2884325264","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99585253,0.0000893316,0.0030083715,0.000026692378,0.00010263008,0.000082423976,0.000043393607,0.0000048137863,0.00078982377],"genre_scores_gemma":[0.994396,0.000033563516,0.005114117,0.000067165616,0.000104131694,0.0000015919275,0.00020316255,0.0000047921244,0.0000755336],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99959016,0.000006765043,0.00019637065,0.00006582721,0.0000634158,0.000077464756],"domain_scores_gemma":[0.9995668,0.0000027531273,0.00011082012,0.00012264683,0.00016016004,0.000036807938],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000057842964,0.000063839194,0.000057360612,0.000027608668,0.00006284042,0.000020071515,0.000054774096,0.000049217335,0.000014610487],"category_scores_gemma":[0.000041887517,0.000056475405,0.0000191667,0.000042813244,0.000080663376,0.000009586679,0.000032081298,0.000013828967,0.0000036991319],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005042334,0.00018796325,0.06402973,0.0010200383,0.00065681874,0.0000033559634,0.011015093,0.00057898846,0.80469036,0.014395303,0.026798468,0.076119624],"study_design_scores_gemma":[0.0029750315,0.0017830954,0.28422892,0.000088946574,0.00019535559,0.0001442056,0.0034727543,0.033132773,0.6459956,0.0026174313,0.02424549,0.0011203612],"about_ca_topic_score_codex":0.0000052576383,"about_ca_topic_score_gemma":0.0000037885272,"teacher_disagreement_score":0.22019918,"about_ca_system_score_codex":0.0000027430365,"about_ca_system_score_gemma":0.00004059315,"threshold_uncertainty_score":0.23030002},"labels":[],"label_agreement":null},{"id":"W2884335298","doi":"10.1093/bioinformatics/bty655","title":"The epiGenomic Efficient Correlator (epiGeEC) tool allows fast comparison of user datasets with thousands of public epigenomic datasets","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Epigenetics and DNA Methylation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University and Génome Québec Innovation Centre; Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada; Canarie","keywords":"Epigenomics; Computer science; Epigenome; Source code; Variety (cybernetics); R package; Data mining; Biology; Artificial intelligence; DNA methylation; Computational science; Genetics","score_opus":0.017196482251295987,"score_gpt":0.2739516866853645,"score_spread":0.2567552044340685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2884335298","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9684794,0.00082905026,0.027744785,0.00003039529,0.00021498422,0.0004050988,0.0018193935,0.000009261618,0.00046763202],"genre_scores_gemma":[0.990314,0.00019918644,0.006189802,0.000027958524,0.00009657402,0.000010165351,0.0030944112,0.000024295347,0.000043621167],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982294,0.00007264299,0.0008438712,0.00020224917,0.00029597292,0.0003558748],"domain_scores_gemma":[0.99797034,0.000068311696,0.00065238745,0.0010163231,0.00019214876,0.00010048177],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00074460695,0.00022054875,0.00028919248,0.00006711002,0.00023867928,0.00005402101,0.0005198713,0.00014861133,0.000014613203],"category_scores_gemma":[0.00013473628,0.00015178602,0.00007599373,0.00015775579,0.000468135,0.000014006824,0.00025577948,0.00009783138,0.000025261726],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016837526,0.0018036832,0.13851674,0.00080735603,0.0016108277,0.0000032465066,0.005547805,0.008358818,0.6625514,0.0032766564,0.029169358,0.14667036],"study_design_scores_gemma":[0.0019627765,0.0023026904,0.01798308,0.000070723625,0.00015846746,0.000006905013,0.0012647652,0.030392788,0.6772775,0.000032989246,0.26785022,0.00069711526],"about_ca_topic_score_codex":0.000017729666,"about_ca_topic_score_gemma":0.00011046081,"teacher_disagreement_score":0.23868085,"about_ca_system_score_codex":0.000024335608,"about_ca_system_score_gemma":0.00020834671,"threshold_uncertainty_score":0.61896545},"labels":[],"label_agreement":null},{"id":"W2889339419","doi":"10.1093/bioinformatics/bty780","title":"Co-registration and analysis of multiple imaging mass spectrometry datasets targeting different analytes","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Mass Spectrometry Techniques and Applications","field":"Chemistry","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Workflow; Mass spectrometry imaging; Source code; Sample (material); Data mining; Multivariate statistics; R package; Analyte; Code (set theory); Pattern recognition (psychology); Mass spectrometry; Artificial intelligence; Database; Machine learning; Computational science; Chemistry; Programming language","score_opus":0.011835380283237948,"score_gpt":0.2730484600134204,"score_spread":0.2612130797301825,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889339419","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7780426,0.00013670376,0.18529189,0.00014945524,0.000025267878,0.00018833787,0.0029412915,0.00025664334,0.032967795],"genre_scores_gemma":[0.9446434,0.000039689734,0.053142205,0.000018778868,0.000045647455,0.0000071199433,0.0020597207,0.0000075218436,0.00003591354],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99900025,0.0000051363604,0.0004803992,0.00013509567,0.00019827629,0.00018086475],"domain_scores_gemma":[0.9990645,0.000082407816,0.00034315663,0.00038782606,0.00005570403,0.00006642032],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00013531887,0.00013550522,0.000251115,0.00029477756,0.000109852415,0.00006086031,0.0001659445,0.000048803602,0.00096305495],"category_scores_gemma":[0.00007938625,0.000119426826,0.00007738288,0.00057225634,0.00012367709,0.00015083677,0.000038909588,0.00008371821,0.000004312237],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019722465,0.00013682421,0.6249961,0.00038530378,0.0006902944,0.0000010147797,0.00038411477,0.0000081412545,0.36095703,0.003641468,0.004884384,0.0038956027],"study_design_scores_gemma":[0.00030166315,0.000035329544,0.025865592,0.000031584677,0.0006486839,0.0000030733534,0.00068873394,0.50699776,0.4620798,0.00044691586,0.002582893,0.0003179852],"about_ca_topic_score_codex":0.00003012011,"about_ca_topic_score_gemma":0.000019535235,"teacher_disagreement_score":0.5991305,"about_ca_system_score_codex":0.00003932998,"about_ca_system_score_gemma":0.000009947699,"threshold_uncertainty_score":0.9999502},"labels":[],"label_agreement":null},{"id":"W2889433641","doi":"10.1093/bioinformatics/bty725","title":"Efficient computation of the kinship coefficients","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic and phenotypic traits in livestock","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Kinship; Inbreeding; Pedigree chart; Population; Mendelian inheritance; Biology; Mathematics; Genetics; Combinatorics; Genealogy; Statistics; Computer science; Demography; Sociology","score_opus":0.013356671602386468,"score_gpt":0.24442406810928294,"score_spread":0.23106739650689648,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889433641","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86262375,0.00003385046,0.13086389,0.000023509692,0.00038180506,0.0001411247,0.000010935946,0.0000052577516,0.0059158904],"genre_scores_gemma":[0.97771275,6.145368e-7,0.021945078,0.0001306332,0.00009004818,0.0000015766367,0.000008427039,0.0000049443365,0.00010594254],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.999494,0.000016944114,0.00019143707,0.000062623905,0.00012871416,0.00010626409],"domain_scores_gemma":[0.99956083,0.0000052000887,0.00010423085,0.00020741198,0.000095396914,0.000026902775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008557363,0.000066025386,0.00005599334,0.000014570133,0.00007277078,0.000006618041,0.00017302822,0.000057000845,0.0000056809563],"category_scores_gemma":[0.000044067674,0.00004535211,0.000042497904,0.000085235246,0.00019365572,5.6374205e-7,0.00008825258,0.000029654504,0.000018728064],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00080702757,0.002271579,0.065911084,0.0014030376,0.00061811483,3.1759365e-7,0.024572555,0.40164885,0.16058087,0.07400222,0.06359789,0.20458645],"study_design_scores_gemma":[0.002660258,0.0023594738,0.6202934,0.0001847459,0.00010246521,0.000031053634,0.0010986144,0.100815535,0.24438098,0.0015068854,0.025788901,0.00077772007],"about_ca_topic_score_codex":0.0000021166038,"about_ca_topic_score_gemma":0.0000021319015,"teacher_disagreement_score":0.55438226,"about_ca_system_score_codex":0.000003944534,"about_ca_system_score_gemma":0.000043376578,"threshold_uncertainty_score":0.18494053},"labels":[],"label_agreement":null},{"id":"W2890693027","doi":"10.1093/bioinformatics/bty812","title":"PRESM: personalized reference editor for somatic mutation discovery in cancer genomics","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Children's Hospital; University of Calgary","funders":"Canada Foundation for Innovation; Arkansas Children’s Hospital Research Institute","keywords":"Somatic cell; Genomics; Computational biology; Mutation; Cancer genetics; Personalized medicine; Germline mutation; Cancer; Computer science; Genetics; Biology; Genome; Gene","score_opus":0.016820696563665267,"score_gpt":0.2798510192886188,"score_spread":0.2630303227249535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2890693027","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9564778,0.0005365051,0.03725556,0.0001959975,0.0023832095,0.0008562248,0.0005938812,0.000016637636,0.0016841887],"genre_scores_gemma":[0.9523063,0.0018553255,0.033659562,0.0013279108,0.008076827,0.00043640056,0.0010233835,0.000063716674,0.0012506042],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99921316,0.000008817937,0.00031332418,0.00014343274,0.000090846384,0.00023043754],"domain_scores_gemma":[0.99944115,0.000035773053,0.00013781668,0.00021906814,0.00011506449,0.000051149957],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012200638,0.00013019609,0.00013430676,0.000047878235,0.00006818793,0.00006670238,0.0001550146,0.00012422519,0.000012115933],"category_scores_gemma":[0.00014679415,0.00012646902,0.000051997064,0.000061345585,0.00009533491,0.000017875627,0.00006568996,0.000045130684,0.000011973493],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0043050433,0.0011457675,0.017729588,0.0035101208,0.0008187845,0.000008777134,0.018184042,0.004072952,0.34584665,0.010570992,0.4782859,0.11552136],"study_design_scores_gemma":[0.00559257,0.0015410483,0.0040060785,0.00017293262,0.0001135293,0.000014816112,0.0016869054,0.062058873,0.10655649,0.0011652975,0.8159849,0.0011065697],"about_ca_topic_score_codex":0.00005203056,"about_ca_topic_score_gemma":0.00036693458,"teacher_disagreement_score":0.33769897,"about_ca_system_score_codex":0.00007334341,"about_ca_system_score_gemma":0.0002658349,"threshold_uncertainty_score":0.5157257},"labels":[],"label_agreement":null},{"id":"W2890720538","doi":"10.1093/bioinformatics/bty773","title":"SCOP: a novel scaffolding algorithm based on contig classification and optimization","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Higher Education Discipline Innovation Project; National Natural Science Foundation of China","keywords":"Contig; Computer science; Scaffold; Spurious relationship; Graph; Sequence assembly; Algorithm; Cuboid; Pattern recognition (psychology); Artificial intelligence; Theoretical computer science; Genome; Machine learning; Biology; Mathematics; Genetics; Programming language","score_opus":0.018884952096979497,"score_gpt":0.24170945418960468,"score_spread":0.2228245020926252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2890720538","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12391831,0.00016727786,0.8674689,0.00019266983,0.00030978353,0.000352927,0.00006634634,0.000013177445,0.007510591],"genre_scores_gemma":[0.70780367,0.00007477582,0.29122958,0.00053318305,0.00022893336,0.000010238557,0.000063650725,0.000011575692,0.000044408316],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99951214,0.0000065698396,0.00016691157,0.00011549844,0.00007594933,0.00012294108],"domain_scores_gemma":[0.99958944,0.000008767405,0.00008457331,0.00017797353,0.00009625916,0.00004299714],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010635235,0.00009934256,0.00007773508,0.000040484447,0.00012076669,0.000035780497,0.0000655109,0.00007479292,0.0000035570451],"category_scores_gemma":[0.000035607143,0.00009103249,0.000023596287,0.000053571122,0.00008966735,0.000001541421,0.000041054987,0.000021973166,0.000005573147],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037698614,0.00053614087,0.008591719,0.00029786912,0.00036469856,9.647176e-7,0.0017718578,0.02945452,0.6022046,0.0020579626,0.0089959465,0.3453467],"study_design_scores_gemma":[0.00062402734,0.00039176014,0.0027892094,0.000019837988,0.000014427556,0.0000027671138,0.00014612824,0.97401375,0.014154079,0.0000112501175,0.0076711625,0.00016162053],"about_ca_topic_score_codex":0.0000015744191,"about_ca_topic_score_gemma":0.0000015434023,"teacher_disagreement_score":0.9445592,"about_ca_system_score_codex":0.000008276237,"about_ca_system_score_gemma":0.000030840903,"threshold_uncertainty_score":0.37121972},"labels":[],"label_agreement":null},{"id":"W2892158700","doi":"10.1093/bioinformatics/bty740","title":"ECCB 2018: The 17th European Conference on Computational Biology","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Computational biology; Biology","score_opus":0.037408995564868465,"score_gpt":0.302256421269661,"score_spread":0.2648474257047925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2892158700","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21032742,0.0002468046,0.17712292,0.0071208347,0.002543735,0.0015328757,0.00047090105,0.00015797088,0.6004765],"genre_scores_gemma":[0.9833458,0.00020851905,0.010462784,0.0034689836,0.0008424967,0.000007863643,0.0004533327,0.000021061047,0.0011891754],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985759,0.00009368715,0.00044316318,0.00016329846,0.000314779,0.00040916877],"domain_scores_gemma":[0.99890673,0.00004262855,0.00014486819,0.00047556395,0.00026625858,0.00016392788],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00064362405,0.00018759722,0.00013164456,0.000067813184,0.00026253227,0.00008858338,0.0006053936,0.00013055322,0.000094608826],"category_scores_gemma":[0.00025086701,0.00011902964,0.000079607315,0.000116962685,0.0008837294,0.000007123674,0.00029665674,0.00016079494,0.0013245092],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005530386,0.00054108055,0.0021628,0.00030401934,0.00051971106,0.0000065990207,0.0044308417,0.0002574956,0.020073,0.028134128,0.557042,0.38597527],"study_design_scores_gemma":[0.0020626942,0.004990573,0.0071362327,0.00008013864,0.000036735175,0.000056023982,0.0014324575,0.07576209,0.01490504,0.0035477867,0.8891006,0.0008896259],"about_ca_topic_score_codex":0.000005403681,"about_ca_topic_score_gemma":0.000010737644,"teacher_disagreement_score":0.77301836,"about_ca_system_score_codex":0.000015229861,"about_ca_system_score_gemma":0.00014622547,"threshold_uncertainty_score":0.99945307},"labels":[],"label_agreement":null},{"id":"W2894104460","doi":"10.1093/bioinformatics/bty832","title":"A systematic method for surveying data visualizations and a resulting genomic epidemiology visualization typology: GEViT","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Centre for Disease Control; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; University of British Columbia; Canada Research Chairs; Michael Smith Health Research BC; Fred Hutchinson Cancer Research Center","keywords":"Typology; Visualization; Data science; Computer science; Data visualization; Computational biology; Data mining; Biology; Geography; Archaeology","score_opus":0.1553546717332538,"score_gpt":0.43647967099048524,"score_spread":0.28112499925723144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2894104460","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011409666,0.0001208863,0.99812746,0.0002397149,0.0002548275,0.0005857986,0.00012480203,0.00016933237,0.00026310954],"genre_scores_gemma":[0.0068171183,0.00009682871,0.98969877,0.0021755507,0.0001491582,0.000029212342,0.0008813883,0.000022425205,0.00012952494],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976291,0.000415345,0.0011308566,0.0003524909,0.00013108269,0.00034112917],"domain_scores_gemma":[0.99615395,0.0016444843,0.00065687456,0.0011291017,0.0003022366,0.000113344155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005356327,0.00017475773,0.00044860778,0.00024131437,0.000389926,0.00020037654,0.0010466286,0.00011815676,0.000004454809],"category_scores_gemma":[0.0068359585,0.00015411967,0.00003603243,0.0005176798,0.00010619156,0.0010067194,0.00081907725,0.000054634886,0.000036699057],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010485557,0.00006290025,0.0012005715,0.0070962743,0.00017091217,6.0589815e-7,0.0042115175,0.000089385496,0.000098053875,0.97354376,0.009072015,0.0044434997],"study_design_scores_gemma":[0.00030999206,0.00007651251,0.0001644334,0.0003025629,0.000051239436,0.000023504148,0.00031421095,0.9950775,0.0000260769,0.0012870826,0.002181514,0.00018536758],"about_ca_topic_score_codex":0.00001727821,"about_ca_topic_score_gemma":0.000029961706,"teacher_disagreement_score":0.99498814,"about_ca_system_score_codex":0.000035662688,"about_ca_system_score_gemma":0.00010211098,"threshold_uncertainty_score":0.81837744},"labels":[],"label_agreement":null},{"id":"W2895908163","doi":"10.1093/bioinformatics/bty883","title":"Landscape of multi-tissue global gene expression reveals the regulatory signatures of feed efficiency in beef cattle","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic and phenotypic traits in livestock","field":"Biochemistry, Genetics and Molecular Biology","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Agriculture and Agri-Food Canada; Alberta Livestock and Meat Agency; Alberta Agriculture and Forestry","keywords":"Transcriptome; Biology; Residual feed intake; Gene; Feed conversion ratio; Rumen; Gene expression; Beef cattle; Phenotype; Genetics; Regulator gene; Gene expression profiling; Trait; Computational biology; Body weight; Biochemistry","score_opus":0.009546474809135003,"score_gpt":0.2493989742368527,"score_spread":0.2398524994277177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2895908163","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98834133,0.0010552756,0.008826963,0.000016058017,0.00014989362,0.00021162641,0.000055086035,0.000004430434,0.0013393421],"genre_scores_gemma":[0.9469737,0.00001566952,0.05276205,0.00004894526,0.00007395146,0.0000040203886,0.000024746565,0.000005355786,0.000091601156],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99921596,0.000032511463,0.00036196416,0.000097898424,0.00014020027,0.00015149433],"domain_scores_gemma":[0.9993112,0.000014193845,0.00018751583,0.00036349174,0.00008907334,0.000034510776],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018151027,0.0001037729,0.00013866526,0.000023532779,0.000038884475,0.0000046394393,0.00028012326,0.00014535928,0.000014096628],"category_scores_gemma":[0.00006916328,0.0000716288,0.000039786784,0.00011100084,0.00021730289,0.0000035358476,0.00010697518,0.000047676236,0.0000036937402],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018522119,0.00031558747,0.019689048,0.0002717367,0.000046702244,1.9303997e-7,0.0027399745,0.0028292558,0.96006626,0.0013444386,0.0058061234,0.0067054434],"study_design_scores_gemma":[0.00072248944,0.0004985794,0.23083726,0.000059472455,0.000014447811,0.0000042740385,0.00043480578,0.00033722792,0.7660228,0.00020906019,0.00071245624,0.00014715405],"about_ca_topic_score_codex":0.000008287755,"about_ca_topic_score_gemma":0.000014097124,"teacher_disagreement_score":0.2111482,"about_ca_system_score_codex":0.000005399244,"about_ca_system_score_gemma":0.00005965791,"threshold_uncertainty_score":0.29209375},"labels":[],"label_agreement":null},{"id":"W2896090507","doi":"10.1093/bioinformatics/bty825","title":"MetaOmics: analysis pipeline and browser-based software suite for transcriptomic meta-analysis","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Centre for Addiction and Mental Health","funders":"National Cancer Institute; National Institutes of Health; U.S. National Library of Medicine; National Natural Science Foundation of China","keywords":"Suite; Pipeline (software); Computer science; Software; Software suite; Software engineering; World Wide Web; Operating system","score_opus":0.04819263447781635,"score_gpt":0.2974941623703049,"score_spread":0.24930152789248855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2896090507","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02828118,0.0008290501,0.96975416,0.000268636,0.000060896768,0.0002948777,0.00030001445,0.00002624676,0.00018492813],"genre_scores_gemma":[0.89912605,0.00007202947,0.096736,0.0014956299,0.00011578094,0.00010341597,0.001192123,0.000019328305,0.0011396621],"study_design_codex":"meta_analysis","study_design_gemma":"meta_analysis","domain_scores_codex":[0.9989893,0.000029367928,0.00041419367,0.00023983288,0.00013582763,0.00019152118],"domain_scores_gemma":[0.9989678,0.000020767964,0.00019603867,0.0004963341,0.00021937283,0.00009963934],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029270077,0.00017607652,0.00045960787,0.00030021791,0.00011639453,0.00005887853,0.00017402908,0.00013132216,0.00009229494],"category_scores_gemma":[0.000061023453,0.00013986847,0.00089292345,0.000589891,0.00009211639,0.000009703199,0.00002623488,0.000036268862,0.0000054221778],"study_design_candidate":"meta_analysis","study_design_consensus":"meta_analysis","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014907175,0.00053875364,0.008522249,0.0007468404,0.5582501,8.248469e-7,0.0023095293,0.007514024,0.335335,0.0006120205,0.061131317,0.023548594],"study_design_scores_gemma":[0.0015909524,0.00039945354,0.0013158666,0.0000022545175,0.39960957,0.000001443398,0.00031950636,0.19060308,0.26415843,0.00010345307,0.14118005,0.00071595784],"about_ca_topic_score_codex":0.000006735356,"about_ca_topic_score_gemma":0.00014856095,"teacher_disagreement_score":0.87301815,"about_ca_system_score_codex":0.000009764638,"about_ca_system_score_gemma":0.00005793294,"threshold_uncertainty_score":0.5703671},"labels":[],"label_agreement":null},{"id":"W2897133367","doi":"10.1093/bioinformatics/bty878","title":"BMDExpress 2: enhanced transcriptomic dose-response analysis workflow","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":227,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Canada","funders":"National Institute of Environmental Health Sciences; National Institutes of Health","keywords":"Workflow; Computer science; Software; Transcriptome; Software engineering; Data mining; Data science; Database; Operating system; Biology; Gene","score_opus":0.012719542668610605,"score_gpt":0.2668319319701167,"score_spread":0.2541123893015061,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2897133367","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75000536,0.00012294526,0.24362879,0.00015851243,0.00032968758,0.00018542126,0.000026903854,0.00004127723,0.005501118],"genre_scores_gemma":[0.99237895,0.00006213914,0.0052868375,0.00044808807,0.00018851995,0.000026136559,0.00009485852,0.000012355972,0.0015021006],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99907064,0.000054151922,0.00030956266,0.00018320381,0.0001627092,0.00021972418],"domain_scores_gemma":[0.99911314,0.0000092445225,0.00012051243,0.00053777563,0.00011834648,0.00010096891],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022426488,0.00014340751,0.00014551285,0.00015112838,0.00010874064,0.000045894853,0.00024858388,0.00014296966,0.00013408477],"category_scores_gemma":[0.00005146385,0.00012777367,0.00015444154,0.00042691827,0.000103913655,0.000009499994,0.000041922158,0.000052310254,0.000096402386],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007002221,0.000035140645,0.00018365486,0.000011882234,0.00018073489,1.5073473e-7,0.00058618333,0.00007590882,0.97831196,0.000025124067,0.0068425825,0.013046464],"study_design_scores_gemma":[0.0006938564,0.00024485472,0.0066666007,0.000012899234,0.00014201069,0.0000017038911,0.0002091133,0.0038409103,0.88342905,0.000036980033,0.10443895,0.0002830936],"about_ca_topic_score_codex":0.0000022281545,"about_ca_topic_score_gemma":0.000014129605,"teacher_disagreement_score":0.24237362,"about_ca_system_score_codex":0.00001750604,"about_ca_system_score_gemma":0.00007618158,"threshold_uncertainty_score":0.5210459},"labels":[],"label_agreement":null},{"id":"W2898449026","doi":"10.1093/bioinformatics/bty888","title":"Alignment-free clustering of UMI tagged DNA molecules","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"","keywords":"Barcode; Cluster analysis; Computer science; DNA sequencing; Computational biology; Genomics; Data mining; Biology; DNA; Genetics; Genome; Gene; Artificial intelligence","score_opus":0.00933349121835504,"score_gpt":0.23147020391928735,"score_spread":0.22213671270093233,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2898449026","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8615527,0.00052823644,0.102044776,0.00022072828,0.0008751983,0.00041442274,0.00031628294,0.000031120693,0.034016512],"genre_scores_gemma":[0.94553256,0.00039302552,0.052267063,0.000846898,0.00048780895,0.000011246749,0.00013351357,0.000029407101,0.00029847163],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999272,0.0000075287967,0.00031183113,0.00010035584,0.00011936056,0.000188918],"domain_scores_gemma":[0.9991451,0.000010927357,0.00014437755,0.00053547614,0.00009831951,0.00006583714],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010059505,0.00011606727,0.00012166096,0.000037461672,0.000050324805,0.000020416315,0.00029268858,0.00009056979,0.000021700787],"category_scores_gemma":[0.00014447278,0.00011355347,0.00006474803,0.000058994687,0.00012375134,0.000004260255,0.00032759854,0.000030000998,0.00002198718],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034689304,0.00022864733,0.0020092942,0.00047086325,0.00034034526,0.000004141646,0.0018408727,0.00053580164,0.8346651,0.0024802578,0.12888457,0.028193178],"study_design_scores_gemma":[0.0014587139,0.0009088978,0.00077015406,0.000052740506,0.00004455487,0.000017424707,0.00044079512,0.011715539,0.8624481,0.00030960148,0.12143537,0.0003981403],"about_ca_topic_score_codex":0.000014908124,"about_ca_topic_score_gemma":0.000050923998,"teacher_disagreement_score":0.08397984,"about_ca_system_score_codex":0.000013859544,"about_ca_system_score_gemma":0.00006409667,"threshold_uncertainty_score":0.4630576},"labels":[],"label_agreement":null},{"id":"W2899545492","doi":"10.1093/bioinformatics/bty908","title":"BiXGBoost: a scalable, flexible boosting-based method for reconstructing gene regulatory networks","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":86,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Higher Education Discipline Innovation Project; National Natural Science Foundation of China","keywords":"Computer science; Scalability; Gene regulatory network; Inference; Data mining; Python (programming language); Boosting (machine learning); Machine learning; Artificial intelligence; Gene; Gene expression; Biology; Database","score_opus":0.014920243380440353,"score_gpt":0.2667671860171329,"score_spread":0.25184694263669255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2899545492","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.062402856,0.00044017137,0.934535,0.00005994718,0.00041507804,0.0004380206,0.000027266387,0.00008133576,0.001600288],"genre_scores_gemma":[0.2170135,0.000023444923,0.77932614,0.0009170726,0.0015147248,0.00005595378,0.00032170885,0.00006808423,0.0007593977],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99819195,0.000059933678,0.00064416736,0.000337707,0.00019009366,0.00057617325],"domain_scores_gemma":[0.99824846,0.000059740018,0.00038753625,0.0007724138,0.0003559846,0.00017587095],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00089637906,0.00029183127,0.0003148099,0.00013096977,0.00035368945,0.0000718683,0.00031746092,0.0003194904,0.00003155344],"category_scores_gemma":[0.00017096633,0.00028910986,0.00026430227,0.00033157755,0.00018920223,0.000012780164,0.00012547043,0.00009347967,0.000018928049],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010403802,0.0002493463,0.012461647,0.0006557096,0.0017253052,0.0000038376984,0.0004567701,0.15329252,0.21344085,0.00082792423,0.099892184,0.51595354],"study_design_scores_gemma":[0.00072437356,0.00028288254,0.00021915307,0.00003913285,0.00011809956,0.000026652904,0.00007724243,0.7385625,0.23836562,0.0000663935,0.021125052,0.00039287287],"about_ca_topic_score_codex":0.000004969989,"about_ca_topic_score_gemma":0.000014789154,"teacher_disagreement_score":0.58527,"about_ca_system_score_codex":0.000038665665,"about_ca_system_score_gemma":0.00018117586,"threshold_uncertainty_score":0.99995613},"labels":[],"label_agreement":null},{"id":"W2899971763","doi":"10.1093/bioinformatics/bty911","title":"Discovering network phenotype between genetic risk factors and disease status via diagnosis-aligned multi-modality regression method in Alzheimer’s disease","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institute on Aging; Canadian Institutes of Health Research; National Institutes of Health; Stanley Medical Research Institute; National Natural Science Foundation of China; U.S. Department of Defense","keywords":"Disease; Phenotype; Regression; Clinical phenotype; Computational biology; Computer science; Artificial intelligence; Medicine; Bioinformatics; Genetics; Biology; Statistics; Pathology; Gene; Mathematics","score_opus":0.06549029352753541,"score_gpt":0.32384701547034633,"score_spread":0.2583567219428109,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2899971763","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9418461,0.00052330707,0.05517321,0.0005732374,0.0005165385,0.0007448892,0.00043954654,0.00012539657,0.00005778704],"genre_scores_gemma":[0.9833213,0.00024934844,0.015670136,0.00043874618,0.0002184836,0.000052403637,0.000016177357,0.000026479916,0.000006914802],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9978141,0.00029542737,0.0005051066,0.00041876305,0.00039773923,0.0005688353],"domain_scores_gemma":[0.99516636,0.0034913595,0.0002960666,0.00044337622,0.000047419544,0.0005554388],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00035025054,0.00032701218,0.00033532086,0.00011152467,0.0005036873,0.00010055056,0.0001932204,0.000063978274,0.000014552741],"category_scores_gemma":[0.0077529876,0.00025429408,0.00007959165,0.00039305285,0.00029349915,0.00054576783,0.00041205416,0.00014748273,0.000024944542],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012789616,0.00007918441,0.9860976,0.00006320944,0.000029195371,0.000005719162,0.0013262753,0.00109456,0.000037548776,0.00006528847,0.00043446245,0.010639072],"study_design_scores_gemma":[0.0005319628,0.00008306024,0.9101578,0.00008548421,0.00013990016,3.1351593e-7,0.000111442234,0.08563853,0.0006627942,0.0015813598,0.00067177584,0.0003355518],"about_ca_topic_score_codex":0.00026263125,"about_ca_topic_score_gemma":0.00011257636,"teacher_disagreement_score":0.084543966,"about_ca_system_score_codex":0.00008509755,"about_ca_system_score_gemma":0.00009927358,"threshold_uncertainty_score":0.99999094},"labels":[],"label_agreement":null},{"id":"W2903232627","doi":"10.1093/bioinformatics/bty976","title":"Detection of rare disease variants in extended pedigrees using RVS","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"National Institute of Dental and Craniofacial Research","keywords":"Pedigree chart; Bioconductor; Genetics; Biology; Genetic linkage; Linkage (software); Computational biology; Computer science; Gene","score_opus":0.018304788989561893,"score_gpt":0.27315039777806716,"score_spread":0.25484560878850526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2903232627","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9768531,0.00008734331,0.022281965,0.00002107591,0.00014415801,0.000100248355,0.000020671563,0.00000454509,0.00048694163],"genre_scores_gemma":[0.98908055,0.000041195857,0.010592819,0.00007788539,0.00012121741,0.000003256221,0.00002914424,0.0000057998864,0.000048136928],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99935806,0.000032527172,0.0003087475,0.00008340275,0.00006285608,0.00015440074],"domain_scores_gemma":[0.9995122,0.000009386544,0.00015392703,0.00019250468,0.00008262043,0.00004939294],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019351974,0.00007482234,0.000110781264,0.000055531356,0.00004312574,0.0000048619104,0.000083156454,0.00009682249,0.000009720637],"category_scores_gemma":[0.00026701644,0.00007026459,0.00004094153,0.00009236539,0.000073813164,0.000005080314,0.00005696417,0.000032534263,0.0000066828343],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005853215,0.00045576325,0.39336216,0.00041386997,0.00020738156,0.000005469091,0.0018961943,0.0016144566,0.5405296,0.00032614844,0.0016171425,0.058986504],"study_design_scores_gemma":[0.0010835414,0.00047025026,0.8533596,0.000049991086,0.000048227226,0.000012416163,0.00063252676,0.11405582,0.026829517,0.00052118575,0.0026028885,0.00033404128],"about_ca_topic_score_codex":0.000025522044,"about_ca_topic_score_gemma":0.00006599984,"teacher_disagreement_score":0.51370007,"about_ca_system_score_codex":0.000014498704,"about_ca_system_score_gemma":0.00006840469,"threshold_uncertainty_score":0.28653067},"labels":[],"label_agreement":null},{"id":"W2904816621","doi":"10.1093/bioinformatics/bty1019","title":"ModL: exploring and restoring regularity when testing for positive selection","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Type I and type II errors; Selection (genetic algorithm); Context (archaeology); Statistics; Statistical power; Null hypothesis; Statistical hypothesis testing; Mathematics; Mixing (physics); Likelihood-ratio test; Power (physics); Model selection; Type (biology); Variety (cybernetics); Chi-square test; Computer science; Artificial intelligence; Biology","score_opus":0.09692745390537694,"score_gpt":0.2875576846226645,"score_spread":0.19063023071728757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2904816621","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004552093,0.000017884113,0.9924436,0.00018663643,0.0002434345,0.00018091852,0.0000016537906,0.000121499004,0.0022522497],"genre_scores_gemma":[0.027182665,0.0000025451156,0.97238797,0.00015132602,0.0001940079,0.000019841904,6.7188057e-7,0.00000606425,0.00005492739],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993294,0.000019708945,0.00019321832,0.00013074711,0.00011874498,0.00020821927],"domain_scores_gemma":[0.9993659,0.00011421097,0.00008874373,0.00018601092,0.00017723381,0.00006789698],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005327513,0.00009297713,0.00010418265,0.00006783351,0.00026276076,0.00016960391,0.00019211345,0.000047641144,3.5184223e-7],"category_scores_gemma":[0.0001826496,0.00008600365,0.000021829048,0.0001577616,0.00004340055,0.0010700064,0.00018140966,0.00006814916,0.0000021847648],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008625115,0.000011190257,0.00025197555,0.00008463855,0.000013426929,3.9547427e-7,0.007406994,0.000004274257,0.00084204844,0.11999956,0.00035034865,0.8710265],"study_design_scores_gemma":[0.00024051062,0.00029127373,0.0013388181,0.00007752763,0.000009400335,0.000030576128,0.000042023323,0.9071298,0.009241336,0.0804938,0.00091221766,0.00019271477],"about_ca_topic_score_codex":0.0000147117835,"about_ca_topic_score_gemma":0.0000030061392,"teacher_disagreement_score":0.90712553,"about_ca_system_score_codex":0.000036632362,"about_ca_system_score_gemma":0.000034035733,"threshold_uncertainty_score":0.35071272},"labels":[],"label_agreement":null},{"id":"W2904871025","doi":"10.1093/bioinformatics/bty992","title":"Gene expression models based on transcription factor binding events confer insight into functional <i>cis</i> -regulatory variants","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Children's Hospital; University of British Columbia","funders":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; Genome British Columbia; BC Children’s Hospital Foundation; BC Children's Hospital; National Institutes of Health; Children's Hospital Foundation; Canadian Institutes of Health Research; China Scholarship Council; Genome Canada","keywords":"CTCF; Computational biology; Transcription factor; Gene; Biology; Genetics; DNA binding site; Regulation of gene expression; Regulatory sequence; Gene expression; Enhancer; Promoter","score_opus":0.015847253369992757,"score_gpt":0.21414458782602006,"score_spread":0.1982973344560273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2904871025","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7648156,0.000025501125,0.23243704,0.000030988016,0.0005500481,0.00020929035,0.0001017114,0.000024234223,0.0018055539],"genre_scores_gemma":[0.9844337,0.000024222896,0.013980112,0.00049707096,0.0002245845,0.0000128344345,0.0006265776,0.000027257785,0.00017360535],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989177,0.000026437168,0.00035750077,0.00020459446,0.00026180255,0.00023197096],"domain_scores_gemma":[0.9992273,0.0000074434497,0.00014679918,0.00038771462,0.0001220943,0.00010868031],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011799269,0.00021227899,0.0001400275,0.000087757355,0.0001964423,0.00003776513,0.00016954137,0.00023207434,0.000056534915],"category_scores_gemma":[0.000013516534,0.0001913694,0.000095912976,0.00006866796,0.0000620668,0.00002357711,0.000053543703,0.00008237507,0.00005714156],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001683581,0.0001040778,0.00014917881,0.000056186414,0.00003301024,4.4961166e-7,0.0004765019,0.0033352163,0.99314445,0.00010798686,0.0010316735,0.0013929044],"study_design_scores_gemma":[0.0014909907,0.00053094374,0.0016673171,0.0000690515,0.000021999087,0.000006349411,0.000081986844,0.4150087,0.57654685,0.00025112042,0.0038910937,0.0004336141],"about_ca_topic_score_codex":0.0000024653677,"about_ca_topic_score_gemma":0.0000044098497,"teacher_disagreement_score":0.4165976,"about_ca_system_score_codex":0.000050191822,"about_ca_system_score_gemma":0.00011970355,"threshold_uncertainty_score":0.78038174},"labels":[],"label_agreement":null},{"id":"W2905275624","doi":"10.1093/bioinformatics/bty1003","title":"Pathogen–Host Analysis Tool (PHAT): an integrative platform to analyze next-generation sequencing data","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bacteriophages and microbial interactions","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"NOSM University; Lakehead University; Thunder Bay Regional Research Institute","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Host (biology); Pathogen; Computer science; Computational biology; Data science; Biology; Genetics","score_opus":0.07464074968777398,"score_gpt":0.29671725205821314,"score_spread":0.22207650237043916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2905275624","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9184277,0.000003814405,0.0760241,0.00007853425,0.00026149288,0.0002613191,0.00044446322,0.000055855064,0.004442718],"genre_scores_gemma":[0.91791666,0.000013059533,0.079019226,0.0010620554,0.0002232184,0.000008265068,0.0012680553,0.000012278372,0.00047718326],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988801,0.000018715724,0.0004249228,0.00024476185,0.0001771782,0.00025435208],"domain_scores_gemma":[0.9988316,0.000016718033,0.0001486269,0.0008263765,0.00003463951,0.00014200638],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002703997,0.00016912856,0.000184374,0.0001290681,0.00028136699,0.00028551446,0.00050194986,0.00006784795,0.002296398],"category_scores_gemma":[0.00005861152,0.0001369055,0.00006521156,0.0008194666,0.00009042591,0.0031307617,0.0003902651,0.000098805554,0.0012778455],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022762308,0.00006997224,0.0008638412,0.000007082959,0.00020939036,0.0000031182658,0.010352944,0.0005079087,0.92531866,0.00006856367,0.008027994,0.054547776],"study_design_scores_gemma":[0.00020867573,0.0003828195,0.01300739,0.000024181274,0.00045132687,0.000021892598,0.0044131833,0.9169342,0.028986268,0.000013948223,0.03496226,0.0005938539],"about_ca_topic_score_codex":0.0007937282,"about_ca_topic_score_gemma":0.008855508,"teacher_disagreement_score":0.9164263,"about_ca_system_score_codex":0.0002867938,"about_ca_system_score_gemma":0.000028451399,"threshold_uncertainty_score":0.9994998},"labels":[],"label_agreement":null},{"id":"W2905575949","doi":"10.1093/bioinformatics/bty1015","title":"SPRING: a next-generation compressor for FASTQ data","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":91,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Cancer Institute; University of Illinois at Urbana-Champaign; National Institutes of Health; Sunnybrook Research Institute; Silicon Valley Community Foundation","keywords":"Computer science; Lossless compression; Scalability; Lossy compression; Data compression; Data mining; Redundancy (engineering); Identifier; Compression (physics); Database; Artificial intelligence; Computer network; Operating system","score_opus":0.1701892097079504,"score_gpt":0.3126197987859841,"score_spread":0.14243058907803371,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2905575949","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00074692833,0.000060269245,0.9971479,0.00019370389,0.0007101656,0.00023380847,0.00007962579,0.00012077879,0.00070681993],"genre_scores_gemma":[0.01607756,0.0000152105495,0.98249674,0.00044561567,0.00062257005,0.0000107841715,0.00022090218,0.000006815025,0.000103827755],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991232,0.0000093666495,0.00027830063,0.00018587275,0.00019511381,0.00020815927],"domain_scores_gemma":[0.9982447,0.000040699513,0.00012428677,0.0014023059,0.00011468189,0.00007329384],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024551226,0.00010206468,0.0001053807,0.000053047082,0.00023098747,0.00041431142,0.0016152527,0.000048171034,0.000007584535],"category_scores_gemma":[0.000056040157,0.00008337503,0.000022978025,0.0001220508,0.00004068995,0.002564783,0.0010711899,0.00004526722,0.00011456797],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016717175,0.00012638117,0.00009604392,0.00017065745,0.000040886298,0.0000013034982,0.001805887,0.000058453472,0.0026427119,0.04581898,0.22916602,0.72005594],"study_design_scores_gemma":[0.00019828975,0.000062375846,0.00005742482,0.00001173194,0.000003321231,0.00000279969,0.000016058775,0.7751544,0.0009569521,0.00013158501,0.22330806,0.00009697581],"about_ca_topic_score_codex":0.00001745193,"about_ca_topic_score_gemma":0.000012150121,"teacher_disagreement_score":0.77509594,"about_ca_system_score_codex":0.000013334259,"about_ca_system_score_gemma":0.00005016436,"threshold_uncertainty_score":0.39952147},"labels":[],"label_agreement":null},{"id":"W2906587988","doi":"10.1093/bioinformatics/bty1035","title":"Systematic selection of chemical fingerprint features improves the Gibbs energy prediction of biochemical reactions","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"King Abdullah University of Science and Technology","keywords":"Computer science; Software; Feature selection; Fingerprint (computing); Data mining; Artificial intelligence; Gibbs free energy; Machine learning; Selection (genetic algorithm); Energy (signal processing); Feature (linguistics); Mathematics; Statistics","score_opus":0.0071927714951737845,"score_gpt":0.23005514919194137,"score_spread":0.2228623776967676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2906587988","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.979021,0.000029568608,0.018175883,0.00011065449,0.0008069561,0.00029800742,0.000033690998,0.00011583815,0.0014083763],"genre_scores_gemma":[0.98022777,0.0000052013625,0.019499792,0.00002978287,0.00013579581,0.00002075594,0.000005509312,0.000007622624,0.00006779936],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998443,0.000079631245,0.00078104564,0.000121271674,0.00038902444,0.00018604755],"domain_scores_gemma":[0.9985431,0.00017019574,0.00067154196,0.0003427905,0.000230218,0.000042144045],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008497892,0.00012075372,0.00025025735,0.00007327445,0.00010411193,0.00005158412,0.0003798216,0.00009785516,0.0000932679],"category_scores_gemma":[0.0008048728,0.000076465876,0.000060901213,0.00026319493,0.00043597913,0.00019680566,0.00011889125,0.0000828929,0.000022190727],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015532985,0.00002459715,0.00003478667,0.0018479901,0.000007664,2.1634037e-8,0.000526068,0.000039598737,0.99594474,0.001030777,0.00048215952,0.000046065823],"study_design_scores_gemma":[0.00008166583,0.00010622828,0.0005178548,0.0004842706,0.000029972249,0.000029068346,0.00013685913,0.053490747,0.9448508,0.00015428566,0.000050130286,0.00006811691],"about_ca_topic_score_codex":0.000121361045,"about_ca_topic_score_gemma":0.0000032555324,"teacher_disagreement_score":0.05345115,"about_ca_system_score_codex":0.00004128465,"about_ca_system_score_gemma":0.00006569422,"threshold_uncertainty_score":0.31181878},"labels":[],"label_agreement":null},{"id":"W2907347464","doi":"10.1093/bioinformatics/bty1053","title":"The COP9 signalosome influences the epigenetic landscape of <i>Arabidopsis thaliana</i>","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Ubiquitin and proteasome pathways","field":"Biochemistry, Genetics and Molecular Biology","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Azrieli Foundation; H2020 European Research Council; Tel Aviv University","keywords":"Arabidopsis thaliana; COP9 signalosome; Epigenetics; Biology; Computational biology; Arabidopsis; Genetics; Gene","score_opus":0.013554330975524229,"score_gpt":0.24077501050217973,"score_spread":0.2272206795266555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2907347464","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9605334,0.002955356,0.0010567197,0.00067010033,0.00039635174,0.00053737964,0.00008507634,0.000022765416,0.033742882],"genre_scores_gemma":[0.9975218,0.0004262165,0.00074389944,0.0005699789,0.00026876858,0.000020506212,0.000019554625,0.000009873227,0.00041938416],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991282,0.000046346064,0.00032406868,0.00008804302,0.00018539194,0.0002279293],"domain_scores_gemma":[0.9991088,0.00005367028,0.00018618691,0.00046226452,0.00014096386,0.000048135655],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038150765,0.00011975251,0.00010249799,0.000016725477,0.0002760006,0.00004670382,0.00046646493,0.0000874499,0.000037123275],"category_scores_gemma":[0.00011645952,0.00006270908,0.00007818811,0.000113614245,0.00042812567,0.0000056069716,0.0001254528,0.00006423289,0.000085186875],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008840881,0.00032136237,0.048782162,0.0007836968,0.0012742662,0.000004323071,0.011265101,0.00024904526,0.550085,0.009781292,0.20655823,0.1700114],"study_design_scores_gemma":[0.0004070422,0.00077302597,0.002676671,0.000036475514,0.00003960198,0.00001874719,0.0012156169,0.0010519574,0.6983563,0.00052764907,0.2946415,0.00025547817],"about_ca_topic_score_codex":0.0000084446,"about_ca_topic_score_gemma":0.000021898419,"teacher_disagreement_score":0.16975592,"about_ca_system_score_codex":0.0000031542986,"about_ca_system_score_gemma":0.00007901894,"threshold_uncertainty_score":0.25572017},"labels":[],"label_agreement":null},{"id":"W2907957654","doi":"10.1093/bioinformatics/bty1067","title":"UbiHub: a data hub for the explorers of ubiquitination pathways","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Ubiquitin and proteasome pathways","field":"Biochemistry, Genetics and Molecular Biology","cited_by":68,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor; Structural Genomics Consortium; University of Toronto","funders":"Eshelman Institute for Innovation, University of North Carolina at Chapel Hill; Janssen Biotech; Innovative Medicines Initiative; Novartis Pharma; Ontario Genomics Institute; Canada Foundation for Innovation; Wellcome Trust; Ontario Ministry of Research, Innovation and Science; Ontario Genomics; Fundação de Amparo à Pesquisa do Estado de São Paulo; Genome Canada; AbbVie; European Federation of Pharmaceutical Industries and Associations; Structural Genomics Consortium; Merck KGaA; Pfizer; Boehringer Ingelheim","keywords":"Ubiquitin; Proteasome; Drug discovery; Deubiquitinating enzyme; Computational biology; Protein degradation; Biology; Ubiquitin-Protein Ligases; Ubiquitin ligase; Cell biology; Bioinformatics; Biochemistry","score_opus":0.07489918757800679,"score_gpt":0.29358765037220486,"score_spread":0.21868846279419807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2907957654","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3354945,0.0014898891,0.6149598,0.0011002087,0.0016558276,0.0038247195,0.0032523738,0.00011466242,0.038108055],"genre_scores_gemma":[0.9705771,0.00015294018,0.026996335,0.0005272409,0.0006138539,0.00006577781,0.0009183117,0.000020950733,0.0001274924],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99926883,0.000014946279,0.00028756898,0.000122026715,0.00012895222,0.00017766439],"domain_scores_gemma":[0.9988003,0.000042935553,0.0001755923,0.0007763457,0.00016724772,0.000037576476],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047368722,0.000101713216,0.00009544817,0.000026575088,0.00012520612,0.000022860731,0.00056249753,0.000088037894,0.000016794675],"category_scores_gemma":[0.00022807585,0.00007210515,0.000052257783,0.000069954396,0.00016227056,0.000013848092,0.00026239874,0.000037631467,0.000016585063],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006786546,0.00025457254,0.0005330155,0.00095585897,0.0004512947,6.01686e-7,0.0067298897,0.000044014167,0.3408538,0.012030679,0.13116331,0.5063043],"study_design_scores_gemma":[0.00074418634,0.0007924009,0.0001413397,0.000033807446,0.000045286662,0.000008014596,0.0014967012,0.030007804,0.63148403,0.00036218463,0.33466682,0.00021746052],"about_ca_topic_score_codex":0.0000034127058,"about_ca_topic_score_gemma":0.000009951201,"teacher_disagreement_score":0.6350826,"about_ca_system_score_codex":0.0000051258603,"about_ca_system_score_gemma":0.00008149034,"threshold_uncertainty_score":0.29403627},"labels":[],"label_agreement":null},{"id":"W2908677338","doi":"10.1093/bioinformatics/btz012","title":"A web application and service for imputing and visualizing missense variant effect maps","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Advanced Research; Sinai Health System; Lunenfeld-Tanenbaum Research Institute; University of Toronto","funders":"National Human Genome Research Institute; Canadian Institutes of Health Research; National Institutes of Health; Canada Research Chairs","keywords":"Missense mutation; Imputation (statistics); Computer science; Pipeline (software); Software; Source code; Data mining; Web service; Missing data; Open source; Exome; Computational biology; Biology; Mutation; World Wide Web; Genetics; Machine learning; Exome sequencing; Gene; Programming language","score_opus":0.004101546701540773,"score_gpt":0.23331096607724777,"score_spread":0.229209419375707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2908677338","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9961949,0.0003498654,0.0025980126,0.00006371804,0.000044980465,0.00046486684,0.000047452104,0.0000089973255,0.00022719856],"genre_scores_gemma":[0.99447405,0.000058919402,0.004669084,0.00050210394,0.00005482527,0.000016920932,0.00018641067,0.000011365883,0.000026319516],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995959,0.0000078727135,0.0001354568,0.000109066736,0.000035901754,0.0001158075],"domain_scores_gemma":[0.9996754,0.000022522441,0.000069435555,0.0001366737,0.00003924972,0.000056715904],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001410728,0.000086055596,0.000088687775,0.000019864448,0.000057163517,0.000037950642,0.000044672066,0.00006803158,5.10411e-7],"category_scores_gemma":[0.000023843972,0.00007696443,0.000024682327,0.000028930783,0.00001075268,0.0000040996224,0.000071058595,0.000019976547,0.000005141235],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045212364,0.00007641053,0.0051064906,0.0046723005,0.0002235543,0.0000046985733,0.0010315822,0.000108814245,0.917208,0.0025304228,0.0014804478,0.067105114],"study_design_scores_gemma":[0.010136652,0.0024097713,0.007034289,0.00025034338,0.00034945505,0.0010486857,0.0021979702,0.7429595,0.06631044,0.0007362261,0.16475908,0.0018075963],"about_ca_topic_score_codex":0.0000045520724,"about_ca_topic_score_gemma":0.0000030456576,"teacher_disagreement_score":0.8508976,"about_ca_system_score_codex":0.000003637373,"about_ca_system_score_gemma":0.000024759534,"threshold_uncertainty_score":0.31385183},"labels":[],"label_agreement":null},{"id":"W2909472027","doi":"10.1093/bioinformatics/bty1054","title":"DIABLO: an integrative approach for identifying key molecular drivers from multi-omics assays","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1056,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Prevention of Organ Failure; University of British Columbia","funders":"National Institute of Allergy and Infectious Diseases; National Health and Medical Research Council","keywords":"Bioconductor; Omics; Computer science; Computational biology; Benchmark (surveying); Identification (biology); Relevance (law); Data integration; Visualization; Data mining; Data science; Bioinformatics; Biology; Ecology; Cartography; Geography","score_opus":0.015892733093059504,"score_gpt":0.25083534586353734,"score_spread":0.23494261277047784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2909472027","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38802147,0.000039524664,0.6097022,0.000008924712,0.00014160221,0.00053021865,0.000087847766,0.000022222235,0.0014460013],"genre_scores_gemma":[0.5583916,0.000023746044,0.43927783,0.00044436267,0.00006453268,0.000037770315,0.001630119,0.00002449334,0.000105562685],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987283,0.00002457989,0.00047965065,0.00023972584,0.00015157263,0.0003761935],"domain_scores_gemma":[0.9989345,0.000022472997,0.00022555822,0.0005469025,0.00011832252,0.00015224071],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028300146,0.0002572433,0.00024501473,0.00005702283,0.0001170694,0.00011909527,0.00040657082,0.0002289902,0.000011794292],"category_scores_gemma":[0.000039674644,0.00022554424,0.00016319257,0.00008920644,0.00006687825,0.000049971233,0.00015260132,0.00012947644,0.000038009613],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044215284,0.0005757445,0.010352669,0.00036530235,0.0008882314,0.000002104192,0.0120528415,0.025898233,0.9063955,0.009622977,0.0019357692,0.03146845],"study_design_scores_gemma":[0.0025557538,0.00038151524,0.0004967008,0.000023008251,0.0000517729,0.0000066365474,0.006362132,0.8888485,0.09633284,0.00054070924,0.003751747,0.0006487275],"about_ca_topic_score_codex":0.000015541698,"about_ca_topic_score_gemma":0.000008987007,"teacher_disagreement_score":0.8629502,"about_ca_system_score_codex":0.000031483483,"about_ca_system_score_gemma":0.00006034605,"threshold_uncertainty_score":0.9197427},"labels":[],"label_agreement":null},{"id":"W2911619868","doi":"10.1093/bioinformatics/btz043","title":"SRG extractor: a skinny reference genome approach for reduced-representation sequencing","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; Université Laval","funders":"Génome Québec; Iowa State University; Genome Canada","keywords":"Reference genome; Genome; Genotyping; Extractor; Computational biology; Computer science; DNA sequencing; Pipeline (software); Biology; Genetics; Gene; Genotype; Operating system","score_opus":0.03827263071399067,"score_gpt":0.2684018089181237,"score_spread":0.23012917820413303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2911619868","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.971576,0.00032039013,0.013344068,0.000013333192,0.00014803828,0.0006538967,0.00008137496,0.000007632154,0.013855305],"genre_scores_gemma":[0.9422772,0.00013730014,0.05647669,0.00010322313,0.000115933064,0.000051202027,0.00036838232,0.000016433234,0.00045367057],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99918354,0.000013818993,0.00028030723,0.00018787223,0.00010012508,0.0002343505],"domain_scores_gemma":[0.99934894,0.000017300883,0.0001323822,0.00034649286,0.000102982405,0.000051912197],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017323287,0.00014244349,0.00015232562,0.00003611284,0.00007406645,0.000036547863,0.00017614818,0.000114973176,0.0000066603543],"category_scores_gemma":[0.00003953555,0.00013135068,0.000076479824,0.000057244564,0.00003122405,0.0000032413488,0.00009043511,0.000051368974,0.000020569953],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056336175,0.00002414155,0.0010604162,0.0001816351,0.00008431616,9.7234434e-8,0.00046779,0.0008716403,0.9945712,0.00043982334,0.00038169618,0.0018609071],"study_design_scores_gemma":[0.0072600977,0.0029497163,0.06559598,0.00009748809,0.00028880424,0.00013481938,0.01625883,0.06720473,0.607395,0.0016259556,0.22772859,0.0034600026],"about_ca_topic_score_codex":0.0000069243697,"about_ca_topic_score_gemma":0.0000015561483,"teacher_disagreement_score":0.38717622,"about_ca_system_score_codex":0.00002795385,"about_ca_system_score_gemma":0.00008461609,"threshold_uncertainty_score":0.5356325},"labels":[],"label_agreement":null},{"id":"W2912368193","doi":"10.1093/bioinformatics/btz531","title":"Simultaneous prediction of multiple outcomes using revised stacking algorithms","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"HIV/AIDS drug development and treatment","field":"Medicine","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria; University of Saskatchewan","funders":"Canada Research Chairs","keywords":"Stacking; Computer science; Algorithm; Chemistry","score_opus":0.025746495298406714,"score_gpt":0.2706057821646921,"score_spread":0.24485928686628539,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912368193","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9917599,0.00005692434,0.004607461,0.0001089572,0.00026982705,0.00089710054,0.00005643507,0.0000919173,0.0021515065],"genre_scores_gemma":[0.8902178,0.000029081897,0.10661938,0.00007155621,0.000027667409,0.0000033673111,0.00010883262,0.00001608492,0.0029062484],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989687,0.000007786289,0.00048215353,0.00007794729,0.00029294632,0.0001704378],"domain_scores_gemma":[0.99930626,0.00012094708,0.00017950381,0.0002212632,0.00010408412,0.00006792728],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011588185,0.00013210361,0.00031945034,0.000116508556,0.00003612674,0.000011352553,0.00004619819,0.00006675638,0.00006421005],"category_scores_gemma":[0.00012696434,0.00009842079,0.00008380387,0.00013325893,0.00002072515,0.0001328977,0.000030918254,0.000067877074,0.00010434089],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009373678,0.00024747927,0.9685046,0.0011279946,0.000415097,0.00001946594,0.0045205387,0.00086473156,0.0011794332,0.000034633165,0.00032668182,0.022665594],"study_design_scores_gemma":[0.0041418695,0.00016095708,0.012690758,0.0004671339,0.0001964561,0.00003540092,0.0011874994,0.97231805,0.0034196223,0.000006278141,0.005206561,0.00016942188],"about_ca_topic_score_codex":0.0000059010267,"about_ca_topic_score_gemma":6.144507e-7,"teacher_disagreement_score":0.9714533,"about_ca_system_score_codex":0.000102637765,"about_ca_system_score_gemma":0.0000844203,"threshold_uncertainty_score":0.40134832},"labels":[],"label_agreement":null},{"id":"W2914005557","doi":"10.1093/bioinformatics/btz084","title":"Multispectral tracing in densely labeled mouse brain with nTracer","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Institute of Allergy and Infectious Diseases; National Institute of Neurological Disorders and Stroke; National Institute of General Medical Sciences; National Institute of Mental Health; National Institutes of Health; National Science Foundation","keywords":"Tracing; Multispectral image; Computer science; Plug-in; Software; Documentation; Sample (material); Open source; Artificial intelligence; Computer graphics (images); Computer vision; Pattern recognition (psychology); Programming language; Chemistry","score_opus":0.004266281759108959,"score_gpt":0.2284269188327291,"score_spread":0.22416063707362013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2914005557","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9919088,0.00005356304,0.0045186915,0.00005744782,0.000007931119,0.00025029894,0.000003419278,0.000033511573,0.0031663722],"genre_scores_gemma":[0.9658542,0.00003919243,0.031373374,0.00044435234,0.00002570241,0.000010369469,0.000083599036,0.000020370104,0.0021488434],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992182,0.000017933584,0.00026239236,0.00014101001,0.00012270914,0.0002377201],"domain_scores_gemma":[0.99945086,0.000012371475,0.00009267105,0.00035404775,0.000044608212,0.000045432123],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017117834,0.00013766729,0.00015704101,0.000085335734,0.000020724008,0.00003756339,0.00014232386,0.0001085939,0.000030297342],"category_scores_gemma":[0.00003625144,0.00011615854,0.000052740943,0.00013186291,0.000031250584,0.00001534083,0.000044360673,0.00010229282,0.00005147707],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012578804,0.00011662955,0.021315608,0.00010926005,0.00008615969,0.000010089271,0.00064503564,0.00032143778,0.9678275,0.00004338585,0.0056744157,0.0037247024],"study_design_scores_gemma":[0.001485059,0.00039442303,0.0024110202,0.00004107662,0.00002033341,0.000034395114,0.00043517404,0.0147642875,0.9696516,0.000010333898,0.010310129,0.00044215887],"about_ca_topic_score_codex":0.000026223228,"about_ca_topic_score_gemma":0.0002284428,"teacher_disagreement_score":0.02685468,"about_ca_system_score_codex":0.000022007509,"about_ca_system_score_gemma":0.000043299468,"threshold_uncertainty_score":0.4736808},"labels":[],"label_agreement":null},{"id":"W2914184348","doi":"10.1093/bioinformatics/btz080","title":"ChimeraUGEM: unsupervised gene expression modeling in any given organism","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Azrieli Foundation; Tel Aviv University; Ministry of Science, Technology and Space","keywords":"Organism; Chlamydomonas reinhardtii; Model organism; Gene; Computational biology; Source code; Computer science; Biology; Gene expression; Coding (social sciences); Software; Coding region; Genetics; Programming language","score_opus":0.010676590549476008,"score_gpt":0.21166432740557284,"score_spread":0.20098773685609683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2914184348","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9906202,0.00034200915,0.007649002,0.000034643566,0.00009756563,0.00019211369,0.000005625429,0.000016341548,0.0010425055],"genre_scores_gemma":[0.98470396,0.00014352362,0.014338056,0.00015373043,0.000090942405,0.0000059571985,0.00016792223,0.00002314385,0.00037274245],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989831,0.000027471067,0.00036466657,0.0001836592,0.00016634582,0.00027476647],"domain_scores_gemma":[0.9992847,0.000003963618,0.00008238291,0.00050001574,0.000051215313,0.00007775164],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017109924,0.00016460888,0.00018908817,0.00008901865,0.000041124415,0.000025200457,0.000225631,0.00017173306,0.000062348976],"category_scores_gemma":[0.000014287799,0.00015271844,0.00008875956,0.00016756936,0.000015805339,0.000011480537,0.00015546694,0.00008052021,0.00012855645],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040327584,0.00006714364,0.010320871,0.00008007565,0.000064168096,0.0000015835247,0.00044923802,0.08117989,0.90531033,0.000014008495,0.0009358963,0.0015364734],"study_design_scores_gemma":[0.0010578398,0.000115306844,0.0008103151,0.000045999273,0.000026379741,0.000009341361,0.00036975642,0.70990616,0.28435373,0.000050978517,0.0028457623,0.0004084435],"about_ca_topic_score_codex":0.0000065309537,"about_ca_topic_score_gemma":0.0000072320818,"teacher_disagreement_score":0.62872624,"about_ca_system_score_codex":0.000022515072,"about_ca_system_score_gemma":0.000059940445,"threshold_uncertainty_score":0.6227677},"labels":[],"label_agreement":null},{"id":"W2914196064","doi":"10.1093/bioinformatics/btz113","title":"Identification of caveolin-1 domain signatures via machine learning and graphlet analysis of single-molecule super-resolution data","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Caveolin-1 and cellular processes","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; China Scholarship Council; Canada Foundation for Innovation; Prostate Cancer Canada","keywords":"Caveolae; Pattern recognition (psychology); Computational biology; Computer science; Artificial intelligence; Chemistry; Biology; Biochemistry; Membrane","score_opus":0.008597539482588387,"score_gpt":0.2346000855288737,"score_spread":0.22600254604628534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2914196064","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.958762,0.0019977528,0.038597032,0.00001330193,0.000041536005,0.00012721166,0.00018290132,0.0000070177225,0.0002712281],"genre_scores_gemma":[0.9957159,0.0002737571,0.0014293808,0.000019075502,0.000015099108,0.0000013364574,0.0024232524,0.000008173366,0.00011398992],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990885,0.000027713946,0.00044261588,0.00016079603,0.00016219294,0.00011815583],"domain_scores_gemma":[0.99910265,0.00001545935,0.00030784222,0.0004251315,0.000114169954,0.000034759014],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030383302,0.000107368105,0.00020883673,0.00016784233,0.00003523025,0.000016722503,0.00020795678,0.00011905615,0.000014285988],"category_scores_gemma":[0.00006668499,0.00010041724,0.00007136063,0.00030557433,0.000077081946,0.000016615013,0.00018059115,0.00006409563,0.0000019848032],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037519334,0.000045882774,0.0049477196,0.00023343344,0.0002646856,1.4743695e-7,0.0001811913,0.00045532282,0.9929166,0.000049903054,0.000037677928,0.0008299397],"study_design_scores_gemma":[0.0005565098,0.0002726895,0.0012838733,0.000023997156,0.0005168333,0.0000059813055,0.00048609645,0.14776088,0.8460417,0.000050319028,0.0027485522,0.00025255978],"about_ca_topic_score_codex":0.000024750098,"about_ca_topic_score_gemma":0.000040628656,"teacher_disagreement_score":0.14730556,"about_ca_system_score_codex":0.0000045181228,"about_ca_system_score_gemma":0.000022340006,"threshold_uncertainty_score":0.4094896},"labels":[],"label_agreement":null},{"id":"W2918710707","doi":"10.1093/bioinformatics/btz155","title":"Enhancing the prediction of disease–gene associations with multimodal deep learning","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":66,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Wuhan Institute of Technology; China Scholarship Council; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Deep learning; Disease; Artificial intelligence; Computational biology; Machine learning; Biology; Medicine; Internal medicine","score_opus":0.004619670751991929,"score_gpt":0.19699379663438568,"score_spread":0.19237412588239375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2918710707","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90681577,0.00019388928,0.088576734,0.00008043927,0.00023102525,0.0005312293,0.000106081454,0.000025157522,0.003439684],"genre_scores_gemma":[0.9929208,0.00006606401,0.0060443184,0.00010450078,0.00008880586,0.000008821097,0.0004315546,0.000011700832,0.00032340613],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992344,0.00001799578,0.00033866006,0.000074481635,0.00016033716,0.00017416938],"domain_scores_gemma":[0.99930716,0.000022366536,0.00025989226,0.00026363035,0.00009146184,0.00005550162],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020478702,0.00010674644,0.00011081488,0.000025399948,0.00010630213,0.000025377722,0.00014114908,0.00008162444,0.00001080618],"category_scores_gemma":[0.00003613274,0.00007164042,0.00006185369,0.000082673585,0.00004376481,0.000012140664,0.000068679365,0.00011014622,0.000021503658],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001273122,0.0005291447,0.29884407,0.0015527282,0.0022276153,0.0000018994086,0.015441646,0.2731785,0.33884156,0.0033612093,0.0030192153,0.061729297],"study_design_scores_gemma":[0.0036985453,0.0018412156,0.12975737,0.00016775004,0.00030063125,0.000019679414,0.004886445,0.7353779,0.09788312,0.00019532657,0.0249644,0.0009076038],"about_ca_topic_score_codex":0.000004328757,"about_ca_topic_score_gemma":0.000008664034,"teacher_disagreement_score":0.46219942,"about_ca_system_score_codex":0.00001506859,"about_ca_system_score_gemma":0.00006673419,"threshold_uncertainty_score":0.29214114},"labels":[],"label_agreement":null},{"id":"W2918882492","doi":"10.1093/bioinformatics/btz139","title":"SinNLRR: a robust subspace clustering method for cell type detection by non-negative and low-rank representation","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":167,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"National Natural Science Foundation of China","keywords":"Cluster analysis; Computer science; Data mining; Rank (graph theory); Similarity (geometry); Spectral clustering; Representation (politics); Noise (video); Embedding; Artificial intelligence; Machine learning; Mathematics; Image (mathematics)","score_opus":0.012537531169978787,"score_gpt":0.2482468645510999,"score_spread":0.2357093333811211,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2918882492","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44833884,0.000059364083,0.55017346,0.000024064206,0.00024536726,0.00042349592,0.000023300303,0.000011696891,0.0007004199],"genre_scores_gemma":[0.90025663,0.000116645526,0.098292224,0.00019685001,0.000086533015,0.000017568178,0.00016932521,0.000026740458,0.0008374573],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993835,0.00001779064,0.00020654968,0.00015505201,0.00007537829,0.00016173573],"domain_scores_gemma":[0.99954516,0.000033823886,0.00010604006,0.00017274937,0.00009291449,0.000049312108],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013781116,0.00012535532,0.00012823526,0.000032049717,0.00006697418,0.000045135635,0.00007004748,0.00013957637,0.0000038588464],"category_scores_gemma":[0.000040104744,0.00012141186,0.000048485657,0.00007650213,0.000021535221,0.000016362685,0.000033878972,0.00005789994,0.000008037977],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024627827,0.000032025866,0.00044000626,0.000264354,0.000026959575,9.14264e-8,0.0005519541,0.00091796956,0.989801,0.0000017868928,0.0006570629,0.0070605096],"study_design_scores_gemma":[0.0011365626,0.0004080715,0.00012081026,0.000014650899,0.000021872034,0.000004107315,0.00044393452,0.31217626,0.68370104,0.000010138039,0.001788543,0.00017398763],"about_ca_topic_score_codex":0.000043260152,"about_ca_topic_score_gemma":0.000044232715,"teacher_disagreement_score":0.4519178,"about_ca_system_score_codex":0.000013791234,"about_ca_system_score_gemma":0.000021621228,"threshold_uncertainty_score":0.4951032},"labels":[],"label_agreement":null},{"id":"W2920549681","doi":"10.1093/bioinformatics/btz151","title":"VHost-Classifier: virus-host classification using natural language processing","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bacteriophages and microbial interactions","field":"Environmental Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Classifier (UML); Computer science; Artificial intelligence; Python (programming language); Virus classification; Identifier; Host (biology); Biology; Programming language; Genetics; Genome","score_opus":0.015616746754287135,"score_gpt":0.2596760937011227,"score_spread":0.24405934694683556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2920549681","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9783263,0.000050024173,0.0008709701,0.000080900274,0.00041297163,0.00021967935,0.000014866635,0.000063531006,0.019960763],"genre_scores_gemma":[0.98833275,0.000006837225,0.009201032,0.0003134216,0.000037328915,0.0000025061825,0.000026318066,0.000011812944,0.0020679992],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99930817,0.000009735418,0.00024385485,0.00010811742,0.00012960183,0.00020051052],"domain_scores_gemma":[0.999579,0.0000092220935,0.00015345837,0.00019837826,0.000010457817,0.000049455495],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000074047486,0.00011082339,0.000096454685,0.0000339347,0.00011844207,0.00010870563,0.0001475797,0.00005969001,0.0013662573],"category_scores_gemma":[0.000011079229,0.00009573061,0.000046281326,0.00015942215,0.000053420124,0.00086527254,0.00009425917,0.00014101715,0.0025546164],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008425832,0.000028063218,0.0009829291,0.000034649256,0.0000048558527,7.023903e-7,0.0018110814,0.00003574605,0.9630398,0.000011866667,0.0006778358,0.033364035],"study_design_scores_gemma":[0.0005495301,0.00006426169,0.11866845,0.00012867502,0.00004083788,0.00008579984,0.0051714205,0.7892742,0.025657468,0.0000052749006,0.059738122,0.00061591767],"about_ca_topic_score_codex":0.000121056575,"about_ca_topic_score_gemma":0.000049880993,"teacher_disagreement_score":0.93738234,"about_ca_system_score_codex":0.0001685389,"about_ca_system_score_gemma":0.000015436683,"threshold_uncertainty_score":0.99954665},"labels":[],"label_agreement":null},{"id":"W2920946515","doi":"10.1093/bioinformatics/btz189","title":"Significance tests for analyzing gene expression data with small sample sizes","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Australian Research Council Centre of Excellence for Mathematical and Statistical Frontiers; Natural Sciences and Engineering Research Council of Canada","keywords":"Sample size determination; Variance (accounting); Monte Carlo method; Statistical hypothesis testing; Computer science; Statistic; Test statistic; Degrees of freedom (physics and chemistry); Sample (material); Distribution (mathematics); Statistics; Mathematics; Expression (computer science); Scripting language; Algorithm","score_opus":0.04233453040245352,"score_gpt":0.281204900667655,"score_spread":0.2388703702652015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2920946515","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3226094,0.00042052384,0.6738301,0.00013624446,0.00025875258,0.0010621002,0.00044280864,0.000046799174,0.001193302],"genre_scores_gemma":[0.6137695,0.0001410455,0.3824307,0.00030237567,0.00018033285,0.00006994199,0.0024998365,0.000030113617,0.00057615474],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992142,0.000013130016,0.00022527002,0.00024832433,0.00010938917,0.00018970737],"domain_scores_gemma":[0.99867004,0.000037561273,0.00017154538,0.00096352014,0.000090680354,0.00006665117],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015577485,0.00012932789,0.000119188575,0.0000374335,0.00006962213,0.00004506208,0.00040603802,0.000098093005,0.000018242652],"category_scores_gemma":[0.00009878626,0.000098800025,0.0000315133,0.00008678879,0.00002660764,0.000016151305,0.00014344121,0.00004692123,0.000013022704],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014553736,0.000032874246,0.004340983,0.00011958166,0.000024648565,8.4112585e-8,0.00008180807,0.00024054604,0.97763795,0.000032005457,0.0063556894,0.010988274],"study_design_scores_gemma":[0.0011507726,0.00034342078,0.0016481092,0.00007059064,0.00002696071,0.0000038386033,0.00028417967,0.0070842695,0.80338985,0.000035382356,0.1856133,0.00034931005],"about_ca_topic_score_codex":0.0000041060352,"about_ca_topic_score_gemma":0.000011460437,"teacher_disagreement_score":0.29139936,"about_ca_system_score_codex":0.000010270558,"about_ca_system_score_gemma":0.000110191264,"threshold_uncertainty_score":0.40289482},"labels":[],"label_agreement":null},{"id":"W2921591500","doi":"10.1093/bioinformatics/btz158","title":"Dr.VAE: improving drug response prediction via modeling of drug perturbation effects","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":197,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network; SickKids Foundation; Vector Institute; University of Toronto","funders":"University of Toronto; Canadian Cancer Society Research Institute; Canadian Institutes of Health Research; Hospital for Sick Children; Cancer Research Society","keywords":"Computer science; Autoencoder; Drug; Machine learning; Artificial intelligence; Deep learning; Medicine; Pharmacology","score_opus":0.0097157888356798,"score_gpt":0.24514708915096356,"score_spread":0.23543130031528375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2921591500","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3363092,0.000034941957,0.6621971,0.00012730359,0.0005582317,0.0002858842,0.0000041195094,0.00009763246,0.00038555867],"genre_scores_gemma":[0.7695482,0.0000030670255,0.2300407,0.000099645404,0.000033214455,0.000008615629,0.0000108281265,0.0000096176855,0.00024611797],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998334,0.00019964193,0.00055967615,0.00017957474,0.0005189566,0.00020816282],"domain_scores_gemma":[0.9981757,0.0008038211,0.00027708444,0.0004992768,0.00017798402,0.00006616656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015224773,0.00015174213,0.00019927512,0.00023991853,0.000075507116,0.000103170256,0.00048450945,0.000052843272,0.0000032477858],"category_scores_gemma":[0.00028638367,0.00014304032,0.00008845467,0.000382863,0.000019643157,0.0017017788,0.00026069934,0.00013293675,0.000057952082],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016014784,0.00007606474,0.00036473403,0.0008428493,0.000034167646,0.0000012275005,0.014069303,0.9183321,0.0034214756,0.007610423,0.0003082676,0.054779235],"study_design_scores_gemma":[0.0003944094,0.000061050516,0.0007802718,0.000078617195,0.000008607251,0.0000070044543,0.00011879391,0.9927262,0.0027669668,0.0028634625,0.00005453849,0.00014004673],"about_ca_topic_score_codex":0.000017588372,"about_ca_topic_score_gemma":7.1007577e-7,"teacher_disagreement_score":0.433239,"about_ca_system_score_codex":0.000109720844,"about_ca_system_score_gemma":0.00017719778,"threshold_uncertainty_score":0.5833015},"labels":[],"label_agreement":null},{"id":"W2922092653","doi":"10.1093/bioinformatics/btz175","title":"SodaPop: a forward simulation suite for the evolutionary dynamics of asexual populations on protein fitness landscapes","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Evolution and Genetic Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Université de Montréal","keywords":"Population; Evolutionary dynamics; Fitness landscape; Biology; Context (archaeology); Experimental evolution; Selection (genetic algorithm); Population size; Fixation (population genetics); Protein dynamics; Evolutionary biology; Computer science; Protein structure; Genetics; Artificial intelligence; Gene","score_opus":0.013455842597538683,"score_gpt":0.27168775451530003,"score_spread":0.25823191191776135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2922092653","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67475617,0.00012624289,0.32073873,0.00040008494,0.0003343821,0.0018264638,0.00054318766,0.000025112084,0.0012496129],"genre_scores_gemma":[0.9883082,0.000008576616,0.008532286,0.00010015329,0.00006897481,0.000043541084,0.001235825,0.000014228664,0.0016882528],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99923754,0.000015782442,0.00031734546,0.00010691857,0.00016206231,0.00016033956],"domain_scores_gemma":[0.9992603,0.000047748545,0.00017572207,0.00033286161,0.00014912707,0.00003421894],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014960648,0.00011754598,0.00011249301,0.000047880338,0.0000986203,0.000014523624,0.00015879665,0.00012215266,0.000013906539],"category_scores_gemma":[0.000104306826,0.00008931295,0.00009611303,0.00008698452,0.00003742233,0.000008566553,0.000052153096,0.000051813488,0.000014433731],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035647806,0.00015953861,0.007454676,0.00032254012,0.000105969746,7.832401e-8,0.00023720239,0.9564744,0.0028641627,0.02425374,0.0018289734,0.005942198],"study_design_scores_gemma":[0.00058956566,0.00036019878,0.0036646007,0.000017942535,0.000020736954,0.000001655605,0.00027230184,0.98943424,0.00036019986,0.00055099704,0.0045938655,0.00013371992],"about_ca_topic_score_codex":0.000004074128,"about_ca_topic_score_gemma":0.00006336058,"teacher_disagreement_score":0.313552,"about_ca_system_score_codex":0.00002516262,"about_ca_system_score_gemma":0.00006635846,"threshold_uncertainty_score":0.36420766},"labels":[],"label_agreement":null},{"id":"W2928574665","doi":"10.1093/bioinformatics/btz223","title":"FusionLearn: a biomarker selection algorithm on cross-platform data","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Data mining; Microarray databases; Software; Microarray analysis techniques; Biomarker discovery; R package; Selection (genetic algorithm); Machine learning; Proteomics; Biology; Gene","score_opus":0.03584298378024424,"score_gpt":0.31129712829661516,"score_spread":0.2754541445163709,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2928574665","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8410672,0.00029928642,0.06802062,0.00034193776,0.002445295,0.0013052882,0.00032710706,0.00016814495,0.08602515],"genre_scores_gemma":[0.95227957,0.00028792248,0.027787413,0.0016316195,0.00041228402,0.000028445795,0.0043617035,0.00005132473,0.01315971],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991632,0.000011348642,0.00023675128,0.00022071679,0.0001933607,0.00017464093],"domain_scores_gemma":[0.9989937,0.0000061411492,0.00012194549,0.0007437145,0.00006933933,0.00006516564],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018759421,0.0001223523,0.00008315201,0.00006362831,0.00008172823,0.00006725955,0.00032649285,0.00015072657,0.00015613023],"category_scores_gemma":[0.000032883916,0.00010290907,0.000037851747,0.00012892389,0.000026686599,0.000022024478,0.00018389818,0.00007701163,0.0004693106],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028218888,0.00019100227,0.0073025823,0.00012169125,0.00009782984,5.39843e-7,0.0001558071,0.00019359073,0.26358813,0.00030618024,0.12625554,0.6015049],"study_design_scores_gemma":[0.001114042,0.00037444942,0.014194239,0.000034144105,0.000011741777,0.000019158822,0.00016663989,0.12813544,0.056087427,0.000037331356,0.7994695,0.0003558814],"about_ca_topic_score_codex":0.0000031601382,"about_ca_topic_score_gemma":0.0000019126137,"teacher_disagreement_score":0.67321396,"about_ca_system_score_codex":0.000018823685,"about_ca_system_score_gemma":0.00007725375,"threshold_uncertainty_score":0.60321945},"labels":[],"label_agreement":null},{"id":"W2935257869","doi":"10.1093/bioinformatics/btz229","title":"<i>RTNsurvival</i>: an R/Bioconductor package for regulatory network survival analysis","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":54,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; BC Cancer Agency","funders":"National Cancer Institute; Cancer Research UK; National Institutes of Health; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Breast Cancer Research Foundation","keywords":"Bioconductor; R package; Computer science; Survival analysis; Network analysis; Computational biology; Biology; Statistics; Mathematics; Genetics; Programming language; Gene","score_opus":0.013043309570168478,"score_gpt":0.24106370461805707,"score_spread":0.2280203950478886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2935257869","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8714567,0.00038046404,0.115231924,0.00006696691,0.0018575834,0.001469824,0.00033308385,0.000088676985,0.009114795],"genre_scores_gemma":[0.95159096,0.000085648106,0.040604092,0.0010313379,0.0011269219,0.000052504933,0.003151846,0.00007016352,0.0022865569],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981572,0.000040329967,0.0006866809,0.00028474638,0.00023296881,0.00059805176],"domain_scores_gemma":[0.99811536,0.00003465235,0.00032858207,0.0011500604,0.00015595222,0.00021537607],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007877322,0.00031046887,0.00043969182,0.000097448676,0.00014365818,0.00010754936,0.0004619184,0.00033184435,0.000071985356],"category_scores_gemma":[0.00002656803,0.00028628288,0.00037561785,0.00034428673,0.00007068061,0.000033135926,0.00015471937,0.00011949311,0.0000850189],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0038347256,0.0016430464,0.19583316,0.0041228803,0.025656903,0.000007728636,0.005817343,0.124119356,0.16992232,0.101071075,0.2613525,0.10661896],"study_design_scores_gemma":[0.0071533336,0.0032516161,0.03025928,0.00008199091,0.002044666,0.00002580948,0.0025294577,0.28233027,0.01308419,0.0024715823,0.65255296,0.004214862],"about_ca_topic_score_codex":0.000005241392,"about_ca_topic_score_gemma":0.00004546066,"teacher_disagreement_score":0.39120042,"about_ca_system_score_codex":0.000022171329,"about_ca_system_score_gemma":0.000104330386,"threshold_uncertainty_score":0.99995893},"labels":[],"label_agreement":null},{"id":"W2936760626","doi":"10.1093/bioinformatics/btz278","title":"ORCA: a comprehensive bioinformatics container environment for education and research","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Genome British Columbia","funders":"National Human Genome Research Institute; Genome British Columbia; Genome Canada","keywords":"License; Container (type theory); MIT License; Computer science; Suite; Debugging; Software; Source code; Software engineering; Operating system; World Wide Web; Bioinformatics; Biology; Engineering","score_opus":0.03086956639264518,"score_gpt":0.31952365313010106,"score_spread":0.28865408673745585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2936760626","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93117356,0.0024208927,0.032576844,0.0015903667,0.0013682453,0.0071796654,0.00036788173,0.00007413113,0.023248432],"genre_scores_gemma":[0.6277651,0.008523933,0.33491462,0.0044314074,0.0012639131,0.0006433645,0.0033219282,0.0001595847,0.018976137],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99781173,0.000045954454,0.0006560166,0.00022541604,0.0006158316,0.00064504443],"domain_scores_gemma":[0.99840844,0.00011801588,0.00016169486,0.00058109564,0.00042286573,0.0003078823],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007799207,0.0002428309,0.00026260447,0.00022424849,0.00019599688,0.00013288026,0.00034614003,0.00029345168,0.00004388117],"category_scores_gemma":[0.00024021966,0.00020508481,0.00009877881,0.00013993039,0.00034905298,0.000030233281,0.00040662265,0.00021707853,0.0003057872],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009834311,0.0011401114,0.006206001,0.007464691,0.000593036,0.00000151771,0.007160317,0.00017684301,0.056395177,0.004987236,0.21348634,0.7014053],"study_design_scores_gemma":[0.0018307548,0.001758014,0.0013969571,0.00008340407,0.000023041544,0.000030692834,0.0073876977,0.021413973,0.007483079,0.00032795145,0.9577857,0.00047873735],"about_ca_topic_score_codex":0.00001237408,"about_ca_topic_score_gemma":0.000004207795,"teacher_disagreement_score":0.74429935,"about_ca_system_score_codex":0.000057704052,"about_ca_system_score_gemma":0.0003756875,"threshold_uncertainty_score":0.8363116},"labels":[],"label_agreement":null},{"id":"W2938712064","doi":"10.1093/bioinformatics/btz266","title":"Discovering novel mutation signatures by latent Dirichlet allocation with variational Bayes inference","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Core Research for Evolutional Science and Technology; Institute of Genetics; Japan Society for the Promotion of Science; Waseda University; Ministry of Education, Culture, Sports, Science and Technology","keywords":"Mutation; Latent Dirichlet allocation; Computer science; Cluster analysis; Bayes' theorem; Inference; Mutation rate; Genetics; Computational biology; Biology; Bayesian probability; Artificial intelligence; Topic model; Gene","score_opus":0.0052565859999535594,"score_gpt":0.2151006418825204,"score_spread":0.20984405588256683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2938712064","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74243325,0.00017919826,0.25528646,0.00013831264,0.00018006105,0.00029972583,0.00019747361,0.000014573224,0.0012709558],"genre_scores_gemma":[0.98717403,0.00009076248,0.010908883,0.00034328885,0.000060922852,0.0000132821415,0.0012229204,0.000011396852,0.00017448836],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994354,0.0000040368336,0.000176924,0.00011405422,0.00014163545,0.0001279239],"domain_scores_gemma":[0.9995683,0.000027572703,0.00011273245,0.0001684802,0.00008238811,0.000040572395],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000060168426,0.0001077424,0.00007758538,0.00002545997,0.000039588533,0.00006139619,0.00009626321,0.00007843607,0.000015192601],"category_scores_gemma":[0.000048517617,0.00009153063,0.000024040859,0.00005870294,0.000019928502,0.000016897919,0.000049191425,0.00005019097,0.000019732704],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004533086,0.0004598462,0.03992584,0.00044332884,0.00041361098,0.0000017658523,0.0018205312,0.2553051,0.66195244,0.0145232305,0.014948615,0.009752339],"study_design_scores_gemma":[0.008500147,0.0032261861,0.09415293,0.00029099837,0.00020248853,0.000052479765,0.0011328168,0.5047256,0.2571709,0.00049302576,0.12732422,0.0027282475],"about_ca_topic_score_codex":0.000022345659,"about_ca_topic_score_gemma":0.000021537593,"teacher_disagreement_score":0.40478158,"about_ca_system_score_codex":0.0000242888,"about_ca_system_score_gemma":0.000099144025,"threshold_uncertainty_score":0.37325108},"labels":[],"label_agreement":null},{"id":"W2944510853","doi":"10.1093/bioinformatics/btz308","title":"gpart: human genome partitioning and visualization of high-density SNP data by identifying haplotype blocks","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto; Hospital for Sick Children; Sinai Health System; Lunenfeld-Tanenbaum Research Institute","funders":"Canadian Statistical Sciences Institute; Canadian Institutes of Health Research; National Research Foundation of Korea; Neurosciences Research Foundation","keywords":"Bioconductor; Visualization; Computer science; Cluster analysis; Genome; Tag SNP; dbSNP; Linkage disequilibrium; Data mining; Single-nucleotide polymorphism; R package; Haplotype; Computational biology; SNP genotyping; Reference genome; DNA sequencing; Biology; Genetics; Gene; Artificial intelligence; Computational science","score_opus":0.03210594169097992,"score_gpt":0.3011335103091326,"score_spread":0.2690275686181527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2944510853","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98124504,0.00019157925,0.017875465,0.000033702607,0.0000786425,0.00013006646,0.0000844123,0.000009146962,0.00035193955],"genre_scores_gemma":[0.993218,0.00014714351,0.0037101828,0.00011111423,0.0000392006,0.000002037113,0.0024761537,0.000008711644,0.00028748065],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9992451,0.000030614152,0.0003484798,0.00014649447,0.000083450286,0.00014583363],"domain_scores_gemma":[0.99924,0.000013293737,0.00024154,0.00039555202,0.00006985798,0.00003979238],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033471792,0.00008648261,0.00015942902,0.000029430483,0.00008530118,0.000019438474,0.00015243323,0.000120015895,0.000025722917],"category_scores_gemma":[0.000085396976,0.00008705653,0.000020189746,0.000053375228,0.000044907545,0.00001320212,0.00025007114,0.000037811827,0.000014591203],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033174354,0.00013531897,0.3177656,0.0003743942,0.00029552256,4.1444278e-7,0.0007409086,0.00048666017,0.6561183,0.0016782499,0.020253194,0.0021182767],"study_design_scores_gemma":[0.0033921339,0.0012314811,0.81522846,0.00013372807,0.00030286436,0.000036761496,0.001622386,0.044496696,0.09287287,0.0016261447,0.037663743,0.0013927004],"about_ca_topic_score_codex":0.000067251436,"about_ca_topic_score_gemma":0.000033782915,"teacher_disagreement_score":0.5632454,"about_ca_system_score_codex":0.0000074679183,"about_ca_system_score_gemma":0.000021025544,"threshold_uncertainty_score":0.35500622},"labels":[],"label_agreement":null},{"id":"W2945501761","doi":"10.1093/bioinformatics/btz413","title":"HyAsP, a greedy tool for plasmids identification","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Contig; Plasmid; Computer science; Genome; Greedy algorithm; Identification (biology); Computational biology; Biology; Genetics; Gene; Algorithm","score_opus":0.01003540163125125,"score_gpt":0.22860359757191284,"score_spread":0.2185681959406616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945501761","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99175954,0.00014055485,0.0051475,0.000058260943,0.000375879,0.0004838743,0.000074683005,0.0000052544974,0.001954477],"genre_scores_gemma":[0.98815674,0.000083506624,0.009333055,0.00021974162,0.000117521704,0.00004594367,0.00012916101,0.000013157945,0.0019011785],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994157,0.000004610754,0.0002434137,0.000110862566,0.00006975638,0.0001556626],"domain_scores_gemma":[0.9995199,0.00001129521,0.000094057876,0.00027196918,0.00007721686,0.000025587206],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013122176,0.000096101954,0.00009311569,0.000024657586,0.000054846907,0.000027871476,0.00013013554,0.00007504328,0.000007734375],"category_scores_gemma":[0.000037030193,0.00008913391,0.00007253826,0.00003508573,0.00002276693,0.0000014845233,0.00006450902,0.000022388182,0.00009058122],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015428822,0.00008090297,0.01821129,0.00039168223,0.00024517,1.5479114e-7,0.0006115061,0.00044268742,0.9338547,0.0027211143,0.019902589,0.02338389],"study_design_scores_gemma":[0.0029161149,0.0011253466,0.04190322,0.000028448017,0.000085540385,0.000019027397,0.000890454,0.018330747,0.27174863,0.0009254462,0.6610654,0.0009616135],"about_ca_topic_score_codex":0.000001243813,"about_ca_topic_score_gemma":0.000002151202,"teacher_disagreement_score":0.6621061,"about_ca_system_score_codex":0.00000747466,"about_ca_system_score_gemma":0.000032150943,"threshold_uncertainty_score":0.36347753},"labels":[],"label_agreement":null},{"id":"W2946813309","doi":"10.1093/bioinformatics/btz402","title":"YeastSpotter: accurate and parameter-free web segmentation for microscopy images of yeast cells","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":109,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Genome Canada; University of Toronto","funders":"Canada Research Chairs","keywords":"Microscopy; Segmentation; Computer science; Artificial intelligence; Computer vision; Yeast; Image segmentation; Biological system; Computer graphics (images); Biology; Optics; Biochemistry; Physics","score_opus":0.006323364051794045,"score_gpt":0.26107417452359144,"score_spread":0.2547508104717974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946813309","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9663255,0.00012944094,0.031494115,0.000024711037,0.000053592834,0.00056453235,0.00016022503,0.0000184402,0.001229415],"genre_scores_gemma":[0.7257417,0.00046835208,0.271686,0.00030837368,0.000062963314,0.000035133617,0.0003666383,0.000028163984,0.0013026919],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994462,0.000009345527,0.00025572864,0.00010412377,0.00006785613,0.000116722855],"domain_scores_gemma":[0.99936557,0.000013824109,0.00017176462,0.0003455741,0.0000736642,0.000029597099],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011361972,0.00009997385,0.00013442339,0.00004195503,0.000021317435,0.000037908358,0.00014242496,0.000069260575,0.000013342412],"category_scores_gemma":[0.000032961227,0.000092569026,0.00006659365,0.000044012457,0.00004686973,0.000014608915,0.00010132238,0.000026134594,0.000006820673],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002816467,0.000016156702,0.00042399726,0.00014299407,0.00003202039,6.59912e-8,0.000053835727,0.000003243206,0.9772991,0.0000019711788,0.01991275,0.00208569],"study_design_scores_gemma":[0.0005030807,0.00018612269,0.00012135579,0.0000143397965,0.00003287013,0.0000021952897,0.00015351558,0.002100648,0.9924449,0.000032274194,0.0042980285,0.000110690824],"about_ca_topic_score_codex":0.0000051973016,"about_ca_topic_score_gemma":0.0000030595786,"teacher_disagreement_score":0.24058382,"about_ca_system_score_codex":0.0000055120913,"about_ca_system_score_gemma":0.000022609904,"threshold_uncertainty_score":0.37748554},"labels":[],"label_agreement":null},{"id":"W2946841580","doi":"10.1093/bioinformatics/bty211","title":"Inference of the human polyadenylation code","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"RNA Research and Splicing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Genomics; University of Toronto","funders":"","keywords":"Polyadenylation; Cleavage and polyadenylation specificity factor; Untranslated region; Computational biology; Genetics; Biology; Three prime untranslated region; Gene; Human genome; Inference; Genome; Computer science; Artificial intelligence; Messenger RNA","score_opus":0.022838912652903266,"score_gpt":0.3096751317458032,"score_spread":0.2868362190928999,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946841580","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99183863,0.000016661463,0.0026982883,0.000051116178,0.00004337822,0.00007499882,0.000008089444,0.0000034065506,0.0052654548],"genre_scores_gemma":[0.99792963,0.000007301687,0.0008706325,0.00008701036,0.00007493048,0.0000014394084,0.000011432075,0.0000031372501,0.0010144974],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995967,0.000011008811,0.00014224662,0.00003915099,0.00010911666,0.00010174717],"domain_scores_gemma":[0.9995874,0.0000043512723,0.00006775241,0.00023227827,0.000082229366,0.00002596689],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000096151445,0.00004215801,0.00004184639,0.000015765328,0.000087558874,0.000011174629,0.00016869263,0.00004556763,0.000012306644],"category_scores_gemma":[0.00009522528,0.0000280184,0.000029835055,0.00006003042,0.000120184755,0.000003697296,0.00009740533,0.000034123237,0.0000113445685],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008218452,0.000012318136,0.013202677,0.000026425407,0.000012720176,3.7891617e-8,0.00016389936,0.000006444006,0.98088306,0.0008295933,0.0020427508,0.0028118505],"study_design_scores_gemma":[0.000245239,0.00023228559,0.026116667,0.00002353705,0.0000045672787,0.000002390477,0.000119513425,0.0036268258,0.9610706,0.000096771524,0.00837785,0.000083736755],"about_ca_topic_score_codex":0.000012313637,"about_ca_topic_score_gemma":0.00003802713,"teacher_disagreement_score":0.019812452,"about_ca_system_score_codex":0.0000041745075,"about_ca_system_score_gemma":0.000040167004,"threshold_uncertainty_score":0.11425571},"labels":[],"label_agreement":null},{"id":"W2949023387","doi":"10.1093/bioinformatics/btz456","title":"eFORGE v2.0: updated analysis of cell type-specific signal in epigenomic data","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":153,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Wellcome Trust; Wellcome","keywords":"Epigenomics; Computer science; SIGNAL (programming language); Type (biology); Programming language; Biology; Genetics; DNA methylation","score_opus":0.011635717343155327,"score_gpt":0.22291294763631644,"score_spread":0.21127723029316112,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949023387","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9950097,0.00018327394,0.0014966321,0.0000070582278,0.0000963611,0.00016131869,0.00029104107,0.0000049636205,0.002749642],"genre_scores_gemma":[0.9848767,0.0002775987,0.009326236,0.000048186983,0.000020134468,9.752329e-7,0.0051543685,0.000013839178,0.00028197738],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990093,0.00001581148,0.0004892558,0.00017956272,0.00010693966,0.00019909852],"domain_scores_gemma":[0.99874073,0.000008291074,0.00021083433,0.0009403692,0.000055363525,0.0000444058],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023098396,0.00012957877,0.0002543161,0.00017185569,0.000016883836,0.000018034862,0.0005348233,0.00012812922,0.00012924093],"category_scores_gemma":[0.0000059288445,0.00012430239,0.0000719264,0.000410911,0.00002951635,0.000008927009,0.00030854804,0.000066764915,0.00007256627],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019619944,0.00034840856,0.06841548,0.0002755456,0.0009868811,0.000002759898,0.0007561058,0.020306217,0.89967626,0.0003286653,0.004853259,0.0038542415],"study_design_scores_gemma":[0.0016097762,0.0003869808,0.024082005,0.000020071224,0.0003198939,0.0000036319382,0.0009070191,0.8699957,0.057559792,0.00003575807,0.044384327,0.0006950184],"about_ca_topic_score_codex":0.00001359264,"about_ca_topic_score_gemma":0.0000459352,"teacher_disagreement_score":0.8496895,"about_ca_system_score_codex":0.000020672152,"about_ca_system_score_gemma":0.00007806747,"threshold_uncertainty_score":0.5068904},"labels":[],"label_agreement":null},{"id":"W2949176808","doi":"10.1093/bioinformatics/bty449","title":"Transfer learning for biomedical named entity recognition with neural networks","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":195,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Human Genome Research Institute; National Institutes of Health; Nvidia","keywords":"Computer science; Named-entity recognition; Transfer of learning; Artificial intelligence; Annotation; Deep learning; Conditional random field; Task (project management); Artificial neural network; Field (mathematics); Machine learning; Natural language processing; Word (group theory); Noise (video); State (computer science); Domain (mathematical analysis); Mathematics","score_opus":0.019899863939700585,"score_gpt":0.25561859100615614,"score_spread":0.23571872706645555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949176808","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43226117,0.00007835414,0.5663976,0.00020451166,0.00028761293,0.00022081083,0.000017529896,0.00006139461,0.00047099078],"genre_scores_gemma":[0.9712829,0.000039408253,0.026782589,0.000514942,0.00060109876,0.000031470925,0.00057233043,0.000015557192,0.00015970104],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99925214,0.000020476771,0.00021184905,0.0001290638,0.000118837466,0.0002676552],"domain_scores_gemma":[0.9996086,0.000024517896,0.000043620792,0.0001238768,0.00010354026,0.00009587263],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018879998,0.00011831346,0.00011944625,0.000034430905,0.00014216188,0.000029007697,0.00011477323,0.00021338538,0.000020679561],"category_scores_gemma":[0.00012962201,0.00008703393,0.000057337777,0.00009030176,0.0003583857,0.0000074091217,0.00002878983,0.0001044764,0.0000101999885],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000854324,0.00013558214,0.0011371826,0.00017554114,0.00017876188,0.0000023457437,0.00059472665,0.00011856944,0.005960059,0.00004195139,0.010331367,0.9804696],"study_design_scores_gemma":[0.004446417,0.010365053,0.00083623745,0.00011469855,0.00013778513,0.0001055128,0.001398442,0.46027836,0.020642597,0.00008546953,0.5007209,0.00086848025],"about_ca_topic_score_codex":0.0000030009678,"about_ca_topic_score_gemma":0.000012075856,"teacher_disagreement_score":0.9796011,"about_ca_system_score_codex":0.0000067825254,"about_ca_system_score_gemma":0.000032980744,"threshold_uncertainty_score":0.35491407},"labels":[],"label_agreement":null},{"id":"W2949679909","doi":"10.1093/bioinformatics/btz112","title":"SUBSTRA: Supervised Bayesian Patient Stratification","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; Simon Fraser University","funders":"","keywords":"Computer science; Benchmark (surveying); Machine learning; Bayesian probability; Artificial intelligence; Population stratification; Source code; Data mining; Biology","score_opus":0.013433835080801506,"score_gpt":0.24442750401290844,"score_spread":0.23099366893210693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949679909","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32673118,0.00007700677,0.6211884,0.0028763223,0.0014808464,0.0011886929,0.000009562161,0.000700932,0.045747053],"genre_scores_gemma":[0.8504633,0.00000410695,0.14896291,0.00042078784,0.000019134226,0.0000076161837,0.000018350254,0.0000062342765,0.000097568],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99886435,0.000037443282,0.0003985402,0.0001417867,0.00031948526,0.00023838192],"domain_scores_gemma":[0.9988744,0.000055682995,0.00014866832,0.00073583616,0.00008598763,0.00009937614],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00017526465,0.000112450245,0.000115196504,0.00008431879,0.0000756025,0.00015059009,0.0005450009,0.00006855594,0.00007194986],"category_scores_gemma":[0.000033358006,0.000100719095,0.000040415045,0.00025443287,0.00001265059,0.00061843754,0.00009049875,0.00016376679,0.0007824961],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010514935,0.000117123825,0.05716277,0.00088375655,0.000026852153,0.000005047166,0.024442585,0.0028043485,0.00024513,0.22494443,0.0025728606,0.68678457],"study_design_scores_gemma":[0.00016311224,0.00014196351,0.011520838,0.000024226867,0.000001461096,0.0000091530155,0.00026348067,0.98362744,0.00030036777,0.000455033,0.0033244085,0.00016853612],"about_ca_topic_score_codex":0.000024716332,"about_ca_topic_score_gemma":0.0000050605827,"teacher_disagreement_score":0.9808231,"about_ca_system_score_codex":0.000046103974,"about_ca_system_score_gemma":0.000094525385,"threshold_uncertainty_score":0.9999955},"labels":[],"label_agreement":null},{"id":"W2949926253","doi":"10.1093/bioinformatics/bty722","title":"Adjutant: an R-based tool to support topic discovery for systematic and literature reviews","year":2018,"lang":"en","type":"review","venue":"Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Centre for Disease Control; University of British Columbia","funders":"Canadian Institutes of Health Research; Canada Research Chairs; Michael Smith Health Research BC","keywords":"Systematic review; Computer science; Data science; Information retrieval; MEDLINE; Biology","score_opus":0.04961544002561298,"score_gpt":0.3508484078449882,"score_spread":0.30123296781937525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949926253","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000031243493,0.98642164,0.010039838,0.000014793049,0.00027607035,0.0027179043,0.0003976978,0.00002440634,0.0000764139],"genre_scores_gemma":[0.0000041745852,0.957733,0.038351454,0.0005202416,0.00043121254,0.0005570047,0.0015541572,0.000034400942,0.00081437366],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99819493,0.00008238208,0.0009849379,0.00030261793,0.00013085357,0.00030425115],"domain_scores_gemma":[0.99862707,0.000054617107,0.00039184626,0.0007071807,0.00007174437,0.00014757409],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006017241,0.00041197642,0.0013341694,0.000098848,0.00008235769,0.00020102662,0.00037167143,0.0005949169,0.0000034715008],"category_scores_gemma":[0.0007001613,0.000259803,0.00032659993,0.00014091028,0.00008534894,0.000012473212,0.00011998334,0.000113447546,0.00003148076],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011302212,0.000026111655,7.804101e-7,0.42792365,0.000067324385,0.00000189439,0.00017406422,4.2534264e-8,0.0000029544783,0.000029039893,0.010406788,0.561356],"study_design_scores_gemma":[0.0001622302,0.0009380017,4.8158796e-7,0.048432153,0.00027275475,0.00004724303,0.000029047922,0.00003531923,0.000012015585,0.000005541882,0.9496934,0.00037182495],"about_ca_topic_score_codex":3.9835356e-7,"about_ca_topic_score_gemma":0.0000029969142,"teacher_disagreement_score":0.9392866,"about_ca_system_score_codex":0.00001931232,"about_ca_system_score_gemma":0.00017517136,"threshold_uncertainty_score":0.9999854},"labels":[],"label_agreement":null},{"id":"W2950021574","doi":"10.1093/bioinformatics/btz504","title":"Towards reliable named entity recognition in the biomedical domain","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Topic Modeling","field":"Computer Science","cited_by":88,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Human Genome Research Institute; Compute Canada; National Institutes of Health; Nvidia","keywords":"CRFS; Conditional random field; Computer science; Artificial intelligence; Dropout (neural networks); Transfer of learning; Named-entity recognition; Natural language processing; Machine learning; Task (project management); Regularization (linguistics); Deep learning; Sequence labeling; Source code; Generalization; Multi-task learning","score_opus":0.021713303600085557,"score_gpt":0.2395539452077731,"score_spread":0.21784064160768754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950021574","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24989374,0.000020295474,0.7249575,0.0018569432,0.0007894712,0.00037261745,0.000004229385,0.000095029034,0.02201014],"genre_scores_gemma":[0.39133057,0.000019469024,0.606612,0.0017982882,0.00007719224,0.00001804333,0.0000261934,0.000005124849,0.00011307595],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990139,0.000028880573,0.0002993145,0.0000954182,0.00036176914,0.00020073855],"domain_scores_gemma":[0.9993755,0.00004071353,0.000071232455,0.00044841476,0.000027308452,0.00003680751],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008242377,0.000070641254,0.00009284179,0.000088204055,0.000038284725,0.00012164375,0.00067593413,0.00006562908,0.000029656076],"category_scores_gemma":[0.000042617346,0.00004830406,0.000032774456,0.00031380504,0.000021289747,0.0005405624,0.00013716664,0.00014073236,0.0005586942],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018899804,0.00039698466,0.0037965707,0.00059453724,0.000032325326,0.000027309741,0.0517214,0.00022341008,0.00021661511,0.096962005,0.013793242,0.8322167],"study_design_scores_gemma":[0.000760508,0.00009149227,0.0013343015,0.000079855294,0.0000030760073,0.000031204738,0.0010460557,0.9359299,0.00012125814,0.024672633,0.03571289,0.00021683086],"about_ca_topic_score_codex":0.00003690306,"about_ca_topic_score_gemma":0.0000052002297,"teacher_disagreement_score":0.9357065,"about_ca_system_score_codex":0.000041663287,"about_ca_system_score_gemma":0.00007126842,"threshold_uncertainty_score":0.718107},"labels":[],"label_agreement":null},{"id":"W2950143580","doi":"10.1093/bioinformatics/btz473","title":"DepthFinder: a tool to determine the optimal read depth for reduced-representation sequencing","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic and phenotypic traits in livestock","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; Université Laval","funders":"Grain Farmers of Ontario; Canadian Field Crop Research Alliance; Genome Canada; Syngenta Canada; Government of Canada; Saskatchewan Pulse Growers","keywords":"Genotyping; DNA sequencing; Computational biology; Identification (biology); Biology; Genome; Selection (genetic algorithm); Computer science; Genetics; Machine learning; DNA; Genotype; Gene; Ecology","score_opus":0.02702048160416613,"score_gpt":0.27424380277383104,"score_spread":0.24722332116966492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950143580","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.873236,0.00003654751,0.12204117,0.00013681635,0.0002717756,0.0008808103,0.000022601036,0.00001463342,0.0033596298],"genre_scores_gemma":[0.6923355,0.0000051215798,0.30492848,0.0007276839,0.000199721,0.00007845909,0.00009491274,0.000017999695,0.0016121329],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99920434,0.000013972593,0.00027259783,0.00015253147,0.00012212426,0.00023442155],"domain_scores_gemma":[0.9993303,0.00003197467,0.0000901308,0.0004154638,0.00007571081,0.000056411714],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013678898,0.00013035398,0.00010673482,0.000026163134,0.0000841451,0.00004437108,0.0002413228,0.000093576215,0.000017603332],"category_scores_gemma":[0.00010226983,0.00009738036,0.00007590724,0.000069099326,0.000028607203,0.000008591369,0.00008751239,0.00005652606,0.000052153933],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008714511,0.00012500206,0.004590171,0.00049538264,0.00037140536,6.585017e-7,0.008287155,0.07024646,0.37242934,0.0072588176,0.03118641,0.50413775],"study_design_scores_gemma":[0.006453775,0.006862527,0.09254166,0.00021369876,0.00030896234,0.0002599124,0.012433217,0.05666829,0.6121372,0.0021751705,0.20721205,0.00273356],"about_ca_topic_score_codex":0.0000057393554,"about_ca_topic_score_gemma":0.000011044278,"teacher_disagreement_score":0.5014042,"about_ca_system_score_codex":0.000016943124,"about_ca_system_score_gemma":0.00010667016,"threshold_uncertainty_score":0.3971056},"labels":[],"label_agreement":null},{"id":"W2950511618","doi":"10.1093/bioinformatics/bty387","title":"Indexed variation graphs for efficient and accurate resistome profiling","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":84,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Science and Technology Facilities Council; Department for Business, Energy and Industrial Strategy, UK Government; Public Health Agency of Canada; World Health Organization","keywords":"Resistome; Metagenomics; Profiling (computer programming); Computer science; Workflow; Data mining; Computational biology; Biology; Bioinformatics; Genome; Gene; Genetics; Database","score_opus":0.015061740084855505,"score_gpt":0.24947379069523234,"score_spread":0.23441205061037684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950511618","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9835233,0.00020426445,0.014852508,0.000044571436,0.00019094252,0.00032762781,0.000040039376,0.000004714775,0.0008119989],"genre_scores_gemma":[0.97117364,0.00006456402,0.02837974,0.00013573353,0.00012417705,0.000024035215,0.000030250909,0.000008168886,0.000059683174],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99951124,0.0000065916965,0.00018296925,0.00010242107,0.0000521435,0.00014463536],"domain_scores_gemma":[0.99961,0.000011613244,0.00008677264,0.00014038937,0.0001155274,0.00003568402],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016142777,0.000087034685,0.00007896952,0.000032954,0.0001431253,0.00002550378,0.00006430619,0.000067558016,8.357615e-7],"category_scores_gemma":[0.000068060705,0.00007658107,0.00003098705,0.000046879763,0.00006858069,7.976024e-7,0.000068814064,0.000018893239,0.0000029897],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004215438,0.00009216509,0.0045232414,0.00037021106,0.0003005248,2.5789464e-7,0.0032669273,0.00033469393,0.9684563,0.008488787,0.0025150718,0.011230223],"study_design_scores_gemma":[0.0060356087,0.0038080958,0.116647206,0.00007896968,0.00025194357,0.000033132943,0.0019151648,0.14757736,0.6194632,0.00485446,0.097538,0.0017968279],"about_ca_topic_score_codex":0.0000017886865,"about_ca_topic_score_gemma":0.000003897777,"teacher_disagreement_score":0.34899312,"about_ca_system_score_codex":0.0000049311466,"about_ca_system_score_gemma":0.000027922735,"threshold_uncertainty_score":0.31228852},"labels":[],"label_agreement":null},{"id":"W2950522632","doi":"10.1093/bioinformatics/btz518","title":"Bayesian GWAS with Structured and Non-Local Priors","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; Takeda Pharmaceutical Company; IXICO; National Institute of General Medical Sciences; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; Roche; University of Southern California; F. Hoffmann-La Roche; Novartis Pharmaceuticals Corporation; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; Merck; Alzheimer's Association; Foundation for the National Institutes of Health; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics","keywords":"Prior probability; Bayesian probability; Computer science; Genome-wide association study; Statistical power; Covariate; Machine learning; Artificial intelligence; Statistics; Mathematics; Single-nucleotide polymorphism; Biology","score_opus":0.0036576116719586166,"score_gpt":0.2119490812847971,"score_spread":0.20829146961283848,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950522632","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9491427,0.00005620954,0.047324013,0.00010308765,0.00007636178,0.00019073539,0.000010743386,0.000007692859,0.0030884393],"genre_scores_gemma":[0.9741585,0.000042231615,0.024929285,0.0003541541,0.000037473957,0.000004252965,0.00006781463,0.000009249416,0.00039704112],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99943405,0.000013447569,0.00018490311,0.00011200154,0.00006773378,0.00018786752],"domain_scores_gemma":[0.999574,0.000009764614,0.000096441916,0.00021567842,0.000038283488,0.000065841974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010644627,0.00010791645,0.00013557154,0.000025147532,0.000044352393,0.000014000709,0.00007867944,0.00013806197,0.000017532453],"category_scores_gemma":[0.000021119222,0.00008123048,0.000025541303,0.00004504807,0.00006177265,0.0000038694566,0.00005784148,0.000055713524,0.000021256188],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020655691,0.0000636814,0.91748065,0.00028790307,0.0003862714,0.000002543577,0.0016492645,0.0043973075,0.015880253,0.0004062134,0.010680211,0.048559118],"study_design_scores_gemma":[0.004232254,0.002570509,0.8263731,0.000059661164,0.00010244741,0.00016391024,0.00430926,0.09738095,0.008756708,0.00033576117,0.054508254,0.001207166],"about_ca_topic_score_codex":0.000008203097,"about_ca_topic_score_gemma":0.000024383122,"teacher_disagreement_score":0.09298364,"about_ca_system_score_codex":0.000008445477,"about_ca_system_score_gemma":0.000051070176,"threshold_uncertainty_score":0.33124828},"labels":[],"label_agreement":null},{"id":"W2950655801","doi":"10.1093/bioinformatics/bty717","title":"C3D: a tool to predict 3D genomic interactions between cis-regulatory elements","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; Ontario Institute for Cancer Research; University of Waterloo; University Health Network","funders":"Canadian Institutes of Health Research","keywords":"Chromatin; Source code; Computational biology; Computer science; Promoter; License; MIT License; Genome; DNA; R package; Gene; Biology; Data mining; Genetics; Programming language; Gene expression; Operating system","score_opus":0.008380410046805961,"score_gpt":0.24221554847552818,"score_spread":0.23383513842872222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950655801","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.979199,0.000015769541,0.016232006,0.000055183347,0.0003359715,0.0002993391,0.00017165359,0.000025864621,0.0036652158],"genre_scores_gemma":[0.94099474,0.000015586089,0.05642482,0.0005780924,0.0007343335,0.00002282732,0.0003560228,0.000029791134,0.00084377546],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988893,0.000012120491,0.00048788887,0.00016955059,0.00013931944,0.00030180966],"domain_scores_gemma":[0.9990996,0.0000068737545,0.00014848071,0.0005101408,0.00010481667,0.00013005317],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001661875,0.00017560019,0.00014612685,0.00007607508,0.00014332448,0.00005839515,0.0002973624,0.000103498736,0.00006148815],"category_scores_gemma":[0.00003924734,0.00017560262,0.000074625175,0.000086916196,0.00006120532,0.000010048706,0.00028233117,0.000071596965,0.0003493692],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032319291,0.00038112284,0.076829135,0.0003971809,0.0014136326,0.000003962426,0.0041378117,0.0006023718,0.5231549,0.0006614995,0.14715488,0.24494031],"study_design_scores_gemma":[0.0017795177,0.0020703655,0.098605394,0.00008504808,0.00016283013,0.000042504354,0.0006645728,0.033081952,0.034241628,0.00018284208,0.8277334,0.0013499144],"about_ca_topic_score_codex":0.0000046665723,"about_ca_topic_score_gemma":0.000025709161,"teacher_disagreement_score":0.68057853,"about_ca_system_score_codex":0.00005479818,"about_ca_system_score_gemma":0.000090898764,"threshold_uncertainty_score":0.7160867},"labels":[],"label_agreement":null},{"id":"W2950705667","doi":"10.1093/bioinformatics/bty549","title":"SATurn: a modular bioinformatics framework for the design of robust maintainable web-based and standalone applications","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Innovative Medicines Initiative; Ontario Ministry of Research, Innovation and Science; Canada Foundation for Innovation; Kennedy Trust for Rheumatology Research; Wellcome Trust; Ontario Genomics Institute; AbbVie; European Federation of Pharmaceutical Industries and Associations; Boehringer Ingelheim","keywords":"Modular design; Computer science; Saturn; Web application; Open source; Simple (philosophy); World Wide Web; Data science; Software engineering; Software; Programming language","score_opus":0.025869866801164123,"score_gpt":0.2816519004378844,"score_spread":0.2557820336367203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950705667","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021475947,0.00042078097,0.994686,0.00044817588,0.0001113188,0.0016355173,0.00019020407,0.000022261584,0.0003381129],"genre_scores_gemma":[0.11954491,0.0010572709,0.8775126,0.0008717491,0.0003703874,0.00025588134,0.00017356465,0.000034723227,0.00017893856],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981332,0.00003180117,0.0007357995,0.00015833281,0.00042669996,0.00051419437],"domain_scores_gemma":[0.99792475,0.00027901123,0.00031693326,0.0007208468,0.0005622047,0.00019628764],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010898575,0.00024326176,0.00025776058,0.00012087402,0.00035326593,0.00009918167,0.00051723816,0.00031702235,0.000015541878],"category_scores_gemma":[0.0006652864,0.000168727,0.000109948865,0.0002710817,0.00094036857,0.000019126881,0.00020658564,0.00015752834,0.000015150629],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0057499497,0.0020242995,0.0021566225,0.018797811,0.003047606,0.0000041304884,0.010615491,0.02587717,0.06347893,0.06903189,0.122743085,0.676473],"study_design_scores_gemma":[0.001575484,0.001726432,0.00013987185,0.00009109394,0.00009049279,0.000010961136,0.0019012433,0.84062594,0.023216534,0.0019697435,0.12825823,0.0003939881],"about_ca_topic_score_codex":0.000004631811,"about_ca_topic_score_gemma":0.000006085816,"teacher_disagreement_score":0.81474876,"about_ca_system_score_codex":0.000027549275,"about_ca_system_score_gemma":0.00039810897,"threshold_uncertainty_score":0.6880488},"labels":[],"label_agreement":null},{"id":"W2950983802","doi":"10.1093/bioinformatics/btz095","title":"Dhaka: variational autoencoder for unmasking tumor heterogeneity from single cell genomic data","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"National Institute of General Medical Sciences; National Institutes of Health; Microsoft Research","keywords":"Autoencoder; Computer science; Computational biology; Dimensionality reduction; Feature (linguistics); Single cell sequencing; Biology; Genomics; Gene; Artificial intelligence; Mutation; Genetics; Genome; Exome sequencing; Deep learning","score_opus":0.03147508797227019,"score_gpt":0.2393536263880751,"score_spread":0.20787853841580492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950983802","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7615729,0.00019620515,0.23432764,0.000041526928,0.0007636938,0.0004557175,0.0013315666,0.000028572647,0.0012821917],"genre_scores_gemma":[0.7714778,0.00002326,0.2204425,0.00091538235,0.00045866676,0.000012474956,0.006365642,0.000042857293,0.00026141352],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99895227,0.000015383866,0.00036658839,0.0002756408,0.00013450012,0.00025559773],"domain_scores_gemma":[0.9989378,0.000033571698,0.00016052813,0.00073185214,0.000065774446,0.00007047863],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016437696,0.00017452145,0.00016958074,0.000029708755,0.00008151216,0.00007239429,0.0005002823,0.00012669935,0.00003690139],"category_scores_gemma":[0.000033739976,0.00017043472,0.00008448521,0.00004034946,0.000028424894,0.000022655038,0.00020466954,0.000066252825,0.00007090598],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022206009,0.0003219956,0.01133481,0.00025187666,0.00017684801,8.8204087e-7,0.00034360145,0.0029695977,0.97641784,0.00009394972,0.005013894,0.0028526674],"study_design_scores_gemma":[0.002952031,0.00044988812,0.00275021,0.000032909018,0.00009897772,0.0000088260595,0.00015793194,0.664998,0.19109406,0.00014746454,0.13657565,0.0007340554],"about_ca_topic_score_codex":0.000027388794,"about_ca_topic_score_gemma":0.000030532803,"teacher_disagreement_score":0.78532374,"about_ca_system_score_codex":0.000027243952,"about_ca_system_score_gemma":0.00012061901,"threshold_uncertainty_score":0.6950126},"labels":[],"label_agreement":null},{"id":"W2951158909","doi":"10.1093/bioinformatics/btw777","title":"Scater: pre-processing, quality control, normalization and visualization of single-cell RNA-seq data in R","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2053,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Health and Medical Research Council; Medical Research Council Canada; Cancer Research UK; Medical Research Council; European Molecular Biology Laboratory","keywords":"Normalization (sociology); Visualization; Computer science; RNA-Seq; Software; Computational biology; Data mining; Biology; Transcriptome; Genetics; Gene expression; Programming language; Gene","score_opus":0.028251786291285042,"score_gpt":0.27560352596503956,"score_spread":0.2473517396737545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951158909","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74109507,0.00031591346,0.25737497,0.000044929544,0.000087139546,0.00018337721,0.00011660478,0.000013763425,0.00076821283],"genre_scores_gemma":[0.9972035,0.00023174209,0.0020080963,0.00011716084,0.000040104427,0.0000027707565,0.00029176104,0.000013235638,0.00009162854],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989736,0.00004281901,0.0005305987,0.00016097666,0.00013667911,0.00015533896],"domain_scores_gemma":[0.9992299,0.000015837302,0.0002485157,0.0003647204,0.000094306684,0.000046686342],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034932647,0.0001221557,0.0001647051,0.000059959937,0.000033645392,0.000027619637,0.00021237963,0.00013566847,0.0000048785305],"category_scores_gemma":[0.00011617692,0.0000927379,0.00002213798,0.000086980544,0.000093425115,0.000048594913,0.00008453898,0.000024735553,0.0000015890549],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018856765,0.00018967171,0.055289242,0.00045865998,0.000014522618,2.2534347e-7,0.00040379693,0.00002709888,0.9170269,0.00011717768,0.00016806937,0.026116082],"study_design_scores_gemma":[0.010577853,0.0009492646,0.034121472,0.00046509184,0.00009341623,0.00001163389,0.00031313478,0.041891955,0.9014316,0.00016912843,0.008987435,0.0009879947],"about_ca_topic_score_codex":0.000039992283,"about_ca_topic_score_gemma":0.00007713669,"teacher_disagreement_score":0.2561084,"about_ca_system_score_codex":0.000012128926,"about_ca_system_score_gemma":0.000055443103,"threshold_uncertainty_score":0.3781742},"labels":[],"label_agreement":null},{"id":"W2951162601","doi":"10.1093/bioinformatics/btz476","title":"Mycorrhiza: genotype assignment using phylogenetic networks","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Mycorrhizal Fungi and Plant Interactions","field":"Agricultural and Biological Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; University of British Columbia; McGill University","funders":"","keywords":"Phylogenetic tree; Genotype; Biology; Phylogenetics; Genetics; Computational biology; Computer science; Evolutionary biology; Gene","score_opus":0.014572050027027907,"score_gpt":0.20421164200267822,"score_spread":0.1896395919756503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951162601","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98262525,0.00029085221,0.0012516519,0.00005595611,0.00090356113,0.0003290524,0.00023297842,0.00006743237,0.01424325],"genre_scores_gemma":[0.99589473,0.0002704303,0.002022007,0.00046756704,0.00025514688,0.0000037475638,0.00055826176,0.0000011891219,0.00052690535],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99928117,0.00001753,0.000230854,0.00009130692,0.00014010475,0.00023906355],"domain_scores_gemma":[0.9994217,0.0003100162,0.0000940952,0.00006499724,0.000032581353,0.00007659858],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000087916625,0.0001125214,0.00012026176,0.000010791328,0.000102434155,0.000062341926,0.00015132817,0.00008167109,0.0057235025],"category_scores_gemma":[0.000018010845,0.00004389095,0.00006419763,0.00016667371,0.000002885595,0.00011895294,0.000051009578,0.000097510456,0.0024014818],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001744974,0.0002794074,0.5404277,0.000116253235,0.0001503364,0.000010821659,0.00052744185,0.037087608,0.2335877,0.004037526,0.027249135,0.15635158],"study_design_scores_gemma":[0.000098891964,0.00036280588,0.012608258,0.00009894496,0.000042373616,0.000090704154,0.0005057701,0.8144473,0.0010299225,0.00018754893,0.1699837,0.0005437689],"about_ca_topic_score_codex":0.00011403044,"about_ca_topic_score_gemma":0.000013249608,"teacher_disagreement_score":0.7773597,"about_ca_system_score_codex":0.000027551077,"about_ca_system_score_gemma":0.000006867186,"threshold_uncertainty_score":0.99837524},"labels":[],"label_agreement":null},{"id":"W2951421219","doi":"10.1093/bioinformatics/btz150","title":"RECAP reveals the true statistical significance of ChIP-seq peak calls","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"False discovery rate; Computer science; Resampling; Statistical hypothesis testing; Chip; Statistical model; Data mining; Statistics; Biology; Mathematics; Algorithm; Machine learning; Genetics","score_opus":0.00652173639743256,"score_gpt":0.22257576152622724,"score_spread":0.21605402512879468,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951421219","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9881592,0.00009458928,0.0042713145,0.000099965924,0.00019165942,0.00037604006,0.00019730638,0.0000073325114,0.006602609],"genre_scores_gemma":[0.98749113,0.000108852924,0.0109759765,0.00026070708,0.00006042639,0.000009253291,0.00016898436,0.000015709427,0.000908934],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99908525,0.000029107567,0.00041673228,0.000115118295,0.00015021444,0.000203567],"domain_scores_gemma":[0.9991055,0.000040490984,0.00020648426,0.0005229403,0.00007025439,0.000054291617],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025206548,0.00012844257,0.00016937793,0.000018720695,0.00004306361,0.000022494763,0.0003075433,0.00010821972,0.000050182472],"category_scores_gemma":[0.000076984375,0.00009220237,0.00006652047,0.00006030363,0.00009194237,0.0000039911392,0.00010810332,0.00008409871,0.00006714832],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018049577,0.00020940941,0.009792368,0.0011216456,0.00028870563,0.0000022757365,0.0015984492,0.0017575155,0.92586285,0.023779912,0.025185268,0.0102211265],"study_design_scores_gemma":[0.0077026775,0.0053939223,0.15396191,0.00044929676,0.00041806445,0.00019955524,0.008703322,0.21901827,0.37814853,0.010665265,0.21116124,0.0041779494],"about_ca_topic_score_codex":0.000007317518,"about_ca_topic_score_gemma":0.0000068957056,"teacher_disagreement_score":0.5477143,"about_ca_system_score_codex":0.0000123954005,"about_ca_system_score_gemma":0.00008437777,"threshold_uncertainty_score":0.37599036},"labels":[],"label_agreement":null},{"id":"W2951662798","doi":"10.1093/bioinformatics/btz433","title":"CoCo: RNA-seq read assignment correction for nested genes and multimapped reads","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"RNA Research and Splicing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":60,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Coco; Transcriptome; RNA-Seq; Python (programming language); Gene; Computational biology; Computer science; R package; Biology; Genetics; Gene expression; Programming language; Artificial intelligence","score_opus":0.01459678843746658,"score_gpt":0.2730451811645093,"score_spread":0.25844839272704273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951662798","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9752022,0.00019930235,0.02102949,0.00008338201,0.00033487444,0.0007682254,0.000021517057,0.00001983352,0.0023411494],"genre_scores_gemma":[0.95202017,0.00066422625,0.025172316,0.0004219658,0.00023054042,0.00011421106,0.00053886074,0.000038925224,0.020798778],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99931884,0.0000135379505,0.00020415125,0.00012160116,0.000116930394,0.00022496097],"domain_scores_gemma":[0.99951893,0.000024018469,0.00008006286,0.00021324742,0.00007858623,0.000085155734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019128516,0.00010652806,0.00011422974,0.000038758175,0.000071467446,0.00004467087,0.00008083514,0.00010890418,0.00001054475],"category_scores_gemma":[0.00007353118,0.00009130896,0.000043542837,0.000043926095,0.00003080288,0.0000101026735,0.00006221627,0.00004794164,0.000022018894],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027102334,0.000060198607,0.00570307,0.00023900623,0.000069990274,5.913631e-7,0.00017597314,0.00016278327,0.8678096,0.000049018323,0.0083768675,0.11708191],"study_design_scores_gemma":[0.0035698228,0.0023629179,0.003993656,0.00009860724,0.000035999445,0.000050412295,0.0014392815,0.34061807,0.5421569,0.000027597947,0.10504562,0.0006011668],"about_ca_topic_score_codex":0.000024433355,"about_ca_topic_score_gemma":0.000012051799,"teacher_disagreement_score":0.3404553,"about_ca_system_score_codex":0.000017148976,"about_ca_system_score_gemma":0.000047115725,"threshold_uncertainty_score":0.37234715},"labels":[],"label_agreement":null},{"id":"W2952106966","doi":"10.1093/bioinformatics/btz064","title":"Variational infinite heterogeneous mixture model for semi-supervised clustering of heart enhancers","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Ontario Ministry of Research and Innovation; Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation","keywords":"Enhancer; Cluster analysis; Computer science; Python (programming language); Inference; Context (archaeology); Mixture model; Dirichlet process; Machine learning; Data mining; Artificial intelligence; Biology; Gene; Genetics; Gene expression","score_opus":0.015514781661221754,"score_gpt":0.2525756993871091,"score_spread":0.23706091772588736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952106966","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22153896,0.0001578428,0.7750451,0.00016040272,0.00034521305,0.0006483899,0.00013401134,0.00001836395,0.0019517356],"genre_scores_gemma":[0.9498625,0.000045739558,0.048389103,0.0005386682,0.00006661694,0.000038872706,0.0002819559,0.000014141674,0.00076240685],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99937177,0.000007806502,0.0002696598,0.00010952055,0.000114942566,0.00012629642],"domain_scores_gemma":[0.99946886,0.000008919453,0.000121118755,0.0002539973,0.000105020685,0.00004205814],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008646812,0.00009503795,0.000111099966,0.000040111852,0.0000306262,0.00001271547,0.00011598597,0.00012039119,0.000021370292],"category_scores_gemma":[0.000020156147,0.00008902623,0.00008464332,0.00004914185,0.000015738677,0.000007712244,0.000047302477,0.000032904118,0.000008735912],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001391716,0.000028801378,0.00028695396,0.00024675185,0.000038359136,1.7368334e-8,0.00040496094,0.1321473,0.86093986,0.000086922555,0.0042751697,0.0014057397],"study_design_scores_gemma":[0.0005215453,0.00009629295,0.000061172825,0.000019765874,0.000007820508,0.000002295538,0.00004736871,0.853486,0.13674137,0.000041566895,0.008863585,0.000111204645],"about_ca_topic_score_codex":8.082793e-7,"about_ca_topic_score_gemma":0.0000014143108,"teacher_disagreement_score":0.7283235,"about_ca_system_score_codex":0.000012732075,"about_ca_system_score_gemma":0.000098838944,"threshold_uncertainty_score":0.36303842},"labels":[],"label_agreement":null},{"id":"W2952191365","doi":"10.1093/bioinformatics/btz485","title":"SIGN: similarity identification in gene expression","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Montreal Clinical Research Institute; Institute of Cancer Research; Ontario Institute for Cancer Research; Institut universitaire de cardiologie et de pneumologie de Québec; Université de Montréal; Université Laval; Princess Margaret Cancer Centre; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Ontario Institute for Cancer Research; Canadian Institutes of Health Research; Government of Ontario; Cancer Research Society","keywords":"Similarity (geometry); Identification (biology); Expression (computer science); Computer science; Computational biology; Breast cancer; Sign (mathematics); Artificial intelligence; Machine learning; Data mining; Bioinformatics; Biology; Cancer; Genetics; Mathematics","score_opus":0.009305137900203311,"score_gpt":0.22990952976610174,"score_spread":0.22060439186589842,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952191365","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9672756,0.00019735808,0.023310058,0.000073177085,0.000444965,0.0005163787,0.000027025706,0.000021426415,0.008133968],"genre_scores_gemma":[0.9889026,0.000098745746,0.009644132,0.00033689302,0.000084350686,0.00001133049,0.00029960932,0.000012561228,0.00060975895],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990273,0.000016307908,0.00046755568,0.00012846029,0.00013276013,0.0002275918],"domain_scores_gemma":[0.9992887,0.000008041313,0.00016037883,0.00044349147,0.000041974254,0.000057458114],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030944345,0.0001299205,0.0001277312,0.000061288076,0.000037759084,0.000045285306,0.00021157916,0.00019226043,0.000035552333],"category_scores_gemma":[0.000021417285,0.00012103541,0.00005710273,0.00009837294,0.000025245015,0.000017664835,0.000125296,0.00010453617,0.00020547298],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020353933,0.00022636232,0.027319958,0.00043941548,0.000056993664,0.000002338641,0.0015460454,0.0051287985,0.9138415,0.0008719685,0.019004965,0.031358134],"study_design_scores_gemma":[0.0038013433,0.0005012863,0.029311495,0.00015721616,0.000026724721,0.00004148199,0.0013309158,0.12955253,0.7607591,0.0013920305,0.07166692,0.0014589605],"about_ca_topic_score_codex":0.0000032212085,"about_ca_topic_score_gemma":0.00000571553,"teacher_disagreement_score":0.15308239,"about_ca_system_score_codex":0.000020080026,"about_ca_system_score_gemma":0.00004439185,"threshold_uncertainty_score":0.49356806},"labels":[],"label_agreement":null},{"id":"W2952228520","doi":"10.1093/bioinformatics/btz130","title":"LIONS: analysis suite for detecting and quantifying transposable element initiated transcription from RNA-seq","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Chromosomal and Genetic Variations","field":"Agricultural and Biological Sciences","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; Terry Fox Research Institute; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; University of British Columbia","keywords":"RNA-Seq; Transposable element; Suite; Container (type theory); Computer science; Source code; Computational biology; Transcription (linguistics); Transcriptome; Biology; Genetics; Genome; Gene; Gene expression; Programming language","score_opus":0.060007125401452754,"score_gpt":0.2551174693935599,"score_spread":0.19511034399210714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952228520","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99729687,0.000078147365,0.0013873847,0.00023434794,0.00007580994,0.00035303916,0.0003152268,0.000042173553,0.00021697878],"genre_scores_gemma":[0.9942523,0.000050656756,0.0050290604,0.00010792069,0.00004413327,0.000017331036,0.00046596504,6.7206787e-7,0.000031928706],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99930197,0.000014438829,0.00029637342,0.000112053174,0.000107269436,0.00016788067],"domain_scores_gemma":[0.99961185,0.00015898577,0.000088883084,0.000042592674,0.000045739,0.000051941155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001400412,0.000091965485,0.00015413153,0.000025721887,0.00018711961,0.000084649764,0.000075451244,0.000063298525,0.00029157876],"category_scores_gemma":[0.000015644895,0.000041324452,0.000105376144,0.00037780975,0.000011439639,0.000169571,0.000010495903,0.000043348966,0.000017211245],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010980582,0.00015807198,0.082026556,0.00016762117,0.0007557977,5.841299e-7,0.005774734,0.00089283934,0.73727775,0.0008989375,0.000048129667,0.17188916],"study_design_scores_gemma":[0.0019993656,0.0009690113,0.32267845,0.00012688253,0.0014488886,0.0000034126078,0.007942821,0.6146985,0.035330616,0.001985437,0.011866421,0.00095016725],"about_ca_topic_score_codex":0.00018896737,"about_ca_topic_score_gemma":0.0012261388,"teacher_disagreement_score":0.70194715,"about_ca_system_score_codex":0.000012224038,"about_ca_system_score_gemma":0.000005095741,"threshold_uncertainty_score":0.3192583},"labels":[],"label_agreement":null},{"id":"W2952588534","doi":"10.1093/bioinformatics/btw695","title":"EGAD: ultra-fast functional analysis of gene networks","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":78,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"National Institute of Mental Health; National Institutes of Health","keywords":"Bioconductor; Computer science; Set (abstract data type); R package; Data mining; Software; Gene regulatory network; MIT License; Task (project management); Throughput; Network analysis; Machine learning; Gene; Biology; Programming language; Genetics","score_opus":0.008504445161484603,"score_gpt":0.206415465538498,"score_spread":0.19791102037701339,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952588534","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06853901,0.00026513237,0.9229621,0.00008921137,0.0003423556,0.0001684898,0.00016767277,0.000020407264,0.0074455943],"genre_scores_gemma":[0.98973817,0.00030310894,0.008056889,0.00035426128,0.0002494934,0.000008909476,0.00044434168,0.000015771137,0.0008290782],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99881196,0.0000144379055,0.0005931717,0.00012687412,0.000175188,0.00027834444],"domain_scores_gemma":[0.998999,0.000027617203,0.000290561,0.0004560348,0.00012271595,0.000104097555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023751677,0.00016984636,0.00025645213,0.00014572915,0.000060860544,0.000018740466,0.00020370743,0.00019828524,0.00009970592],"category_scores_gemma":[0.000029280212,0.00011645311,0.00025134202,0.0003346592,0.00011318142,0.000012124025,0.000055553963,0.00005434524,0.000021362726],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010200785,0.00055285305,0.03843027,0.00029726568,0.01631857,0.00000453055,0.0011730468,0.10978346,0.32768992,0.008314653,0.110064685,0.3863507],"study_design_scores_gemma":[0.008162228,0.0018307989,0.07894956,0.0002062733,0.004554287,0.00011251941,0.0011960185,0.5495661,0.18867421,0.0005824972,0.16261977,0.0035457797],"about_ca_topic_score_codex":0.0000031614884,"about_ca_topic_score_gemma":0.000013047363,"teacher_disagreement_score":0.92119914,"about_ca_system_score_codex":0.000016373315,"about_ca_system_score_gemma":0.000053493237,"threshold_uncertainty_score":0.474882},"labels":[],"label_agreement":null},{"id":"W2952646324","doi":"10.1093/bioinformatics/btx603","title":"Segway 2.0: Gaussian mixture models and minibatch training","year":2017,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Princess Margaret Cancer Centre; University of British Columbia","funders":"National Human Genome Research Institute; Canadian Institutes of Health Research; National Institutes of Health; Natural Sciences and Engineering Research Council of Canada; University Health Network","keywords":"Computer science; Scripting language; Annotation; Source code; Gaussian; Mixture model; Training set; Data mining; Code (set theory); Artificial intelligence; Machine learning; Pattern recognition (psychology); Set (abstract data type); Programming language","score_opus":0.02396829629731378,"score_gpt":0.25035827344199824,"score_spread":0.22638997714468445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952646324","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47218665,0.0018407897,0.17041352,0.002501659,0.0015560355,0.0011648284,0.0002344029,0.00010464007,0.34999746],"genre_scores_gemma":[0.9665604,0.0003631633,0.030639471,0.0006509816,0.00030529147,0.000009479609,0.000098289805,0.000022425875,0.001350444],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990915,0.000008147453,0.00032606596,0.00013771848,0.00011789665,0.00031864204],"domain_scores_gemma":[0.99886084,0.0000068729746,0.00025453305,0.00068268704,0.00004220417,0.00015288233],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023485764,0.00019243722,0.00018038883,0.000030233154,0.00043883655,0.00025337265,0.00035613446,0.00023927512,0.000007669585],"category_scores_gemma":[0.000038023645,0.00016685622,0.000066998975,0.000018655446,0.0001573996,0.000034893714,0.000255589,0.00012251851,0.000012830418],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029091616,0.0001449122,0.0024381853,0.0009039276,0.0007194522,0.000018780225,0.02227751,0.0015144625,0.008759579,0.023948077,0.11491969,0.8240645],"study_design_scores_gemma":[0.004423298,0.0007987828,0.0047102394,0.0002612308,0.00015660476,0.00037384295,0.0056756972,0.569251,0.0049678814,0.012657934,0.3943719,0.0023516053],"about_ca_topic_score_codex":0.000006657035,"about_ca_topic_score_gemma":0.000020509986,"teacher_disagreement_score":0.8217129,"about_ca_system_score_codex":0.000006869657,"about_ca_system_score_gemma":0.00006154667,"threshold_uncertainty_score":0.68041986},"labels":[],"label_agreement":null},{"id":"W2952713926","doi":"10.1093/bioinformatics/bty244","title":"COSSMO: predicting competitive alternative splice site selection using deep learning","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"RNA Research and Splicing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":66,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Ontario Genomics; University of Toronto","funders":"","keywords":"splice; Computer science; RNA splicing; Sequence (biology); Alternative splicing; Computational biology; Selection (genetic algorithm); Artificial intelligence; Data mining; Gene; Biology; Genetics; RNA","score_opus":0.01461999723287225,"score_gpt":0.2846627027470284,"score_spread":0.2700427055141561,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952713926","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93153495,0.00005272544,0.06233791,0.000009736915,0.00009730195,0.00014963424,0.0000065272234,0.000026996146,0.0057842326],"genre_scores_gemma":[0.984849,0.00006340805,0.013822333,0.00012087603,0.0005629859,0.0000045882007,0.000067300694,0.000017991979,0.0004915659],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99906415,0.00004543796,0.00022911926,0.00014290279,0.00019381972,0.00032460058],"domain_scores_gemma":[0.99935496,0.000019119172,0.00014109405,0.0001214673,0.00026643238,0.00009690793],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024896456,0.00012593341,0.00010616372,0.00006547443,0.00032250173,0.000049329392,0.00011960301,0.0000910929,0.00002248784],"category_scores_gemma":[0.0001911364,0.00012138608,0.00004809906,0.0001459756,0.0001074668,0.00002054569,0.00012917818,0.0001602033,0.000056031062],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001927162,0.000047434325,0.049371142,0.0000916205,0.00016937384,0.0000029688974,0.002522172,0.0023610124,0.93220234,0.00024093005,0.0002673902,0.012530929],"study_design_scores_gemma":[0.0004807279,0.00064844725,0.0011414364,0.000048919494,0.0000148187055,0.000046921938,0.0015612209,0.81927544,0.16998003,0.000009311044,0.006583198,0.00020951536],"about_ca_topic_score_codex":0.00009632026,"about_ca_topic_score_gemma":0.000109906185,"teacher_disagreement_score":0.81691444,"about_ca_system_score_codex":0.000044750894,"about_ca_system_score_gemma":0.00005467964,"threshold_uncertainty_score":0.49499807},"labels":[],"label_agreement":null},{"id":"W2952985080","doi":"10.1093/bioinformatics/btz445","title":"A scalable method for parameter identification in kinetic models of metabolism using steady-state data","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Microbial Metabolic Engineering and Bioproduction","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Identifiability; Computer science; Scalability; Estimation theory; A priori and a posteriori; Biological system; Steady state (chemistry); Identification (biology); Experimental data; Data mining; Algorithm; Mathematics; Statistics; Machine learning; Chemistry; Biology; Database","score_opus":0.033322204304405655,"score_gpt":0.2872780953079232,"score_spread":0.25395589100351756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952985080","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5097166,0.00027573353,0.48923904,0.000010220212,0.00023392666,0.0003669832,0.00011376825,0.0000059189892,0.000037821894],"genre_scores_gemma":[0.5712525,0.00011544089,0.4278128,0.000032574364,0.00007067458,0.000009114953,0.00041184385,0.00001758502,0.00027740683],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991825,0.00001906973,0.00040200973,0.00017095152,0.00007553853,0.0001498989],"domain_scores_gemma":[0.99914294,0.0000070676465,0.00014934366,0.00060413586,0.00007363127,0.000022853967],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051373045,0.00009725682,0.00017251757,0.00008070114,0.0000127183785,0.000017180697,0.0002140593,0.000075696385,0.000002067901],"category_scores_gemma":[0.00008018533,0.000089751884,0.000037916874,0.00011890132,0.000014657057,0.000026801908,0.00009085519,0.000040131174,0.000003019832],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003243176,0.000025740646,0.000025345438,0.00024087721,0.000024753412,1.966113e-8,0.00013357351,0.038369503,0.9555014,0.00008712936,0.00012530012,0.0054339617],"study_design_scores_gemma":[0.000396972,0.000027165739,0.00010972753,0.000023575654,0.000027579026,0.0000042974416,0.000052380423,0.71571225,0.27889314,0.00012898094,0.00450561,0.000118309785],"about_ca_topic_score_codex":0.000039989907,"about_ca_topic_score_gemma":0.0000050844405,"teacher_disagreement_score":0.6773428,"about_ca_system_score_codex":0.0000069360135,"about_ca_system_score_gemma":0.000032482505,"threshold_uncertainty_score":0.36599755},"labels":[],"label_agreement":null},{"id":"W2953282636","doi":"10.1093/bioinformatics/btx732","title":"MOSAIC: a chemical-genetic interaction data repository and web resource for exploring chemical modes of action","year":2017,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Institute of General Medical Sciences; National Human Genome Research Institute; RIKEN; Japan Society for the Promotion of Science; Canadian Institutes of Health Research; University of Minnesota; National Institutes of Health; National Science Foundation","keywords":"Computer science; Interface (matter); Resource (disambiguation); Computational biology; Annotation; Mosaic; User interface; Similarity (geometry); Web site; Ontology; Action (physics); Biology; The Internet; Artificial intelligence; World Wide Web","score_opus":0.1828911589620814,"score_gpt":0.36057274565214587,"score_spread":0.17768158669006445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2953282636","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42838982,0.000027386353,0.5703599,0.00014406,0.00023492207,0.00017892626,0.000026638536,0.000046924495,0.0005914292],"genre_scores_gemma":[0.52406627,0.000009344225,0.4757946,0.000015312593,0.000064783606,0.000013716896,0.000021174774,0.000004671344,0.000010126983],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991786,0.000017976035,0.00033060307,0.00017383583,0.00018213772,0.0001168514],"domain_scores_gemma":[0.998313,0.00024600577,0.0003349113,0.0009923573,0.00006233781,0.000051395135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027218866,0.000090361034,0.00013181305,0.00005309822,0.0001311923,0.00022680346,0.00090585597,0.000042368858,2.8510496e-7],"category_scores_gemma":[0.0002707071,0.00008821645,0.000031345025,0.00004130764,0.00006484081,0.0019211319,0.0008392117,0.000072289506,9.441249e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017564143,0.00016731097,0.0005396782,0.0012925359,0.00012818132,0.0000021345195,0.0032529703,0.0059167263,0.24204557,0.007879557,0.0035637484,0.73503596],"study_design_scores_gemma":[0.00021042678,0.000016682166,0.00017699937,0.00005176508,0.000009806991,0.000019780478,0.00010593263,0.87588793,0.12129989,0.00053210114,0.0016009457,0.00008775548],"about_ca_topic_score_codex":0.000007827917,"about_ca_topic_score_gemma":4.3648936e-7,"teacher_disagreement_score":0.86997116,"about_ca_system_score_codex":0.000034348683,"about_ca_system_score_gemma":0.00005536769,"threshold_uncertainty_score":0.35973626},"labels":[],"label_agreement":null},{"id":"W2953326935","doi":"10.1093/bioinformatics/btz400","title":"ntEdit: scalable genome sequence polishing","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":132,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia; Genome British Columbia; Université Laval; Natural Resources Canada; Ministry of Forests","funders":"National Human Genome Research Institute; National Institutes of Health","keywords":"Sequence (biology); Scalability; Polishing; Computer science; Whole genome sequencing; Genome; Computational biology; Genetics; Biology; Gene; Materials science; Database; Metallurgy","score_opus":0.014467627052544538,"score_gpt":0.2310440146055117,"score_spread":0.21657638755296715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2953326935","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9795126,0.00045926817,0.0002840223,0.00010112363,0.00050744816,0.00019112778,0.000068496265,0.000008006606,0.018867942],"genre_scores_gemma":[0.99176115,0.0002698132,0.0045717787,0.0005932786,0.00021254882,0.0000066303733,0.000073303585,0.00001599978,0.002495479],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992921,0.000008005217,0.00021402215,0.00012927815,0.00010511898,0.00025149423],"domain_scores_gemma":[0.9994588,0.00000675098,0.000079868114,0.00032930155,0.00006277155,0.000062492356],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011996112,0.00012394821,0.000118612734,0.00002916369,0.00006485997,0.000043258005,0.00021121936,0.0000876641,0.000029825596],"category_scores_gemma":[0.000027771819,0.000113305214,0.000047614285,0.00006500528,0.000039017832,0.0000025955671,0.000173572,0.000055962057,0.00023300611],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027229902,0.000024041341,0.008510365,0.00009963682,0.0000926272,8.2862067e-7,0.00041228748,0.0005450562,0.9824949,0.0004580807,0.004768429,0.002566524],"study_design_scores_gemma":[0.0009441041,0.0005663937,0.022505226,0.00003091796,0.000031505606,0.00004847487,0.0009613584,0.0035427443,0.040192764,0.00023051104,0.93017155,0.0007744279],"about_ca_topic_score_codex":0.000012407665,"about_ca_topic_score_gemma":0.0000043554796,"teacher_disagreement_score":0.9423021,"about_ca_system_score_codex":0.000013565713,"about_ca_system_score_gemma":0.00005273424,"threshold_uncertainty_score":0.46204525},"labels":[],"label_agreement":null},{"id":"W2953409640","doi":"10.1093/bioinformatics/btz522","title":"Pygenprop: a Python library for programmatic exploration and comparison of organism genome properties","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Université de Genève; Nuclear Waste Management Organization","keywords":"Python (programming language); Computer science; Documentation; Genome; Source code; Organism; Software; MIT License; Genomics; Programming language; World Wide Web; Biology; Genetics; Gene","score_opus":0.025425893781296366,"score_gpt":0.23177017140923153,"score_spread":0.20634427762793517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2953409640","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99495673,0.0013332453,0.0023198952,0.00009532957,0.000078426834,0.0008435688,0.000029410681,0.000008047773,0.0003353538],"genre_scores_gemma":[0.9749147,0.00021895376,0.024394928,0.00004803106,0.000045479643,0.000040565552,0.0000913365,0.000019391791,0.0002265826],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99940723,0.000008336751,0.0003001411,0.000094825744,0.00006275291,0.00012669407],"domain_scores_gemma":[0.99959874,0.000006408905,0.00014355483,0.00017044478,0.000049668073,0.000031162246],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000063537766,0.00010523013,0.00017050905,0.000027407152,0.000043299027,0.000029383395,0.00008385198,0.00006783985,0.00000273926],"category_scores_gemma":[0.000016590948,0.00008468707,0.000037403388,0.000040055,0.000048910933,0.0000062419826,0.00009839995,0.000023206592,0.0000048920615],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013536043,0.000099571276,0.008198342,0.0015069449,0.00014094482,5.2708717e-8,0.004937992,0.00015676663,0.9688927,0.00044265803,0.00048287484,0.015005798],"study_design_scores_gemma":[0.0021027036,0.0035618574,0.0049485876,0.00009605425,0.00010647889,0.000008726152,0.008145404,0.021654377,0.86887354,0.0008851323,0.08889751,0.00071961636],"about_ca_topic_score_codex":8.145507e-7,"about_ca_topic_score_gemma":0.0000010777618,"teacher_disagreement_score":0.10001914,"about_ca_system_score_codex":0.0000026898963,"about_ca_system_score_gemma":0.000038155642,"threshold_uncertainty_score":0.34534386},"labels":[],"label_agreement":null},{"id":"W2953737873","doi":"10.1093/bioinformatics/btz534","title":"<i>RTNduals</i>: an R/Bioconductor package for analysis of co-regulation and inference of <i>dual regulons</i>","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; BC Cancer Agency","funders":"National Cancer Institute; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Cancer Research UK; Breast Cancer Research Foundation","keywords":"Bioconductor; Regulon; Computer science; Inference; R package; Computational biology; Biology; Data mining; Regulation of gene expression; Gene; Genetics; Artificial intelligence; Programming language","score_opus":0.0168775380279266,"score_gpt":0.27257583472530783,"score_spread":0.25569829669738126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2953737873","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9782941,0.00010049115,0.019822856,0.000011680826,0.00007401401,0.00042434625,0.00046762713,0.000006647931,0.0007982415],"genre_scores_gemma":[0.9860028,0.0000641685,0.012385106,0.000097970325,0.000035051045,0.000007756317,0.0012702445,0.0000107436435,0.00012617302],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99895215,0.000016345795,0.0006050931,0.0001247118,0.00012855734,0.00017315583],"domain_scores_gemma":[0.99882746,0.00004013866,0.0004443397,0.00045707356,0.0001586682,0.000072350216],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032242152,0.00014434534,0.00033775554,0.00012939192,0.000032023592,0.000019373294,0.00013344556,0.00017549001,0.000019661979],"category_scores_gemma":[0.000036851216,0.0001297487,0.00012335416,0.00019065876,0.00010508004,0.00002667937,0.00004935139,0.000043171076,0.0000020943035],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003668343,0.0002272646,0.027270975,0.0013060808,0.0019334649,1.1070515e-7,0.0024510873,0.00209677,0.9379917,0.0069618463,0.0026246745,0.01676924],"study_design_scores_gemma":[0.003974715,0.0033533452,0.039620094,0.00011112908,0.0015456439,0.0000098858845,0.002251892,0.23108768,0.6974327,0.00080882845,0.018614942,0.0011891682],"about_ca_topic_score_codex":0.0000056091562,"about_ca_topic_score_gemma":0.000012076312,"teacher_disagreement_score":0.24055898,"about_ca_system_score_codex":0.0000053203385,"about_ca_system_score_gemma":0.00005927351,"threshold_uncertainty_score":0.5290999},"labels":[],"label_agreement":null},{"id":"W2953949806","doi":"10.1093/bioinformatics/btz343","title":"Large-scale mammalian genome rearrangements coincide with chromatin interactions","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Agence Nationale de la Recherche","keywords":"Breakpoint; Chromosomal rearrangement; Biology; Genome; Chromatin; Chromosome; Genetics; Gene rearrangement; Computational biology; Gene; Gene duplication; Karyotype","score_opus":0.006863780160027628,"score_gpt":0.22537573313091283,"score_spread":0.21851195297088521,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2953949806","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9610608,0.000066812034,0.008326279,0.00009915113,0.00020794928,0.00060611696,0.00008961514,0.00003873124,0.029504538],"genre_scores_gemma":[0.9376072,0.000054868233,0.04991502,0.0004912926,0.00019386469,0.00004993744,0.000996749,0.000055727283,0.010635301],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989422,0.000017652921,0.00029052192,0.0001807251,0.0002215969,0.00034733603],"domain_scores_gemma":[0.9991536,0.000004651696,0.0001500143,0.0005098506,0.00008209071,0.00009977149],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00015505741,0.00018621807,0.00015626369,0.000073416435,0.00007766414,0.000051634725,0.0002192224,0.00007581233,0.0005106963],"category_scores_gemma":[0.000008627127,0.0001593664,0.000064906715,0.00012276275,0.00003110399,0.000019724726,0.00013432273,0.00008815944,0.00096056465],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00064624526,0.0011188817,0.064787775,0.001585668,0.0014772766,0.000027992339,0.011352365,0.0015513527,0.8765152,0.00024290162,0.033239037,0.007455305],"study_design_scores_gemma":[0.0054880623,0.0017877091,0.0383356,0.00012253052,0.00013146832,0.00017502581,0.011443297,0.009371596,0.033511993,0.000028788983,0.89820695,0.0013969927],"about_ca_topic_score_codex":0.0000055673554,"about_ca_topic_score_gemma":0.00004384368,"teacher_disagreement_score":0.8649679,"about_ca_system_score_codex":0.000034909815,"about_ca_system_score_gemma":0.000047527596,"threshold_uncertainty_score":0.9998173},"labels":[],"label_agreement":null},{"id":"W2955502047","doi":"10.1093/bioinformatics/btz318","title":"MOLI: multi-omics late integration with deep neural networks for drug response prediction","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":407,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"Canadian Institutes of Health Research; Terry Fox Foundation; Canada Foundation for Innovation","keywords":"Drug response; Computer science; Representation (politics); Machine learning; Artificial intelligence; Omics; Precision oncology; Artificial neural network; Computational biology; Data mining; Drug; Precision medicine; Bioinformatics; Biology","score_opus":0.007039244457505459,"score_gpt":0.21430855938702414,"score_spread":0.2072693149295187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2955502047","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39643925,0.000118803604,0.60157377,0.00008652623,0.00045260412,0.0009474637,0.00007340361,0.000037427813,0.00027076903],"genre_scores_gemma":[0.9383566,0.000074826494,0.0582154,0.00071880646,0.00021839075,0.00006399735,0.0011536705,0.00004426564,0.0011540868],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988811,0.000028654777,0.00046462248,0.000164358,0.00011959286,0.00034167475],"domain_scores_gemma":[0.9990695,0.000034845034,0.00024541604,0.00041061742,0.00014242133,0.00009717936],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004239053,0.00022962582,0.00018552576,0.000059054753,0.00010894,0.000083615996,0.00019468187,0.00021527799,0.000006223783],"category_scores_gemma":[0.000032407086,0.00018419763,0.000097729564,0.00009727219,0.000051326126,0.000030847743,0.000071995026,0.00014533247,0.000016587475],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.016711853,0.00036838622,0.007036805,0.00064823154,0.00069182937,0.0000027759027,0.0057034073,0.767199,0.02502389,0.0009686112,0.015130098,0.16051516],"study_design_scores_gemma":[0.0016433222,0.0005111439,0.00080214714,0.000020316693,0.000029002495,0.000015314263,0.00039154582,0.98910636,0.0016375982,0.000018112301,0.0055735414,0.00025162427],"about_ca_topic_score_codex":0.0000030853064,"about_ca_topic_score_gemma":0.000025000989,"teacher_disagreement_score":0.5433583,"about_ca_system_score_codex":0.00003298366,"about_ca_system_score_gemma":0.000048924645,"threshold_uncertainty_score":0.7511362},"labels":[],"label_agreement":null},{"id":"W2955780193","doi":"","title":"Method Choice in Gene Set Analysis Has Important Consequences for Analysis Outcome.","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal University Hospital; University of Saskatchewan","funders":"","keywords":"Outcome (game theory); Set (abstract data type); Computer science; Genetic analysis; Computational biology; Gene; Genetics; Biology; Mathematical economics; Mathematics; Programming language","score_opus":0.05818490484697021,"score_gpt":0.36843060612477324,"score_spread":0.31024570127780304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2955780193","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76617634,0.0005039684,0.22813813,0.00091259327,0.0003027284,0.0016022892,0.0009361795,0.000039796094,0.0013879818],"genre_scores_gemma":[0.7919556,0.00039489949,0.20226687,0.0009711839,0.00013041183,0.000075304146,0.002812062,0.000025256097,0.0013684004],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972251,0.000062132,0.0012472497,0.00032045454,0.00050495303,0.00064008357],"domain_scores_gemma":[0.9982597,0.00015153403,0.00039759514,0.0007142048,0.00023156172,0.0002453982],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001622064,0.00028289997,0.0006750884,0.0007908342,0.00009243979,0.00013752977,0.0005443133,0.00032599168,0.00009929944],"category_scores_gemma":[0.0004866476,0.00023140377,0.00060516456,0.0015469107,0.00021466734,0.00001885283,0.0001910474,0.00015305389,0.000045165936],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019487941,0.00017386132,0.95540416,0.00063778367,0.0067587527,0.0000042847646,0.00076546025,0.0038380402,0.020757154,0.00013475343,0.0035057836,0.007825068],"study_design_scores_gemma":[0.0044665346,0.0015284184,0.09093941,0.000031452095,0.0043693813,0.000016643042,0.0026918643,0.6777439,0.0800855,0.00021347447,0.13604906,0.0018643561],"about_ca_topic_score_codex":0.0001519964,"about_ca_topic_score_gemma":0.0007032753,"teacher_disagreement_score":0.86446476,"about_ca_system_score_codex":0.000046406385,"about_ca_system_score_gemma":0.0002483017,"threshold_uncertainty_score":0.9436372},"labels":[],"label_agreement":null},{"id":"W2956622428","doi":"10.1093/bioinformatics/btz393","title":"MCS2: minimal coordinated supports for fast enumeration of minimal cut sets in metabolic networks","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Microbial Metabolic Engineering and Bioproduction","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Correctness; Set (abstract data type); Enumeration; Metabolic network; Computation; Constraint (computer-aided design); Novelty; Dual (grammatical number); Algorithm; Mathematical optimization; Theoretical computer science; Discrete mathematics; Mathematics; Programming language; Bioinformatics","score_opus":0.00520616366990512,"score_gpt":0.21934020487152653,"score_spread":0.2141340412016214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2956622428","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9906647,0.00032196075,0.007773135,0.000033954933,0.0004905655,0.0004495972,0.000051587274,0.0000120491695,0.00020244789],"genre_scores_gemma":[0.9923878,0.00010067316,0.006480505,0.000042114607,0.00014406588,0.000014705557,0.00048522375,0.000014052551,0.00033087115],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991744,0.000012433136,0.00040340165,0.00013549394,0.000066408844,0.00020784934],"domain_scores_gemma":[0.9995169,0.0000044322755,0.00014492102,0.00021032005,0.00008749072,0.000035915495],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022415923,0.00013168008,0.00020748732,0.000078335375,0.000018310384,0.000012900167,0.00009154503,0.00015649704,0.0000114311315],"category_scores_gemma":[0.000048847283,0.00012431634,0.00007254125,0.00012682416,0.000022338314,0.0000125461465,0.000034036562,0.000057081063,0.0000056653503],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026139923,0.0001140303,0.00426542,0.0003266811,0.00008407215,3.6363667e-7,0.00034911532,0.0073133595,0.96792674,0.00020031,0.0032055697,0.01595291],"study_design_scores_gemma":[0.0023405054,0.0006559711,0.00931566,0.00006955302,0.00006656674,0.0000348238,0.00030637064,0.09127116,0.8211818,0.000008872744,0.07420196,0.0005467618],"about_ca_topic_score_codex":0.0000104349565,"about_ca_topic_score_gemma":0.000011182326,"teacher_disagreement_score":0.14674497,"about_ca_system_score_codex":0.0000063005023,"about_ca_system_score_gemma":0.000039037066,"threshold_uncertainty_score":0.50694734},"labels":[],"label_agreement":null},{"id":"W2960228950","doi":"10.1093/bioinformatics/btz335","title":"Enhancing the drug discovery process: Bayesian inference for the analysis and comparison of dose–response experiments","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Institute for Research in Immunology and Cancer","funders":"Genome Canada","keywords":"Computer science; Bayesian probability; Inference; Data mining; Bayesian inference; Machine learning; Artificial intelligence","score_opus":0.23821785965506612,"score_gpt":0.530511155671486,"score_spread":0.29229329601641985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2960228950","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2729477,0.00005399253,0.72547257,0.00016692707,0.0001596648,0.0009859573,0.00006508622,0.000018358503,0.00012976809],"genre_scores_gemma":[0.68087393,0.000008994127,0.31885716,0.00007055839,0.00002244002,0.00004999522,0.0000012477162,0.000009020377,0.00010664133],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99783677,0.00025043968,0.001219956,0.00012564319,0.00035963653,0.00020754561],"domain_scores_gemma":[0.91756946,0.08111648,0.00063190644,0.00052868464,0.00010775291,0.00004571296],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0038171557,0.00015718941,0.00061672134,0.00007174382,0.00012221393,0.00010483103,0.00038588548,0.00007033898,0.00003828939],"category_scores_gemma":[0.028626295,0.00007938072,0.00015792038,0.00036260035,0.00018337878,0.00018568886,0.00012071445,0.00014316721,0.000005000818],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.015263485,0.002926471,0.14471175,0.0171131,0.015242774,0.0000019661911,0.3265348,0.0018771534,0.009862334,0.3044024,0.0044370196,0.15762672],"study_design_scores_gemma":[0.0035770782,0.0006411716,0.015306821,0.0005110642,0.0036146177,0.00000176336,0.05017954,0.5059682,0.09106355,0.32794568,0.0003775382,0.0008129804],"about_ca_topic_score_codex":0.000006441531,"about_ca_topic_score_gemma":0.000010999955,"teacher_disagreement_score":0.504091,"about_ca_system_score_codex":0.000018874776,"about_ca_system_score_gemma":0.00007142623,"threshold_uncertainty_score":0.979556},"labels":[],"label_agreement":null},{"id":"W2961295341","doi":"10.1093/bioinformatics/btz439","title":"ISMB/ECCB 2019 Proceedings","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science","score_opus":0.006793132206369344,"score_gpt":0.2020652547703505,"score_spread":0.19527212256398116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2961295341","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.965883,0.00012558092,0.0011201528,0.00007895445,0.00043722228,0.00025345501,0.00001870683,0.00003363171,0.032049276],"genre_scores_gemma":[0.9815549,0.00015163294,0.010296084,0.00096293545,0.00022331008,0.0000041779567,0.00014552288,0.000029158342,0.0066322307],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.999284,0.0000029065563,0.00023267025,0.00012529812,0.00012924112,0.0002258749],"domain_scores_gemma":[0.999588,0.000003518894,0.00007661214,0.00018724319,0.00007531924,0.000069273075],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000971967,0.00013554507,0.000119735,0.000035198915,0.00004101179,0.000046744844,0.00019571345,0.00014652775,0.00004824002],"category_scores_gemma":[0.000017117078,0.000120892226,0.00007780847,0.0000681795,0.000031279298,0.000011343835,0.0000545381,0.00007615354,0.00045077704],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024972056,0.00023778046,0.054962885,0.00061068276,0.00017068426,0.0000012972159,0.0015063465,0.00008097142,0.7787638,0.0022253643,0.13795894,0.02323153],"study_design_scores_gemma":[0.002080039,0.0009040535,0.0030872554,0.00006674564,0.00003806331,0.000043787295,0.0006852296,0.009878445,0.24418879,0.0000913636,0.73806643,0.00086977263],"about_ca_topic_score_codex":0.0000061700266,"about_ca_topic_score_gemma":0.0000015471164,"teacher_disagreement_score":0.60010755,"about_ca_system_score_codex":0.000009828517,"about_ca_system_score_gemma":0.000041877913,"threshold_uncertainty_score":0.5793977},"labels":[],"label_agreement":null},{"id":"W2962028921","doi":"10.1093/bioinformatics/btz355","title":"Collaborative intra-tumor heterogeneity detection","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; Simon Fraser University","funders":"","keywords":"Computer science; Inference; Phylogenetic tree; Deconvolution; Source code; Process (computing); Data mining; Computational biology; Machine learning; Artificial intelligence; Biology; Algorithm; Genetics; Gene","score_opus":0.004623206389557855,"score_gpt":0.22304652164240288,"score_spread":0.21842331525284503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2962028921","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99038815,0.00018554137,0.003669668,0.000029101366,0.0004951032,0.00028494606,0.000066956316,0.000014270698,0.004866235],"genre_scores_gemma":[0.99611026,0.00013259027,0.0027235404,0.00066308206,0.00014566028,0.000013144927,0.000072145864,0.000013107784,0.00012647895],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994179,0.000010554823,0.00020143678,0.0001162392,0.000088372435,0.00016548499],"domain_scores_gemma":[0.9994508,0.000011060512,0.00010016915,0.00027833902,0.00009589523,0.00006371911],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000084013576,0.00011151923,0.000102484875,0.000030093439,0.000046505058,0.000040707928,0.00010690493,0.00007526792,0.000021288586],"category_scores_gemma":[0.00005472873,0.000108043445,0.00004972577,0.000094344075,0.000028804905,0.0000061585124,0.00007503789,0.00005085994,0.00018600053],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00056369364,0.0002279318,0.019998888,0.00037585566,0.00033217738,0.000005864459,0.000930263,0.0024630928,0.8994079,0.0010238459,0.015126197,0.059544295],"study_design_scores_gemma":[0.000896866,0.0006332622,0.0026545085,0.000012538432,0.000018736491,0.000023434664,0.00040628223,0.004377111,0.7655974,0.000052230404,0.22496842,0.00035918225],"about_ca_topic_score_codex":0.000005845326,"about_ca_topic_score_gemma":0.000058478552,"teacher_disagreement_score":0.20984223,"about_ca_system_score_codex":0.000026201198,"about_ca_system_score_gemma":0.00009039281,"threshold_uncertainty_score":0.44058838},"labels":[],"label_agreement":null},{"id":"W2962655813","doi":"10.1093/bioinformatics/btz337","title":"Prediction of mRNA subcellular localization using deep recurrent neural networks","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":86,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Montreal Clinical Research Institute; McGill University","funders":"Institut de Valorisation des Données","keywords":"Computational biology; Sequence (biology); Computer science; Identification (biology); RNA; Subcellular localization; Variety (cybernetics); Messenger RNA; Biology; Set (abstract data type); Deep learning; RNA-binding protein; Artificial neural network; Artificial intelligence; Gene; Genetics","score_opus":0.012123227150818776,"score_gpt":0.23152418127151167,"score_spread":0.21940095412069288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2962655813","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.51645035,0.0002149016,0.4809129,0.000007328431,0.00063824,0.00034949495,0.00001808411,0.000028346945,0.0013803965],"genre_scores_gemma":[0.98630756,0.000084200015,0.012686647,0.00011178786,0.0001271832,0.0000026766832,0.00059834245,0.000021399368,0.000060216043],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988273,0.000033706307,0.0005916753,0.00010685478,0.00021727404,0.00022321114],"domain_scores_gemma":[0.99904644,0.000010160478,0.000372779,0.00038416026,0.00012398504,0.00006249459],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023193382,0.00016322471,0.00017118857,0.00007228552,0.000055936303,0.000025757703,0.00018085937,0.00018959594,0.000031709533],"category_scores_gemma":[0.00006412285,0.00015412565,0.00008806523,0.00015406833,0.000049036604,0.000021814409,0.00011650169,0.00012737617,0.000013602436],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000079887344,0.000066357294,0.08589184,0.0005727056,0.00007807434,3.6341345e-7,0.00054803945,0.895071,0.006911257,0.000182685,0.0006111136,0.009986633],"study_design_scores_gemma":[0.00039611247,0.00025980294,0.00081845606,0.000034652858,0.000024598272,0.00001551847,0.0001277927,0.99231416,0.0028785588,0.0000050550266,0.0029838143,0.00014147432],"about_ca_topic_score_codex":0.0000056420927,"about_ca_topic_score_gemma":0.0000017752035,"teacher_disagreement_score":0.46985722,"about_ca_system_score_codex":0.000024182618,"about_ca_system_score_gemma":0.000031630563,"threshold_uncertainty_score":0.6285062},"labels":[],"label_agreement":null},{"id":"W2964417596","doi":"10.1093/bioinformatics/btz602","title":"Non-parametric individual treatment effect estimation for survival data with random forests","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Random forest; Censoring (clinical trials); Computer science; Estimation; Statistics; Parametric statistics; Population; Random effects model; Survival analysis; Average treatment effect; Machine learning; Artificial intelligence; Data mining; Mathematics; Medicine; Propensity score matching; Engineering","score_opus":0.112018737931895,"score_gpt":0.39302598033528546,"score_spread":0.2810072424033905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964417596","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1851714,0.000012751024,0.80891335,0.000016892367,0.00017987065,0.0037762127,0.0002701334,0.00031489867,0.0013445212],"genre_scores_gemma":[0.3368844,0.000010839663,0.6616674,0.000022289134,0.000053943364,0.00024568182,0.00090553425,0.000045855806,0.00016406835],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985863,0.000025097077,0.0004801307,0.00019979489,0.00037554093,0.00033315824],"domain_scores_gemma":[0.99636173,0.001982547,0.00035239634,0.0010888953,0.00013571058,0.00007872725],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007355984,0.0003041165,0.00052687887,0.00020000411,0.000073964155,0.00009599676,0.00047089832,0.00012037239,0.000016299966],"category_scores_gemma":[0.0009647264,0.0001934859,0.00006412326,0.00029850466,0.00004346644,0.0008075175,0.00013346043,0.00009099999,0.00006549839],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0078123184,0.0023698346,0.11891598,0.0136947045,0.0034959791,0.000019007644,0.0075799115,0.007511971,0.00014313118,0.070370354,0.037251245,0.73083556],"study_design_scores_gemma":[0.016943535,0.007909044,0.0023892622,0.00041563768,0.0007379927,0.000023330536,0.00028976102,0.92900187,0.007831642,0.030692903,0.0026814444,0.0010835706],"about_ca_topic_score_codex":0.000008807459,"about_ca_topic_score_gemma":0.000031663323,"teacher_disagreement_score":0.9214899,"about_ca_system_score_codex":0.000115666786,"about_ca_system_score_gemma":0.00008935427,"threshold_uncertainty_score":0.7890126},"labels":[],"label_agreement":null},{"id":"W2964526879","doi":"10.1093/bioinformatics/btz573","title":"TFEA.ChIP: a tool kit for transcription factor binding site enrichment analysis capitalizing on ChIP-seq datasets","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":55,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Child and Family Research Institute; University of British Columbia","funders":"Ministerio de Ciencia e Innovación; Fundación Caja Madrid; Comunidad de Madrid","keywords":"Chip; Transcription factor; Computer science; Computational biology; Software; Factor (programming language); Data mining; Embedded system; Biology; Gene; Genetics; Operating system; Programming language; Telecommunications","score_opus":0.009978782737267027,"score_gpt":0.23460678342288,"score_spread":0.22462800068561298,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964526879","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9855529,0.000059374197,0.00984164,0.000028427285,0.00021583802,0.00053910894,0.003479589,0.000017506733,0.00026560284],"genre_scores_gemma":[0.9753068,0.000106727406,0.009147881,0.0002705161,0.00007378801,0.000029507639,0.014662035,0.00002532815,0.00037740113],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99884117,0.000013969906,0.00042667345,0.00023322258,0.00017333151,0.00031162793],"domain_scores_gemma":[0.9991506,0.000016042957,0.00020279971,0.00051444554,0.00004108453,0.00007504502],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015094757,0.00022344972,0.00023987902,0.00014887215,0.0001010255,0.00009407807,0.0002101082,0.00015330664,0.00003597824],"category_scores_gemma":[0.000021396738,0.00020754842,0.0002462571,0.00015427034,0.000017619215,0.000016117367,0.000060273967,0.000070639355,0.00009949233],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020055588,0.00022024706,0.007948953,0.0006836283,0.0014626748,0.0000012046745,0.0015019791,0.0073880437,0.97157943,0.00055427203,0.0035415457,0.00491745],"study_design_scores_gemma":[0.0068153883,0.0031385894,0.02243844,0.00015992633,0.001967565,0.000015922402,0.0020158312,0.71551627,0.14282696,0.00012440752,0.10196604,0.0030146663],"about_ca_topic_score_codex":0.0000071264335,"about_ca_topic_score_gemma":0.000022962098,"teacher_disagreement_score":0.82875246,"about_ca_system_score_codex":0.00005215624,"about_ca_system_score_gemma":0.00003960781,"threshold_uncertainty_score":0.8463579},"labels":[],"label_agreement":null},{"id":"W2964875256","doi":"10.1093/bioinformatics/btz616","title":"MultiGuideScan: a multi-processing tool for designing CRISPR guide RNA libraries","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"CRISPR and Genetic Engineering","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"CRISPR; Cas9; RNA; Guide RNA; Computational biology; Genome; Computer science; Genome editing; Biology; Gene; Genetics","score_opus":0.015178518619465653,"score_gpt":0.29648346503472606,"score_spread":0.2813049464152604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964875256","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06936246,0.00078367285,0.92798376,0.00004282558,0.00024538347,0.00048081906,0.000022100156,0.000051313782,0.0010276779],"genre_scores_gemma":[0.3458267,0.000040264385,0.65129155,0.0003216921,0.00016101063,0.00004022621,0.000109030814,0.00004060314,0.002168944],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99902326,0.0000065533804,0.00038782245,0.00016432007,0.0001040803,0.00031396214],"domain_scores_gemma":[0.9994345,0.00002052568,0.00009679032,0.0002938999,0.00008891223,0.00006541148],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016687938,0.00018411687,0.00016134736,0.00005105963,0.00008699045,0.00010201429,0.00019961513,0.00013600243,0.000011836207],"category_scores_gemma":[0.00013653305,0.00017561382,0.000099999364,0.000067733454,0.000028741904,0.000021606616,0.000095708274,0.000058812882,0.00002559515],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011865706,0.00007495641,0.004521927,0.0013892098,0.00012730056,0.0000012784155,0.0015778971,0.009507883,0.85258883,0.00019118475,0.023437446,0.10646343],"study_design_scores_gemma":[0.001444189,0.00020123196,0.000611027,0.00008290309,0.00002927903,0.000009241661,0.0007464885,0.19955744,0.67407095,0.000014651822,0.12274331,0.00048927055],"about_ca_topic_score_codex":0.0000033740791,"about_ca_topic_score_gemma":0.0000017873817,"teacher_disagreement_score":0.2766922,"about_ca_system_score_codex":0.00001220803,"about_ca_system_score_gemma":0.00009676824,"threshold_uncertainty_score":0.71613234},"labels":[],"label_agreement":null},{"id":"W2965351431","doi":"10.1093/bioinformatics/btz593","title":"DEEPCON: protein contact prediction using dilated convolutional neural networks with dropout","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Ryerson University; University of Missouri; Nvidia; University of Missouri-St. Louis; National Science Foundation","keywords":"Computer science; Convolutional neural network; Dropout (neural networks); Artificial intelligence; Artificial neural network; Residual; Deep learning; Range (aeronautics); Machine learning; Pattern recognition (psychology); Algorithm","score_opus":0.005098687638019777,"score_gpt":0.2017933459060781,"score_spread":0.19669465826805832,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2965351431","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90576917,0.00010720819,0.09250933,0.000013714413,0.00016462531,0.00056898623,0.00003659674,0.000029631694,0.00080072216],"genre_scores_gemma":[0.990873,0.0000061441206,0.0082135135,0.0001497508,0.00013657757,0.000009476999,0.000421076,0.00001653232,0.00017395735],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992238,0.00001665978,0.0002446862,0.00013503958,0.00014755757,0.00023225755],"domain_scores_gemma":[0.999445,0.0000038006438,0.00014349223,0.00024760343,0.000093512885,0.00006658645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000709736,0.00015846707,0.0001306119,0.000030148587,0.000073196716,0.000036654033,0.00011016109,0.0001816164,0.0000221638],"category_scores_gemma":[0.000010275722,0.00012649604,0.000048113197,0.00008057778,0.000047518646,0.000018944302,0.00005818133,0.00011545128,0.000006998726],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002890371,0.00020260175,0.1908064,0.0006572579,0.0010236865,0.000019817022,0.0004833931,0.28150958,0.5062331,0.0046861283,0.001050223,0.01043745],"study_design_scores_gemma":[0.00094014907,0.0004753631,0.0017733285,0.000036706486,0.000023316708,0.00008052803,0.00006175047,0.99117804,0.003977564,0.000019961417,0.0012172238,0.00021605536],"about_ca_topic_score_codex":0.0000086460395,"about_ca_topic_score_gemma":0.0000059083595,"teacher_disagreement_score":0.70966846,"about_ca_system_score_codex":0.000028108609,"about_ca_system_score_gemma":0.00007574206,"threshold_uncertainty_score":0.51583594},"labels":[],"label_agreement":null},{"id":"W2970462530","doi":"10.1093/bioinformatics/btz671","title":"Automatic local resolution-based sharpening of cryo-EM maps","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Advanced Electron Microscopy Techniques and Applications","field":"Biochemistry, Genetics and Molecular Biology","cited_by":166,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Ministerio de Economía y Competitividad; European Commission; Comunidad de Madrid","keywords":"Sharpening; Computer science; Visualization; Artificial intelligence; Workflow; Initialization; Resolution (logic); Flexibility (engineering); Interpretability; Cryo-electron microscopy; Algorithm; Data mining; Pattern recognition (psychology); Mathematics; Physics","score_opus":0.005560192124800248,"score_gpt":0.2713040208489383,"score_spread":0.26574382872413804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970462530","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31005862,0.00014082564,0.6869552,0.000046642566,0.00003741216,0.00039113313,0.00004663239,0.000055951274,0.0022675628],"genre_scores_gemma":[0.84203875,0.000019004514,0.15715027,0.00022006748,0.000019190493,0.000022723756,0.0002492637,0.000014174473,0.00026656856],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99934185,0.0000074252566,0.0002866265,0.00009765494,0.000091490954,0.00017493365],"domain_scores_gemma":[0.9993972,0.000009472219,0.00015002106,0.0003469606,0.000059126793,0.0000371951],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008757513,0.00009874237,0.00011487955,0.000036941743,0.00003891366,0.000009911351,0.00016415048,0.00009357587,0.00005087442],"category_scores_gemma":[0.0000139216545,0.00009438706,0.000061212035,0.00009600533,0.000048955735,0.0000058102737,0.000049169324,0.00006042668,0.000048708433],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005891817,0.0001303402,0.0010485536,0.00052367867,0.00004855137,3.0392246e-7,0.00016271793,0.0055674817,0.94047445,0.0030337162,0.011906751,0.037044525],"study_design_scores_gemma":[0.00052254315,0.0003858464,0.0002244418,0.00006875747,0.000015581614,0.0000052936916,0.00022287821,0.17794687,0.7724006,0.00023143303,0.04771056,0.00026516442],"about_ca_topic_score_codex":0.0000025604468,"about_ca_topic_score_gemma":0.0000019519744,"teacher_disagreement_score":0.5319801,"about_ca_system_score_codex":0.000018869247,"about_ca_system_score_gemma":0.00007626926,"threshold_uncertainty_score":0.38489926},"labels":[],"label_agreement":null},{"id":"W2970852745","doi":"10.1093/bioinformatics/btz645","title":"DeepCOP: deep learning-based approach to predict gene regulating effects of small molecules","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Canadian Institutes of Health Research","keywords":"Deep learning; Computational biology; Computer science; Drug discovery; Artificial intelligence; Genomics; Gene expression; Gene; Gene regulatory network; Machine learning; Biology; Bioinformatics; Genetics; Genome","score_opus":0.00474345889461414,"score_gpt":0.20703925714135216,"score_spread":0.20229579824673802,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970852745","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4867091,0.00012878966,0.5006805,0.000020042116,0.00017163607,0.00085527764,0.000008319858,0.000068398025,0.01135795],"genre_scores_gemma":[0.61102796,0.0000118136295,0.38771984,0.00036924696,0.00007508037,0.000030192938,0.0003555435,0.00004685642,0.0003635111],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99834424,0.000069568174,0.0006554707,0.00021173392,0.0003176787,0.00040131365],"domain_scores_gemma":[0.9985818,0.00006467416,0.00040687792,0.0006394819,0.00014743237,0.00015970641],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00034182513,0.00029268814,0.00032480436,0.00014791556,0.00007673653,0.00004110338,0.00042390372,0.00024329573,0.000008601799],"category_scores_gemma":[0.000546193,0.00027305345,0.00014983315,0.00022848559,0.000059277994,0.000010896588,0.00023529888,0.00021761503,0.000071792245],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002286651,0.00026640197,0.028237294,0.00514508,0.00023363883,0.0000011993482,0.0021246127,0.8711361,0.07549017,0.00035054868,0.000614506,0.016171774],"study_design_scores_gemma":[0.0012401287,0.0010442331,0.0031315263,0.00011018724,0.000043563366,0.0000141305045,0.00021278048,0.8764609,0.11228821,0.0000073277497,0.0050021964,0.0004448168],"about_ca_topic_score_codex":0.0000065587774,"about_ca_topic_score_gemma":0.000001823317,"teacher_disagreement_score":0.124318846,"about_ca_system_score_codex":0.000024669444,"about_ca_system_score_gemma":0.00007934212,"threshold_uncertainty_score":0.99997216},"labels":[],"label_agreement":null},{"id":"W2971034312","doi":"10.1093/bioinformatics/btz681","title":"breakpointR: an R/Bioconductor package to localize strand state changes in Strand-seq data","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":60,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"","keywords":"Bioconductor; Computer science; DNA sequencing; Directionality; R package; Computational biology; DNA; Biology; Data mining; Genetics; Computational science; Gene","score_opus":0.02961237499436232,"score_gpt":0.26459468354524496,"score_spread":0.23498230855088265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2971034312","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9943418,0.00008527064,0.0031333542,0.00015224848,0.00030743348,0.00054794276,0.00068856805,0.000025159177,0.00071826216],"genre_scores_gemma":[0.9912378,0.00018129783,0.005356055,0.000964843,0.00013537488,0.000008099557,0.0016241374,0.000037540864,0.0004548339],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99871886,0.000032651045,0.00037438195,0.00030955212,0.00017994543,0.0003846165],"domain_scores_gemma":[0.9986565,0.000010619801,0.000077950244,0.0010129896,0.000049504444,0.00019240554],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028599854,0.00022611844,0.00024027577,0.000083829866,0.00003593491,0.000085475775,0.0005871561,0.00015376022,0.00007005471],"category_scores_gemma":[0.000026593714,0.00020549323,0.000037368874,0.00012739182,0.00004544762,0.00003594213,0.00014518216,0.00011697688,0.000092442875],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007851587,0.00043214048,0.014392596,0.0006306541,0.0001270035,0.000012416584,0.0029463072,0.00044403967,0.9358021,0.000087071974,0.0034945316,0.040845957],"study_design_scores_gemma":[0.011336452,0.0045976266,0.013023066,0.00031650782,0.00009441281,0.000076138815,0.0029218919,0.027089123,0.6906395,0.0001991454,0.2468558,0.0028503456],"about_ca_topic_score_codex":0.000092161026,"about_ca_topic_score_gemma":0.0013819797,"teacher_disagreement_score":0.24516264,"about_ca_system_score_codex":0.000016999333,"about_ca_system_score_gemma":0.000088279165,"threshold_uncertainty_score":0.83797705},"labels":[],"label_agreement":null},{"id":"W2971052755","doi":"10.1093/bioinformatics/btz673","title":"A Gaussian process-based definition reveals new and bona fide genetic interactions compared to a multiplicative model in the Gram-negative <i>Escherichia coli</i>","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan; University of Regina","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Multiplicative function; Epistasis; Computer science; Computational biology; Gene; Biology; Machine learning; Data mining; Genetics; Artificial intelligence; Mathematics","score_opus":0.01868175590371989,"score_gpt":0.26243915728513884,"score_spread":0.24375740138141894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2971052755","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9037849,0.00008016754,0.08832814,0.0009381071,0.00007043012,0.0016019897,0.00010825669,0.000018278337,0.0050697504],"genre_scores_gemma":[0.92099756,0.000021265736,0.074013814,0.004573829,0.000040473846,0.00009049302,0.00013487283,0.000014496106,0.00011319445],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989257,0.000031650598,0.00046326275,0.00016957396,0.00014099639,0.0002688107],"domain_scores_gemma":[0.99919873,0.00005167293,0.00019802115,0.00035905748,0.000069683214,0.00012285872],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017585204,0.00020256409,0.00019540206,0.00006781064,0.000081814615,0.00007886461,0.00024124396,0.000136727,0.000006080831],"category_scores_gemma":[0.000050174123,0.00015872144,0.000055502864,0.00020805205,0.000049196267,0.000019553583,0.00006707154,0.00021454503,0.00003938468],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004741888,0.0021127358,0.02697686,0.0037298265,0.0009353168,0.000012014016,0.17845637,0.4454362,0.1314842,0.0118300235,0.1398841,0.054400466],"study_design_scores_gemma":[0.0023084811,0.0003996753,0.006767439,0.00017869833,0.000042882704,0.000016431177,0.0039973245,0.9745181,0.002035286,0.0057798866,0.0033643714,0.0005913846],"about_ca_topic_score_codex":0.00002533583,"about_ca_topic_score_gemma":0.0001242823,"teacher_disagreement_score":0.52908194,"about_ca_system_score_codex":0.00002504287,"about_ca_system_score_gemma":0.00015083193,"threshold_uncertainty_score":0.64724725},"labels":[],"label_agreement":null},{"id":"W2971405760","doi":"10.1093/bioinformatics/btz699","title":"Protein–protein interaction site prediction through combining local and global features with deep neural networks","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":296,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Higher Education Discipline Innovation Project; National Natural Science Foundation of China; Fundamental Research Funds for the Central Universities; Central South University; Virginia Commonwealth University","keywords":"Computer science; Convolutional neural network; Sequence (biology); Artificial intelligence; Deep learning; Artificial neural network; Source code; Code (set theory); Protein sequencing; Sliding window protocol; Machine learning; Peptide sequence; Window (computing); Biology","score_opus":0.0047272565283904555,"score_gpt":0.20812378998873063,"score_spread":0.20339653346034017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2971405760","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.686982,0.00035793186,0.30739683,0.000076831435,0.00025571213,0.000829152,0.00002977981,0.00004368664,0.0040281024],"genre_scores_gemma":[0.990287,0.000026114929,0.008723098,0.0003483817,0.00012190589,0.000022796567,0.0003189675,0.00001633479,0.00013542006],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989852,0.000020228425,0.00035545276,0.00017353988,0.00015542688,0.00031019357],"domain_scores_gemma":[0.9993302,0.0000056479635,0.00021784382,0.00029443018,0.0000667429,0.00008511977],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012008529,0.00023023963,0.00017944915,0.000020401056,0.000109318054,0.00011380981,0.00011778562,0.0002421281,0.000008992907],"category_scores_gemma":[0.0000071272684,0.00018554773,0.000050801318,0.000102457045,0.00009773959,0.00005628607,0.00013767603,0.00020638756,0.000014213028],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006840742,0.0005614285,0.037104014,0.0026559304,0.0016778033,0.000024127732,0.006886265,0.40740344,0.019813024,0.0140832225,0.010949126,0.49200088],"study_design_scores_gemma":[0.0016854315,0.0013067039,0.0017468366,0.00012839059,0.0000376001,0.00019031689,0.0012314109,0.9866479,0.0012009802,0.00014045308,0.005249027,0.00043493923],"about_ca_topic_score_codex":0.000020980016,"about_ca_topic_score_gemma":0.000047718848,"teacher_disagreement_score":0.5792445,"about_ca_system_score_codex":0.00003439415,"about_ca_system_score_gemma":0.00002523814,"threshold_uncertainty_score":0.7566417},"labels":[],"label_agreement":null},{"id":"W2974257601","doi":"10.1093/bioinformatics/btz709","title":"Subtype-specific transcriptional regulators in breast tumors subjected to genetic and epigenetic alterations","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Human Genome Research Institute; Kreftforeningen; National Institute of General Medical Sciences; Canadian Institute for Advanced Research; National Institutes of Health; National Science Foundation","keywords":"Epigenetics; Biology; DNA methylation; Breast cancer; Transcriptional regulation; Transcription factor; Genetics; Computational biology; Gene; ENCODE; Regulation of gene expression; Gene expression; Cancer","score_opus":0.006417791607965352,"score_gpt":0.19851005491516588,"score_spread":0.19209226330720053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2974257601","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9919141,0.00037153752,0.0057209744,0.00019354104,0.00019526099,0.00050767354,0.000093916606,0.000014105742,0.0009889054],"genre_scores_gemma":[0.98627853,0.00018028634,0.012434652,0.00046744363,0.000100608166,0.000019860398,0.00023851034,0.000021523176,0.00025855473],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99880725,0.000019510473,0.0005167946,0.000189007,0.00014757515,0.00031987007],"domain_scores_gemma":[0.9993499,0.0000098518685,0.000086797125,0.00034473365,0.000055875895,0.00015283746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014576015,0.00019396542,0.00018331199,0.00013859585,0.000060895207,0.00006915384,0.00016489645,0.00014311679,0.000053877313],"category_scores_gemma":[0.000005927938,0.00019109176,0.000054123448,0.00020252819,0.000048737616,0.000013981948,0.00007280023,0.00010106216,0.000101321515],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012548711,0.0006731912,0.24755663,0.0012333215,0.0004021493,0.000019032776,0.011706712,0.02834589,0.54655087,0.017432002,0.032067835,0.11275752],"study_design_scores_gemma":[0.0035474305,0.00082391244,0.86394656,0.00022111785,0.00003317248,0.00045703215,0.0011884817,0.046270918,0.007804778,0.00069804495,0.073340744,0.001667827],"about_ca_topic_score_codex":0.000007609586,"about_ca_topic_score_gemma":0.000041434447,"teacher_disagreement_score":0.61638993,"about_ca_system_score_codex":0.000025482752,"about_ca_system_score_gemma":0.00007569701,"threshold_uncertainty_score":0.7792496},"labels":[],"label_agreement":null},{"id":"W2974534360","doi":"10.1093/bioinformatics/btv095","title":"NAIL, a software toolset for inferring, analyzing and visualizing regulatory networks","year":2015,"lang":"en","type":"erratum","venue":"Bioinformatics","topic":"Information and Cyber Security","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency","funders":"","keywords":"Computer science; Software; Visualization; Data mining; Programming language","score_opus":0.024421380029254532,"score_gpt":0.27085366004537587,"score_spread":0.24643228001612133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2974534360","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000023789116,0.0014849524,0.9743654,0.000085481384,0.008887379,0.0006030563,0.00006185804,0.00048021288,0.014007837],"genre_scores_gemma":[0.0014057491,0.0017950836,0.9387398,0.0082609225,0.0049848207,0.0003471746,0.004607169,0.00022602998,0.039633304],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976994,0.00002968213,0.00095070794,0.00024900842,0.0005054731,0.00056574127],"domain_scores_gemma":[0.9976574,0.00008923801,0.00073570426,0.00082395005,0.00041651723,0.00027715304],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009691136,0.0004132079,0.00053234416,0.00033447973,0.00032816592,0.0009639227,0.0009562971,0.00064232765,0.0000043105642],"category_scores_gemma":[0.0002574315,0.00041375682,0.00015734852,0.0003360087,0.000074491654,0.0026472986,0.0006965165,0.00060090754,0.000025486008],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000039471556,0.000010117023,0.000019443429,0.0005674208,0.000048703056,0.0000011083815,0.0031264035,0.000099808836,2.2963802e-8,0.012661641,0.92757523,0.055886127],"study_design_scores_gemma":[0.00028674142,0.00005310959,0.00006837091,0.00019677571,0.000022912354,0.000016963291,0.00009955523,0.4789629,0.0000011653361,0.000514479,0.5193816,0.00039545435],"about_ca_topic_score_codex":0.000008744753,"about_ca_topic_score_gemma":0.00001684393,"teacher_disagreement_score":0.4788631,"about_ca_system_score_codex":0.00015767402,"about_ca_system_score_gemma":0.0005120311,"threshold_uncertainty_score":0.99983144},"labels":[],"label_agreement":null},{"id":"W2978380288","doi":"10.1093/bioinformatics/btz743","title":"Fast and flexible coarse-grained prediction of protein folding routes using ensemble modeling and evolutionary sequence variation","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Leverage (statistics); Protein folding; Folding (DSP implementation); Data mining; Machine learning; Chemistry","score_opus":0.015492938426154098,"score_gpt":0.23175904906454817,"score_spread":0.21626611063839407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2978380288","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7831717,0.00020254329,0.21608417,0.000007921931,0.00003810718,0.0002744626,0.00003598499,0.000010369708,0.00017472423],"genre_scores_gemma":[0.90734875,0.00004457919,0.09243551,0.000019125879,0.000029893348,0.0000042416095,0.00007266442,0.0000069115927,0.00003834998],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99945515,0.000011234306,0.00022602855,0.00010500236,0.00009225057,0.000110307556],"domain_scores_gemma":[0.9996442,0.000004254599,0.000115237846,0.00013322405,0.00007137588,0.000031691998],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011193124,0.0000903811,0.00010023563,0.00004362754,0.000056295736,0.000018558729,0.000043918983,0.0001113832,0.0000011195787],"category_scores_gemma":[0.000030391482,0.00008657339,0.000019778992,0.000054359207,0.000030241079,0.00003006734,0.00007241545,0.000043055275,4.2136088e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041273437,0.000007377973,0.0014870857,0.00023752704,0.000026281861,1.2201441e-7,0.00030482744,0.018454159,0.97558266,0.00085687474,0.0000040387704,0.0029977495],"study_design_scores_gemma":[0.00031050332,0.00013337005,0.00025059583,0.00005906881,0.000013931362,0.000020014926,0.0001566283,0.9817968,0.016334174,0.00081027084,0.000025594529,0.00008905835],"about_ca_topic_score_codex":0.000024042587,"about_ca_topic_score_gemma":0.0000014151557,"teacher_disagreement_score":0.9633426,"about_ca_system_score_codex":0.000014908208,"about_ca_system_score_gemma":0.000053589578,"threshold_uncertainty_score":0.35303605},"labels":[],"label_agreement":null},{"id":"W2979095428","doi":"10.1093/bioinformatics/btz716","title":"VikNGS: a C++ variant integration kit for next generation sequencing association analysis","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; SickKids Foundation; Hospital for Sick Children","funders":"Wellcome Trust; Genome Canada","keywords":"Computer science; Spurious relationship; Data mining; Covariate; Software; R package; Graphical user interface; Genetic association; Visualization; Association test; Sample size determination; Computational biology; Genotype; Statistics; Biology; Machine learning; Operating system; Genetics; Single-nucleotide polymorphism; Computational science; Mathematics","score_opus":0.03261885538734776,"score_gpt":0.26305040613424846,"score_spread":0.2304315507469007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2979095428","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6399962,0.000051873685,0.3573308,0.00024884247,0.0003260167,0.00045482337,0.000073480114,0.000017775134,0.001500216],"genre_scores_gemma":[0.93589973,0.000069692775,0.059246212,0.000726694,0.0002607457,0.00005213998,0.0024791614,0.0000116304045,0.0012539832],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99899244,0.00004956543,0.00044112187,0.00016458835,0.0001202969,0.00023199622],"domain_scores_gemma":[0.99904597,0.000047225996,0.00038219488,0.00024961398,0.00023096381,0.000044022396],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007342593,0.0001219907,0.00021253014,0.00010387375,0.000091267066,0.000059404705,0.00010279286,0.00025237678,0.000029282055],"category_scores_gemma":[0.00047447986,0.000113551665,0.00018260536,0.00021360663,0.000007939086,0.000017274884,0.000032758788,0.00005514479,0.000047349695],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000097432385,0.00013577458,0.09752575,0.00015878188,0.0038540761,5.077523e-7,0.0028303524,0.042727225,0.77451813,0.0033551403,0.04847061,0.026326217],"study_design_scores_gemma":[0.0006908806,0.00031500458,0.008208641,0.000007447077,0.00044069925,0.0000030558538,0.0009460221,0.96585965,0.007585815,0.00015163858,0.015459849,0.0003313004],"about_ca_topic_score_codex":0.00003352275,"about_ca_topic_score_gemma":0.00011667376,"teacher_disagreement_score":0.9231324,"about_ca_system_score_codex":0.00016890251,"about_ca_system_score_gemma":0.00009785962,"threshold_uncertainty_score":0.46305025},"labels":[],"label_agreement":null},{"id":"W2979820532","doi":"10.1093/bioinformatics/btz744","title":"Soft windowing application to improve analysis of high-throughput phenotyping data","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; Mount Sinai Hospital; University of Manitoba; Toronto Centre for Phenogenomics; Hospital for Sick Children","funders":"Deutsches Zentrum für Diabetesforschung; National Human Genome Research Institute; National Institutes of Health; Agence Nationale de la Recherche; European Molecular Biology Laboratory","keywords":"Computer science; Throughput; Software; Data mining; Computational biology; Programming language; Biology; Operating system","score_opus":0.015526743440320546,"score_gpt":0.27634203815419134,"score_spread":0.26081529471387077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2979820532","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46590447,0.00012548508,0.53247786,0.00014520067,0.00018520617,0.00027457322,0.00019168819,0.000027608661,0.00066788745],"genre_scores_gemma":[0.9464256,0.000016849875,0.05204468,0.0003556988,0.00006285827,0.0000064043375,0.00097354397,0.00000766793,0.000106704734],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99916095,0.000010251229,0.0003231131,0.00019959609,0.00014095164,0.00016513973],"domain_scores_gemma":[0.9987683,0.000023156057,0.00014222525,0.00095654774,0.000053743195,0.00005599363],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023938216,0.00009690555,0.0002191183,0.00009241953,0.0000281799,0.000014539496,0.00044434457,0.00012518199,0.0000106543675],"category_scores_gemma":[0.00014006004,0.00008398594,0.000057164903,0.00033260952,0.00004086887,0.00000822417,0.00038853724,0.00004799163,0.000042745414],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000114474075,0.00010379409,0.008864442,0.000295224,0.0016492937,3.0529876e-7,0.0008261501,0.0024807018,0.19694027,0.0004630624,0.0035152058,0.78474706],"study_design_scores_gemma":[0.0021653904,0.0010336053,0.03011095,0.00010713488,0.0016353007,0.0000046401688,0.0028027017,0.61987466,0.105903365,0.00017089672,0.23488732,0.0013040706],"about_ca_topic_score_codex":0.000045186123,"about_ca_topic_score_gemma":0.000017182027,"teacher_disagreement_score":0.783443,"about_ca_system_score_codex":0.000008715485,"about_ca_system_score_gemma":0.000040978084,"threshold_uncertainty_score":0.34248474},"labels":[],"label_agreement":null},{"id":"W2982906277","doi":"10.1093/bioinformatics/btz824","title":"<tt>MDiNE</tt> : a model to estimate differential co-occurrence networks in microbiome studies","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":60,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; HEC Montréal; Jewish General Hospital","funders":"Canadian Institutes of Health Research","keywords":"Covariate; Microbiome; Computer science; Multinomial distribution; Mixture model; Gaussian; Data mining; Statistics; Artificial intelligence; Machine learning; Mathematics; Biology; Bioinformatics","score_opus":0.02227945325592585,"score_gpt":0.33256682864261705,"score_spread":0.3102873753866912,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2982906277","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9867111,0.00029067267,0.011445074,0.00012241521,0.00034236,0.0005214741,0.00017219689,0.00002138566,0.00037336358],"genre_scores_gemma":[0.9897624,0.0002826041,0.008077416,0.0007731434,0.00007061096,0.000019341807,0.0005891691,0.000016819842,0.0004084441],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987919,0.000016718872,0.00043881047,0.00021180711,0.00008735196,0.00045342214],"domain_scores_gemma":[0.9993432,0.00001021098,0.00011070407,0.00035262588,0.00006990123,0.00011333415],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014362903,0.00022030645,0.0002823035,0.0001008633,0.00005785926,0.00003581614,0.00024087513,0.00016412583,0.000013541706],"category_scores_gemma":[0.000025470734,0.00019542471,0.00006681792,0.00013601546,0.00004535514,0.000010185147,0.00020245876,0.00013078016,0.000117223906],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049809564,0.00042602624,0.018843094,0.001830258,0.00026567472,0.0000059992644,0.0049432255,0.076596774,0.784845,0.00043325842,0.104929335,0.0063832477],"study_design_scores_gemma":[0.0070926934,0.002022277,0.015529125,0.00089160906,0.000109451474,0.00010042892,0.0015849529,0.8748296,0.04693757,0.00011167155,0.047792014,0.0029986354],"about_ca_topic_score_codex":0.000004288884,"about_ca_topic_score_gemma":0.000033546345,"teacher_disagreement_score":0.7982328,"about_ca_system_score_codex":0.000041243293,"about_ca_system_score_gemma":0.00009727799,"threshold_uncertainty_score":0.79691887},"labels":[],"label_agreement":null},{"id":"W2987116017","doi":"10.1093/bioinformatics/btz834","title":"DiscoRhythm: an easy-to-use web application and R package for discovering rhythmicity","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Circadian rhythm and melatonin","field":"Neuroscience","cited_by":67,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Addiction and Mental Health","funders":"Canadian Institutes of Health Research; National Institute of Mental Health; Krembil Foundation","keywords":"Computer science; R package; World Wide Web; Software package; Web application; Software; Data science; Programming language","score_opus":0.023196733752914162,"score_gpt":0.2569678781145153,"score_spread":0.23377114436160115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2987116017","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9412842,0.0000073297756,0.056352966,0.00009800345,0.00018929694,0.0010559801,0.00017929527,0.00008617274,0.00074677984],"genre_scores_gemma":[0.99185973,0.000020198426,0.006729615,0.0007682706,0.000066631525,0.00005815563,0.000017035227,0.000021733413,0.00045863885],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99908423,0.000012700456,0.00025776835,0.00021875754,0.00015167674,0.0002748726],"domain_scores_gemma":[0.9991462,0.00012903432,0.0001013614,0.00041441317,0.000019400817,0.00018956725],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011509289,0.00014227218,0.000158155,0.0000826046,0.000110659166,0.00017921283,0.000107739805,0.000059388964,0.0000056587733],"category_scores_gemma":[0.00014792503,0.00012758665,0.000040391576,0.0001544845,0.00003961214,0.0011542247,0.00007557367,0.00007592013,0.00020289447],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021311971,0.00014477728,0.016395532,0.0008147402,0.000012989899,0.0000049969017,0.006211305,0.00034263954,0.63721627,0.28422785,0.00045210673,0.05396367],"study_design_scores_gemma":[0.002737909,0.00064238685,0.044747192,0.00015529402,0.000040598592,0.0002475659,0.0009118756,0.4220135,0.4086299,0.00088691147,0.117640756,0.0013461054],"about_ca_topic_score_codex":0.0000063870275,"about_ca_topic_score_gemma":0.000008493764,"teacher_disagreement_score":0.42167085,"about_ca_system_score_codex":0.000033387263,"about_ca_system_score_gemma":0.00003580267,"threshold_uncertainty_score":0.5202832},"labels":[],"label_agreement":null},{"id":"W2989634691","doi":"10.1093/bioinformatics/btaa500","title":"iSOM-GSN: an integrative approach for transforming multi-omic data into gene similarity networks via self-organizing maps","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Dimensionality reduction; Convolutional neural network; Graph; Euclidean distance; Visualization; Grid; Similarity (geometry); Artificial intelligence; Data mining; Pattern recognition (psychology); Theoretical computer science; Mathematics; Image (mathematics)","score_opus":0.029755114328808348,"score_gpt":0.2581663139303418,"score_spread":0.22841119960153344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2989634691","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0054878816,0.0005268738,0.991931,0.00017880209,0.00017491053,0.0010357528,0.0002786206,0.00008825276,0.00029787055],"genre_scores_gemma":[0.22908026,0.0004581597,0.7537576,0.0031995012,0.0008193208,0.000046520887,0.01253687,0.00007916371,0.000022594995],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980034,0.00003779671,0.00083105353,0.000433394,0.00016786471,0.00052648585],"domain_scores_gemma":[0.9983097,0.000022947968,0.0002911746,0.0009016524,0.00013341945,0.0003411079],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00041800214,0.00043159508,0.00040521202,0.000044809385,0.00031217,0.00014416272,0.0011146654,0.00044788353,0.00000491546],"category_scores_gemma":[0.000060630533,0.00038446326,0.00013803295,0.00017500402,0.00009116224,0.000095374206,0.00045676282,0.00032300537,0.000008163599],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028085771,0.0031032932,0.0016559263,0.007110833,0.005165156,0.0000148334475,0.12831795,0.0926051,0.1590819,0.0021470254,0.12323565,0.47475374],"study_design_scores_gemma":[0.0012500192,0.00040320642,0.0000128791235,0.000014732095,0.000095981035,0.000014300383,0.0020044015,0.971212,0.0054224418,0.000042235508,0.018987741,0.00054003095],"about_ca_topic_score_codex":0.000013060478,"about_ca_topic_score_gemma":0.000028912329,"teacher_disagreement_score":0.8786069,"about_ca_system_score_codex":0.00004004157,"about_ca_system_score_gemma":0.0001412374,"threshold_uncertainty_score":0.9998607},"labels":[],"label_agreement":null},{"id":"W2990665925","doi":"10.1093/bioinformatics/btz875","title":"Easy-HLA: a validated web application suite to reveal the full details of HLA typing","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"vaccines and immunoinformatics approaches","field":"Biochemistry, Genetics and Molecular Biology","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University and Génome Québec Innovation Centre","funders":"Institut National de la Santé et de la Recherche Médicale; Agence Nationale de la Recherche; National Institute of Allergy and Infectious Diseases; European Commission","keywords":"Suite; Human leukocyte antigen; Typing; Computer science; Web application; World Wide Web; Biology; Genetics; Antigen; Speech recognition; Geography","score_opus":0.010953251528008443,"score_gpt":0.22960791220949608,"score_spread":0.21865466068148764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990665925","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98034316,0.00015869676,0.011169769,0.00020163514,0.0001286467,0.00095302897,0.000041605163,0.000020534031,0.006982923],"genre_scores_gemma":[0.9906795,0.0000496177,0.007976452,0.00040621887,0.00006149285,0.0000342004,0.00020442941,0.000017878387,0.0005701903],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989767,0.000017915156,0.0005342842,0.00010690123,0.00014005488,0.0002241566],"domain_scores_gemma":[0.998871,0.00001577415,0.00026134416,0.00066296355,0.00013074833,0.00005816256],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003565812,0.00015656905,0.00018090566,0.00005398138,0.00006397934,0.000043093052,0.0003853004,0.00011804111,0.000011375744],"category_scores_gemma":[0.000058230013,0.00011122731,0.0000930126,0.00020108926,0.000025361922,0.000017476257,0.00020880546,0.00008190296,0.00019609566],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026600188,0.000098872755,0.0038475448,0.0007204658,0.00023205362,1.1813625e-7,0.0014461655,0.0012346965,0.9633035,0.0016550049,0.008200456,0.018995091],"study_design_scores_gemma":[0.0034521047,0.0018159531,0.009317642,0.00023752636,0.0001880401,0.00010147088,0.005406238,0.16815586,0.40316457,0.00018001578,0.4064614,0.0015191825],"about_ca_topic_score_codex":0.0000071071013,"about_ca_topic_score_gemma":0.0000053667172,"teacher_disagreement_score":0.56013894,"about_ca_system_score_codex":0.000013420645,"about_ca_system_score_gemma":0.00007426541,"threshold_uncertainty_score":0.4535718},"labels":[],"label_agreement":null},{"id":"W2991026871","doi":"10.1093/bioinformatics/btz881","title":"SimRVSequences: an R package to simulate genetic sequence data for pedigrees","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Statistical Sciences Institute; Canadian Institutes of Health Research","keywords":"Pedigree chart; R package; Sequence (biology); Computer science; Sample (material); Data mining; Computational biology; Genetics; Biology; Programming language; Gene","score_opus":0.0579715405356776,"score_gpt":0.33166235434410263,"score_spread":0.273690813808425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2991026871","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9233523,0.0000835289,0.07421529,0.00020418545,0.00026978806,0.00071481057,0.00064435066,0.000023500603,0.00049224054],"genre_scores_gemma":[0.77041996,0.00006833224,0.22539036,0.0015152638,0.00021785249,0.000026850765,0.0018731748,0.000022514101,0.00046567142],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99878126,0.000035225617,0.00039962877,0.00030844242,0.000112342605,0.00036311048],"domain_scores_gemma":[0.9982842,0.000047637463,0.00014556115,0.0012593572,0.00011634923,0.00014688363],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040489057,0.00016120146,0.0001973324,0.000042693002,0.00006996531,0.00003923261,0.00072152494,0.00016428051,0.000021886268],"category_scores_gemma":[0.0003681246,0.00014550533,0.00004980415,0.00008415786,0.000037342506,0.000017796548,0.00027959677,0.000047540336,0.00011678961],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004618587,0.00048336454,0.2578002,0.001087011,0.0007518486,0.000006685833,0.0033861264,0.088172205,0.40096304,0.0013049911,0.0816677,0.16391496],"study_design_scores_gemma":[0.002216225,0.0035068474,0.030069668,0.00006201685,0.00013694164,0.000042764706,0.0017482927,0.6250986,0.0060396492,0.0009772762,0.32836074,0.0017409745],"about_ca_topic_score_codex":0.000019223595,"about_ca_topic_score_gemma":0.000035752473,"teacher_disagreement_score":0.5369264,"about_ca_system_score_codex":0.000016299924,"about_ca_system_score_gemma":0.00011750021,"threshold_uncertainty_score":0.5933535},"labels":[],"label_agreement":null},{"id":"W2992956341","doi":"10.1093/bioinformatics/btz902","title":"Fusion-Bloom: fusion detection in assembled transcriptomes","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Canada's Michael Smith Genome Sciences Centre","funders":"National Human Genome Research Institute; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Fusion; Computer science; Bloom; Bloom filter; Computational biology; Transcriptome; Artificial intelligence; Biology; Algorithm; Genetics; Gene expression; Gene","score_opus":0.00669476493309633,"score_gpt":0.21643492601708136,"score_spread":0.20974016108398502,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2992956341","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9776119,0.00020476546,0.00873602,0.00005857044,0.0005852865,0.00045845695,0.000008370272,0.000025498844,0.0123111075],"genre_scores_gemma":[0.99591875,0.0002506243,0.0026200626,0.00039681472,0.00009927993,0.0000126352215,0.000090558155,0.000017973896,0.00059331243],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988538,0.000019496692,0.0004974795,0.00014512333,0.00016518393,0.00031894323],"domain_scores_gemma":[0.99935806,0.000010967788,0.00013579389,0.00037081924,0.00004667843,0.00007771005],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002903686,0.00018585601,0.00018929997,0.000113397655,0.000056851466,0.000045859186,0.00019922742,0.00026495708,0.000059840644],"category_scores_gemma":[0.000015873029,0.00016799223,0.00009897186,0.00017506353,0.000018951361,0.000019933943,0.000088345994,0.00015011775,0.0002026554],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003864162,0.00020184551,0.008279842,0.00051979773,0.000097452925,0.0000030002873,0.001806316,0.0015983887,0.7613768,0.00039674056,0.0034877916,0.22184563],"study_design_scores_gemma":[0.010534452,0.0021646481,0.026266437,0.00034501203,0.00008352718,0.0001353345,0.0037751137,0.40439025,0.28228977,0.00088424864,0.26657405,0.0025571669],"about_ca_topic_score_codex":0.000013936604,"about_ca_topic_score_gemma":0.000076093515,"teacher_disagreement_score":0.479087,"about_ca_system_score_codex":0.000027587292,"about_ca_system_score_gemma":0.00005335483,"threshold_uncertainty_score":0.6850524},"labels":[],"label_agreement":null},{"id":"W2996887063","doi":"10.1093/bioinformatics/btz918","title":"MLDSP-GUI: an alignment-free standalone tool with an interactive graphical user interface for DNA sequence comparison and analysis","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Fractal and DNA sequence analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Graphical user interface; Executable; Computer science; Graphical user interface testing; Software; User interface; Open source; Source code; Data mining; Programming language; Python (programming language); User interface design","score_opus":0.013248105958841972,"score_gpt":0.2835636738212264,"score_spread":0.2703155678623844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996887063","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9478461,0.000049568633,0.051366583,0.00006885219,0.00003096884,0.00029084232,0.00018176963,0.000017458015,0.00014787015],"genre_scores_gemma":[0.97853255,0.000037927504,0.02032364,0.00022895103,0.00003021446,0.000019713176,0.00065622834,0.000014125123,0.00015663903],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99886525,0.00003137192,0.00036304555,0.00028593684,0.00020106789,0.0002533365],"domain_scores_gemma":[0.9988233,0.000022712833,0.00019975769,0.0006690634,0.00015066634,0.00013449129],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001863118,0.00021200354,0.00033871632,0.00012514327,0.00007653172,0.000113877235,0.00030365336,0.00013168805,0.000024253273],"category_scores_gemma":[0.00003993386,0.00016242337,0.00011023409,0.00025491806,0.00011797988,0.00009619946,0.000119455726,0.000088636974,0.0000054175207],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00858476,0.0017122136,0.44159117,0.00082622655,0.011200937,0.000012653677,0.010204913,0.008689757,0.4846409,0.0024925454,0.002701337,0.027342604],"study_design_scores_gemma":[0.0070020147,0.017534642,0.023038268,0.00014667523,0.0034475569,0.00006324728,0.019532511,0.55354637,0.3536811,0.0007323799,0.018551396,0.0027238168],"about_ca_topic_score_codex":0.000046828998,"about_ca_topic_score_gemma":0.00028556425,"teacher_disagreement_score":0.54485667,"about_ca_system_score_codex":0.00002405184,"about_ca_system_score_gemma":0.000042938686,"threshold_uncertainty_score":0.66234326},"labels":[],"label_agreement":null},{"id":"W2997453389","doi":"10.1093/bioinformatics/btz951","title":"Multi-omics reveals functional genomic and metabolic mechanisms of milk production and quality in dairy cows","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Ruminant Nutrition and Digestive Physiology","field":"Agricultural and Biological Sciences","cited_by":55,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Metabolomics; Biology; Biotechnology; Ruminant; Rumen; Omics; Metagenomics; Microbiome; Forage; Metabolome; Food science; Crop; Biochemistry; Agronomy; Bioinformatics; Fermentation; Gene","score_opus":0.043010523610600586,"score_gpt":0.24695242706680479,"score_spread":0.2039419034562042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997453389","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9991566,0.00014783678,0.00004257996,0.00019289424,0.00009695747,0.00022632064,0.000041762163,0.000009657561,0.000085376465],"genre_scores_gemma":[0.9969427,0.00025133125,0.0025254495,0.00011838228,0.00002331084,0.000004782378,0.00004590318,4.1964822e-7,0.000087693814],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99942696,0.000035818084,0.0002735872,0.00009940723,0.00006568793,0.000098540455],"domain_scores_gemma":[0.9997102,0.000059242495,0.00012466003,0.00003458684,0.00003841092,0.00003291301],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024739257,0.00007041254,0.00017794661,0.000018666855,0.00003434282,0.000009552571,0.000039061382,0.000057924644,0.00002385048],"category_scores_gemma":[0.0000535655,0.000031352447,0.000021716834,0.000091265065,0.00005088166,0.00012764713,0.00004243104,0.000047537997,0.000010644163],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005461241,0.0000624351,0.035597883,0.00006649716,0.0000054702136,5.5552935e-8,0.00013005635,0.0000058659907,0.9559306,0.004921918,0.00004831102,0.0031762838],"study_design_scores_gemma":[0.00024909683,0.00008041679,0.98981655,0.000016260481,0.000003884212,0.000004285412,0.0005188893,0.0005591957,0.007036305,0.0013174675,0.00031280486,0.00008487646],"about_ca_topic_score_codex":0.00004189641,"about_ca_topic_score_gemma":0.00004716816,"teacher_disagreement_score":0.9542186,"about_ca_system_score_codex":0.0000067897104,"about_ca_system_score_gemma":0.0000045447355,"threshold_uncertainty_score":0.12785158},"labels":[],"label_agreement":null},{"id":"W2998529923","doi":"10.1093/bioinformatics/btaa039","title":"<tt>incaRNAfbinv 2.0</tt>: a webserver and software with motif control for fragment-based design of RNAs","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université du Québec à Montréal","funders":"College of Natural Resources and Sciences, Humboldt State University; Centre National de la Recherche Scientifique; Ministry of Science and Technology","keywords":"Computer science; Web server; Fragment (logic); Software; Motif (music); Computational biology; Operating system; World Wide Web; Biology; Programming language; The Internet; Art","score_opus":0.01839855060877201,"score_gpt":0.21210891677918414,"score_spread":0.19371036617041212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2998529923","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031042144,0.000253191,0.967492,0.00026429057,0.000026301374,0.0007624112,0.00010079753,0.000017332892,0.000041517495],"genre_scores_gemma":[0.6969358,0.00005012596,0.30101445,0.0016764265,0.00007553121,0.00009356009,0.000071301,0.000032302047,0.00005051011],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99924666,0.000029654242,0.00027241817,0.00013628668,0.0001318464,0.00018311325],"domain_scores_gemma":[0.9993633,0.000050052968,0.00018356917,0.00019593659,0.00009546829,0.00011167082],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016657975,0.00016018676,0.00021494676,0.00002180597,0.000055684057,0.000024492858,0.00014254988,0.00012337105,0.000010876551],"category_scores_gemma":[0.00014204286,0.00012591448,0.000063119274,0.00004949175,0.00005489532,0.000008796894,0.000029495795,0.00003715772,0.0000031896586],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0048117284,0.00020570456,0.0026973265,0.0027166738,0.00073863205,0.0000057288594,0.0009395819,0.010523936,0.93130773,0.0007659222,0.006036131,0.03925091],"study_design_scores_gemma":[0.0046787765,0.003337873,0.00012016798,0.000094418094,0.00013385808,0.0000056912518,0.0002380812,0.048422776,0.9329779,0.00012506434,0.009448314,0.00041708845],"about_ca_topic_score_codex":0.0000023220819,"about_ca_topic_score_gemma":0.0000010742706,"teacher_disagreement_score":0.66647756,"about_ca_system_score_codex":0.0000047381727,"about_ca_system_score_gemma":0.00009590713,"threshold_uncertainty_score":0.51346433},"labels":[],"label_agreement":null},{"id":"W2999299543","doi":"10.1093/bioinformatics/btaa024","title":"Nearest-neighbor Projected-Distance Regression (NPDR) for detecting network interactions with adjustments for multiple tests and confounding","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"National Institute of General Medical Sciences; National Institutes of Health","keywords":"Covariate; Feature selection; Computer science; Spurious relationship; Regression; Feature (linguistics); Artificial intelligence; Inference; Machine learning; k-nearest neighbors algorithm; Confounding; Multiple comparisons problem; Data mining; Statistics; Mathematics","score_opus":0.03123330608107756,"score_gpt":0.3010418191188315,"score_spread":0.26980851303775394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2999299543","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5927946,0.00024341124,0.4045704,0.0004693295,0.00019715817,0.001349436,0.00009237672,0.000036129295,0.00024718122],"genre_scores_gemma":[0.80881065,0.000038285656,0.18990627,0.00051604025,0.00028165823,0.00016732015,0.00018093694,0.000018283523,0.000080567326],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992267,0.000018455245,0.000282835,0.00016224523,0.000050242215,0.0002595466],"domain_scores_gemma":[0.99926317,0.00016390345,0.00024673398,0.00011824327,0.00012369697,0.00008424783],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014232799,0.00013210064,0.00016418185,0.00001613101,0.0002518434,0.00003122948,0.00007445303,0.00009161352,0.0000014522274],"category_scores_gemma":[0.0008183065,0.000104361665,0.000044462096,0.00007083456,0.00003620031,0.000010681935,0.000049677463,0.000058199024,9.611351e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0037022615,0.0002253289,0.7487979,0.0021189018,0.0011354141,0.0000024700835,0.0058809873,0.010096504,0.042812154,0.001099358,0.08475584,0.099372864],"study_design_scores_gemma":[0.006414655,0.0033924275,0.043452844,0.00031501573,0.00021962423,0.00003565945,0.0031549248,0.67804706,0.0072365953,0.00019626663,0.25657204,0.0009629052],"about_ca_topic_score_codex":0.000003519581,"about_ca_topic_score_gemma":0.000088490335,"teacher_disagreement_score":0.7053451,"about_ca_system_score_codex":0.00001696265,"about_ca_system_score_gemma":0.000054069136,"threshold_uncertainty_score":0.4255745},"labels":[],"label_agreement":null},{"id":"W3001892728","doi":"10.1093/bioinformatics/btaa001","title":"GSOAP: a tool for visualization of gene set over-representation analysis","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Krembil Foundation","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation; Cummings Foundation","keywords":"Visualization; Representation (politics); Set (abstract data type); Computer science; Computational biology; Artificial intelligence; Biology; Programming language","score_opus":0.01917918027975292,"score_gpt":0.2852849429940011,"score_spread":0.2661057627142482,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3001892728","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13391024,0.00007424297,0.8648632,0.00009431307,0.00006492242,0.00038295094,0.0002100163,0.00001367238,0.00038642986],"genre_scores_gemma":[0.95402056,0.00009121889,0.04137982,0.0010561286,0.00020526098,0.000024911644,0.0031347058,0.000016919148,0.00007044438],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990798,0.000011428165,0.0005210613,0.00010685541,0.00012922465,0.00015162514],"domain_scores_gemma":[0.9992842,0.000015897998,0.0002962212,0.0002172319,0.00012086381,0.00006558027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012924155,0.000116761104,0.00020299567,0.00006061406,0.000045652258,0.00002821632,0.0001423088,0.00012060736,0.000017451262],"category_scores_gemma":[0.00007939209,0.00011222523,0.00019242131,0.00033021878,0.000031163883,0.000012952337,0.000053530202,0.000028368318,0.0000047374065],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026769883,0.0004975063,0.07016036,0.003981857,0.012209984,0.0000021171309,0.024177575,0.15202804,0.42135584,0.012656635,0.2051596,0.095093496],"study_design_scores_gemma":[0.001385404,0.00049227296,0.0021109153,0.000008784432,0.000538805,0.0000017736455,0.0004967825,0.9009891,0.07624745,0.00009799117,0.017263073,0.00036761796],"about_ca_topic_score_codex":0.000003426308,"about_ca_topic_score_gemma":0.0000031051054,"teacher_disagreement_score":0.8234834,"about_ca_system_score_codex":0.0000071274417,"about_ca_system_score_gemma":0.000042415362,"threshold_uncertainty_score":0.4576412},"labels":[],"label_agreement":null},{"id":"W3002103667","doi":"10.1093/bioinformatics/btaa043","title":"Transfer index, NetUniFrac and some useful shortest path-based distances for community analysis in sequence similarity networks","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Phylogenetic tree; Phylogenetic network; Similarity (geometry); Horizontal gene transfer; UniFrac; Biology; Evolutionary biology; Phylogenetics; Tree (set theory); Genome; Computational biology; Artificial intelligence; Gene; Genetics; Computer science; Mathematics","score_opus":0.03580043274894369,"score_gpt":0.25190005433598767,"score_spread":0.216099621587044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3002103667","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93074906,0.00069534563,0.06771091,0.0002747466,0.00002912393,0.0002631764,0.00022860627,0.000005058171,0.000043971457],"genre_scores_gemma":[0.9956788,0.00034261667,0.0020166016,0.0016628592,0.00005023495,0.000023432513,0.00021387651,0.000008892026,0.0000026897596],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99923486,0.000041288262,0.00031263646,0.00013027532,0.00007053367,0.00021042257],"domain_scores_gemma":[0.99953526,0.000053005897,0.000050830284,0.00022018037,0.000048350557,0.00009237533],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020915529,0.00015609644,0.00024828748,0.000035090132,0.00013475127,0.00003620137,0.00017616813,0.00012071356,0.0000016644241],"category_scores_gemma":[0.000048148933,0.00014669204,0.00009781518,0.00017069244,0.00011291627,0.000004918941,0.00006578258,0.00013271409,2.425258e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00059068704,0.00025705047,0.78015435,0.0005321683,0.0011154625,0.0000036037459,0.0033163296,0.18591864,0.017647829,0.00052642776,0.0006124352,0.009325046],"study_design_scores_gemma":[0.0016755464,0.00073225494,0.1336681,0.000021930384,0.0003321206,0.0000010808548,0.001690373,0.85046256,0.0031777069,0.00016293868,0.0074335807,0.0006418385],"about_ca_topic_score_codex":0.00004393781,"about_ca_topic_score_gemma":0.00041722303,"teacher_disagreement_score":0.66454387,"about_ca_system_score_codex":0.000008982501,"about_ca_system_score_gemma":0.00004127708,"threshold_uncertainty_score":0.59819275},"labels":[],"label_agreement":null},{"id":"W3003794061","doi":"10.1093/bioinformatics/btaa049","title":"CoMeBack: DNA methylation array data analysis for co-methylated regions","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Epigenetics and DNA Methylation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":75,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Children's Hospital; Pacific Centre for Reproductive Medicine; Simon Fraser University; University of British Columbia","funders":"Canadian Institutes of Health Research","keywords":"DNA methylation; Methylation; DNA; Computational biology; Methylated DNA immunoprecipitation; Genetics; Biology; Computer science; Gene; Gene expression","score_opus":0.07130694085583668,"score_gpt":0.32100795630313245,"score_spread":0.24970101544729578,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3003794061","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032474063,0.0004346682,0.96325105,0.000778186,0.00008283537,0.00043617113,0.0010573085,0.000037101297,0.0014486361],"genre_scores_gemma":[0.8874773,0.000350562,0.091463506,0.000758804,0.00031911532,0.000020547059,0.01943196,0.00003261973,0.00014561118],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99880815,0.000041540497,0.0004768405,0.00027986843,0.00017434706,0.00021926504],"domain_scores_gemma":[0.99866354,0.00004894639,0.00024426566,0.00075274083,0.00013589927,0.00015463027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038256333,0.00016670943,0.00023592843,0.00009068057,0.00012352939,0.00004620833,0.0004106304,0.00017768308,0.000017116576],"category_scores_gemma":[0.0004028602,0.00016030663,0.00014603966,0.0004418851,0.000047431666,0.000019367484,0.0001020402,0.00006856908,0.000014714716],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029749237,0.00014040031,0.0058334004,0.0003126485,0.002774373,0.0000010001954,0.0012498588,0.007228387,0.94830346,0.0012182875,0.019341735,0.013298956],"study_design_scores_gemma":[0.0012955759,0.0005361706,0.0017687934,0.0000081811495,0.00087280467,8.08266e-7,0.00044163066,0.24553953,0.48363966,0.000475467,0.26478764,0.00063373125],"about_ca_topic_score_codex":0.0000034555853,"about_ca_topic_score_gemma":0.00001268949,"teacher_disagreement_score":0.87178755,"about_ca_system_score_codex":0.000009887723,"about_ca_system_score_gemma":0.00006815364,"threshold_uncertainty_score":0.6537115},"labels":[],"label_agreement":null},{"id":"W3006429100","doi":"10.1093/bioinformatics/btaa104","title":"Michela<scp>Ngl</scp>o: sculpting protein views on web pages without coding","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Eshelman Institute for Innovation, University of North Carolina at Chapel Hill; National Institute for Health and Care Research; Novartis Pharma; Canada Foundation for Innovation; Ontario Ministry of Economic Development and Innovation; Ministero dello Sviluppo Economico; National Institute on Handicapped Research; Kennedy Trust for Rheumatology Research; Genome Canada; AbbVie; European Federation of Pharmaceutical Industries and Associations; Merck KGaA; Innovative Medicines Initiative; Wellcome; Wellcome Trust; Pfizer; Boehringer Ingelheim","keywords":"Coding (social sciences); Computer science; World Wide Web; Computational biology; Biology; Mathematics","score_opus":0.04376914577511182,"score_gpt":0.28878770850128405,"score_spread":0.24501856272617223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3006429100","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90937614,0.0007574542,0.015267159,0.0026021514,0.0004896823,0.0025147933,0.00020950678,0.00022701462,0.06855607],"genre_scores_gemma":[0.9555757,0.0011978351,0.03369842,0.0057953605,0.0010666116,0.00008091078,0.00044982176,0.00008227925,0.002053033],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973389,0.000066018445,0.00084522937,0.00030405962,0.0007030988,0.0007427227],"domain_scores_gemma":[0.9984259,0.000051332692,0.0003072164,0.000484744,0.00017775179,0.0005530457],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00059849076,0.00037445052,0.00036169682,0.00010315222,0.0002130127,0.00017503646,0.00062157906,0.00034783367,0.000019547122],"category_scores_gemma":[0.001917917,0.00030699855,0.00019308589,0.00025569036,0.0002231182,0.000021758242,0.00040260638,0.00036425187,0.0005432885],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016300721,0.00029761757,0.0023655556,0.0028895414,0.00036708402,0.000016441263,0.005391651,0.00011986789,0.7686894,0.0003965303,0.15090717,0.06839612],"study_design_scores_gemma":[0.0017757327,0.0017877036,0.00035045613,0.00024817497,0.00003877699,0.000015332855,0.0030249595,0.038532555,0.32721925,0.000032438744,0.6265458,0.00042882594],"about_ca_topic_score_codex":0.0000023074442,"about_ca_topic_score_gemma":0.000007672447,"teacher_disagreement_score":0.47563863,"about_ca_system_score_codex":0.000029716924,"about_ca_system_score_gemma":0.00022896622,"threshold_uncertainty_score":0.9999382},"labels":[],"label_agreement":null},{"id":"W3008641372","doi":"10.1093/bioinformatics/btaa136","title":"PSORTm: a bacterial and archaeal protein subcellular localization prediction tool for metagenomics data","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Microbial Community Ecology and Physiology","field":"Environmental Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University; Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Simon Fraser University; Genome British Columbia; Genome Canada","keywords":"Metagenomics; In silico; Computational biology; Identification (biology); Biology; Human Microbiome Project; Microbiome; Source code; Normalization (sociology); Biological classification; Computer science; Bioinformatics; Genetics; Ecology; Gene; Evolutionary biology","score_opus":0.0358246009567333,"score_gpt":0.22478674216198435,"score_spread":0.18896214120525107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3008641372","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8159212,0.0000109863295,0.18162799,0.00035281485,0.0001138274,0.0010480306,0.000548769,0.0000491758,0.00032721038],"genre_scores_gemma":[0.9428884,0.000045663986,0.050206717,0.0014543639,0.00017426178,0.000035413148,0.0051122354,0.000017344975,0.000065608285],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994859,0.000037864433,0.00021286738,0.00009836386,0.000043209748,0.00012177357],"domain_scores_gemma":[0.9996113,0.000026188787,0.00007750849,0.00023196256,0.0000048871434,0.00004813144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019685586,0.00007412982,0.00010293314,0.000008913091,0.00014681276,0.000018454477,0.00024099546,0.0000754641,0.00033181437],"category_scores_gemma":[0.00007608524,0.000070662,0.000014352553,0.00005118743,0.000111564725,0.0002910254,0.00044254624,0.00007209426,0.00005346865],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028886187,0.0005037917,0.018256405,0.0022121603,0.00037979733,0.00000504189,0.036735628,0.008911966,0.67589116,0.0045754556,0.17475891,0.074881084],"study_design_scores_gemma":[0.00087805797,0.00044867824,0.001444006,0.0000070376627,0.00004960257,0.000005089302,0.00013544146,0.7253991,0.0028600348,0.0005186127,0.2680465,0.00020786187],"about_ca_topic_score_codex":0.000019561048,"about_ca_topic_score_gemma":0.000048078935,"teacher_disagreement_score":0.7164871,"about_ca_system_score_codex":0.000018693097,"about_ca_system_score_gemma":0.000011869823,"threshold_uncertainty_score":0.36331347},"labels":[],"label_agreement":null},{"id":"W3012898726","doi":"10.1093/bioinformatics/btaa206","title":"Annotation of tandem mass spectrometry data using stochastic neural networks in shotgun proteomics","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Benchmark (surveying); Fragmentation (computing); Annotation; Context (archaeology); Shotgun; Artificial intelligence; Tandem mass spectrometry; Pattern recognition (psychology); Mass spectrometry; Chemistry; Biology; Gene","score_opus":0.04870397349116574,"score_gpt":0.29562667999238523,"score_spread":0.2469227065012195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3012898726","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1060739,0.000025863083,0.89301634,0.000075613614,0.000011359334,0.00026032183,0.00011700578,0.000063494255,0.000356121],"genre_scores_gemma":[0.51203376,0.0000109161465,0.48761,0.000055472203,0.000054804106,0.000011833031,0.00020696141,0.000013090824,0.000003123007],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990446,0.000004187873,0.0005063499,0.00013629005,0.00012841866,0.000180157],"domain_scores_gemma":[0.9991581,0.000032952164,0.00029428673,0.00041674136,0.000036534617,0.00006139225],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008606559,0.00012107139,0.00018554775,0.000044300064,0.000038484704,0.0000224212,0.00040146397,0.00009834928,0.000025801624],"category_scores_gemma":[0.00007533881,0.00012654501,0.000026978927,0.00032603895,0.000041864925,0.00029297319,0.00016078416,0.00023117328,0.0000017658572],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000164544,0.00016739339,0.005385295,0.0012489433,0.00006973973,0.0000058600826,0.0014377728,0.57507116,0.4045361,0.002530637,0.00031187522,0.009070717],"study_design_scores_gemma":[0.00022188999,0.000016063352,0.000017456685,0.000035426605,0.000012528884,0.0000032239325,0.00016593962,0.98723054,0.011855512,0.00029174273,0.000020124995,0.00012952602],"about_ca_topic_score_codex":0.000005174138,"about_ca_topic_score_gemma":0.0000011660205,"teacher_disagreement_score":0.41215944,"about_ca_system_score_codex":0.000052296957,"about_ca_system_score_gemma":0.000034975277,"threshold_uncertainty_score":0.51603556},"labels":[],"label_agreement":null},{"id":"W3015062804","doi":"10.1093/bioinformatics/btaa232","title":"CircMiner: accurate and rapid detection of circular RNA through splice-aware pseudo-alignment scheme","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Circular RNAs in diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Scheme (mathematics); splice; Circular RNA; Computer science; RNA; Computational biology; Algorithm; Mathematics; Biology; Genetics; Gene","score_opus":0.019972313764952867,"score_gpt":0.2463254117506706,"score_spread":0.22635309798571773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3015062804","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90705085,0.002439371,0.088652276,0.00024085041,0.0001405668,0.00044482108,0.000100957106,0.000042918404,0.00088740507],"genre_scores_gemma":[0.99386483,0.0009136939,0.004251125,0.0007093681,0.0001265068,0.000013038763,0.000092455186,0.000020336387,0.000008626765],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99901867,0.000022221659,0.00038316642,0.00018501116,0.00019967611,0.00019127196],"domain_scores_gemma":[0.99924934,0.000008614682,0.00020589356,0.00032995918,0.00007923973,0.00012695535],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007903238,0.00017410237,0.00018314277,0.000023368168,0.000060250113,0.000021652066,0.00017034229,0.00012812499,0.000016832922],"category_scores_gemma":[0.00012261882,0.00017355006,0.000106739826,0.00011459126,0.000092123795,0.000020087922,0.00016886803,0.000068626825,0.000010461262],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006805668,0.000052642572,0.00070057134,0.0006444081,0.00018512878,0.000003515069,0.0006188348,0.00008750599,0.9841869,0.00004760843,0.0011051891,0.012299671],"study_design_scores_gemma":[0.001284135,0.0004186004,0.0013283321,0.00004847007,0.0001014839,0.000038078346,0.0012449896,0.0150907375,0.95331055,0.000048443737,0.026631292,0.00045487864],"about_ca_topic_score_codex":0.0000052162573,"about_ca_topic_score_gemma":9.000998e-7,"teacher_disagreement_score":0.086814016,"about_ca_system_score_codex":0.000011598642,"about_ca_system_score_gemma":0.00004503244,"threshold_uncertainty_score":0.7077166},"labels":[],"label_agreement":null},{"id":"W3015080146","doi":"10.1093/bioinformatics/btaa228","title":"MaveQuest: a web resource for planning experimental tests of human variant effects","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sinai Health System; Lunenfeld-Tanenbaum Research Institute; University of Toronto","funders":"National Institutes of Health; National Human Genome Research Institute; Canada Excellence Research Chairs, Government of Canada","keywords":"Computer science; Resource (disambiguation); Web resource; World Wide Web; Computational biology; Biology","score_opus":0.01608964652797489,"score_gpt":0.2720287293379269,"score_spread":0.255939082809952,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3015080146","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9955984,0.00066498364,0.0014003995,0.000053787262,0.0000483372,0.00036289802,0.000097861266,0.000015433256,0.0017579141],"genre_scores_gemma":[0.994406,0.000004378515,0.0046593184,0.00052381755,0.0001227135,0.000018664912,0.00022096795,0.000014009025,0.000030140956],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99947387,0.000008554094,0.00021584632,0.00009614618,0.0000667903,0.00013881542],"domain_scores_gemma":[0.9996151,0.000012817337,0.000105349216,0.00014215808,0.000027752749,0.000096856544],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00004685849,0.00010219568,0.000121482895,0.00001836482,0.000058123205,0.000016091117,0.00013297421,0.00006691243,0.0000029455132],"category_scores_gemma":[0.00005916967,0.0000933944,0.00008128932,0.000032498032,0.000032379077,0.0000031294717,0.00008602299,0.000026542084,0.0000027113306],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011062522,0.00007647591,0.0003352384,0.00044052408,0.00006248782,0.00000779491,0.0011097273,0.00009743909,0.9878709,0.00034800108,0.009185792,0.0003550436],"study_design_scores_gemma":[0.0026387041,0.0030098504,0.0008703631,0.00010400842,0.000066929555,0.00002985594,0.0015592127,0.008735265,0.9259659,0.0000433017,0.056497615,0.00047898464],"about_ca_topic_score_codex":8.9673034e-7,"about_ca_topic_score_gemma":2.470462e-7,"teacher_disagreement_score":0.06190494,"about_ca_system_score_codex":0.0000052718106,"about_ca_system_score_gemma":0.000044210505,"threshold_uncertainty_score":0.3808513},"labels":[],"label_agreement":null},{"id":"W3016108274","doi":"10.1093/bioinformatics/btaa243","title":"Pooled variable scaling for cluster analysis","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; KU Leuven","keywords":"Cluster (spacecraft); Scaling; Variable (mathematics); Computer science; Statistics; Mathematics; Programming language","score_opus":0.03153041412441573,"score_gpt":0.292185891279953,"score_spread":0.2606554771555373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3016108274","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015854862,0.000017489565,0.9961986,0.0015552745,0.00007720642,0.0002535734,0.000012733486,0.0001871215,0.0015394803],"genre_scores_gemma":[0.01045589,0.0000036103263,0.9873155,0.001922062,0.00007499853,0.000023956753,0.000013354022,0.000008424033,0.00018221026],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988088,0.00001625923,0.00034093874,0.00017551938,0.00030615,0.00035234343],"domain_scores_gemma":[0.99901825,0.00016308791,0.00009580651,0.00039004727,0.00014291774,0.00018991291],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028303463,0.00011319185,0.00021392516,0.0001383062,0.0001269803,0.00024355845,0.00082052883,0.00005380179,0.000008840074],"category_scores_gemma":[0.00023340822,0.00010259973,0.00011110835,0.0014080835,0.000021312171,0.0006977988,0.00042505827,0.00010148101,0.000068099565],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011666185,0.00012391174,0.00033765685,0.0013363789,0.002149127,0.0000069662083,0.016631218,0.6278728,0.0006995457,0.051421262,0.010330017,0.28897446],"study_design_scores_gemma":[0.00035348622,0.000053621297,0.000023565277,0.000005394274,0.000050219667,0.0000014393595,0.0000639238,0.9888567,0.00034090303,0.00046192616,0.009654395,0.00013446689],"about_ca_topic_score_codex":0.0000028514487,"about_ca_topic_score_gemma":4.17578e-7,"teacher_disagreement_score":0.36098385,"about_ca_system_score_codex":0.00003953218,"about_ca_system_score_gemma":0.00006304022,"threshold_uncertainty_score":0.4183896},"labels":[],"label_agreement":null},{"id":"W3016821318","doi":"10.1093/bioinformatics/btaa253","title":"ntJoin: Fast and lightweight assembly-guided scaffolding using minimizer graphs","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"National Human Genome Research Institute; National Institutes of Health; Genome British Columbia; Genome Canada","keywords":"Sequence assembly; Computer science; Python (programming language); Reference genome; Synteny; Genome; Graph; Programming language; Theoretical computer science; Biology; Genetics; Gene","score_opus":0.03114288380858979,"score_gpt":0.24813345082368043,"score_spread":0.21699056701509065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3016821318","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99381864,0.0010288612,0.0024627524,0.00027738156,0.00012336503,0.00016094041,0.000024964145,0.000008465819,0.0020946024],"genre_scores_gemma":[0.9652467,0.00046388718,0.032916293,0.0011104203,0.0001765072,0.0000041939716,0.000020097721,0.000020368934,0.0000415516],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99917823,0.000013446463,0.00030598333,0.00017075232,0.00010190389,0.00022967518],"domain_scores_gemma":[0.99951327,0.000008924712,0.00011251804,0.00016926459,0.000057448422,0.00013860196],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000079464975,0.00017757918,0.00018282852,0.000033098626,0.0001331563,0.00005333835,0.00012494106,0.00010210594,0.000004912246],"category_scores_gemma":[0.000041747364,0.00015947157,0.00007221879,0.00009165742,0.00006330955,0.0000028091433,0.00022033096,0.00004522982,0.000007521076],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059724025,0.00003338265,0.00909602,0.0002379674,0.00029364502,0.0000042192146,0.002311618,0.00031165473,0.9711359,0.00053847505,0.009474789,0.006502583],"study_design_scores_gemma":[0.0043930514,0.0011377019,0.0074571134,0.000113527465,0.0003565923,0.000192208,0.00400653,0.106809266,0.7122891,0.00036227363,0.16058601,0.0022966485],"about_ca_topic_score_codex":0.0000037738075,"about_ca_topic_score_gemma":0.0000016009145,"teacher_disagreement_score":0.25884685,"about_ca_system_score_codex":0.0000057945035,"about_ca_system_score_gemma":0.000036782352,"threshold_uncertainty_score":0.65030617},"labels":[],"label_agreement":null},{"id":"W3016851473","doi":"10.1093/bioinformatics/btaa248","title":"Codon optimization: a mathematical programing approach","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":76,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Codon usage bias; Heuristics; Computer science; Genetic code; Solver; Mathematical optimization; Computational biology; Mathematics; Biology; Genetics; Amino acid; Programming language; Gene; Genome","score_opus":0.022471143699864988,"score_gpt":0.23043188396903885,"score_spread":0.20796074026917385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3016851473","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029977488,0.00008884338,0.979807,0.00025868943,0.000030314857,0.00037583802,0.0000067477913,0.000047327216,0.016387455],"genre_scores_gemma":[0.11674881,0.000039900322,0.88154286,0.0010619763,0.00022353228,0.000052361276,0.00013756948,0.000025685633,0.00016733167],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993057,0.000018711966,0.0002465547,0.00011911632,0.00014107925,0.00016880497],"domain_scores_gemma":[0.9995716,0.0000057495154,0.00008150076,0.00018469554,0.000038202128,0.000118256765],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011439072,0.00011900866,0.00012127563,0.000014008521,0.00006678555,0.00005234069,0.00016999115,0.000114289476,0.000043770855],"category_scores_gemma":[0.00011671014,0.00010235481,0.00006319818,0.000085078675,0.000032964497,0.0000069286493,0.00008265915,0.000045596007,0.0000550983],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001125741,0.001623982,0.0006245795,0.0077253915,0.0011640758,0.00002733021,0.01697081,0.09462583,0.3806181,0.044580355,0.037669577,0.41324422],"study_design_scores_gemma":[0.001007479,0.00081698346,0.000011825205,0.000046809153,0.000060837036,0.00006901293,0.0014850011,0.8060309,0.13675912,0.00022192046,0.052743785,0.0007462986],"about_ca_topic_score_codex":1.9874396e-7,"about_ca_topic_score_gemma":3.0920166e-8,"teacher_disagreement_score":0.7114051,"about_ca_system_score_codex":0.0000039713036,"about_ca_system_score_gemma":0.000025224937,"threshold_uncertainty_score":0.4173908},"labels":[],"label_agreement":null},{"id":"W3017020108","doi":"10.1093/bioinformatics/btaa756","title":"HLA predictions from the bronchoalveolar lavage fluid and blood samples of eight COVID-19 patients at the pandemic onset","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"SARS-CoV-2 and COVID-19 Research","field":"Medicine","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Genome British Columbia","funders":"National Human Genome Research Institute; National Institutes of Health; Genome British Columbia; Genome Canada","keywords":"Bronchoalveolar lavage; Human leukocyte antigen; Immunology; Allele; Pandemic; Biology; Population; Coronavirus disease 2019 (COVID-19); Allele frequency; Transcriptome; Disease; Gene; Medicine; Antigen; Genetics; Internal medicine; Infectious disease (medical specialty); Gene expression; Lung","score_opus":0.05237294114448221,"score_gpt":0.3052391455710094,"score_spread":0.2528662044265272,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3017020108","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99387133,0.00080971274,0.00059330324,0.0021718785,0.00006062774,0.00066820544,0.0011446882,0.0000584243,0.00062180957],"genre_scores_gemma":[0.89868873,0.00022227725,0.0005590132,0.10008617,0.00015083412,0.000033631284,0.00021214811,0.00002101681,0.00002618638],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986505,0.00006151552,0.00043070217,0.00012843954,0.0005061732,0.00022269138],"domain_scores_gemma":[0.9984791,0.00077266846,0.00013156695,0.00041207543,0.0000872922,0.00011728142],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025291066,0.00014501066,0.00022670148,0.00003798851,0.00026990022,0.0000336196,0.00024639897,0.00009865366,0.000045868055],"category_scores_gemma":[0.0011542671,0.00007816308,0.00008698009,0.00019398023,0.00030943714,0.00010414771,0.00025330874,0.00024238511,0.00005063],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023799055,0.000100682955,0.9522027,0.0003104324,0.00023170593,0.0000029407884,0.010749724,0.000002593757,0.0016376998,0.00002485229,0.033100598,0.0013981324],"study_design_scores_gemma":[0.0065026213,0.00088924204,0.20654882,0.0001139081,0.00061933394,0.000034146356,0.0031029922,0.008750093,0.0113876145,0.00013553104,0.76164424,0.00027142974],"about_ca_topic_score_codex":0.0002353128,"about_ca_topic_score_gemma":0.000070170216,"teacher_disagreement_score":0.7456538,"about_ca_system_score_codex":0.000058616537,"about_ca_system_score_gemma":0.00028469195,"threshold_uncertainty_score":0.31873977},"labels":[],"label_agreement":null},{"id":"W3017871916","doi":"10.1093/bioinformatics/btaa246","title":"SparkINFERNO: a scalable high-throughput pipeline for inferring molecular mechanisms of non-coding genetic variants","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Weston Brain Institute; National Institute on Aging; Alzheimer's Association","keywords":"Genome-wide association study; Computer science; Inference; Pipeline (software); Scalability; SPARK (programming language); Computational biology; Expression quantitative trait loci; Genomics; Data mining; Biology; Gene; Genome; Artificial intelligence; Genetics; Database; Operating system; Single-nucleotide polymorphism; Programming language; Genotype","score_opus":0.017940404636638648,"score_gpt":0.253130555931134,"score_spread":0.23519015129449533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3017871916","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12162563,0.00006341993,0.8768789,0.00036050347,0.00012678083,0.00035666133,0.00007364427,0.000013732893,0.00050068565],"genre_scores_gemma":[0.7375144,0.00006531626,0.2610218,0.00107412,0.000101044294,0.000026390955,0.00013341187,0.000020859325,0.000042660267],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99865305,0.00002697392,0.0006471144,0.00020791646,0.00012476215,0.00034016598],"domain_scores_gemma":[0.9990774,0.00003223242,0.000325996,0.00028252788,0.00015902841,0.00012283347],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025335205,0.00018610217,0.00033201647,0.000039488245,0.00007458956,0.000016899323,0.00023450551,0.00021275367,0.000014145048],"category_scores_gemma":[0.00045624786,0.00018440718,0.000112359645,0.00012268867,0.000039056104,0.000007257669,0.000172032,0.000067094035,0.000014946279],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017717005,0.00022153027,0.0035732542,0.0009313807,0.0004363472,0.000004209248,0.0007663069,0.021721771,0.9431166,0.0046092123,0.013552136,0.010890064],"study_design_scores_gemma":[0.004072782,0.0014480192,0.0065467437,0.000078376645,0.00021621356,0.000020543319,0.00044155688,0.6631615,0.31228963,0.0035466007,0.007313843,0.0008641604],"about_ca_topic_score_codex":0.000020899028,"about_ca_topic_score_gemma":0.0000037522173,"teacher_disagreement_score":0.64143974,"about_ca_system_score_codex":0.00001450694,"about_ca_system_score_gemma":0.000098285986,"threshold_uncertainty_score":0.7519907},"labels":[],"label_agreement":null},{"id":"W3023043090","doi":"10.1093/bioinformatics/btaa289","title":"pepFunk: a tool for peptide-centric functional analysis of metaproteomic human gut microbiome studies","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Advanced Research; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Ontario Genomics Institute; Genome Canada","keywords":"Workflow; KEGG; Computer science; Metagenomics; Computational biology; Source code; In silico; Metaproteomics; Biology; Database; Gene; Biochemistry; Transcriptome; Programming language","score_opus":0.0484184661842432,"score_gpt":0.3062297102970739,"score_spread":0.25781124411283074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3023043090","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4441644,0.00036898043,0.5488108,0.00089728244,0.00003709522,0.0013675097,0.0017429546,0.00037287996,0.0022381253],"genre_scores_gemma":[0.4518419,0.00013013679,0.54481184,0.0005686302,0.00014047476,0.00068696716,0.00094941846,0.00003628734,0.0008343305],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99889064,0.0000032374157,0.0006443844,0.00014846209,0.00013008082,0.00018320027],"domain_scores_gemma":[0.99900603,0.00007075482,0.0004012612,0.00026940284,0.00019717518,0.000055391967],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009303071,0.00015866905,0.00040194558,0.00013184812,0.00013977576,0.000019895731,0.00019789627,0.00007779483,0.0001801132],"category_scores_gemma":[0.00008116863,0.00014732024,0.00030059172,0.0006139529,0.000072978626,0.000122065,0.00010157078,0.00008913676,0.000009867153],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012744106,0.00018810286,0.001381212,0.002512721,0.0050277086,5.69923e-7,0.0018695394,0.0014987207,0.9536521,0.01212118,0.019092558,0.0025281569],"study_design_scores_gemma":[0.0028011994,0.00025580815,0.00046161178,0.000104964216,0.0062822583,0.000005884635,0.002647287,0.10435744,0.80308235,0.0043237642,0.07429959,0.0013778701],"about_ca_topic_score_codex":0.000002039626,"about_ca_topic_score_gemma":0.0000011393564,"teacher_disagreement_score":0.15056977,"about_ca_system_score_codex":0.00007941052,"about_ca_system_score_gemma":0.000039738432,"threshold_uncertainty_score":0.6007545},"labels":[],"label_agreement":null},{"id":"W3026082741","doi":"10.1093/bioinformatics/btaa529","title":"BioPAX-Parser: parsing and enrichment analysis of BioPAX pathways","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University Health Network","funders":"","keywords":"Parsing; Computer science; MIT License; License; Software; Pathway analysis; Programming language; Artificial intelligence; Biology; Operating system; Gene","score_opus":0.017125912921960085,"score_gpt":0.21962636162523322,"score_spread":0.20250044870327313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3026082741","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93515086,0.0015528882,0.057384565,0.00046070103,0.00015432789,0.00038456763,0.00025062682,0.000036633974,0.0046248334],"genre_scores_gemma":[0.9862817,0.0004820905,0.011860859,0.0010089591,0.000075681506,0.000003872135,0.000257644,0.000010915268,0.000018286772],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989014,0.000013720046,0.0005687502,0.00014225516,0.00014398889,0.00022988292],"domain_scores_gemma":[0.99922085,0.00001168494,0.00026570898,0.00027074956,0.00006117511,0.0001698493],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016569256,0.00017292149,0.00030770685,0.00009621701,0.000063690124,0.00003636463,0.0001693071,0.00013823363,0.000013795024],"category_scores_gemma":[0.000031156276,0.00015478343,0.0001409364,0.0003912543,0.00009365264,0.000010479915,0.00018759961,0.00007255015,0.0000075513403],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011722299,0.0006950282,0.060610928,0.0033879622,0.016563745,0.00001836503,0.035592567,0.030896015,0.4073648,0.013032973,0.037606172,0.39305922],"study_design_scores_gemma":[0.0022968214,0.0015805472,0.008821311,0.00007299726,0.0020854983,0.000020936273,0.0040576374,0.8586654,0.04738319,0.00024991107,0.07336711,0.0013986512],"about_ca_topic_score_codex":0.000004670031,"about_ca_topic_score_gemma":0.000004073694,"teacher_disagreement_score":0.8277694,"about_ca_system_score_codex":0.000008029102,"about_ca_system_score_gemma":0.00004337199,"threshold_uncertainty_score":0.6311885},"labels":[],"label_agreement":null},{"id":"W3028383715","doi":"10.1093/bioinformatics/btaa542","title":"TaxoNN: ensemble of neural networks on stratified microbiome data for disease prediction","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":79,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Princess Margaret Cancer Centre; Hospital for Sick Children; Public Health Ontario; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Crohn's and Colitis Canada; Leona M. and Harry B. Helmsley Charitable Trust","keywords":"Microbiome; Computer science; Artificial intelligence; Machine learning; Convolutional neural network; Artificial neural network; Ensemble learning; Pattern recognition (psychology); Data mining; Bioinformatics; Biology","score_opus":0.04297981616172603,"score_gpt":0.2717342480828832,"score_spread":0.2287544319211572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3028383715","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.63008326,0.00087703724,0.34886578,0.0032366258,0.001054584,0.0029800453,0.011908143,0.000096694625,0.00089782896],"genre_scores_gemma":[0.98649323,0.000077217555,0.0051070866,0.0016431162,0.00030375304,0.00000870782,0.006308114,0.000014694594,0.000044071203],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999263,0.000012283745,0.00032396312,0.00016088727,0.000058609043,0.0001812467],"domain_scores_gemma":[0.99920577,0.000010374005,0.00014235375,0.00044737908,0.000050773728,0.00014333708],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008895298,0.00011224968,0.0001247961,0.000019064933,0.00005603698,0.000017795568,0.0002580618,0.00009062202,0.0000046735904],"category_scores_gemma":[0.000050539948,0.00010225271,0.000052047075,0.000060850376,0.000036284713,0.0000097832935,0.0001088761,0.000056667188,0.0000035397493],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002082284,0.00027217102,0.0011047686,0.0019355566,0.0001665967,0.000001758436,0.00035623735,0.005503476,0.6531857,0.00033625023,0.31908792,0.015967268],"study_design_scores_gemma":[0.0021448745,0.0017784503,0.0020241248,0.000057147412,0.000097241114,0.0000053044937,0.00021640513,0.8788498,0.02371044,0.000012509218,0.090728335,0.00037538816],"about_ca_topic_score_codex":0.0000016327059,"about_ca_topic_score_gemma":0.0000031036677,"teacher_disagreement_score":0.8733463,"about_ca_system_score_codex":0.000005438307,"about_ca_system_score_gemma":0.0000777606,"threshold_uncertainty_score":0.41697446},"labels":[],"label_agreement":null},{"id":"W3036062177","doi":"10.1093/bioinformatics/btaa577","title":"MDIPA: a microRNA–drug interaction prediction approach based on non-negative matrix factorization","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; microRNA; Similarity (geometry); Computational biology; Matrix decomposition; Identification (biology); Data mining; Artificial intelligence; Machine learning; Biology; Gene; Genetics","score_opus":0.027623798108706295,"score_gpt":0.283240223459039,"score_spread":0.2556164253503327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3036062177","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003755751,0.000003188895,0.99025977,0.0010721909,0.00048165082,0.0003743269,0.0000385932,0.00021952641,0.0037950012],"genre_scores_gemma":[0.44552386,0.0000020660914,0.55294174,0.0012573868,0.00013042563,0.000018342562,0.00009078993,0.0000109448965,0.000024474002],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99852055,0.00009242246,0.00047155804,0.00023967454,0.00048784167,0.00018792441],"domain_scores_gemma":[0.99886817,0.00026611268,0.00028191166,0.00027245953,0.00018111028,0.00013021746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027471926,0.00019106362,0.00017378887,0.000169682,0.00012278123,0.0002547675,0.00044181303,0.000059536276,0.000007974306],"category_scores_gemma":[0.0002756306,0.00017813091,0.000090304056,0.00068647496,0.000024281931,0.0014344184,0.00012386456,0.00021601479,0.00011567351],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009063581,0.00018516845,0.00021439367,0.00026664062,0.00004303808,0.0000019837587,0.012477511,0.9563059,0.00037569905,0.0054777954,0.007357143,0.0172041],"study_design_scores_gemma":[0.00044673542,0.00011448459,0.0009216341,0.00003071003,0.00000884766,0.0000032290127,0.00027939407,0.9941286,0.0023069694,0.0002997504,0.001295521,0.00016416809],"about_ca_topic_score_codex":0.000005936642,"about_ca_topic_score_gemma":2.856849e-7,"teacher_disagreement_score":0.44176808,"about_ca_system_score_codex":0.00014555891,"about_ca_system_score_gemma":0.00015836487,"threshold_uncertainty_score":0.72639674},"labels":[],"label_agreement":null},{"id":"W3037207689","doi":"10.1093/bioinformatics/btaa596","title":"DeepAntigen: a novel method for neoantigen prioritization via 3D genome and deep sparse learning","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"vaccines and immunoinformatics approaches","field":"Biochemistry, Genetics and Molecular Biology","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Computational biology; Prioritization; Genome; Web server; ENCODE; Immunogenicity; Source code; Deep learning; Artificial intelligence; Machine learning; Biology; The Internet; Genetics; Antigen; Gene","score_opus":0.02133889510537646,"score_gpt":0.24811301357242543,"score_spread":0.22677411846704898,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037207689","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023140209,0.00056058046,0.9749649,0.00017081617,0.00004953388,0.00049111113,0.000021057213,0.000030247405,0.0005715371],"genre_scores_gemma":[0.086594574,0.00056877837,0.9104421,0.0011963028,0.00026014447,0.000037171663,0.000736368,0.000044968416,0.000119575554],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990235,0.000013036538,0.0004380826,0.00015465167,0.00010316525,0.00026753708],"domain_scores_gemma":[0.9993935,0.000016824637,0.00020084964,0.00016589157,0.00010050318,0.00012238827],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022017153,0.00019235136,0.00020514711,0.00003806403,0.00016822247,0.00008616645,0.00015356726,0.00014553637,0.000006997525],"category_scores_gemma":[0.000150155,0.00018182493,0.00007731267,0.00010432005,0.000024202218,0.000026859358,0.00015230228,0.000089973524,0.000011804976],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045267024,0.00013878106,0.0018442376,0.0022729728,0.0005838475,0.0000012364403,0.010254288,0.00972925,0.79150826,0.0010857104,0.0008320562,0.18129669],"study_design_scores_gemma":[0.0011773045,0.00049532694,0.00049310207,0.000010428633,0.00005724974,0.000049851136,0.00096970046,0.8871455,0.00895908,0.000014229638,0.1002644,0.00036383775],"about_ca_topic_score_codex":0.0000021854698,"about_ca_topic_score_gemma":0.0000012505561,"teacher_disagreement_score":0.87741625,"about_ca_system_score_codex":0.0000077103805,"about_ca_system_score_gemma":0.000042213876,"threshold_uncertainty_score":0.7414605},"labels":[],"label_agreement":null},{"id":"W3037253559","doi":"10.1093/bioinformatics/btaa580","title":"ProbeRating: a recommender system to infer binding profiles for nucleic acid-binding proteins","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"RNA Research and Splicing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Genome Canada","keywords":"Nucleic acid; Computer science; Recommender system; Computational biology; DNA-binding protein; Chemistry; Biochemistry; World Wide Web; Biology; Transcription factor; Gene","score_opus":0.033628283545524384,"score_gpt":0.2824179649258074,"score_spread":0.248789681380283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037253559","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9471282,0.000033955646,0.047156334,0.0015440338,0.00009451103,0.0025925373,0.000105335675,0.0000838568,0.0012612492],"genre_scores_gemma":[0.88475263,0.000007978266,0.11244421,0.0010317249,0.00042133252,0.0004960486,0.00025850706,0.000053573673,0.0005339854],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988103,0.000022506094,0.00037365855,0.0001943398,0.00017594232,0.00042325785],"domain_scores_gemma":[0.9993015,0.000012287023,0.00011047534,0.00021054689,0.00009578228,0.00026938724],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025720175,0.00017107314,0.00017791793,0.000047545018,0.00021338802,0.00013567256,0.00023289866,0.00011822238,0.0000069149423],"category_scores_gemma":[0.0002866325,0.00014872973,0.00008603379,0.00016016565,0.00002239251,0.000017701223,0.000183429,0.00010004285,0.000073652445],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000113488066,0.000022925398,0.00058751786,0.0010733233,0.000063091844,0.0000013149469,0.0007445736,0.000060540086,0.98136187,0.00028373324,0.010775354,0.0049122474],"study_design_scores_gemma":[0.0013032514,0.0015329006,0.00004984805,0.0002532449,0.000021336515,0.000017817018,0.0038052194,0.06168788,0.8877365,0.0000027731098,0.043028653,0.000560579],"about_ca_topic_score_codex":0.0000032706846,"about_ca_topic_score_gemma":0.0000036985243,"teacher_disagreement_score":0.09362539,"about_ca_system_score_codex":0.00004845413,"about_ca_system_score_gemma":0.0000886204,"threshold_uncertainty_score":0.60650223},"labels":[],"label_agreement":null},{"id":"W3041248822","doi":"10.1093/bioinformatics/btaa588","title":"TreeSAPP: the Tree-based Sensitive and Accurate Phylogenetic Profiler","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Genome British Columbia; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; National Energy Research Scientific Computing Center; Joint Genome Institute; Compute Canada","keywords":"Python (programming language); Phylogenetic tree; Metagenomics; Computer science; Tree (set theory); Rank (graph theory); Taxonomic rank; Software; Genome; Biology; Data mining; Ecology; Gene; Genetics; Mathematics","score_opus":0.018115108358277635,"score_gpt":0.22407693987934757,"score_spread":0.20596183152106995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3041248822","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98892033,0.0009212413,0.0037396825,0.002617855,0.00008847597,0.00047745748,0.000085562955,0.000010178064,0.003139242],"genre_scores_gemma":[0.99252105,0.00017645383,0.003475087,0.0035614993,0.00015516687,0.000016533055,0.00003061453,0.00001350439,0.000050069506],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993475,0.000027603017,0.00020395468,0.0001448305,0.00008860785,0.0001875077],"domain_scores_gemma":[0.99955034,0.000021876662,0.00008830237,0.00019398516,0.000059516122,0.00008596007],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000082315375,0.00015635924,0.00012480625,0.000012531169,0.00012517619,0.000037321795,0.00012733895,0.00006921779,0.0000030846254],"category_scores_gemma":[0.00005760216,0.00010642875,0.00005445213,0.00007059444,0.00013130845,9.397133e-7,0.000126064,0.00006002387,0.000015499661],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005408702,0.00010529829,0.01120165,0.00033048046,0.00068210566,0.000009910776,0.007125412,0.0022155235,0.8641919,0.0006878535,0.018772209,0.094136804],"study_design_scores_gemma":[0.0040545296,0.0023753052,0.085659385,0.00003759502,0.00027560192,0.000036893947,0.0050810315,0.123235956,0.49769774,0.00010685803,0.2799362,0.0015029071],"about_ca_topic_score_codex":0.0000025761308,"about_ca_topic_score_gemma":0.000007881975,"teacher_disagreement_score":0.36649415,"about_ca_system_score_codex":0.0000034831633,"about_ca_system_score_gemma":0.00005053186,"threshold_uncertainty_score":0.43400386},"labels":[],"label_agreement":null},{"id":"W3042330596","doi":"10.1093/bioinformatics/btaa447","title":"EvoLSTM: context-dependent models of sequence evolution using a sequence-to-sequence LSTM","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Compute Canada; Genome Canada","keywords":"Sequence (biology); Context (archaeology); Computer science; Alignment-free sequence analysis; Inference; Mutation; Code (set theory); Probabilistic logic; Sequence learning; Artificial intelligence; Computational biology; Sequence alignment; Biology; Genetics; Peptide sequence; Programming language","score_opus":0.0826937897695777,"score_gpt":0.2807156309608377,"score_spread":0.19802184119125998,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3042330596","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92195886,0.0009840488,0.075103685,0.00020520172,0.0001385129,0.00046110997,0.00030716887,0.000011436935,0.0008299662],"genre_scores_gemma":[0.9773547,0.00015834226,0.021577105,0.0007412731,0.00009099991,0.000011304883,0.000023424023,0.000016542877,0.000026328731],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99872756,0.000023561757,0.0004938076,0.00022891394,0.00023698322,0.0002891891],"domain_scores_gemma":[0.99907017,0.000010045037,0.00019757298,0.0003401171,0.00021385106,0.00016822184],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014594404,0.00020278244,0.00026015224,0.000041729065,0.00008767594,0.000022053808,0.00031792172,0.00011897738,0.000007369701],"category_scores_gemma":[0.00010007967,0.00019642698,0.00011180198,0.00015700843,0.00011466472,0.0000073633264,0.00025664663,0.00007523883,0.0000210774],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006500845,0.000022447024,0.0006165089,0.00013721529,0.00010967733,0.0000018526299,0.0014701529,0.025541905,0.9680844,0.00074332114,0.00025996685,0.002947524],"study_design_scores_gemma":[0.0015740558,0.0015676832,0.00044291336,0.00015216657,0.00017444679,0.00007604223,0.0037612638,0.70868903,0.27370787,0.0017118076,0.006920125,0.0012225881],"about_ca_topic_score_codex":0.000071635885,"about_ca_topic_score_gemma":0.000013495451,"teacher_disagreement_score":0.6943766,"about_ca_system_score_codex":0.000054880555,"about_ca_system_score_gemma":0.00021854526,"threshold_uncertainty_score":0.80100596},"labels":[],"label_agreement":null},{"id":"W3042374971","doi":"10.1093/bioinformatics/btaa488","title":"Factorized embeddings learns rich and biologically meaningful embedding spaces using factorized tensor decomposition","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Tensor decomposition and applications","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute; Institute for Research in Immunology and Cancer","funders":"Canadian Institutes of Health Research; Institut de Valorisation des Données; Canada First Research Excellence Fund; Canadian Institute for Advanced Research","keywords":"Representation (politics); Computer science; Tensor (intrinsic definition); Dimensionality reduction; Embedding; Curse of dimensionality; Rank (graph theory); Sample (material); Artificial intelligence; Multifactor dimensionality reduction; Matrix decomposition; Theoretical computer science; Pattern recognition (psychology); Gene; Mathematics; Biology","score_opus":0.08759766551448768,"score_gpt":0.35351002339032034,"score_spread":0.2659123578758327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3042374971","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7819094,0.000025131421,0.21491869,0.0013515935,0.000059543752,0.00048742877,0.00008489912,0.00044249077,0.0007207909],"genre_scores_gemma":[0.7182931,0.000028546234,0.28056946,0.00086876046,0.00013195189,0.000011645873,0.0000459076,0.000029459447,0.000021174239],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983827,0.000053470023,0.0006914491,0.00025161653,0.00027613572,0.00034463685],"domain_scores_gemma":[0.99856454,0.00032242358,0.00043399932,0.00019162182,0.00015320523,0.00033418587],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000159928,0.00030364277,0.0004648637,0.00007564558,0.00031159917,0.0002534032,0.00021771113,0.00018487018,0.00014152464],"category_scores_gemma":[0.00038969648,0.00025441215,0.000111285866,0.00030169205,0.00008225903,0.0003746755,0.00013556505,0.00025416643,0.00006638919],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012672193,0.0011102816,0.014248842,0.0046107196,0.0014876911,0.000045083612,0.15214095,0.0034616867,0.6657314,0.12004456,0.023973368,0.011878218],"study_design_scores_gemma":[0.0029619434,0.00042286282,0.0005296991,0.00015106474,0.00029638945,0.00006474439,0.007533985,0.96581316,0.006996482,0.005151428,0.008869844,0.001208415],"about_ca_topic_score_codex":0.000003421546,"about_ca_topic_score_gemma":4.4508752e-7,"teacher_disagreement_score":0.96235144,"about_ca_system_score_codex":0.000051763003,"about_ca_system_score_gemma":0.00002906341,"threshold_uncertainty_score":0.9999908},"labels":[],"label_agreement":null},{"id":"W3042645205","doi":"10.1093/bioinformatics/btaa442","title":"AITL: Adversarial Inductive Transfer Learning with input and output space adaptation for pharmacogenomics","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":60,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"Canadian Institutes of Health Research; Terry Fox Foundation; Canada Foundation for Innovation","keywords":"Pharmacogenomics; Adaptation (eye); Adversarial system; Computer science; Transfer of learning; Space (punctuation); Artificial intelligence; Machine learning; Biology; Bioinformatics; Neuroscience","score_opus":0.01805784941033034,"score_gpt":0.23809088593746033,"score_spread":0.22003303652713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3042645205","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34250003,0.00006464646,0.6539189,0.0007347241,0.00013788608,0.00078800705,0.00007564621,0.00006215831,0.0017180117],"genre_scores_gemma":[0.8534362,0.00011092167,0.1441498,0.0012110738,0.00042021775,0.000032657048,0.00040984293,0.000047862122,0.00018144652],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99912995,0.000026595844,0.00030625716,0.00016025227,0.00014385575,0.00023305889],"domain_scores_gemma":[0.99948585,0.000027506108,0.000121794175,0.00011477664,0.00010643796,0.00014364187],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015202316,0.00020755,0.00017801659,0.000038049413,0.00013795192,0.000057073532,0.000125526,0.00013957167,0.0000041663698],"category_scores_gemma":[0.00015036383,0.00018346935,0.000054129952,0.00008048737,0.00008062366,0.00002949844,0.000061654646,0.00020176028,0.000008382663],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.014192301,0.00034677674,0.015454873,0.005804185,0.002868255,0.000011734436,0.1771482,0.27384144,0.13101536,0.006421468,0.015631976,0.35726342],"study_design_scores_gemma":[0.0049012955,0.0024941296,0.00018510732,0.000030002484,0.00016338578,0.000022104605,0.0050286725,0.6784739,0.023122868,0.000016745118,0.28488937,0.0006724075],"about_ca_topic_score_codex":0.0000052110695,"about_ca_topic_score_gemma":0.0000042719066,"teacher_disagreement_score":0.51093614,"about_ca_system_score_codex":0.000014244027,"about_ca_system_score_gemma":0.0000965688,"threshold_uncertainty_score":0.7481663},"labels":[],"label_agreement":null},{"id":"W3042874372","doi":"10.1093/bioinformatics/btaa456","title":"Graph neural representational learning of RNA secondary structures for predicting RNA-protein interactions","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":53,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"Institut de Valorisation des Données","keywords":"In silico; Computer science; RNA; Source code; Graph; Sequence (biology); Computational biology; RNase P; Artificial intelligence; Machine learning; Representation (politics); Exploit; Theoretical computer science; Biology; Genetics; Gene; Programming language","score_opus":0.01989641482810419,"score_gpt":0.26378689942756817,"score_spread":0.24389048459946397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3042874372","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83097357,0.00014482715,0.1654249,0.00038036326,0.00019394784,0.00055354065,0.00011673245,0.00003242926,0.0021797034],"genre_scores_gemma":[0.96975875,0.000009433567,0.029508168,0.00019437159,0.00020065393,0.000032081367,0.00017201826,0.000013572506,0.00011092289],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992865,0.000026791407,0.00033076658,0.00011287887,0.000113223745,0.00012987795],"domain_scores_gemma":[0.99947226,0.000028908018,0.00023314563,0.000118592245,0.000082798,0.000064271255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009335925,0.00010230227,0.000117243435,0.000032622364,0.00010167775,0.000023451357,0.00013335957,0.00006921797,0.000047262165],"category_scores_gemma":[0.0003284354,0.000096322314,0.000111183675,0.00005959713,0.000033285298,0.000016545513,0.000064491775,0.0000943272,0.0000019382053],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012135853,0.000008017409,0.00019610788,0.00017378858,0.00006562284,2.549932e-7,0.00048618927,0.0008763908,0.9771588,0.000535927,0.0005831603,0.019794386],"study_design_scores_gemma":[0.0004029832,0.0003290891,0.00020027973,0.000018817042,0.000018978037,0.0000055776018,0.0008016287,0.013579038,0.97931826,0.0005730126,0.0046172775,0.00013502922],"about_ca_topic_score_codex":0.00000405267,"about_ca_topic_score_gemma":0.0000010163301,"teacher_disagreement_score":0.13878523,"about_ca_system_score_codex":0.0000035658666,"about_ca_system_score_gemma":0.000044267028,"threshold_uncertainty_score":0.392791},"labels":[],"label_agreement":null},{"id":"W3043192906","doi":"10.1093/bioinformatics/btaa453","title":"Identification of conserved evolutionary trajectories in tumors","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Genome British Columbia; University of British Columbia; Simon Fraser University","funders":"National Cancer Institute; National Institutes of Health; Francis Crick Institute","keywords":"Phylogenetic tree; Identification (biology); Conserved sequence; Set (abstract data type); Computational biology; Computer science; Biology; Evolutionary biology; Gene; Genetics; Base sequence; Ecology","score_opus":0.012552316219340496,"score_gpt":0.2282734148533736,"score_spread":0.2157210986340331,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3043192906","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99614286,0.00034850993,0.0024516615,0.0002577206,0.000078899444,0.0001365008,0.00009434242,0.00000603433,0.00048345287],"genre_scores_gemma":[0.99812555,0.00012865405,0.0013110951,0.0002595857,0.00005397653,0.0000056376048,0.000094210736,0.000005323264,0.000015955578],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99943525,0.0000074907202,0.00034339007,0.0000668593,0.00006569401,0.000081315375],"domain_scores_gemma":[0.9996673,0.000011771167,0.0001157751,0.00011659044,0.000049120412,0.00003946945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000059150625,0.00005908599,0.00008648791,0.000022443048,0.000014907132,0.000007712913,0.000094191986,0.000048413116,0.0000052538403],"category_scores_gemma":[0.00019087778,0.00006269316,0.000034225573,0.00009129403,0.000046398105,0.0000042510183,0.000041909236,0.000030418652,0.0000069657817],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004421799,0.00020825857,0.09561009,0.000810979,0.00008682967,0.000004874209,0.0040857387,0.004635878,0.86244315,0.0042249793,0.022898132,0.0045489054],"study_design_scores_gemma":[0.0024164317,0.0007996919,0.116358265,0.00006527539,0.00003754459,0.0000137497245,0.0028909296,0.0508697,0.79965466,0.00042498138,0.0258215,0.00064726645],"about_ca_topic_score_codex":0.000011787534,"about_ca_topic_score_gemma":0.0000127517515,"teacher_disagreement_score":0.062788494,"about_ca_system_score_codex":0.000009961069,"about_ca_system_score_gemma":0.000101625126,"threshold_uncertainty_score":0.2556553},"labels":[],"label_agreement":null},{"id":"W3043435966","doi":"10.1093/bioinformatics/btaa469","title":"Finding the direct optimal RNA barrier energy and improving pathways with an arbitrary energy model","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Core Research for Evolutional Science and Technology; Ministry of Education, Culture, Sports, Science and Technology; Japan Society for the Promotion of Science; Institute of Genetics; Artificial Intelligence Research Center; National Institute of Advanced Industrial Science and Technology","keywords":"Heuristics; Computer science; Source code; Hamming distance; Code (set theory); Folding (DSP implementation); Energy (signal processing); RNA; Theoretical computer science; Algorithm; Chemistry; Mathematics","score_opus":0.015246508073107491,"score_gpt":0.1968845897067588,"score_spread":0.1816380816336513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3043435966","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4713139,0.0010075028,0.5147833,0.0003613975,0.000082204715,0.00023965654,0.0001020905,0.00008530439,0.012024628],"genre_scores_gemma":[0.9489147,0.00016512624,0.048387308,0.0021551433,0.00015475423,0.000025060297,0.000049769795,0.000028610842,0.00011949734],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992423,0.000029755005,0.00019770718,0.00017262889,0.00013563765,0.00022194245],"domain_scores_gemma":[0.99944353,0.000012508221,0.00010387048,0.00025354215,0.000028432245,0.00015809665],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011413939,0.00017519925,0.00013258569,0.000018805975,0.00017230357,0.000080036116,0.0002055392,0.000114526294,0.000005356411],"category_scores_gemma":[0.000029957027,0.00011441931,0.00004305367,0.000053988886,0.00005746581,0.000023905684,0.00011688927,0.000050591796,7.799058e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031127315,0.00002788464,0.00002720011,0.00008768599,0.00010901631,0.0000069970765,0.001667502,0.0024505488,0.8786367,0.0054036872,0.0004395119,0.11083199],"study_design_scores_gemma":[0.00024788585,0.0005089105,0.0000031099448,0.00001151885,0.00002410638,0.00001468933,0.00041587223,0.36968207,0.6240785,0.00012093144,0.0046442193,0.0002481621],"about_ca_topic_score_codex":0.00001215238,"about_ca_topic_score_gemma":0.0000076236406,"teacher_disagreement_score":0.47760084,"about_ca_system_score_codex":0.0000048523707,"about_ca_system_score_gemma":0.000087002096,"threshold_uncertainty_score":0.4665884},"labels":[],"label_agreement":null},{"id":"W3043467106","doi":"10.1093/bioinformatics/btaa434","title":"Identifying diagnosis-specific genotype–phenotype associations via joint multitask sparse canonical correlation analysis and classification","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; H. Lundbeck A/S; Servier; National Natural Science Foundation of China; Eisai; China Postdoctoral Science Foundation; National Institutes of Health; Northwestern Polytechnical University; Genentech; IXICO; Northern California Institute for Research and Education; Novartis Pharmaceuticals Corporation; BioClinica; Biogen; Pfizer; Northwestern University; University of Pennsylvania; University of Southern California; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; Meso Scale Diagnostics; Alzheimer's Association","keywords":"Canonical correlation; Correlation; Phenotype; Joint (building); Genotype; Computational biology; Computer science; Genetics; Artificial intelligence; Biology; Mathematics; Gene","score_opus":0.12460659311314032,"score_gpt":0.28276698208212503,"score_spread":0.1581603889689847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3043467106","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39816174,0.00040841952,0.5737638,0.018167406,0.0014221874,0.0016353801,0.0005437977,0.000751055,0.0051462515],"genre_scores_gemma":[0.99168926,0.00018266964,0.0059496164,0.0019452161,0.00009337172,0.000032644763,0.00006475304,0.000012583266,0.000029878165],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9985664,0.00007932397,0.00047946218,0.0002775736,0.00039502425,0.0002022239],"domain_scores_gemma":[0.9977915,0.0014893947,0.00030978248,0.00019467724,0.00009475983,0.00011987712],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021484355,0.00015088027,0.00024965007,0.00016903285,0.000395803,0.00013870669,0.00010817586,0.00008839678,0.000044077377],"category_scores_gemma":[0.004379508,0.00015083353,0.00009285875,0.0011266251,0.00009543266,0.00048442988,0.0001124701,0.00018765652,0.0002707978],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000293518,0.0009861639,0.5331125,0.0006104783,0.0020745143,0.00003060747,0.053145383,0.017750869,0.18403313,0.06734616,0.05815762,0.082459055],"study_design_scores_gemma":[0.0004301498,0.00007599595,0.533424,0.000009881355,0.0003018779,0.000002425292,0.00049217313,0.45618722,0.0033983197,0.00027837398,0.0050796364,0.0003199589],"about_ca_topic_score_codex":0.000028147135,"about_ca_topic_score_gemma":0.00008455167,"teacher_disagreement_score":0.59352756,"about_ca_system_score_codex":0.0001421106,"about_ca_system_score_gemma":0.00004048102,"threshold_uncertainty_score":0.61508125},"labels":[],"label_agreement":null},{"id":"W3046214778","doi":"10.1093/bioinformatics/btaa683","title":"Hive Panel Explorer: an interactive network visualization tool","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; Genome British Columbia; University of British Columbia","funders":"Genome British Columbia; Genome Canada","keywords":"Computer science; Visualization; License; Representation (politics); MIT License; Software; Interactive visualization; Function (biology); Data science; Data visualization; Data mining; World Wide Web; Programming language; Biology","score_opus":0.026032707409416673,"score_gpt":0.2550425047605303,"score_spread":0.22900979735111363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3046214778","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2226985,0.00038807906,0.7641136,0.0005469641,0.0008994744,0.0010585166,0.00011776703,0.00019462292,0.009982481],"genre_scores_gemma":[0.96180815,0.00021994827,0.026406076,0.008197906,0.0015943808,0.000029633164,0.0015989318,0.000050314193,0.000094666895],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988345,0.000030537445,0.00049521844,0.00016854492,0.00015159842,0.00031961367],"domain_scores_gemma":[0.9991731,0.000011596398,0.00023231558,0.00030288298,0.00009667682,0.00018343903],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014869214,0.00021128228,0.00018330071,0.000021829777,0.00011662052,0.00009760321,0.00027022863,0.00017471892,0.00003846495],"category_scores_gemma":[0.000057820063,0.00019720403,0.00008606116,0.00013771321,0.000050759598,0.000046349913,0.00018090657,0.00012093703,0.00011179137],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024619165,0.0005712162,0.005029974,0.00097193534,0.0015019554,0.000019703511,0.056104932,0.06016707,0.020215016,0.019909246,0.46896538,0.36408165],"study_design_scores_gemma":[0.0015842167,0.0016784797,0.0008682506,0.00005485382,0.00008557958,0.000027803175,0.0035145907,0.7621979,0.00598962,0.0006284097,0.22231974,0.0010505343],"about_ca_topic_score_codex":0.0000015958547,"about_ca_topic_score_gemma":0.0000030195592,"teacher_disagreement_score":0.73910964,"about_ca_system_score_codex":0.00001628528,"about_ca_system_score_gemma":0.00006367257,"threshold_uncertainty_score":0.8041747},"labels":[],"label_agreement":null},{"id":"W3047830475","doi":"10.1093/bioinformatics/btaa700","title":"FastBMD: an online tool for rapid benchmark dose–response analysis of transcriptomics data","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Genome Canada","keywords":"Benchmark (surveying); Computer science; Transcriptome; Data mining; Biology","score_opus":0.07772542409987128,"score_gpt":0.3109088631813704,"score_spread":0.23318343908149913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3047830475","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7862084,0.00023149814,0.20798028,0.0008183341,0.00012262739,0.00043978763,0.004033636,0.000022098102,0.00014334846],"genre_scores_gemma":[0.93882,0.00021459827,0.045248203,0.001457068,0.00012476454,0.000014476572,0.0140496595,0.000015811995,0.00005538941],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99909854,0.000037649115,0.00041360094,0.00019543243,0.00012573098,0.0001290395],"domain_scores_gemma":[0.9988877,0.000017265818,0.00017739639,0.000717726,0.00010414144,0.00009576448],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024974917,0.00011269594,0.00019444757,0.000081106235,0.000039369963,0.000022234497,0.00048141813,0.000104441446,0.000029409308],"category_scores_gemma":[0.00016648557,0.00010279636,0.000111501904,0.0002994557,0.000037516325,0.00001995673,0.0000795848,0.000040117367,0.00000113926],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00236994,0.00017638637,0.0005109544,0.00014216911,0.0005999299,1.5197918e-7,0.0009819454,0.00083494757,0.9328162,0.00006242821,0.015587007,0.045917936],"study_design_scores_gemma":[0.001760062,0.0010368904,0.0095132515,0.000011586384,0.0008225624,0.0000010386178,0.0015563809,0.5235468,0.08987304,0.0000074039503,0.37146345,0.00040750354],"about_ca_topic_score_codex":0.0000013639499,"about_ca_topic_score_gemma":0.0000062778126,"teacher_disagreement_score":0.8429432,"about_ca_system_score_codex":0.0000061439787,"about_ca_system_score_gemma":0.0001155771,"threshold_uncertainty_score":0.4191914},"labels":[],"label_agreement":null},{"id":"W3080498684","doi":"10.1093/bioinformatics/btaa750","title":"DELPHI: accurate deep ensemble model for protein interaction sites prediction","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":167,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Computer science; Delphi; Deep learning; Delphi method; Ensemble learning; Data mining; Artificial intelligence; Machine learning; Ensemble forecasting; Web server; The Internet","score_opus":0.02283886874922888,"score_gpt":0.25817084603009527,"score_spread":0.23533197728086638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3080498684","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.113673225,0.00005250538,0.88467276,0.0002049486,0.00005824546,0.0005828596,0.00008616412,0.000036500594,0.000632823],"genre_scores_gemma":[0.9224554,0.000024316882,0.07570096,0.0007468889,0.00021095306,0.00007864536,0.0006493746,0.000016745365,0.000116719064],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999358,0.000007071923,0.00026194536,0.00012609572,0.00008420576,0.00016268001],"domain_scores_gemma":[0.9995452,0.000003940585,0.0001249603,0.00015466493,0.000091231064,0.00007995706],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000057039266,0.00012561644,0.00009748202,0.000020480567,0.00007514074,0.00003926948,0.00011420757,0.00013636716,0.0000027600847],"category_scores_gemma":[0.00012088731,0.000115152565,0.00007188954,0.000052255775,0.000019380099,0.00002292396,0.00006129845,0.000066556306,0.00000887868],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007260434,0.000043192755,0.000121095625,0.0005523209,0.00012888608,6.501378e-7,0.0020737106,0.049796786,0.91223687,0.0009896611,0.007361552,0.025969226],"study_design_scores_gemma":[0.00035909723,0.00023449065,0.000009675223,0.000007646175,0.000015557045,0.0000041210646,0.00014100096,0.93565613,0.058538184,0.00031605264,0.0045923316,0.00012573271],"about_ca_topic_score_codex":8.08333e-7,"about_ca_topic_score_gemma":0.000007724963,"teacher_disagreement_score":0.8858593,"about_ca_system_score_codex":0.000013473619,"about_ca_system_score_gemma":0.000044517128,"threshold_uncertainty_score":0.46957853},"labels":[],"label_agreement":null},{"id":"W3085471204","doi":"10.1093/bioinformatics/btaa781","title":"CHESPA/CHESCA-SPARKY: automated NMR data analysis plugins for SPARKY to map protein allostery","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"National Institute of General Medical Sciences; National Heart, Lung, and Blood Institute; University of Colorado Denver; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; National Science Foundation","keywords":"Plug-in; Computer science; Visualization; Allosteric regulation; Software; Download; Data mining; Nuclear magnetic resonance; World Wide Web; Programming language; Physics","score_opus":0.047450940346056465,"score_gpt":0.28628587133260136,"score_spread":0.2388349309865449,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3085471204","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54704726,0.0016716778,0.41861904,0.017053582,0.0005481857,0.0053794035,0.0056586238,0.00065984303,0.0033623674],"genre_scores_gemma":[0.72008526,0.00019803416,0.26626816,0.0053589926,0.0007216622,0.00022821473,0.0059453277,0.00007745571,0.0011168962],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984629,0.00002180067,0.0005080866,0.00040427124,0.00019397869,0.0004089322],"domain_scores_gemma":[0.9985152,0.000016728405,0.00019279242,0.0009249509,0.00011152139,0.00023881916],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030476815,0.00026742974,0.00043669937,0.00012860511,0.00011760848,0.000088060915,0.00070274033,0.00014013797,0.000022447142],"category_scores_gemma":[0.00038567834,0.0002407734,0.000168049,0.0005032104,0.00004251814,0.00001742646,0.0007787971,0.00007387234,0.00006256389],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001167859,0.0003963697,0.0033334275,0.0018614604,0.011444859,0.0000085824895,0.0021470147,0.002534207,0.41712588,0.0014517615,0.55136055,0.0071680443],"study_design_scores_gemma":[0.0011068089,0.00071667077,0.001041213,0.000019973266,0.00078132754,0.0000021367582,0.00048823876,0.18573438,0.05683032,0.00002414635,0.75250053,0.0007542515],"about_ca_topic_score_codex":0.000008829743,"about_ca_topic_score_gemma":0.000041907508,"teacher_disagreement_score":0.36029553,"about_ca_system_score_codex":0.000017040162,"about_ca_system_score_gemma":0.000080000835,"threshold_uncertainty_score":0.9818454},"labels":[],"label_agreement":null},{"id":"W3089154911","doi":"10.1093/bioinformatics/btaa829","title":"IsoResolve: predicting splice isoform functions by integrating gene and isoform-level features with domain adaptation","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"National Cancer Institute; National Institutes of Health; National Institute of Environmental Health Sciences; National Key Research and Development Program of China; Higher Education Discipline Innovation Project; National Natural Science Foundation of China","keywords":"Gene isoform; splice; Adaptation (eye); Alternative splicing; Computational biology; Domain (mathematical analysis); Focus (optics); Gene; Biology; Computer science; Genetics; Neuroscience; Mathematics","score_opus":0.011538196552200689,"score_gpt":0.20273656914766616,"score_spread":0.19119837259546546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3089154911","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27191773,0.0010593596,0.7200495,0.0007557448,0.00012775448,0.0005908698,0.000394377,0.00007612142,0.005028531],"genre_scores_gemma":[0.74766445,0.00037850637,0.2452599,0.0036713027,0.00051519903,0.00004951823,0.0019265731,0.000063226,0.0004713431],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988422,0.000012491698,0.00044662532,0.00018743824,0.0001811164,0.00033015318],"domain_scores_gemma":[0.9992228,0.000018799496,0.00025717675,0.00021687275,0.00008797045,0.0001963688],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016659034,0.0002561914,0.00018866132,0.00003435662,0.00032102104,0.00012473107,0.00016328295,0.00019797844,0.0000068026625],"category_scores_gemma":[0.000045756897,0.00020315287,0.000054234402,0.00014721672,0.000114122966,0.000041616535,0.00013735773,0.0002180399,0.000011406654],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026083677,0.00037570595,0.017506361,0.0023526167,0.002024237,0.000011797395,0.093356445,0.0082435245,0.1776819,0.0025408815,0.31854346,0.3747547],"study_design_scores_gemma":[0.0072257672,0.00527167,0.005777077,0.00028907877,0.00033344398,0.00046340248,0.07562667,0.680439,0.022579243,0.00032266643,0.19886707,0.002804942],"about_ca_topic_score_codex":0.000024009345,"about_ca_topic_score_gemma":0.000070365444,"teacher_disagreement_score":0.67219543,"about_ca_system_score_codex":0.000017461129,"about_ca_system_score_gemma":0.00008980028,"threshold_uncertainty_score":0.8284334},"labels":[],"label_agreement":null},{"id":"W3092157588","doi":"10.1093/bioinformatics/btaa867","title":"Particle Gibbs sampling for Bayesian phylogenetic inference","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Markov chain Monte Carlo; Gibbs sampling; Phylogenetic tree; Computer science; Particle filter; Inference; Tree (set theory); Bayesian inference; Bayesian probability; Markov chain; Sampling (signal processing); Monte Carlo method; Algorithm; Data mining; Theoretical computer science; Artificial intelligence; Mathematics; Machine learning; Statistics; Biology; Combinatorics","score_opus":0.04092308051789186,"score_gpt":0.275039594293375,"score_spread":0.23411651377548312,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092157588","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7331757,0.001119644,0.26298052,0.0008586951,0.00016588077,0.000569435,0.00011918261,0.000017222214,0.0009937286],"genre_scores_gemma":[0.9602338,0.00016140992,0.037865177,0.001389888,0.0002271801,0.000035008794,0.00003591765,0.000016159876,0.000035441688],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992312,0.000008325456,0.0002724241,0.00015521402,0.00007539607,0.00025743767],"domain_scores_gemma":[0.9995011,0.000024816642,0.000081950435,0.0001920563,0.00007273517,0.00012735174],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007454285,0.00013926781,0.00013760227,0.000010026323,0.00010535456,0.00003431378,0.00017690496,0.0000723278,0.0000065381405],"category_scores_gemma":[0.0001665784,0.00013164141,0.00008071723,0.00006409185,0.00004761365,0.0000012430145,0.00011591853,0.00003625501,0.000016245],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022827993,0.00008324831,0.021129506,0.00043017813,0.00028558096,7.5806184e-7,0.002944836,0.0039180126,0.9095521,0.0019012094,0.0034380686,0.056088235],"study_design_scores_gemma":[0.0033003613,0.0027224405,0.011235899,0.00003476076,0.00015359334,0.000010500561,0.0017649222,0.13681456,0.42068863,0.0010068663,0.42080912,0.00145835],"about_ca_topic_score_codex":0.0000015608596,"about_ca_topic_score_gemma":0.0000034296345,"teacher_disagreement_score":0.48886347,"about_ca_system_score_codex":0.00000469244,"about_ca_system_score_gemma":0.0000548869,"threshold_uncertainty_score":0.53681815},"labels":[],"label_agreement":null},{"id":"W3092159560","doi":"10.1093/bioinformatics/btaa882","title":"DoubleRecViz: a web-based tool for visualizing transcript–gene–species tree reconciliation","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Phylogenetic tree; Tree (set theory); Visualization; Toolbox; Python (programming language); Phylogenetic network; Biology; Computer science; Phylogenetics; Gene; Computational biology; Data mining; Genetics; Programming language","score_opus":0.040083956390118754,"score_gpt":0.25121907701317914,"score_spread":0.2111351206230604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092159560","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90232736,0.0008599337,0.08957834,0.001676213,0.00045010124,0.0010472874,0.00034731868,0.000036350917,0.003677078],"genre_scores_gemma":[0.96583056,0.00018347299,0.030553719,0.00256768,0.00035000325,0.00007810331,0.00024508734,0.000025654032,0.00016572111],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99912393,0.000012706471,0.0003626463,0.00016641371,0.000106291336,0.00022799111],"domain_scores_gemma":[0.99950314,0.000019385923,0.00011615589,0.00017493573,0.000111848996,0.00007452588],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012662381,0.00017077384,0.0001761199,0.000026311,0.00011601474,0.000046591536,0.00015716745,0.00010812924,0.000009154004],"category_scores_gemma":[0.000088488334,0.00016270287,0.0001510303,0.0000748834,0.00003936296,0.0000026067655,0.00003374256,0.00003943389,0.000009950639],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026489721,0.000033996897,0.0015625797,0.00024139721,0.00012103253,2.9723685e-7,0.0009291142,0.0005466702,0.9757211,0.00028670914,0.011961187,0.008330991],"study_design_scores_gemma":[0.0031803544,0.0008758531,0.0013917425,0.00001532473,0.00007238425,0.0000019903757,0.00049863063,0.040006083,0.43708375,0.00004113395,0.5163321,0.00050066534],"about_ca_topic_score_codex":0.0000014714582,"about_ca_topic_score_gemma":0.000011952459,"teacher_disagreement_score":0.5386374,"about_ca_system_score_codex":0.0000137462275,"about_ca_system_score_gemma":0.00011331622,"threshold_uncertainty_score":0.6634831},"labels":[],"label_agreement":null},{"id":"W3093585277","doi":"10.1093/bioinformatics/btaa906","title":"Leveraging heterogeneous network embedding for metabolic pathway prediction","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Genome British Columbia; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Genome British Columbia; Compute Canada; Genome Canada","keywords":"Computer science; Embedding; Computational biology; Artificial intelligence; Biology","score_opus":0.017715284303641308,"score_gpt":0.22994934628557556,"score_spread":0.21223406198193426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3093585277","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058748756,0.0015726764,0.9349934,0.00028997395,0.000837795,0.00092280697,0.00018448815,0.000107629756,0.0023424812],"genre_scores_gemma":[0.893571,0.00031383103,0.097030886,0.004837081,0.0030370322,0.000079477824,0.00091255177,0.00006264792,0.00015544148],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99878365,0.000013192891,0.000506335,0.0001650203,0.00012360953,0.000408165],"domain_scores_gemma":[0.99929786,0.000015480025,0.0001922979,0.000244247,0.00007206401,0.00017807384],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020265741,0.00020537553,0.00021062247,0.000021950997,0.00018322375,0.00007691723,0.0002152963,0.00013751771,0.000010339962],"category_scores_gemma":[0.000053451487,0.00019577508,0.00016260328,0.000100032405,0.000033031327,0.000014006555,0.0001318283,0.0000945852,0.000022620643],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007507253,0.00011834249,0.001958003,0.0011892894,0.001245429,0.000005157159,0.0073349117,0.5334431,0.020064011,0.003536773,0.153354,0.27700025],"study_design_scores_gemma":[0.0007565612,0.00031277005,0.000043573637,0.000018419556,0.000041104253,0.00001989386,0.00021718843,0.5996467,0.0062012346,0.00018703764,0.3922528,0.0003027473],"about_ca_topic_score_codex":7.193169e-7,"about_ca_topic_score_gemma":9.0320515e-7,"teacher_disagreement_score":0.8379625,"about_ca_system_score_codex":0.000009689087,"about_ca_system_score_gemma":0.000065899876,"threshold_uncertainty_score":0.7983476},"labels":[],"label_agreement":null},{"id":"W3095372394","doi":"10.1093/bioinformatics/btaa945","title":"ALeS: adaptive-length spaced-seed design","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Metaheuristic Optimization Algorithms Research","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Computer science; Heuristic; Software; Source code; Computation; Similarity (geometry); Algorithm; Code (set theory); Sensitivity (control systems); Sequence (biology); Data mining; Theoretical computer science; Programming language; Artificial intelligence; Biology","score_opus":0.08403751598559044,"score_gpt":0.27139443497950566,"score_spread":0.1873569189939152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3095372394","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000012041261,0.00003733157,0.99217045,0.002128303,0.00012325405,0.00033286377,0.0000051206184,0.00022570924,0.0049649454],"genre_scores_gemma":[0.005348897,0.000046840636,0.993045,0.0012748007,0.000064650136,0.000010386299,0.0000040880277,0.0000111891495,0.00019418112],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99837875,0.000088771296,0.00039255514,0.00018416565,0.0006174251,0.00033832502],"domain_scores_gemma":[0.99870116,0.00019334335,0.00013416281,0.0004508756,0.00018129127,0.0003391434],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00039991163,0.00015538243,0.000193901,0.00010262659,0.00011173922,0.00026333044,0.0010808242,0.0000639507,0.000068193054],"category_scores_gemma":[0.0005036046,0.00013688905,0.00005344026,0.0007205994,0.000057913476,0.00075278146,0.0003648954,0.00017405502,0.0012826355],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020238376,0.00046883788,0.00040143324,0.00082664215,0.00048588068,0.00019435197,0.056502733,0.1635991,0.00064968446,0.2537267,0.19745198,0.32549027],"study_design_scores_gemma":[0.00032760383,0.00016158506,0.00008390615,0.000008147,0.000003967564,0.0000062558133,0.00022717369,0.9943033,0.00051160314,0.00014400628,0.004053848,0.00016860347],"about_ca_topic_score_codex":0.000002560119,"about_ca_topic_score_gemma":1.9854845e-7,"teacher_disagreement_score":0.8307042,"about_ca_system_score_codex":0.00003627089,"about_ca_system_score_gemma":0.00020068244,"threshold_uncertainty_score":0.99949497},"labels":[],"label_agreement":null},{"id":"W3097039570","doi":"10.1093/bioinformatics/btad167","title":"Finite mixtures of matrix variate Poisson-log normal distributions for three-way count data","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Carleton University; University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; University of Toronto; Carleton University","keywords":"Random variate; Cluster analysis; Computer science; Poisson distribution; Markov chain Monte Carlo; Covariance matrix; Algorithm; Gaussian; Mixture model; Data mining; Mathematics; Statistics; Artificial intelligence; Bayesian probability; Random variable","score_opus":0.04948721312213769,"score_gpt":0.31552877440143295,"score_spread":0.26604156127929524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3097039570","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014709031,0.000068140966,0.99563164,0.00069762074,0.0005038688,0.00034111316,0.001840446,0.00017304497,0.0005970552],"genre_scores_gemma":[0.011340581,0.000040471034,0.9875301,0.000119142125,0.000086730324,0.000021529582,0.00067421136,0.000010287404,0.00017691815],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985558,0.000027009266,0.0005417987,0.00019760821,0.00028801415,0.00038976272],"domain_scores_gemma":[0.99775374,0.0004021668,0.0002466783,0.001351577,0.00014551953,0.00010030099],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012023593,0.00015992037,0.00025024798,0.00013101175,0.00017558003,0.00013066472,0.0016692366,0.000110362744,0.000006130798],"category_scores_gemma":[0.00027703552,0.00013194093,0.000085147665,0.00061922387,0.00005735334,0.0008286086,0.00077849336,0.000107583095,0.000047287922],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027167656,0.0000964307,0.0001220885,0.00059467985,0.00012226595,0.000005596167,0.0016281803,0.000491403,0.00027725473,0.7545588,0.067737885,0.17433827],"study_design_scores_gemma":[0.000334089,0.000062625935,0.00044770233,0.000029713152,0.000025656112,0.0000061526985,0.000011057845,0.95289415,0.00047101063,0.03214168,0.013398309,0.00017782359],"about_ca_topic_score_codex":0.0000191476,"about_ca_topic_score_gemma":0.000013465385,"teacher_disagreement_score":0.9524028,"about_ca_system_score_codex":0.000019744106,"about_ca_system_score_gemma":0.00013092355,"threshold_uncertainty_score":0.5380395},"labels":[],"label_agreement":null},{"id":"W3102269903","doi":"10.1093/bioinformatics/btaa287","title":"DTF: Deep Tensor Factorization for predicting anticancer drug synergy","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":85,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"CancerCare Manitoba; Research Institute in Oncology and Hematology; University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Computer science; Artificial intelligence; Machine learning; Logistic regression; Drug; Classifier (UML); Artificial neural network; Data mining; Pharmacology; Biology","score_opus":0.029312767236159363,"score_gpt":0.2798065312882639,"score_spread":0.2504937640521045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3102269903","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035414267,0.000027831145,0.9930749,0.0016282874,0.00041632398,0.00027879517,0.00001865803,0.00022378117,0.0007900036],"genre_scores_gemma":[0.2725364,0.000008508688,0.7254911,0.0016350527,0.00023262874,0.000022799535,0.000029688581,0.00001274267,0.000031083222],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988724,0.000031651623,0.00039140217,0.00016626967,0.0003129511,0.0002253503],"domain_scores_gemma":[0.9989422,0.00039492815,0.00018007617,0.0002047951,0.0001543967,0.0001236227],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002204541,0.00012851432,0.00015497036,0.00005622347,0.00012350525,0.00019336138,0.00050117075,0.000038244038,0.000005830976],"category_scores_gemma":[0.00049835397,0.000118742464,0.000071709655,0.00036774334,0.000022398655,0.0010173721,0.00018035485,0.000072118,0.000025069661],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060332415,0.00010563704,0.00483015,0.0010343725,0.00016025658,0.000004152306,0.0374162,0.40941453,0.00031863883,0.21123162,0.00793532,0.32748878],"study_design_scores_gemma":[0.00025593807,0.000043142303,0.0008652276,0.000014184074,0.0000077389905,0.0000019736565,0.00015134457,0.9914489,0.0005240134,0.0015317338,0.0050077573,0.00014809049],"about_ca_topic_score_codex":0.0000030916538,"about_ca_topic_score_gemma":0.0000010729426,"teacher_disagreement_score":0.58203435,"about_ca_system_score_codex":0.00004470998,"about_ca_system_score_gemma":0.000107668086,"threshold_uncertainty_score":0.48421773},"labels":[],"label_agreement":null},{"id":"W3104008342","doi":"10.1093/bioinformatics/btaa973","title":"MetaADEDB 2.0: a comprehensive database on adverse drug events","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Pharmacovigilance and Adverse Drug Reactions","field":"Pharmacology, Toxicology and Pharmaceutics","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"National Key Research and Development Program of China; China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Adverse Event Reporting System; Computer science; Database; Drug; Online database; Drug reaction; Adverse effect; Information retrieval; World Wide Web; Data mining; Medicine; Pharmacology","score_opus":0.1810652966885001,"score_gpt":0.4259213948965154,"score_spread":0.24485609820801532,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3104008342","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8776074,0.00047987606,0.0020243449,0.016992852,0.004854858,0.0026895932,0.0032551629,0.0012818403,0.09081405],"genre_scores_gemma":[0.94694275,0.00040676593,0.0014771144,0.049396507,0.00053203607,0.00005608912,0.0003996871,0.000038246584,0.00075082475],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984419,0.00013156151,0.00048512805,0.00021909186,0.00026876235,0.0004536069],"domain_scores_gemma":[0.9986428,0.00026103377,0.00021945024,0.0002441514,0.0000829545,0.00054959656],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00017376659,0.00029504835,0.00030900165,0.00009845259,0.0002814639,0.000012297335,0.0003583633,0.00013185361,0.0010672841],"category_scores_gemma":[0.00008494322,0.00027074513,0.00016993757,0.00032931945,0.00009676891,0.00049121527,0.00013476948,0.0008826432,0.0056040804],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002467971,0.0016903728,0.005966472,0.0012641189,0.0019413166,0.00034304327,0.017550718,0.026551506,0.035704672,0.0058980044,0.8775103,0.023111513],"study_design_scores_gemma":[0.0028262916,0.000091465256,0.00041838086,0.00002943229,0.00024268952,0.000016133177,0.0014292138,0.05887735,0.019145284,0.00004097811,0.91646576,0.0004170092],"about_ca_topic_score_codex":0.000004885133,"about_ca_topic_score_gemma":0.0000013898687,"teacher_disagreement_score":0.09006322,"about_ca_system_score_codex":0.00005854174,"about_ca_system_score_gemma":0.00009296767,"threshold_uncertainty_score":0.9999745},"labels":[],"label_agreement":null},{"id":"W3108043540","doi":"10.1093/bioinformatics/btab158","title":"Conditional canonical correlation estimation based on covariates with random forests","year":2021,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Centre Hospitalier Universitaire Sainte-Justine; HEC Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Canonical correlation; Correlation; Statistics; Random forest; Mathematics; Computer science; Data mining; Artificial intelligence","score_opus":0.022750724464176218,"score_gpt":0.2514645990948229,"score_spread":0.22871387463064666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3108043540","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02617417,0.000008602181,0.9521559,0.0043960814,0.0006599077,0.00047051013,0.00015149769,0.00019997619,0.015783338],"genre_scores_gemma":[0.9785864,0.0000015415615,0.016359588,0.0046314327,0.000053617732,0.00003401476,0.00014660746,0.000010108407,0.00017671827],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99896514,0.000056179648,0.00022072312,0.00015580455,0.00045261288,0.00014955678],"domain_scores_gemma":[0.994935,0.004554788,0.00011607259,0.0001693765,0.00017713218,0.000047664886],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00013830225,0.00011919173,0.00013544956,0.00006789169,0.00024384954,0.000067842964,0.000059872073,0.000050539256,0.00008521713],"category_scores_gemma":[0.009767904,0.00009653925,0.0000410229,0.00025379073,0.00009706552,0.0002935497,0.000024095592,0.00011619406,0.00014812399],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000863852,0.00030170497,0.005226403,0.000123001,0.000031260734,0.000036242323,0.0003402296,0.9000392,0.00047699237,0.07238532,0.018307703,0.0018680873],"study_design_scores_gemma":[0.0022050552,0.00016815122,0.010431206,0.000044821343,0.000016476857,0.000026113217,0.000040223033,0.9765396,0.007228056,0.00139366,0.0017618003,0.00014480304],"about_ca_topic_score_codex":0.000003159482,"about_ca_topic_score_gemma":0.000035786004,"teacher_disagreement_score":0.9524122,"about_ca_system_score_codex":0.000080959355,"about_ca_system_score_gemma":0.00027484354,"threshold_uncertainty_score":0.99857324},"labels":[],"label_agreement":null},{"id":"W3111754743","doi":"10.1093/bioinformatics/btaa1019","title":"<i>MorphOT</i> : transport-based interpolation between EM maps with UCSF <i>ChimeraX</i>","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Advanced Electron Microscopy Techniques and Applications","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Morphing; Computer science; Interpolation (computer graphics); Documentation; Code (set theory); Source code; Software; Metric (unit); Algorithm; Linear interpolation; Computer graphics (images); Data mining; Computational science; Theoretical computer science; Image (mathematics); Artificial intelligence; Programming language; Pattern recognition (psychology); Set (abstract data type)","score_opus":0.009067360275982882,"score_gpt":0.2572769591131348,"score_spread":0.24820959883715193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3111754743","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07919076,0.000057125984,0.9185291,0.00052643224,0.000010316512,0.00036136562,0.00021900565,0.000093039904,0.0010128487],"genre_scores_gemma":[0.8644585,0.000028938837,0.13091934,0.0028345545,0.00012861758,0.000037459453,0.0015140008,0.000029257115,0.000049319293],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992891,0.000006880314,0.00025785516,0.00015280269,0.00009730173,0.00019603777],"domain_scores_gemma":[0.99949765,0.0000049991095,0.00012071149,0.00022234055,0.000047693946,0.000106595384],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00004111832,0.00015375235,0.00012901862,0.000019634594,0.000073167335,0.000017765316,0.00016723378,0.00009113084,0.000012689808],"category_scores_gemma":[0.000004951151,0.00013416623,0.00005411001,0.00013790246,0.00004393283,0.000010110019,0.000020306952,0.00010272079,0.000014186808],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039173508,0.000105268264,0.011442882,0.00026897714,0.00012515543,0.0000022744534,0.0007516961,0.00077687635,0.93994176,0.00034767605,0.026971372,0.018874338],"study_design_scores_gemma":[0.0007969997,0.00092020526,0.0004121365,0.00002915553,0.00005533298,0.000004813826,0.00016312882,0.0031595908,0.73772544,0.000048314218,0.25624803,0.00043685443],"about_ca_topic_score_codex":0.0000023600905,"about_ca_topic_score_gemma":0.0000057456696,"teacher_disagreement_score":0.78760976,"about_ca_system_score_codex":0.000008352451,"about_ca_system_score_gemma":0.00005474214,"threshold_uncertainty_score":0.547114},"labels":[],"label_agreement":null},{"id":"W3112246030","doi":"10.1093/bioinformatics/btaa1038","title":"Identification of differentially expressed gene modules in heterogeneous diseases","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Identification (biology); Gene; Computational biology; Genetics; Biology; Computer science","score_opus":0.01023522611631228,"score_gpt":0.2154059868898163,"score_spread":0.20517076077350402,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3112246030","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9307458,0.00041789128,0.067992315,0.00011200201,0.00010000774,0.00025819856,0.000190989,0.000014710462,0.00016807749],"genre_scores_gemma":[0.99660236,0.00020096164,0.0025521414,0.00024747496,0.000088827044,0.000009995804,0.00026867687,0.000011692153,0.000017862634],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989685,0.000014862605,0.0006180929,0.00011044539,0.00012351252,0.00016463271],"domain_scores_gemma":[0.99935734,0.000006311215,0.0002355568,0.0002629953,0.000045068336,0.00009272755],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000061291954,0.00012655121,0.00016718551,0.000028197019,0.000025663141,0.000026596195,0.00022861837,0.00009967261,0.000008628176],"category_scores_gemma":[0.000040699506,0.0001199097,0.00008077983,0.00008380615,0.000049135302,0.000009473841,0.00011763744,0.000049262617,0.0000110981855],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035334853,0.0002534045,0.005091273,0.00082501426,0.00018039951,0.0000037872155,0.0022129035,0.020885734,0.9332985,0.0004111648,0.0031610087,0.03332343],"study_design_scores_gemma":[0.0018596775,0.00037756545,0.006456922,0.000042210042,0.000059646114,0.000007878279,0.00034077864,0.37234592,0.61386526,0.00044795487,0.003609458,0.00058672973],"about_ca_topic_score_codex":0.0000018013762,"about_ca_topic_score_gemma":0.0000032474925,"teacher_disagreement_score":0.3514602,"about_ca_system_score_codex":0.0000066222265,"about_ca_system_score_gemma":0.00003180121,"threshold_uncertainty_score":0.48897758},"labels":[],"label_agreement":null},{"id":"W3112841179","doi":"10.1093/bioinformatics/btaa1008","title":"Prioritizing genes for systematic variant effect mapping","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sinai Health System; Lunenfeld-Tanenbaum Research Institute; University of Toronto","funders":"National Human Genome Research Institute; Canada Excellence Research Chairs, Government of Canada","keywords":"Missense mutation; Prioritization; Gene; Computational biology; Pathogenicity; Protein function; Source code; Biology; Genetics; Mutation; Computer science","score_opus":0.013396985121383712,"score_gpt":0.2290038695373218,"score_spread":0.2156068844159381,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3112841179","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73731613,0.005147515,0.24819766,0.0006598972,0.0006643506,0.005552603,0.00034161814,0.00013733801,0.0019828635],"genre_scores_gemma":[0.9755606,0.000089924615,0.02219652,0.0012489817,0.00044308315,0.00012810799,0.00023843085,0.000032390435,0.000061965635],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99929476,0.000019198997,0.0003057899,0.0001171771,0.00007726269,0.00018579041],"domain_scores_gemma":[0.99951434,0.00002773298,0.00011606054,0.00017522431,0.000050983115,0.000115643685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014509769,0.00013322588,0.00019959321,0.000020737147,0.00008865952,0.000055290344,0.0001525965,0.00007421922,0.0000013942262],"category_scores_gemma":[0.00020928166,0.00010782683,0.00013248937,0.00005018098,0.000016119202,0.0000044827157,0.000075049946,0.000027107939,0.00001980536],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005480833,0.00016217456,0.0012230821,0.29030088,0.0014530536,0.00006907019,0.004963209,0.00090165535,0.6676892,0.0023274464,0.017612116,0.012750042],"study_design_scores_gemma":[0.013855289,0.008146123,0.0011762588,0.008229901,0.0014248777,0.0006144218,0.009662083,0.5537897,0.19983971,0.00028055737,0.19766536,0.0053157243],"about_ca_topic_score_codex":7.058446e-7,"about_ca_topic_score_gemma":3.3004898e-7,"teacher_disagreement_score":0.55288804,"about_ca_system_score_codex":0.000007204197,"about_ca_system_score_gemma":0.00004713851,"threshold_uncertainty_score":0.43970504},"labels":[],"label_agreement":null},{"id":"W3115522577","doi":"10.1093/bioinformatics/btaa842","title":"Supervised learning on phylogenetically distributed data","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; McGill University","funders":"Genome Canada","keywords":"Computer science; Generalization; Phylogenetic tree; Context (archaeology); Machine learning; Artificial intelligence; Independent and identically distributed random variables; Flexibility (engineering); Artificial neural network; Tree (set theory); Data mining; Biology; Mathematics; Statistics; Genetics","score_opus":0.026320987439237244,"score_gpt":0.26800879019179735,"score_spread":0.2416878027525601,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3115522577","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3641326,0.00045208453,0.59783787,0.0029751167,0.000064623295,0.000903523,0.00042686687,0.00051735435,0.032689925],"genre_scores_gemma":[0.9666054,0.00021969524,0.023621019,0.0029780762,0.00020473586,0.000005942153,0.006239883,0.000026122269,0.00009912871],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99914885,0.00002833066,0.0002667358,0.00021485596,0.00015724589,0.0001839967],"domain_scores_gemma":[0.99907583,0.000011424847,0.000074458156,0.00065848837,0.000057964597,0.00012183804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012248404,0.0001362014,0.00013447476,0.000021571306,0.000059073227,0.000050211922,0.0005554548,0.000097170574,0.000036121233],"category_scores_gemma":[0.00041905962,0.00012522175,0.000057929323,0.00012764725,0.000047708465,0.000007191072,0.00045316058,0.00012073156,0.00009849],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029317682,0.00022528623,0.005705547,0.00022767097,0.0004100302,0.000018781704,0.00044270963,0.0011733114,0.6527526,0.00017166558,0.2677403,0.07083893],"study_design_scores_gemma":[0.0006667276,0.0009553337,0.00064120686,0.000016613174,0.00008547237,0.0000061073843,0.00025502118,0.19765407,0.3040449,0.000013283701,0.4951499,0.0005113775],"about_ca_topic_score_codex":0.0000016965914,"about_ca_topic_score_gemma":0.0000014199521,"teacher_disagreement_score":0.6024728,"about_ca_system_score_codex":0.0000057452307,"about_ca_system_score_gemma":0.000036008012,"threshold_uncertainty_score":0.5106394},"labels":[],"label_agreement":null},{"id":"W3115554950","doi":"10.1093/bioinformatics/btab189","title":"The NRGTEN Python package: an extensible toolkit for coarse-grained normal mode analysis of proteins, nucleic acids, small molecules and their complexes","year":2021,"lang":"en","type":"preprint","venue":"Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Institute for Research in Immunology and Cancer","funders":"","keywords":"Python (programming language); Computer science; Extensibility; Docking (animal); Chemistry; Programming language","score_opus":0.013682821071897035,"score_gpt":0.24898436254100595,"score_spread":0.23530154146910892,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3115554950","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70952284,0.0018161248,0.28468296,0.00012680702,0.00015600477,0.0015497276,0.0018576605,0.000036427482,0.00025141498],"genre_scores_gemma":[0.7617436,0.0012582988,0.22555786,0.00034707022,0.00017907472,0.0002344067,0.010460589,0.00007967368,0.00013938572],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983422,0.00007217425,0.0006990578,0.00035550783,0.00016577746,0.00036523904],"domain_scores_gemma":[0.9977353,0.000044009023,0.00054745225,0.0011515552,0.0004055822,0.00011605989],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00033479475,0.00041509347,0.00062215066,0.00012656245,0.00022002438,0.00022690168,0.00053609174,0.000470477,0.000002273275],"category_scores_gemma":[0.00015780299,0.0002945284,0.00039111692,0.00018526435,0.00024024,0.000014547533,0.0007961453,0.00022334489,2.2461288e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023180232,0.00058285985,0.0021902386,0.0068413024,0.019414628,0.000012895938,0.011623138,0.043582473,0.74499834,0.008089434,0.0013270605,0.1590196],"study_design_scores_gemma":[0.0010871473,0.00068110385,0.001740324,0.00013316952,0.0014441457,0.000021960705,0.0036058465,0.8757084,0.10852699,0.0019942657,0.003957353,0.0010993062],"about_ca_topic_score_codex":0.00007196963,"about_ca_topic_score_gemma":0.00071776885,"teacher_disagreement_score":0.8321259,"about_ca_system_score_codex":0.000017635226,"about_ca_system_score_gemma":0.00022772285,"threshold_uncertainty_score":0.9999507},"labels":[],"label_agreement":null},{"id":"W3117084002","doi":"10.1093/bioinformatics/btaa1077","title":"Improving circRNA–disease association prediction by sequence and ontology representations with convolutional and recurrent neural networks","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Circular RNAs in diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Higher Education Discipline Innovation Project; National Natural Science Foundation of China","keywords":"Computer science; Ontology; Convolutional neural network; Identification (biology); Sequence (biology); Artificial intelligence; Disease; Machine learning; Computational biology; Biology; Genetics; Medicine","score_opus":0.012069895630337916,"score_gpt":0.2344749164493988,"score_spread":0.22240502081906088,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3117084002","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93702936,0.0024292092,0.05826319,0.001046564,0.00014582997,0.000439238,0.00047593244,0.000048947983,0.00012170762],"genre_scores_gemma":[0.9973091,0.0002612043,0.000930563,0.00060165307,0.00011608217,0.000019554918,0.0007338947,0.000008146313,0.00001978752],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99938273,0.000027881457,0.00017595435,0.00015583154,0.000120164696,0.0001374356],"domain_scores_gemma":[0.9994975,0.00001743546,0.00013785172,0.00010236299,0.00007022297,0.00017467946],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000059161554,0.00009272725,0.000076943026,0.000013671488,0.00009450242,0.00004231947,0.000051449697,0.00006906194,0.0000028877766],"category_scores_gemma":[0.00024738655,0.000090521586,0.000020844358,0.000050700906,0.00007281904,0.000021890291,0.00006332265,0.00007082061,6.3705016e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006707486,0.00014765511,0.8999865,0.000542086,0.00045202876,0.000011915863,0.00077480637,0.0055188993,0.026898237,0.00047726624,0.035447028,0.029072825],"study_design_scores_gemma":[0.0012263343,0.00036690614,0.057717044,0.000020514766,0.00016846608,0.000031939027,0.000246705,0.9369001,0.00044954158,0.000021215727,0.0025643443,0.00028692043],"about_ca_topic_score_codex":0.000007747725,"about_ca_topic_score_gemma":0.0000053393796,"teacher_disagreement_score":0.93138117,"about_ca_system_score_codex":0.000027188484,"about_ca_system_score_gemma":0.000053338706,"threshold_uncertainty_score":0.3691363},"labels":[],"label_agreement":null},{"id":"W3118845805","doi":"10.1093/bioinformatics/btaa1105","title":"PhyloCorrelate: inferring bacterial gene–gene functional associations through large-scale phylogenetic profiling","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo","keywords":"Phylogenetic tree; Computational biology; Profiling (computer programming); Gene; Biology; Genetics; Computer science","score_opus":0.017719928573947816,"score_gpt":0.2259968109679526,"score_spread":0.20827688239400477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3118845805","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6110641,0.00044022783,0.37733078,0.00045121927,0.0013957057,0.00088106643,0.0007235168,0.00012119802,0.0075922096],"genre_scores_gemma":[0.88923705,0.00022731126,0.10030357,0.0033484658,0.0023346501,0.000052584815,0.004225426,0.00006741472,0.00020356015],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983299,0.000027018019,0.00068762625,0.00022656353,0.00024423166,0.00048470116],"domain_scores_gemma":[0.99905694,0.000014590559,0.00031190313,0.00031627843,0.00012293225,0.00017735586],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00019434337,0.00027588406,0.0002514926,0.000030061954,0.0002667873,0.00010432424,0.00025290824,0.00031695963,0.000063502586],"category_scores_gemma":[0.00006086646,0.0002749531,0.00016983335,0.0001747123,0.000052589832,0.000029458168,0.00027870963,0.00021139842,0.00014946489],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00076600845,0.0005313362,0.020447163,0.00069472933,0.0014394441,0.000008455475,0.012932832,0.038497314,0.861951,0.0023268517,0.049805723,0.010599122],"study_design_scores_gemma":[0.0074222386,0.0014553146,0.00823499,0.00006208759,0.00034162842,0.000073138275,0.0023410267,0.35295463,0.43586504,0.0006575141,0.18787919,0.0027132062],"about_ca_topic_score_codex":0.0000023486643,"about_ca_topic_score_gemma":0.000007067651,"teacher_disagreement_score":0.42608598,"about_ca_system_score_codex":0.000035085308,"about_ca_system_score_gemma":0.00015823898,"threshold_uncertainty_score":0.99997026},"labels":[],"label_agreement":null},{"id":"W3122382017","doi":"10.1093/bioinformatics/btab022","title":"PrInCE: an R/Bioconductor package for protein–protein interaction network inference from co-fractionation mass spectrometry data","year":2021,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"","keywords":"Bioconductor; Computer science; Source code; Scripting language; Software; Plug-in; Inference; Workflow; Data mining; Programming language; Database; Artificial intelligence; Chemistry","score_opus":0.033643065196177366,"score_gpt":0.3009317678640216,"score_spread":0.2672887026678442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3122382017","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3063627,0.00020597051,0.68842185,0.00017365562,0.000637346,0.0011528156,0.0011765175,0.000056250836,0.0018129327],"genre_scores_gemma":[0.56230193,0.00011652256,0.40243602,0.00052935,0.0018769581,0.00011647492,0.03179126,0.000050575232,0.00078092306],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984212,0.000045543347,0.0006168234,0.00033577136,0.00021319816,0.00036747265],"domain_scores_gemma":[0.997983,0.000031618052,0.00040505402,0.0012242466,0.00021999594,0.00013611808],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037667112,0.00024465454,0.00022118159,0.000047122834,0.00019218039,0.00021717347,0.0004872093,0.0002935871,0.00009504173],"category_scores_gemma":[0.00022735121,0.00024517238,0.00007773466,0.00015350778,0.000051808358,0.0001343096,0.0002336421,0.00020995637,0.000042971504],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034144812,0.00027755377,0.000615075,0.00038238583,0.000408682,0.000004528726,0.00041906233,0.000736241,0.9422017,0.0027849865,0.01698522,0.034843154],"study_design_scores_gemma":[0.002967638,0.0009026777,0.001183844,0.0002770417,0.00013681641,0.000034949586,0.0022316936,0.16365397,0.470869,0.0070702713,0.3490143,0.0016577947],"about_ca_topic_score_codex":0.000011219421,"about_ca_topic_score_gemma":0.000050657385,"teacher_disagreement_score":0.47133267,"about_ca_system_score_codex":0.00005059192,"about_ca_system_score_gemma":0.00025372967,"threshold_uncertainty_score":0.99978393},"labels":[],"label_agreement":null},{"id":"W3124991397","doi":"10.1093/bioinformatics/btab018","title":"Mouse Quantitative Proteomics Knowledgebase: reference protein concentration ranges in 20 mouse tissues using 5000 quantitative proteomics assays","year":2021,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Jewish General Hospital; Genome British Columbia; University of Victoria","funders":"McGill University","keywords":"Proteomics; Computational biology; Quantitative proteomics; Biology; Laboratory mouse; Gene; Bioinformatics; Genetics","score_opus":0.05352775581482376,"score_gpt":0.3313772763677119,"score_spread":0.27784952055288814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3124991397","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69717985,0.00031968998,0.29458192,0.0001933634,0.000026871134,0.0021611361,0.0006146259,0.00031050757,0.0046120626],"genre_scores_gemma":[0.037428398,0.00025504938,0.9594377,0.000050426184,0.000040874856,0.00084056944,0.0005539438,0.00006580113,0.0013271979],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9976589,0.00006570247,0.0010314168,0.00040311195,0.00032399743,0.00051683735],"domain_scores_gemma":[0.9979363,0.000112533606,0.0006386523,0.0006386151,0.0005376694,0.00013624823],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00031513008,0.00040966625,0.0004838384,0.000098509816,0.00023703519,0.00016961589,0.00035067275,0.00033907167,0.00010709383],"category_scores_gemma":[0.0004131109,0.0004310442,0.00008871302,0.0004611375,0.000192331,0.00075411954,0.0001696447,0.00059509935,0.000056151715],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001233882,0.00023561335,0.00019034349,0.00062218367,0.00003596871,0.00000818078,0.00215003,0.00077556726,0.96750796,0.027600145,0.00008609457,0.0006645427],"study_design_scores_gemma":[0.0007372712,0.00006762574,0.0000034362247,0.0003196036,0.000020438583,0.000009895297,0.0022935679,0.094550766,0.89799917,0.0019676066,0.0015238532,0.00050677895],"about_ca_topic_score_codex":0.00005453179,"about_ca_topic_score_gemma":0.00013318953,"teacher_disagreement_score":0.66485584,"about_ca_system_score_codex":0.0004164237,"about_ca_system_score_gemma":0.00044795033,"threshold_uncertainty_score":0.99981415},"labels":[],"label_agreement":null},{"id":"W3126228859","doi":"10.1093/bioinformatics/btab077","title":"Detecting high-scoring local alignments in pangenome graphs","year":2021,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"German Network for Bioinformatics Infrastructure; Michael Smith Health Research BC; Bundesministerium für Bildung und Forschung; Deutsche Forschungsgemeinschaft; Natural Sciences and Engineering Research Council of Canada; European Commission; California Department of Fish and Game","keywords":"De Bruijn graph; Computer science; Spurious relationship; De Bruijn sequence; Graph; Sequence (biology); Similarity (geometry); Theoretical computer science; Artificial intelligence; Mathematics; Combinatorics; Biology; Machine learning; Genetics","score_opus":0.01144780682644667,"score_gpt":0.21991272058270583,"score_spread":0.20846491375625917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3126228859","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9943573,0.0009291582,0.00280678,0.0000364698,0.00022332495,0.00008083983,0.000013927429,0.0000037481402,0.001548477],"genre_scores_gemma":[0.9916296,0.0004044045,0.007583622,0.00019008399,0.000056577912,0.000009878646,0.000029655634,0.000011420441,0.00008472732],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99924487,0.000015570353,0.00027053335,0.00013671469,0.000091398695,0.00024093193],"domain_scores_gemma":[0.99960715,0.000008829842,0.00006359791,0.00022855873,0.00004411965,0.00004774133],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001096063,0.000118004114,0.00012623012,0.000038192087,0.00006238302,0.000022050745,0.0000999983,0.000078627745,0.000005925558],"category_scores_gemma":[0.000034676817,0.00012027793,0.00005200026,0.0001122756,0.000035306675,0.0000013383158,0.0001858404,0.000052592783,0.000011619754],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005198484,0.00014904977,0.05341109,0.00022149461,0.00028674546,0.000040468953,0.0016510203,0.0025325834,0.82642865,0.0009443383,0.00039116197,0.113891415],"study_design_scores_gemma":[0.002453946,0.0003837448,0.09648819,0.00008820598,0.000055104734,0.00008919582,0.0053443555,0.0021405558,0.8612593,0.0014772969,0.029181754,0.0010383643],"about_ca_topic_score_codex":0.000020834088,"about_ca_topic_score_gemma":0.00009001569,"teacher_disagreement_score":0.11285305,"about_ca_system_score_codex":0.000019142391,"about_ca_system_score_gemma":0.000046199424,"threshold_uncertainty_score":0.49047917},"labels":[],"label_agreement":null},{"id":"W3127276189","doi":"10.1093/bioinformatics/btab075","title":"RAD: a web application to identify region associated differentially expressed genes","year":2021,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Fundamental Research Funds for the Central Universities; Canadian Institutes of Health Research","keywords":"Biology; Gene; Computational biology; Python (programming language); Genetics; Web server; Genome; Chromatin; Computer science; The Internet; World Wide Web","score_opus":0.011409763270810988,"score_gpt":0.24695676855460863,"score_spread":0.23554700528379763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3127276189","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.57581574,0.00055647397,0.41654426,0.000622383,0.0005836596,0.0006484016,0.00009996497,0.00008578158,0.0050433096],"genre_scores_gemma":[0.98653144,0.00033431317,0.009055097,0.0014286083,0.0002679714,0.00005575821,0.0011992587,0.00003167214,0.001095892],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987957,0.000032665357,0.0004939948,0.00018995297,0.00019050267,0.0002972037],"domain_scores_gemma":[0.998885,0.000011768322,0.00020331793,0.00055964786,0.00019069442,0.00014960369],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016453797,0.00019278897,0.00019146474,0.00005248768,0.0001208168,0.00011856525,0.0002583243,0.00024030912,0.000012061497],"category_scores_gemma":[0.000075833064,0.00019184948,0.00011761179,0.00019206064,0.000029505052,0.000012116467,0.00026662237,0.00009180336,0.00008888672],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008287011,0.00020637063,0.0012562091,0.0001704123,0.00026189277,0.0000069248813,0.0006774329,0.0007578041,0.87690413,0.0007783445,0.057364974,0.061532635],"study_design_scores_gemma":[0.004870247,0.00059480127,0.017236222,0.0002490853,0.00026258273,0.00014925784,0.0016216408,0.13392414,0.28071514,0.0015635748,0.5563061,0.0025072035],"about_ca_topic_score_codex":0.0000033546282,"about_ca_topic_score_gemma":0.000040766157,"teacher_disagreement_score":0.59618896,"about_ca_system_score_codex":0.000028956796,"about_ca_system_score_gemma":0.00014922445,"threshold_uncertainty_score":0.7823395},"labels":[],"label_agreement":null},{"id":"W3127513279","doi":"10.1093/bioinformatics/btab076","title":"WgLink: reconstructing whole-genome viral haplotypes using L0+L1-regularization","year":2021,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; Alberta Children's Hospital","funders":"Canada Foundation for Innovation","keywords":"Haplotype; Regularization (linguistics); Computational biology; Genome; Genetics; Computer science; Biology; Virology; Artificial intelligence; Gene; Genotype","score_opus":0.017051819490013154,"score_gpt":0.2314050820654523,"score_spread":0.21435326257543913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3127513279","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9825102,0.0011159526,0.012798708,0.00009958793,0.00039010137,0.00012428357,0.00008796141,0.000010339581,0.0028628604],"genre_scores_gemma":[0.87185043,0.00031460854,0.12531784,0.0005977778,0.0005191057,0.000006361647,0.0005078714,0.00004120902,0.00084479176],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99914473,0.000022063172,0.0003361966,0.0001637378,0.00010091866,0.00023232543],"domain_scores_gemma":[0.99934506,0.0000074253826,0.00013924674,0.00028268222,0.000152098,0.00007348984],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010948202,0.00015111596,0.00015276595,0.00003448054,0.00017663321,0.000061802726,0.000111566165,0.00012658414,0.000010431783],"category_scores_gemma":[0.00011529383,0.00015487253,0.00008175298,0.00009313131,0.00006454003,0.0000034586797,0.00018480708,0.000060867253,0.000015811343],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011706631,0.000021706994,0.0028820033,0.000060477538,0.00011768353,0.0000024473366,0.00040814458,0.001146986,0.989922,0.000310894,0.000122617,0.00499336],"study_design_scores_gemma":[0.0026588603,0.00047103994,0.006994354,0.00012107741,0.00029927545,0.00056502974,0.0057531493,0.05629273,0.66184324,0.0023576138,0.26054296,0.002100655],"about_ca_topic_score_codex":0.0000031092804,"about_ca_topic_score_gemma":0.00000520367,"teacher_disagreement_score":0.32807872,"about_ca_system_score_codex":0.000017607112,"about_ca_system_score_gemma":0.00015756128,"threshold_uncertainty_score":0.6315518},"labels":[],"label_agreement":null},{"id":"W3127538277","doi":"10.1093/bioinformatics/btab072","title":"Motif-Raptor: a cell type-specific and transcription factor centric approach for post-GWAS prioritization of causal regulators","year":2021,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Montreal Heart Institute","funders":"National Human Genome Research Institute; National Heart, Lung, and Blood Institute; National Institutes of Health","keywords":"Computational biology; Genome-wide association study; Chromatin; Biology; Transcription factor; Gene; Genetics; Single-nucleotide polymorphism; Genotype","score_opus":0.01624833803372405,"score_gpt":0.22994435342991612,"score_spread":0.21369601539619207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3127538277","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8660438,0.0013257352,0.13142163,0.000055709963,0.0001861987,0.0003033973,0.00017642614,0.000008862863,0.00047822835],"genre_scores_gemma":[0.9397874,0.00082065066,0.057767242,0.00007344816,0.00007564,0.00000763207,0.0011719906,0.000012231707,0.00028377748],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992655,0.000031879274,0.0003339456,0.00013293016,0.000073346564,0.00016239584],"domain_scores_gemma":[0.9993339,0.000017201097,0.00015196831,0.00017090957,0.00027501624,0.000050996558],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011967878,0.0001014036,0.00016030669,0.000040349183,0.000056776356,0.000012993843,0.000054589633,0.00018258765,0.000007131452],"category_scores_gemma":[0.00009176928,0.000099033714,0.000063297506,0.00010281143,0.00003760917,0.000006558233,0.000025376736,0.000036542955,0.0000011545358],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018110024,0.00040411775,0.025156312,0.0011175536,0.00020026714,5.449706e-7,0.002237263,0.0019752816,0.9424281,0.0007587025,0.009142464,0.016398303],"study_design_scores_gemma":[0.007827527,0.0027064504,0.22001246,0.00006810572,0.00034332104,0.00008682623,0.0076833856,0.10278959,0.5261448,0.00041769567,0.130166,0.0017538611],"about_ca_topic_score_codex":0.0000023376215,"about_ca_topic_score_gemma":0.000002185092,"teacher_disagreement_score":0.4162833,"about_ca_system_score_codex":0.000015836247,"about_ca_system_score_gemma":0.000084923784,"threshold_uncertainty_score":0.40384775},"labels":[],"label_agreement":null},{"id":"W3133006703","doi":"10.1093/bioinformatics/btab112","title":"Accurate deep learning off-target prediction with novel sgRNA-DNA sequence encoding in CRISPR-Cas9 gene editing","year":2021,"lang":"en","type":"article","venue":"Bioinformatics","topic":"CRISPR and Genetic Engineering","field":"Biochemistry, Genetics and Molecular Biology","cited_by":54,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University and Génome Québec Innovation Centre; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Computer science; Deep learning; Encoding (memory); Recurrent neural network; Artificial intelligence; Convolutional neural network; CRISPR; Artificial neural network; Machine learning; Gene; Biology; Genetics","score_opus":0.01337359534881089,"score_gpt":0.2686154771607254,"score_spread":0.25524188181191454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3133006703","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45906216,0.00081439764,0.53750116,0.0000640712,0.0003089157,0.00016419405,0.00004046997,0.000048271777,0.0019963696],"genre_scores_gemma":[0.9470291,0.00037008582,0.051765524,0.000096466545,0.00027702615,0.000014575239,0.00031141634,0.000024326862,0.00011143753],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998965,0.000015395319,0.00035273572,0.00018685781,0.0001649353,0.00031504614],"domain_scores_gemma":[0.99948347,0.000014809451,0.00010821267,0.00021135937,0.00010617983,0.00007598303],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019271282,0.00016971353,0.00014514408,0.000059597605,0.00009044688,0.000062365354,0.000110576504,0.00012234571,0.0000113423575],"category_scores_gemma":[0.00017131848,0.00016644185,0.00004452131,0.00018704872,0.000028407714,0.000024726132,0.000097303855,0.00017932651,0.0000043119785],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030367792,0.000047936344,0.007759983,0.00019554132,0.00006210588,0.000027301461,0.0011886152,0.14940938,0.83433247,0.000033032924,0.00015648946,0.0067567714],"study_design_scores_gemma":[0.0009701451,0.00018255101,0.0028591277,0.00012204539,0.00002386491,0.00024871726,0.0020532315,0.30916834,0.67247486,0.000006152159,0.011531707,0.000359246],"about_ca_topic_score_codex":0.0000059085487,"about_ca_topic_score_gemma":0.000032804724,"teacher_disagreement_score":0.48796698,"about_ca_system_score_codex":0.000034419496,"about_ca_system_score_gemma":0.000081771046,"threshold_uncertainty_score":0.6787302},"labels":[],"label_agreement":null},{"id":"W3134330704","doi":"10.1093/bioinformatics/btab157","title":"KibioR &amp; Kibio: a new architecture for next-generation data querying and sharing in big biology","year":2021,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Computer science; Scalability; Data management; Identification (biology); Data exchange; Database; Biological database; Big data; Data science; Simple (philosophy); Biological data; Data access; World Wide Web; Data mining; Bioinformatics","score_opus":0.08786989134044719,"score_gpt":0.2923718289039058,"score_spread":0.20450193756345858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134330704","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30430025,0.0042711087,0.6869147,0.0011228211,0.00089481863,0.000862126,0.00038365606,0.000036852805,0.0012136942],"genre_scores_gemma":[0.3564581,0.0021644745,0.61254907,0.0039495453,0.002721982,0.000045475957,0.020325974,0.000085226464,0.0017001424],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99885136,0.000014875908,0.00047566413,0.00028367783,0.00005970303,0.00031470525],"domain_scores_gemma":[0.99897695,0.000021468633,0.00013490014,0.0007084637,0.00005089094,0.000107309555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030298298,0.00018074912,0.00019728683,0.00006749864,0.00008879362,0.00013075018,0.0003032101,0.00024559285,0.0000057438538],"category_scores_gemma":[0.00015672982,0.00017142734,0.000045863784,0.000113639,0.00004424986,0.000021246693,0.0005602584,0.000120612785,0.0000046431414],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012259433,0.00008365206,0.00261585,0.00053398946,0.0001809966,0.000002410727,0.0016608428,0.0009680857,0.29801497,0.00240016,0.025395963,0.6680205],"study_design_scores_gemma":[0.0037442683,0.00027051137,0.00038929106,0.0001553111,0.00008207027,0.0001694192,0.00064643065,0.2484709,0.018380675,0.0034347242,0.72311234,0.0011440542],"about_ca_topic_score_codex":0.000029321092,"about_ca_topic_score_gemma":0.0011624551,"teacher_disagreement_score":0.69771636,"about_ca_system_score_codex":0.0000139794365,"about_ca_system_score_gemma":0.00018143535,"threshold_uncertainty_score":0.6990604},"labels":[],"label_agreement":null},{"id":"W3138390968","doi":"10.1093/bioinformatics/btab188","title":"PoseFilter: a PyMOL plugin for filtering and analyzing small molecule docking in symmetric binding sites","year":2021,"lang":"en","type":"article","venue":"Bioinformatics","topic":"14-3-3 protein interactions","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Canada First Research Excellence Fund","keywords":"Plug-in; Docking (animal); Computer science; Graphical user interface; Software; Interface (matter); Computational biology; Data mining; Programming language; Operating system; Biology","score_opus":0.0231698618666592,"score_gpt":0.26680804518820156,"score_spread":0.24363818332154236,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3138390968","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9714241,0.0005832306,0.02665079,0.00007865078,0.0000994394,0.00025374084,0.000039812912,0.000016774286,0.0008534638],"genre_scores_gemma":[0.92749625,0.00017081184,0.07149475,0.00017894928,0.00009160466,0.000061841594,0.00025002687,0.000026798067,0.0002289537],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99914163,0.000018739613,0.00033032385,0.0001768386,0.0000664651,0.00026599522],"domain_scores_gemma":[0.9994811,0.000048137113,0.00011061077,0.000220453,0.0000802514,0.000059460097],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015883744,0.00013939591,0.00014862369,0.0002106118,0.00008929266,0.000109888766,0.000101894766,0.00010171783,0.0000075879143],"category_scores_gemma":[0.00041061334,0.00015019048,0.00007173225,0.00028097542,0.000020965814,0.000017430504,0.00017904758,0.00009292465,0.0000048049715],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031142074,0.000047214897,0.0055958647,0.00031806016,0.00008247461,0.000010958616,0.00042785172,0.00023471548,0.98566157,0.00018639231,0.00023426722,0.007169508],"study_design_scores_gemma":[0.0009389592,0.00015476643,0.00086718594,0.00017816375,0.00003386114,0.0001144023,0.0008119721,0.02574743,0.96551865,0.000051878975,0.0051849457,0.00039777465],"about_ca_topic_score_codex":0.000010510404,"about_ca_topic_score_gemma":0.00006227849,"teacher_disagreement_score":0.04484396,"about_ca_system_score_codex":0.00003264566,"about_ca_system_score_gemma":0.000052507174,"threshold_uncertainty_score":0.612459},"labels":[],"label_agreement":null},{"id":"W3138529574","doi":"10.1093/bioinformatics/btac326","title":"Building alternative consensus trees and supertrees using <i>k</i> -means and Robinson and Foulds distance","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science","score_opus":0.015281997913291155,"score_gpt":0.24037222629088925,"score_spread":0.2250902283775981,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3138529574","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9935366,0.004301736,0.0015704845,0.000079255835,0.000077396835,0.000118558426,0.000112925016,0.0000029704026,0.00020005192],"genre_scores_gemma":[0.98152447,0.00094099954,0.017263334,0.00017201636,0.000039288512,0.0000070812494,0.0000082881925,0.000010129162,0.000034375047],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994504,0.000020106747,0.00016431013,0.00014092543,0.000074555166,0.0001497439],"domain_scores_gemma":[0.9997272,0.000020817579,0.00006948872,0.000108357126,0.000022918517,0.00005120136],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010224704,0.00012229168,0.0001248216,0.000028158385,0.00028390158,0.00003448109,0.00005743178,0.000031632942,0.0000012501996],"category_scores_gemma":[0.00001985885,0.00011737275,0.00001902564,0.00003553638,0.00013910855,0.0000015623026,0.00033520817,0.000053732925,7.523319e-8],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030885305,0.00010712877,0.085482866,0.00033346668,0.0005788078,0.000016290816,0.00864298,0.0045426027,0.85191214,0.005421555,0.001600191,0.041053113],"study_design_scores_gemma":[0.008638242,0.0036249966,0.050400905,0.00013990959,0.00046343863,0.0015617027,0.027088858,0.4097351,0.0916679,0.0039401334,0.39934367,0.0033951178],"about_ca_topic_score_codex":0.00003427931,"about_ca_topic_score_gemma":0.000035068206,"teacher_disagreement_score":0.76024425,"about_ca_system_score_codex":0.000010435018,"about_ca_system_score_gemma":0.000018651295,"threshold_uncertainty_score":0.47863218},"labels":[],"label_agreement":null},{"id":"W3149048453","doi":"10.1093/bioinformatics/btab215","title":"MaveRegistry: a collaboration platform for multiplexed assays of variant effect","year":2021,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; University of Toronto","funders":"National Institutes of Health; National Human Genome Research Institute; Canada Excellence Research Chairs, Government of Canada","keywords":"Computer science; Source code; Multiplexing; Workflow; Computational biology; NOMINATE; Data mining; Biology; Database; Machine learning; Programming language; Telecommunications","score_opus":0.008754319354611684,"score_gpt":0.24459441916459593,"score_spread":0.23584009980998424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3149048453","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97499454,0.00049407844,0.019391024,0.000085019456,0.00040011533,0.00068856083,0.0010325345,0.000015861437,0.0028982859],"genre_scores_gemma":[0.97510004,0.00007405116,0.022653356,0.00011155558,0.00009481547,0.000032544605,0.0016264081,0.000013759197,0.00029348652],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99943244,0.000009999401,0.0002505899,0.000095614625,0.00008068922,0.00013066942],"domain_scores_gemma":[0.9993239,0.000025809357,0.0001373179,0.00024834825,0.0002116372,0.00005295473],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000118784425,0.00009859999,0.0001356148,0.000020489753,0.000050350256,0.00002745989,0.00008309932,0.000105413244,0.000007178178],"category_scores_gemma":[0.00025138946,0.000087717264,0.000094940915,0.00007527016,0.000025897543,0.0000056615845,0.000053429576,0.000021980335,0.0000032218811],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006226451,0.00023188522,0.0008147319,0.0013672109,0.00035609622,0.000016091615,0.00047463254,0.00058393006,0.9645612,0.0029219426,0.01732584,0.0107237585],"study_design_scores_gemma":[0.0029901376,0.00074501126,0.000606462,0.000046135407,0.00010713357,0.00006569782,0.00085134996,0.013651082,0.9107957,0.00017428133,0.0696197,0.0003473042],"about_ca_topic_score_codex":0.0000022018758,"about_ca_topic_score_gemma":0.000012249518,"teacher_disagreement_score":0.053765528,"about_ca_system_score_codex":0.0000106283505,"about_ca_system_score_gemma":0.00020851142,"threshold_uncertainty_score":0.35770062},"labels":[],"label_agreement":null},{"id":"W3159344430","doi":"10.1093/bioinformatics/btab249","title":"MetaFusion: a high-confidence metacaller for filtering and prioritizing RNA-seq gene fusion candidates","year":2021,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; University of Toronto; SickKids Foundation; Hospital for Sick Children","funders":"","keywords":"Computer science; Benchmarking; Data mining; Graph; Fusion; Cluster analysis; Precision and recall; Majority rule; Selection (genetic algorithm); Machine learning; Information retrieval; Artificial intelligence; Theoretical computer science","score_opus":0.01830368811237904,"score_gpt":0.25958593528051555,"score_spread":0.2412822471681365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3159344430","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7094929,0.004389092,0.28231895,0.0009214186,0.00067427946,0.0005372614,0.00009157668,0.00004390648,0.0015306141],"genre_scores_gemma":[0.8529475,0.0027366753,0.14110598,0.000811459,0.00021229374,0.000083162544,0.00042661454,0.000024000428,0.0016523248],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99927825,0.000016857484,0.00025337658,0.00017872725,0.000110264904,0.00016254804],"domain_scores_gemma":[0.99941355,0.000014206195,0.000101837424,0.00026271548,0.00012826623,0.00007941799],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001311816,0.00011703187,0.00013074647,0.000033587152,0.00012908557,0.000068943395,0.00008968128,0.00010018821,0.000021409056],"category_scores_gemma":[0.000093119976,0.00010469068,0.000053373948,0.000072064,0.00002901006,0.000013013602,0.00014147266,0.000043418517,0.0000038489507],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025931206,0.000010726559,0.000031355445,0.00007440453,0.000025318583,9.110423e-7,0.000118258955,0.00001128423,0.9872041,0.0003154737,0.0016345212,0.010547725],"study_design_scores_gemma":[0.0005735839,0.00007307348,0.0005529098,0.000038004877,0.00003422578,0.000032055676,0.0002725054,0.0030159948,0.92650235,0.00018005914,0.068535164,0.00019007553],"about_ca_topic_score_codex":0.0000061020196,"about_ca_topic_score_gemma":0.000010526553,"teacher_disagreement_score":0.14345458,"about_ca_system_score_codex":0.000010182548,"about_ca_system_score_gemma":0.000088743574,"threshold_uncertainty_score":0.42691618},"labels":[],"label_agreement":null},{"id":"W3162343445","doi":"10.1093/bioinformatics/btab363","title":"PaIntDB: network-based omics integration and visualization using protein–protein interactions in <i>Pseudomonas aeruginosa</i>","year":2021,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Canadian Institutes of Health Research","keywords":"Interactome; Visualization; Computer science; Source code; Computational biology; Pseudomonas aeruginosa; Web server; Data mining; Bioinformatics; Biology; World Wide Web; The Internet; Genetics; Gene; Programming language","score_opus":0.014712646126482511,"score_gpt":0.25610344437096333,"score_spread":0.24139079824448081,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3162343445","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48140892,0.0002808529,0.51652616,0.00012547632,0.00018385846,0.00053919456,0.000023394678,0.00002367656,0.0008884238],"genre_scores_gemma":[0.9299871,0.00005851009,0.06815516,0.0006926483,0.0002017689,0.00003337392,0.0006939355,0.00002623147,0.00015132144],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987897,0.000057775498,0.0005731102,0.0001668032,0.00012182686,0.0002907412],"domain_scores_gemma":[0.999264,0.00001400443,0.00022508395,0.0002817819,0.0001334931,0.000081648854],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031267936,0.0001980285,0.00018267136,0.00007220948,0.00012217804,0.00011733363,0.00009492039,0.00015651927,0.000010020635],"category_scores_gemma":[0.00007954585,0.00020161743,0.00006284116,0.0002461596,0.000059871716,0.000033203985,0.00011031296,0.0001591889,0.0000047112812],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049779855,0.00057946745,0.006147199,0.001099114,0.0002442328,0.00002649896,0.0020976164,0.07922812,0.77554905,0.019791473,0.0040446417,0.11069478],"study_design_scores_gemma":[0.0012110535,0.00011709902,0.00024912244,0.00031933238,0.000026738457,0.000044780976,0.00054805883,0.88730806,0.09880863,0.0008750783,0.009981732,0.0005103304],"about_ca_topic_score_codex":0.000018627841,"about_ca_topic_score_gemma":0.00017768091,"teacher_disagreement_score":0.8080799,"about_ca_system_score_codex":0.000050858413,"about_ca_system_score_gemma":0.00019655756,"threshold_uncertainty_score":0.822172},"labels":[],"label_agreement":null},{"id":"W3163233738","doi":"10.1093/bioinformatics/btab340","title":"CLEP: a hybrid data- and knowledge-driven framework for generating patient representations","year":2021,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Bundesministerium für Bildung und Forschung; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; University of Southern California; Eli Lilly and Company; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Bristol-Myers Squibb; National Institute on Aging; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Computer science; Python (programming language); Embedding; Cluster analysis; Documentation; Machine learning; Domain knowledge; Artificial intelligence; Graph; Knowledge graph; Data mining; Theoretical computer science; Programming language","score_opus":0.05388756787387535,"score_gpt":0.35343735952302524,"score_spread":0.2995497916491499,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3163233738","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009752173,0.00032041606,0.9872522,0.0011970527,0.000436817,0.00025491425,0.0000686959,0.00011710535,0.0006006588],"genre_scores_gemma":[0.037442964,0.000030318824,0.9616053,0.00059520063,0.00010840753,0.00002553552,0.0001366348,0.000008575605,0.000047050955],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989227,0.00006086531,0.00039835853,0.00024167566,0.000154546,0.00022183366],"domain_scores_gemma":[0.9979859,0.00047110504,0.00016119954,0.0010742857,0.00020027444,0.00010724994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020121408,0.0001021936,0.00013559299,0.000050999068,0.00029152975,0.00027119843,0.0004990951,0.000046838526,0.0000058944324],"category_scores_gemma":[0.0011498645,0.00009992047,0.000027958195,0.00020313534,0.000024012177,0.00050620333,0.00096585345,0.00017259178,0.000017665725],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000043103983,0.0000966557,0.0059086788,0.00088580867,0.00005659648,0.000015954305,0.024055885,0.003100645,0.00003316629,0.12991847,0.01679115,0.8191327],"study_design_scores_gemma":[0.00011681997,0.000040699062,0.00028082886,0.00005694409,0.0000061498454,0.00004230662,0.0003871492,0.98111093,0.0001422343,0.0016793467,0.016017357,0.00011921961],"about_ca_topic_score_codex":0.000008768583,"about_ca_topic_score_gemma":0.000013610561,"teacher_disagreement_score":0.9780103,"about_ca_system_score_codex":0.000024111096,"about_ca_system_score_gemma":0.00022036237,"threshold_uncertainty_score":0.40746385},"labels":[],"label_agreement":null},{"id":"W3174345118","doi":"10.1093/bioinformatics/btab457","title":"VSS: variance-stabilized signals for sequencing-based genomic signals","year":2021,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Fractal and DNA sequence analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Variance (accounting); Computer science; Imputation (statistics); Data mining; Computational biology; Biology; Machine learning; Missing data","score_opus":0.021658282613532025,"score_gpt":0.2577184315385112,"score_spread":0.23606014892497917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3174345118","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6264325,0.0015935671,0.36615828,0.0005766814,0.00028927904,0.00070783,0.00039818377,0.00007115729,0.0037725375],"genre_scores_gemma":[0.9205653,0.00012513468,0.07353767,0.0031604758,0.00024497026,0.00008697904,0.0011894661,0.00003372247,0.0010562887],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987777,0.000033668555,0.00047201847,0.00022944677,0.00015701856,0.00033016986],"domain_scores_gemma":[0.99892414,0.000052482214,0.00018411262,0.0004418385,0.0002840689,0.000113362934],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026715637,0.00019438178,0.000259266,0.000049856375,0.00011973653,0.000074451316,0.0001998227,0.00017064504,0.00013344291],"category_scores_gemma":[0.00027700263,0.00017898009,0.00027797674,0.00017099886,0.00006669402,0.000014360727,0.00006375916,0.00006219342,0.00004810963],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007371481,0.000047792164,0.00017718223,0.00015530652,0.00012306646,0.000004987244,0.00009529964,0.0057507344,0.98944604,0.000107574226,0.00203222,0.0019860915],"study_design_scores_gemma":[0.0011999424,0.00033407484,0.000044990622,0.000037357928,0.00011679492,0.000017167067,0.00059659465,0.04640357,0.9115349,0.0005002615,0.03877869,0.00043568268],"about_ca_topic_score_codex":0.000009188214,"about_ca_topic_score_gemma":0.000017508308,"teacher_disagreement_score":0.2941328,"about_ca_system_score_codex":0.000049526414,"about_ca_system_score_gemma":0.0006528322,"threshold_uncertainty_score":0.72985965},"labels":[],"label_agreement":null},{"id":"W3174992442","doi":"10.1093/bioinformatics/btab459","title":"JBrowseR: an R interface to the JBrowse 2 genome browser","year":2021,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"National Institute of General Medical Sciences; National Cancer Institute; National Human Genome Research Institute; National Institutes of Health","keywords":"Genome browser; Computer science; Interface (matter); Web browser; Variety (cybernetics); Visualization; Download; World Wide Web; Source code; Genome; User interface; Software; Code (set theory); The Internet; Genomics; Operating system; Biology; Programming language; Set (abstract data type); Genetics; Data mining","score_opus":0.013206211296484414,"score_gpt":0.2460707830635001,"score_spread":0.2328645717670157,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3174992442","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9845618,0.0015685412,0.0061047734,0.001036175,0.00038182884,0.00025009562,0.00007798236,0.00000967062,0.0060091256],"genre_scores_gemma":[0.98099005,0.00033019343,0.01337882,0.0029904959,0.00035944284,0.000025647092,0.000083365514,0.000025415022,0.0018165635],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991416,0.00003057383,0.00026249612,0.00018050877,0.0001193006,0.00026553727],"domain_scores_gemma":[0.99901325,0.000008850954,0.00005845685,0.0006551699,0.00014399014,0.000120302895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015015145,0.00015704124,0.00012557843,0.000021448452,0.00015190098,0.000073538606,0.00032683942,0.00007843412,0.000031151507],"category_scores_gemma":[0.00006665676,0.00011799936,0.000072935785,0.00011521638,0.000042031133,0.0000022165802,0.00036401438,0.00006728234,0.0001304297],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008088611,0.00015117043,0.0013843947,0.00007674031,0.00028868226,0.00000605291,0.0047780587,0.003918293,0.95149475,0.0004964878,0.021124149,0.016200352],"study_design_scores_gemma":[0.0002966032,0.00030532695,0.006573715,0.000007458844,0.000026824737,0.000047215704,0.001959288,0.00052358006,0.099803865,0.000055841105,0.89007664,0.0003236642],"about_ca_topic_score_codex":0.0000063797934,"about_ca_topic_score_gemma":0.00010610081,"teacher_disagreement_score":0.86895245,"about_ca_system_score_codex":0.000011399304,"about_ca_system_score_gemma":0.00008039106,"threshold_uncertainty_score":0.48118743},"labels":[],"label_agreement":null},{"id":"W3175203932","doi":"10.1093/bioinformatics/btab482","title":"phyLoSTM: a novel deep learning model on disease prediction from longitudinal microbiome data","year":2021,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":56,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto; Princess Margaret Cancer Centre; University Health Network","funders":"Natural Sciences and Engineering Research Council of Canada; Leona M. and Harry B. Helmsley Charitable Trust","keywords":"Microbiome; Computer science; Artificial intelligence; Machine learning; Random forest; Convolutional neural network; Longitudinal study; Deep learning; Bioinformatics; Biology; Medicine; Pathology","score_opus":0.037897150233829044,"score_gpt":0.27322617826641643,"score_spread":0.23532902803258737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3175203932","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83687705,0.0010413055,0.15488414,0.0004844741,0.00043742717,0.00030837645,0.004653906,0.00007003596,0.001243308],"genre_scores_gemma":[0.92272645,0.0006035387,0.04419451,0.0012833575,0.0004088812,0.000007667434,0.029866425,0.000039556573,0.000869614],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99903226,0.00001705163,0.00029115676,0.00029300974,0.000115496594,0.00025100211],"domain_scores_gemma":[0.99889594,0.000009405766,0.000107770626,0.0007474863,0.00008204869,0.00015735764],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009964004,0.00015963402,0.00012931935,0.000035983365,0.00014414721,0.000057542846,0.00025729561,0.00012246826,0.00002288142],"category_scores_gemma":[0.000089720736,0.00015795925,0.00005535994,0.00008305752,0.0000381477,0.000016554444,0.0003381521,0.00014925322,0.000058484748],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029943185,0.0004519408,0.0048756385,0.0002584663,0.00016550638,0.000010718163,0.00035612145,0.007448742,0.9693874,0.00012854398,0.012029535,0.004587917],"study_design_scores_gemma":[0.002405141,0.0002846374,0.035683792,0.00016872432,0.00016121841,0.000039024722,0.0003571169,0.87752473,0.022268109,0.000060466587,0.06036308,0.0006839516],"about_ca_topic_score_codex":0.000008757835,"about_ca_topic_score_gemma":0.000023403476,"teacher_disagreement_score":0.94711936,"about_ca_system_score_codex":0.000025361105,"about_ca_system_score_gemma":0.00022472799,"threshold_uncertainty_score":0.6441391},"labels":[],"label_agreement":null},{"id":"W3180080324","doi":"10.1093/bioinformatics/btab524","title":"Refget: standardized access to reference sequences","year":2021,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"European Molecular Biology Laboratory; National Institute of General Medical Sciences; Wellcome Trust","keywords":"Implementation; Computer science; Identifier; Cloud computing; Suite; Identification (biology); Database; Data mining; Programming language; Biology; Operating system","score_opus":0.02716707637083181,"score_gpt":0.29908076257383037,"score_spread":0.27191368620299855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3180080324","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95932525,0.00074634596,0.006952915,0.0006312602,0.00032641174,0.00024111255,0.00042410035,0.00003074736,0.031321827],"genre_scores_gemma":[0.97702205,0.00052434136,0.017634965,0.0030014329,0.00014136289,0.000019740659,0.00054489815,0.00001678294,0.0010943986],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99933046,0.000014666126,0.00020687337,0.00013852805,0.0001283609,0.00018108159],"domain_scores_gemma":[0.99930006,0.0000052947103,0.000055278073,0.00032941168,0.00017741052,0.00013254439],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007943792,0.00010262521,0.000106997686,0.000026478574,0.000074967145,0.00013093223,0.0002404987,0.00007113548,0.000056507153],"category_scores_gemma":[0.000114590934,0.00008974313,0.00005316853,0.000105196596,0.000025775022,0.000008795128,0.00024567847,0.000037222773,0.00004941233],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00072638015,0.0004059486,0.008270932,0.0007917674,0.0006044003,0.0002296235,0.0016564109,0.0017914248,0.6076272,0.004206054,0.2685281,0.105161764],"study_design_scores_gemma":[0.00056302425,0.00017483441,0.002927196,0.00004004823,0.000028674556,0.00006246318,0.000615381,0.00017077882,0.2298055,0.00022457891,0.7649529,0.00043461737],"about_ca_topic_score_codex":0.0000048404304,"about_ca_topic_score_gemma":0.000027397547,"teacher_disagreement_score":0.49642482,"about_ca_system_score_codex":0.000012980802,"about_ca_system_score_gemma":0.00027178373,"threshold_uncertainty_score":0.36596185},"labels":[],"label_agreement":null},{"id":"W3180876344","doi":"10.1093/bioinformatics/btab292","title":"Expected 10-anonymity of HyperLogLog sketches for federated queries of clinical data repositories","year":2021,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"National Cancer Institute; Division of Mathematical Sciences; University of Toronto","keywords":"Anonymity; Computer science; Confidentiality; Sketch; Probabilistic logic; Aggregate (composite); Sorting; Protocol (science); Code (set theory); Information retrieval; Data mining; Computer security; Algorithm; Programming language","score_opus":0.13502470347922566,"score_gpt":0.36424811112855326,"score_spread":0.2292234076493276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3180876344","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.064272344,0.0004712238,0.9255546,0.004038848,0.0016359177,0.00047654283,0.0008326689,0.0007163671,0.0020015368],"genre_scores_gemma":[0.050043363,0.00008643647,0.9494196,0.000045240748,0.000043356948,0.000008543145,0.0002807616,0.0000073354963,0.000065356886],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997707,0.000066756664,0.0013893928,0.00029586276,0.00031073406,0.00023023959],"domain_scores_gemma":[0.9882727,0.0009329571,0.00074050657,0.0093837995,0.0006213637,0.00004866123],"candidate_categories":["metaresearch","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00086633384,0.00014655266,0.00050665054,0.000064451044,0.00010092465,0.0001143088,0.013180637,0.00021949668,0.000008621826],"category_scores_gemma":[0.077193,0.00013100903,0.00008517091,0.0004924939,0.00029978913,0.0012255901,0.04382094,0.00013886481,0.0000033804754],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001599895,0.00064332964,0.013848319,0.0016568782,0.0005063033,0.000025214942,0.0010376086,0.0000063811244,0.0024562182,0.011588768,0.87098575,0.09708522],"study_design_scores_gemma":[0.001675166,0.0005296097,0.0052388697,0.00025976598,0.00008158632,0.000063021864,0.0017884104,0.65347403,0.2778763,0.0316749,0.026686184,0.0006521424],"about_ca_topic_score_codex":0.000014019488,"about_ca_topic_score_gemma":0.000013309655,"teacher_disagreement_score":0.84429955,"about_ca_system_score_codex":0.000016403677,"about_ca_system_score_gemma":0.00045939485,"threshold_uncertainty_score":0.99215853},"labels":[],"label_agreement":null},{"id":"W3182507784","doi":"10.1093/bioinformatics/btab328","title":"Gene tree and species tree reconciliation with endosymbiotic gene transfer","year":2021,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Biology; Genome; Gene duplication; Horizontal gene transfer; Mitochondrial DNA; Gene; Nuclear gene; Genetics; Genome evolution; Computational biology; Eukaryote; Evolutionary biology","score_opus":0.013586332068311958,"score_gpt":0.19533522625582644,"score_spread":0.1817488941875145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3182507784","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99015886,0.0014550167,0.003160262,0.00017612251,0.000095450865,0.0001280542,0.000046763675,0.0000052706746,0.0047742086],"genre_scores_gemma":[0.9793462,0.0021831219,0.016825292,0.00026396717,0.0001374735,0.000008554769,0.00014234302,0.00001597354,0.0010770404],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993128,0.000014847363,0.00022505094,0.00015982988,0.00010134023,0.00018612086],"domain_scores_gemma":[0.9995461,0.000010938242,0.000038530106,0.00023759308,0.00010270275,0.000064137035],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006967578,0.00015145514,0.00015400018,0.000024639852,0.00008744788,0.000040408388,0.000069373906,0.00008314673,0.000010263095],"category_scores_gemma":[0.000022860466,0.00012763886,0.00004615761,0.00006835172,0.00007051108,0.000002319314,0.000052607153,0.00004261099,0.000005268969],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006702745,0.000046475812,0.0081311995,0.00008109961,0.00023065948,0.0000075177913,0.0007033645,0.00006199735,0.9721432,0.00016908477,0.00046841896,0.017889958],"study_design_scores_gemma":[0.0011407735,0.0003510412,0.038572196,0.000011800865,0.00007147487,0.00011529855,0.00062191114,0.00041991172,0.9409761,0.00003637682,0.0173777,0.00030546123],"about_ca_topic_score_codex":0.0000023427278,"about_ca_topic_score_gemma":0.00011923654,"teacher_disagreement_score":0.031167144,"about_ca_system_score_codex":0.0000103944985,"about_ca_system_score_gemma":0.00007857582,"threshold_uncertainty_score":0.5204962},"labels":[],"label_agreement":null},{"id":"W3185042382","doi":"10.1093/bioinformatics/btab527","title":"miRAnno—network-based functional microRNA annotation","year":2021,"lang":"en","type":"article","venue":"Bioinformatics","topic":"MicroRNA in disease regulation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Discovery Centre; University Health Network","funders":"Canada Foundation for Innovation; University Health Network; International Business Machines Corporation","keywords":"Annotation; microRNA; Computer science; Computational biology; Noise (video); Data mining; Artificial intelligence; Biology; Genetics; Gene","score_opus":0.012221069776055561,"score_gpt":0.22650080378046908,"score_spread":0.21427973400441352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3185042382","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7653007,0.0015489388,0.22576305,0.0005484726,0.00088223856,0.00035218784,0.00012005179,0.00007663241,0.005407756],"genre_scores_gemma":[0.92944586,0.000039455343,0.060915314,0.0021268637,0.0007480274,0.00002396292,0.0056435973,0.000034554636,0.0010223455],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99926245,0.000026413212,0.0002580984,0.00012766928,0.0001437961,0.00018155106],"domain_scores_gemma":[0.9993408,0.000009306003,0.000107561755,0.0002706031,0.00020592425,0.000065851935],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010062853,0.000111524634,0.00008088477,0.000025276204,0.00008580125,0.000038892467,0.0000663812,0.00011426642,0.00009741647],"category_scores_gemma":[0.000060651702,0.00011799009,0.00008851963,0.000132201,0.000035676123,0.000007844099,0.000041010153,0.000045501474,0.000079078185],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000161374,0.00014792311,0.0036419865,0.0002159713,0.00013182651,0.000007651491,0.00007113086,0.021797469,0.8269628,0.00044691347,0.13784488,0.00857008],"study_design_scores_gemma":[0.0023205462,0.00013782276,0.05955137,0.000074962125,0.00008486963,0.000068397356,0.00012347689,0.038187526,0.578842,0.00023892162,0.31967488,0.0006952337],"about_ca_topic_score_codex":6.7247754e-7,"about_ca_topic_score_gemma":0.0000057181746,"teacher_disagreement_score":0.24812081,"about_ca_system_score_codex":0.000021029036,"about_ca_system_score_gemma":0.00022944265,"threshold_uncertainty_score":0.4811496},"labels":[],"label_agreement":null},{"id":"W3186634360","doi":"10.1093/bioinformatics/btab534","title":"CCIP: predicting CTCF-mediated chromatin loops with transitivity","year":2021,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"CTCF; Chromatin; Computer science; Transitive relation; Mechanism (biology); Context (archaeology); Computational biology; Topology (electrical circuits); Biology; Enhancer; Genetics; Physics; Mathematics; Transcription factor; DNA; Gene; Combinatorics","score_opus":0.0047850384362429195,"score_gpt":0.19274127875333955,"score_spread":0.18795624031709662,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3186634360","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97721064,0.00014405981,0.0153629,0.00007608125,0.000091334456,0.00014246882,0.00012240272,0.000037263704,0.0068128556],"genre_scores_gemma":[0.9726451,0.00010011571,0.025628453,0.0003258717,0.00010273483,0.000010579276,0.00094847253,0.000028218725,0.00021042867],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990162,0.000027003576,0.00032022872,0.00017483064,0.0001768851,0.0002848385],"domain_scores_gemma":[0.9992229,0.000018590043,0.00013588056,0.00037976776,0.00013585297,0.00010701957],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014886212,0.00018387727,0.0001725699,0.000026891903,0.00011058763,0.000060702696,0.00013628724,0.00014877976,0.000025415718],"category_scores_gemma":[0.000077365614,0.0001642251,0.00006876878,0.00014064592,0.00006118012,0.000009760109,0.00008079018,0.00010624037,0.00002646799],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002790434,0.00084526103,0.04088272,0.0017754057,0.0010647175,0.00016422456,0.0051631825,0.0047507547,0.92059714,0.00087841885,0.0055683996,0.018030727],"study_design_scores_gemma":[0.009253301,0.001893151,0.05473926,0.00039822492,0.00037416563,0.001598096,0.0076325797,0.3961007,0.47957805,0.00023669805,0.045118343,0.003077432],"about_ca_topic_score_codex":0.0000042537436,"about_ca_topic_score_gemma":0.0000627575,"teacher_disagreement_score":0.4410191,"about_ca_system_score_codex":0.000019168672,"about_ca_system_score_gemma":0.00021646176,"threshold_uncertainty_score":0.6696905},"labels":[],"label_agreement":null},{"id":"W3194988201","doi":"10.1093/bioinformatics/btab589","title":"PyJAMAS: open-source, multimodal segmentation and analysis of microscopy images","year":2021,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ted Rogers Centre for Heart Research; Hospital for Sick Children; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation; Canadian Institutes of Health Research; Government of Ontario","keywords":"Python (programming language); Scripting language; Computer science; Graphical user interface; Open source; Segmentation; Software; Extensibility; Mac OS; Image segmentation; Open source software; Interface (matter); Image processing; Computer graphics (images); User interface; Artificial intelligence; Data mining; Programming language; Operating system; Image (mathematics)","score_opus":0.00716577433905271,"score_gpt":0.2882043148524268,"score_spread":0.2810385405133741,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3194988201","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84734976,0.0006498845,0.14652383,0.000046962326,0.0000144742835,0.00021858157,0.000065152875,0.00002156635,0.0051097623],"genre_scores_gemma":[0.6112265,0.0013827275,0.38246176,0.0005607066,0.000029511602,0.000018394781,0.0021561303,0.000022541888,0.0021417195],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99933213,0.000025023484,0.00031492996,0.00013444669,0.00009023174,0.000103212165],"domain_scores_gemma":[0.9992983,0.000010841091,0.0001654454,0.0003318932,0.00015353714,0.0000400354],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014577204,0.000096766875,0.00021219657,0.00010836735,0.000040918178,0.00008119929,0.00014926445,0.000072158626,0.00003803444],"category_scores_gemma":[0.00006207801,0.00009465271,0.00009595147,0.00033956612,0.00006534219,0.0000167421,0.00030604447,0.00003389833,0.0000018670236],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014859939,0.00005611301,0.008851926,0.000043540113,0.000676734,0.0000010816158,0.00019853913,0.00005320281,0.9768285,0.0000063654406,0.003660351,0.009608782],"study_design_scores_gemma":[0.00026587505,0.000046962236,0.0028365436,0.0000071601003,0.0004891334,0.00000353756,0.00045876516,0.0063958657,0.98473424,0.000004996752,0.00463994,0.000116973504],"about_ca_topic_score_codex":0.000030922056,"about_ca_topic_score_gemma":0.000029686671,"teacher_disagreement_score":0.23612326,"about_ca_system_score_codex":0.0000073672804,"about_ca_system_score_gemma":0.000038368897,"threshold_uncertainty_score":0.3859825},"labels":[],"label_agreement":null},{"id":"W3196432935","doi":"10.1093/bioinformatics/btab844","title":"RNAglib: a python package for RNA 2.5 D graphs","year":2021,"lang":"en","type":"preprint","venue":"Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University","funders":"Agence Nationale de la Recherche","keywords":"Python (programming language); Computer science; Theoretical computer science; Graph; Representation (politics); Artificial intelligence; Programming language","score_opus":0.018474810047135474,"score_gpt":0.25248114482782946,"score_spread":0.234006334780694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196432935","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35607734,0.0040443023,0.62283903,0.00041153736,0.0035858264,0.0033281497,0.00096114,0.00018057234,0.008572082],"genre_scores_gemma":[0.5627985,0.0030834924,0.4218179,0.0016340996,0.0011210428,0.0010130055,0.0057343123,0.00025020677,0.0025474592],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99849373,0.000043787997,0.0005414157,0.0003400414,0.00020987022,0.00037114506],"domain_scores_gemma":[0.998297,0.00002423857,0.00035979968,0.0010084171,0.00018443717,0.00012613865],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00034801182,0.00037163714,0.00037520353,0.00007861601,0.000106154286,0.00018402196,0.00047355818,0.0007427201,0.000027684277],"category_scores_gemma":[0.00021934019,0.00035735598,0.0004670671,0.00006272302,0.000048062266,0.000006305914,0.00062883185,0.00018939225,0.0000151995055],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024845032,0.00021514078,0.00008355673,0.0040181633,0.00087849103,0.000013651723,0.0011887588,0.0001395655,0.87833846,0.002102098,0.024898803,0.08787484],"study_design_scores_gemma":[0.00052242755,0.00024327214,0.00003631887,0.00024172166,0.0001111435,0.00001673003,0.00044836555,0.00071464514,0.95593464,0.0024412312,0.038545925,0.0007435592],"about_ca_topic_score_codex":0.0000061691135,"about_ca_topic_score_gemma":0.000008821693,"teacher_disagreement_score":0.20672114,"about_ca_system_score_codex":0.00001805959,"about_ca_system_score_gemma":0.00024139075,"threshold_uncertainty_score":0.9998878},"labels":[],"label_agreement":null},{"id":"W3197661809","doi":"10.1093/bioinformatics/btab636","title":"mspack: efficient lossless and lossy mass spectrometry data compression","year":2021,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Lossy compression; Lossless compression; Computer science; Mass spectrometry; Compression (physics); Data compression; Algorithm; Chemistry; Artificial intelligence; Materials science; Chromatography","score_opus":0.024762895791205896,"score_gpt":0.2898678943558391,"score_spread":0.2651049985646332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3197661809","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14077783,0.0006350952,0.81852865,0.00044074684,0.00005623015,0.00018624462,0.00068275,0.00029959125,0.038392875],"genre_scores_gemma":[0.15333256,0.00041012868,0.8448167,0.00011491344,0.000080494945,0.000014482237,0.00065651967,0.000020176474,0.00055402017],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992447,0.0000033284837,0.00025727125,0.00016942424,0.00014872808,0.00017654011],"domain_scores_gemma":[0.99877894,0.000040429873,0.000115404735,0.00093433587,0.000049719052,0.000081148944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000694916,0.00011476218,0.00013503611,0.000026246444,0.000118596756,0.000070584916,0.00029577606,0.00008456862,0.00014195457],"category_scores_gemma":[0.000036262056,0.00010687274,0.00002107865,0.00013464811,0.000058842867,0.00011243382,0.0004610091,0.00016127052,0.000023896151],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005768552,0.0006281063,0.0039222795,0.0031307647,0.00015487337,0.0000606642,0.00092452054,0.00078147015,0.8740493,0.04305716,0.015080679,0.058152515],"study_design_scores_gemma":[0.0005557181,0.000011935005,0.00010712936,0.00020525063,0.00003828318,0.00009411659,0.00076959055,0.27406752,0.67450917,0.0026810523,0.046514817,0.00044542903],"about_ca_topic_score_codex":0.0000017680317,"about_ca_topic_score_gemma":7.011294e-7,"teacher_disagreement_score":0.27328604,"about_ca_system_score_codex":0.000030781477,"about_ca_system_score_gemma":0.000038134815,"threshold_uncertainty_score":0.43581438},"labels":[],"label_agreement":null},{"id":"W3199498600","doi":"10.1093/bioinformatics/btab664","title":"timeOmics: an R package for longitudinal multi-omics data integration","year":2021,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"National Health and Medical Research Council; Medical Research Council","keywords":"R package; Computer science; Longitudinal data; Computational biology; Omics; Data integration; Data mining; Data science; Biology; Bioinformatics; Computational science","score_opus":0.04835382042161563,"score_gpt":0.29535634491152235,"score_spread":0.24700252448990673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3199498600","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023811335,0.0003010528,0.97319055,0.00011186243,0.00044243247,0.0003735973,0.0009477721,0.00002863813,0.00079275435],"genre_scores_gemma":[0.15531915,0.0004979944,0.8011165,0.0013209912,0.00082615745,0.00003424068,0.039699323,0.00006218565,0.0011234285],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99883777,0.000017663468,0.0004908074,0.00025184496,0.00010429088,0.00029761053],"domain_scores_gemma":[0.9981794,0.00001646674,0.00018210436,0.0013000737,0.00019817872,0.00012381251],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036191428,0.00019470678,0.00018095876,0.000033119883,0.00013880829,0.00014557446,0.0004966074,0.00022474381,0.000013603154],"category_scores_gemma":[0.00013848994,0.00018542095,0.00007887658,0.000077484765,0.000055564396,0.000047803896,0.00035054746,0.00010384369,0.000029067467],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00071076595,0.0013690828,0.0025500776,0.0010375539,0.001026304,0.000015994287,0.0032147076,0.0015750383,0.20827696,0.009577685,0.18429239,0.5863535],"study_design_scores_gemma":[0.002095135,0.00037057538,0.0004862627,0.000036907,0.00009928207,0.000093289455,0.0014152434,0.8409764,0.061431393,0.0003730087,0.09191332,0.0007091524],"about_ca_topic_score_codex":0.0000034096727,"about_ca_topic_score_gemma":0.00009988873,"teacher_disagreement_score":0.83940136,"about_ca_system_score_codex":0.000019149507,"about_ca_system_score_gemma":0.00018941301,"threshold_uncertainty_score":0.75612473},"labels":[],"label_agreement":null},{"id":"W3210392179","doi":"10.1093/bioinformatics/btab742","title":"SigTools: exploratory visualization for genomic signals","year":2021,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Fractal and DNA sequence analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Visualization; Computer science; Scope (computer science); Source code; Software; Autocorrelation; Data mining; Data science; Programming language","score_opus":0.021617557391683015,"score_gpt":0.2717709809975664,"score_spread":0.2501534236058834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210392179","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60965323,0.001694692,0.38369387,0.00019208677,0.00025604345,0.00034611358,0.000120307945,0.000045212113,0.0039984584],"genre_scores_gemma":[0.96769595,0.0009655813,0.02292328,0.002989787,0.00045616657,0.00008391772,0.00279833,0.000038622275,0.0020483613],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99940926,0.000014138644,0.00024034156,0.00011014765,0.00008018035,0.00014594953],"domain_scores_gemma":[0.9994817,0.000011107976,0.0000880317,0.00020278285,0.00016473915,0.000051668743],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001052429,0.000091502196,0.000104065984,0.000028694962,0.000070550916,0.00004325345,0.000083830826,0.00008840947,0.00003062425],"category_scores_gemma":[0.000117865166,0.00008726869,0.00010547326,0.000098023665,0.00002495796,0.000013047398,0.0000512525,0.000021854068,0.000040570452],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034040517,0.00006526709,0.00038852714,0.00013475344,0.0001271668,0.0000022433624,0.00029024313,0.00060610316,0.97764766,0.0006336778,0.009652923,0.010417417],"study_design_scores_gemma":[0.0005297891,0.00019237094,0.0001364682,0.000018054689,0.00006960291,0.000010397393,0.0013781332,0.0151627315,0.8136055,0.0004096292,0.16814867,0.00033869036],"about_ca_topic_score_codex":9.852937e-7,"about_ca_topic_score_gemma":0.0000064669553,"teacher_disagreement_score":0.36077058,"about_ca_system_score_codex":0.00001173208,"about_ca_system_score_gemma":0.00011512352,"threshold_uncertainty_score":0.35587138},"labels":[],"label_agreement":null},{"id":"W3214075907","doi":"10.1093/bioinformatics/btab768","title":"<scp>Verna</scp>l: a tool for mining fuzzy network motifs in RNA","year":2021,"lang":"en","type":"article","venue":"Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"Natural Sciences and Engineering Research Council of Canada; Agence Nationale de la Recherche","keywords":"Motif (music); Computer science; Structural motif; Cluster analysis; Source code; Web server; Data mining; Theoretical computer science; Artificial intelligence; The Internet; World Wide Web; Biology","score_opus":0.013765716585605228,"score_gpt":0.23308839328544625,"score_spread":0.219322676699841,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3214075907","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9189329,0.0014170845,0.064804114,0.00010751906,0.00062857615,0.00061136344,0.00006238645,0.00003373872,0.013402281],"genre_scores_gemma":[0.5285483,0.0007654562,0.45829192,0.0022349851,0.0013753212,0.0002718675,0.000471079,0.00009926803,0.007941788],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989086,0.000030465162,0.0003853439,0.00016657001,0.00012723211,0.0003817935],"domain_scores_gemma":[0.999314,0.00007474046,0.00013291414,0.000336783,0.00007881701,0.000062742314],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033795205,0.0001595814,0.00018594203,0.000028645716,0.00007616817,0.000057800145,0.00017618788,0.000201494,0.000007337429],"category_scores_gemma":[0.00051896955,0.00015916963,0.000115905044,0.0001249479,0.000020662019,0.000010115164,0.000112840215,0.00005541051,0.000018119652],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013931203,0.00031890796,0.0061326455,0.0011430249,0.00041537493,0.000058042693,0.0029317301,0.004507196,0.6931533,0.0056867925,0.12828459,0.15722908],"study_design_scores_gemma":[0.0016013967,0.00034323026,0.0010107717,0.00018378247,0.00004380837,0.00005322933,0.0014487675,0.0060475725,0.6725046,0.0016890842,0.31474474,0.00032901362],"about_ca_topic_score_codex":0.0000019331746,"about_ca_topic_score_gemma":0.000014876417,"teacher_disagreement_score":0.3934878,"about_ca_system_score_codex":0.000015474738,"about_ca_system_score_gemma":0.00012082782,"threshold_uncertainty_score":0.649075},"labels":[],"label_agreement":null},{"id":"W3214341251","doi":"10.1093/bioinformatics/btab771","title":"DD-GUI: a graphical user interface for deep learning-accelerated virtual screening of large chemical libraries (Deep Docking)","year":2021,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Canadian Institutes of Health Research","keywords":"Graphical user interface; Computer science; MIT License; License; Docking (animal); Virtual screening; Deep learning; User interface; Drug discovery; Software; Human–computer interaction; Data mining; Artificial intelligence; Operating system; Bioinformatics","score_opus":0.02893742099918154,"score_gpt":0.3022683980524978,"score_spread":0.2733309770533162,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3214341251","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07849726,0.00011822763,0.9202987,0.00025193393,0.00021607925,0.00016123193,0.000013441956,0.00014032847,0.00030281095],"genre_scores_gemma":[0.38266167,0.0000074441077,0.616925,0.00022494461,0.000046419984,0.000012338893,0.000055769495,0.0000145322,0.000051900508],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981711,0.00010964247,0.00068357296,0.00024247354,0.0004145255,0.00037871778],"domain_scores_gemma":[0.99808973,0.0008248459,0.00026792887,0.00035648278,0.0003442035,0.00011680057],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046959362,0.0002049859,0.00033479632,0.00014210165,0.00013898719,0.0003462764,0.00067369436,0.00012967599,0.000025618223],"category_scores_gemma":[0.00083050615,0.00020166195,0.00017530452,0.0007822468,0.00008838111,0.001285108,0.0008205942,0.00027426993,0.000009062137],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024672228,0.0005844992,0.001674843,0.00070186344,0.00044955875,0.000030508052,0.019139368,0.18243346,0.004762997,0.64752185,0.0016275747,0.14082676],"study_design_scores_gemma":[0.0007125207,0.00010346566,0.00034791048,0.000057713136,0.000013722684,0.000033677126,0.0005413448,0.96079,0.03057145,0.0016761919,0.0049138586,0.00023819586],"about_ca_topic_score_codex":0.0000015274996,"about_ca_topic_score_gemma":0.000001859142,"teacher_disagreement_score":0.7783565,"about_ca_system_score_codex":0.000024495523,"about_ca_system_score_gemma":0.00017002039,"threshold_uncertainty_score":0.8223536},"labels":[],"label_agreement":null},{"id":"W3214361435","doi":"10.1093/bioinformatics/btab754","title":"Mian: interactive web-based microbiome data table visualization and machine learning platform","year":2021,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Context (archaeology); Categorical variable; Source code; Visualization; Machine learning; Metadata; Data mining; Artificial intelligence; MIT License; Table (database); License; Information retrieval; World Wide Web; Programming language","score_opus":0.024662368003439315,"score_gpt":0.2864016975794296,"score_spread":0.26173932957599033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3214361435","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93732715,0.0038249379,0.050844073,0.0006714515,0.0006321625,0.0006304726,0.0014665256,0.000117567324,0.004485637],"genre_scores_gemma":[0.9412975,0.00130466,0.022128068,0.0025555184,0.0001829033,0.0000069287134,0.029993359,0.000053466116,0.002477649],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992909,0.000021790214,0.00024853853,0.00018095641,0.00006046021,0.00019735911],"domain_scores_gemma":[0.99935514,0.0000133584645,0.00012239367,0.00034639493,0.000092393835,0.000070342016],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015275396,0.00012421403,0.00012576366,0.000046733883,0.00012633503,0.000072083574,0.00014155083,0.00011602086,0.000037836493],"category_scores_gemma":[0.0000919767,0.000120480494,0.000020973104,0.00012162834,0.000037591533,0.000025281586,0.00027614838,0.00010310211,0.000018910121],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009474975,0.00011389011,0.0028630742,0.0004940616,0.00008054938,0.000006071785,0.00041616513,0.00006651726,0.9745411,0.00011946119,0.01678445,0.0044198753],"study_design_scores_gemma":[0.0017834804,0.00021816131,0.0005454295,0.00008648814,0.000037262802,0.00010685765,0.0006540922,0.12762898,0.18637107,0.0000054515717,0.6822077,0.00035503687],"about_ca_topic_score_codex":0.000014496935,"about_ca_topic_score_gemma":0.00007276811,"teacher_disagreement_score":0.78817004,"about_ca_system_score_codex":0.00001758574,"about_ca_system_score_gemma":0.00024630158,"threshold_uncertainty_score":0.4913052},"labels":[],"label_agreement":null},{"id":"W4200168537","doi":"10.1093/bioinformatics/btab836","title":"TMBleR: a bioinformatic tool to optimize TMB estimation and predictive power","year":2021,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Cancer Immunotherapy and Biomarkers","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Izaak Walton Killam Health Centre; Dalhousie University","funders":"Ministero della Salute","keywords":"MIT License; Computer science; License; Container (type theory); Exome; Open source; Interface (matter); Heuristic; Predictive power; Data mining; Computational biology; Exome sequencing; Software; Gene; Operating system; Artificial intelligence; Mutation; Biology","score_opus":0.01103806359430913,"score_gpt":0.2568978572876185,"score_spread":0.24585979369330935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200168537","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.65791935,0.0014838156,0.2716625,0.006842303,0.0011547247,0.0031460566,0.00029063076,0.00047301085,0.057027638],"genre_scores_gemma":[0.34758425,0.00055052614,0.6377139,0.01181295,0.000096370306,0.00010108263,0.00032390296,0.00004778025,0.0017692152],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99885815,0.000010108994,0.0005096465,0.000107752516,0.00028059396,0.00023373673],"domain_scores_gemma":[0.99924415,0.000043572705,0.00010716107,0.00031391942,0.00014581773,0.0001453504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001952151,0.00016373997,0.00025960646,0.00012492463,0.00008868981,0.00008719577,0.000055680433,0.000095197225,0.00021274836],"category_scores_gemma":[0.00016595975,0.00013719339,0.00007970571,0.0003381978,0.000054496155,0.00037340441,0.00006788888,0.00010350422,0.000106220716],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0061407266,0.000579165,0.0022814337,0.003204554,0.001498765,0.00011089497,0.044030227,0.0012868774,0.0050598425,0.0009551383,0.074781545,0.8600708],"study_design_scores_gemma":[0.014105473,0.0028918285,0.041591685,0.0018133948,0.0005175698,0.0019381497,0.010667255,0.82008576,0.014669498,0.00026423053,0.09015322,0.0013019383],"about_ca_topic_score_codex":0.0000041228514,"about_ca_topic_score_gemma":0.0000012169124,"teacher_disagreement_score":0.8587689,"about_ca_system_score_codex":0.00009887698,"about_ca_system_score_gemma":0.00019898896,"threshold_uncertainty_score":0.55945843},"labels":[],"label_agreement":null},{"id":"W4200253063","doi":"10.1093/bioinformatics/btab826","title":"A network-based drug repurposing method via non-negative matrix factorization","year":2021,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Non-negative matrix factorization; Drug repositioning; Matrix decomposition; Repurposing; Factorization; Matrix (chemical analysis); Drug; Algorithm; Artificial intelligence; Pharmacology; Chemistry; Medicine; Engineering; Chromatography","score_opus":0.018187499973003937,"score_gpt":0.3095715465829911,"score_spread":0.2913840466099871,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200253063","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00055210455,0.00005807205,0.996085,0.00047342887,0.0007529552,0.00022032327,0.0000073298047,0.00016456093,0.0016862436],"genre_scores_gemma":[0.0162733,0.0000035352934,0.98255384,0.0008290744,0.000121161014,0.000011676682,0.00004127569,0.0000128977545,0.00015326479],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980926,0.00026243474,0.00056468725,0.00025116713,0.00049981335,0.00032929314],"domain_scores_gemma":[0.9976638,0.001008869,0.00031142918,0.00056086417,0.0003457121,0.00010931767],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00085215276,0.00019679722,0.00024566095,0.000111027744,0.00020490725,0.00038060814,0.00047861296,0.00006855152,0.000015252925],"category_scores_gemma":[0.00027766952,0.00019628405,0.000110112116,0.0011667182,0.0000260914,0.0010909794,0.00029957868,0.00016605333,0.000052840755],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010401814,0.0000687838,0.00021230761,0.00013495891,0.00004416717,0.00001977375,0.0036346803,0.88849866,0.00020304997,0.02075448,0.0022556013,0.084163144],"study_design_scores_gemma":[0.00031588651,0.00001928964,0.00050614204,0.00005514549,0.000012484719,0.000020227502,0.000058461967,0.9742844,0.006456289,0.016565133,0.0014715311,0.00023497567],"about_ca_topic_score_codex":0.000011666858,"about_ca_topic_score_gemma":0.0000039358856,"teacher_disagreement_score":0.085785784,"about_ca_system_score_codex":0.00013157714,"about_ca_system_score_gemma":0.00049365655,"threshold_uncertainty_score":0.8004231},"labels":[],"label_agreement":null},{"id":"W4200301447","doi":"10.1093/bioinformatics/btab852","title":"geoCancerPrognosticDatasetsRetriever: a bioinformatics tool to easily identify cancer prognostic datasets on Gene Expression Omnibus (GEO)","year":2021,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Perl; Computer science; Data mining; DNA microarray; MIT License; Download; Bioinformatics; Computational biology; Information retrieval; Software; Gene; Gene expression; World Wide Web; Biology; Programming language","score_opus":0.01894596870205884,"score_gpt":0.2948328055811739,"score_spread":0.2758868368791151,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200301447","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85206693,0.0036450415,0.1018604,0.0021774631,0.00443854,0.0040928097,0.027340146,0.00033440394,0.004044241],"genre_scores_gemma":[0.751862,0.0047330935,0.14899985,0.018527139,0.001656202,0.0014333302,0.070708044,0.0002272876,0.0018530494],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9975743,0.000055271445,0.0007873587,0.00044767238,0.00059813826,0.0005372341],"domain_scores_gemma":[0.99780846,0.000035632773,0.00031676967,0.0012614812,0.00026037428,0.00031727995],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00024309331,0.00037793667,0.00028977802,0.00014513964,0.00023604957,0.0001972151,0.00045461554,0.000251251,0.00014771438],"category_scores_gemma":[0.0006481607,0.00034550426,0.00012048276,0.0005283462,0.00005978022,0.000052002095,0.00043115419,0.00018634813,0.0003143467],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039220904,0.0003615306,0.0032594192,0.0004296592,0.00013218248,0.00002316938,0.00044046936,0.0012393573,0.42713338,0.000111276204,0.511495,0.05498239],"study_design_scores_gemma":[0.0010291997,0.00029102847,0.0069956654,0.0003230074,0.00006744191,0.000035797308,0.00027662877,0.0019884799,0.6438726,0.000025345611,0.34441814,0.00067664246],"about_ca_topic_score_codex":0.000010058513,"about_ca_topic_score_gemma":0.000016635013,"teacher_disagreement_score":0.21673925,"about_ca_system_score_codex":0.000082192266,"about_ca_system_score_gemma":0.00052793574,"threshold_uncertainty_score":0.9998997},"labels":[],"label_agreement":null},{"id":"W4206241205","doi":"10.1093/bioinformatics/btab874","title":"SPEQ: quality assessment of peptide tandem mass spectra with deep learning","year":2021,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Tandem; Computer science; Quality (philosophy); Peptide; Quality assurance; Quality assessment; Artificial intelligence; Chemistry; Evaluation methods; Materials science; Reliability engineering; Physics; Biochemistry; Engineering; External quality assessment; Operations management","score_opus":0.021111677440230032,"score_gpt":0.3115698301347636,"score_spread":0.29045815269453357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206241205","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06448452,0.00002951041,0.78754294,0.00008194507,0.000007339614,0.00009123613,0.00001575386,0.00012241385,0.14762436],"genre_scores_gemma":[0.25867087,0.00009155204,0.74035895,0.000026504793,0.00002311053,0.000020768399,0.000058144422,0.000011360856,0.0007387246],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991562,0.0000074651507,0.0003905154,0.00009488933,0.00019839639,0.00015254054],"domain_scores_gemma":[0.99917126,0.000050082417,0.00029360488,0.00032238802,0.00011268542,0.000049988175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012049216,0.00010634556,0.00018318734,0.00001649019,0.00007727332,0.000024655888,0.00011683493,0.000063064974,0.00023083895],"category_scores_gemma":[0.000029726354,0.000094814604,0.00005137436,0.00012243347,0.000045253408,0.00009889034,0.000047594043,0.00022317789,0.0000051974353],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005595275,0.00065790315,0.18136244,0.0036391863,0.0004346985,0.00003284705,0.0028583114,0.008320505,0.5389195,0.21692847,0.00044002058,0.046350155],"study_design_scores_gemma":[0.000985392,0.000090718095,0.0038332918,0.00023052655,0.00007035663,0.00004374062,0.005633979,0.050009474,0.9094948,0.006287658,0.022662725,0.00065731915],"about_ca_topic_score_codex":0.000004277056,"about_ca_topic_score_gemma":0.0000063206676,"teacher_disagreement_score":0.3705753,"about_ca_system_score_codex":0.0000698396,"about_ca_system_score_gemma":0.00008365272,"threshold_uncertainty_score":0.38664272},"labels":[],"label_agreement":null},{"id":"W4206552974","doi":"10.1093/bioinformatics/btaa924","title":"Scool: a new data storage format for single-cell Hi-C data","year":2020,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Deutsche Forschungsgemeinschaft; Royal Bank of Canada; National Bar Institute","keywords":"Computer science; File format; Reuse; Database; Data format; Data file; Computer data storage; Raw data; Operating system; Programming language; Computer hardware","score_opus":0.12624920128489087,"score_gpt":0.27267642649154566,"score_spread":0.1464272252066548,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206552974","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02591024,0.0015406762,0.9579459,0.0015808726,0.00087007496,0.0013001558,0.0044987136,0.00014846658,0.006204906],"genre_scores_gemma":[0.54632646,0.000697809,0.38183904,0.012123676,0.0032821994,0.000019528912,0.05425462,0.00020281356,0.0012538569],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99861246,0.000013452362,0.00047937568,0.00035806684,0.00018034028,0.0003563299],"domain_scores_gemma":[0.99781823,0.000022232356,0.00016890829,0.0016550628,0.000058858426,0.00027672143],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018973673,0.00023760511,0.00022477136,0.000027119326,0.00010481928,0.00012314762,0.0017743058,0.00018092037,0.000015729374],"category_scores_gemma":[0.00019956261,0.00022433978,0.00006772318,0.00010272791,0.00004971775,0.000070515984,0.00083832734,0.00010684729,0.000049153146],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00054835767,0.00027559543,0.00024964547,0.0010784686,0.00015518058,0.000003780894,0.0011279454,0.00018976134,0.2726592,0.00006510906,0.6857031,0.037943877],"study_design_scores_gemma":[0.0020568455,0.0005993173,0.00000847247,0.000023978224,0.000088373876,0.000012173305,0.0002738424,0.17943166,0.04129871,0.00001521463,0.7757258,0.00046565125],"about_ca_topic_score_codex":0.000014566043,"about_ca_topic_score_gemma":0.000021017197,"teacher_disagreement_score":0.57610685,"about_ca_system_score_codex":0.000011554514,"about_ca_system_score_gemma":0.000224711,"threshold_uncertainty_score":0.91483104},"labels":[],"label_agreement":null},{"id":"W4206944890","doi":"10.1093/bioinformatics/btab854","title":"BATL: Bayesian annotations for targeted lipidomics","year":2021,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; Ottawa Hospital; University of Ottawa","funders":"National Institute of Neurological Disorders and Stroke; Natural Sciences and Engineering Research Council of Canada","keywords":"Lipidomics; Bayesian probability; Computer science; Computational biology; Data mining; Bioinformatics; Artificial intelligence; Biology","score_opus":0.010961671639871308,"score_gpt":0.250181686187481,"score_spread":0.2392200145476097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206944890","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19481331,0.0044503273,0.7704935,0.002341835,0.0023133105,0.0010761981,0.00097206765,0.00009477013,0.023444666],"genre_scores_gemma":[0.41186258,0.00232627,0.57352316,0.0028692516,0.0010485027,0.00014403358,0.0028316788,0.00006510944,0.0053293835],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992903,0.000010932823,0.00026992772,0.00013162722,0.00007657697,0.0002206517],"domain_scores_gemma":[0.99936193,0.000019986901,0.00008914486,0.00026834584,0.0001980865,0.00006252989],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010953264,0.000119722696,0.00015130827,0.000040053103,0.00013606282,0.000040295607,0.00009970411,0.00008979064,0.000020730551],"category_scores_gemma":[0.00030407432,0.000115986,0.00011381666,0.00012882805,0.000033822525,0.0000055778887,0.00008265355,0.000042241096,0.000009369754],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001592721,0.00031053854,0.001341361,0.0004219293,0.00087186036,0.0000038130922,0.0008420861,0.0003188525,0.7230989,0.029596409,0.22109182,0.021943167],"study_design_scores_gemma":[0.0011537893,0.00018392937,0.0005962422,0.000008248047,0.000062475534,0.000017843075,0.00082984427,0.0056392746,0.2412254,0.0007767159,0.7491508,0.0003554441],"about_ca_topic_score_codex":9.094478e-7,"about_ca_topic_score_gemma":0.000014255495,"teacher_disagreement_score":0.52805895,"about_ca_system_score_codex":0.000009422526,"about_ca_system_score_gemma":0.000108107146,"threshold_uncertainty_score":0.47297716},"labels":[],"label_agreement":null},{"id":"W4210425469","doi":"10.1093/bioinformatics/btac037","title":"GenomeTornadoPlot: a novel R package for CNV visualization and focality analysis","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomic variations and chromosomal abnormalities","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; Deutschen Konsortium für Translationale Krebsforschung; Deutsche Forschungsgemeinschaft","keywords":"R package; Visualization; Computer science; Parallel computing; Computational science; Artificial intelligence","score_opus":0.014098011942831874,"score_gpt":0.24234130736854387,"score_spread":0.228243295425712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210425469","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.59171295,0.00014320889,0.40641803,0.000053789914,0.000085943,0.00028014695,0.0008421245,0.000015648162,0.00044815548],"genre_scores_gemma":[0.9906005,0.000025697274,0.007326847,0.0002675336,0.000055012977,0.00008347163,0.0012462041,0.000010010593,0.00038468605],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993898,0.000015654694,0.00024442014,0.0001117482,0.00009666574,0.00014165473],"domain_scores_gemma":[0.99958766,0.0000104321025,0.00011431643,0.00019108085,0.00005070811,0.00004583402],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021455646,0.000088420355,0.00011679042,0.00008077242,0.00028002018,0.000036962454,0.00009854831,0.000038270016,0.00003352928],"category_scores_gemma":[0.000028740493,0.000090304995,0.00008960933,0.00019143788,0.00002539361,0.0000066702446,0.00015490652,0.000029128569,9.84004e-7],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014765204,0.0028571333,0.13378508,0.002533613,0.017166128,0.0000045835063,0.03922795,0.028308213,0.4644195,0.26953107,0.024601214,0.016088955],"study_design_scores_gemma":[0.006021969,0.0026503284,0.06493795,0.000009317255,0.0028544052,0.00009525245,0.022426302,0.23439495,0.03520607,0.0011316922,0.6281319,0.002139848],"about_ca_topic_score_codex":0.000014318647,"about_ca_topic_score_gemma":0.000015063535,"teacher_disagreement_score":0.6035307,"about_ca_system_score_codex":0.000023131537,"about_ca_system_score_gemma":0.000045093115,"threshold_uncertainty_score":0.36825308},"labels":[],"label_agreement":null},{"id":"W4210607727","doi":"10.1093/bioinformatics/btac077","title":"PDMDA: predicting deep-level miRNA–disease associations with graph neural networks and sequence features","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"MicroRNA in disease regulation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"National Natural Science Foundation of China-Zhejiang Joint Fund for the Integration of Industrialization and Informatization; Higher Education Discipline Innovation Project; Guizhou Science and Technology Department; National Natural Science Foundation of China","keywords":"Softmax function; Computer science; Artificial neural network; Artificial intelligence; Disease; Computational biology; Feature (linguistics); Association (psychology); microRNA; Machine learning; Biology; Genetics; Gene; Medicine; Pathology","score_opus":0.013996187747695224,"score_gpt":0.23173156990943583,"score_spread":0.2177353821617406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210607727","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9805398,0.0010331875,0.016903207,0.00018772295,0.00014560718,0.00039633358,0.0004090768,0.00004739586,0.00033767184],"genre_scores_gemma":[0.9951596,0.00002900627,0.0033648624,0.00029487337,0.0000857916,0.000039735536,0.0009310007,0.000015633832,0.000079451725],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99924594,0.000045315086,0.00018625992,0.00013507494,0.00018977304,0.00019764464],"domain_scores_gemma":[0.9994196,0.000016284645,0.0001682398,0.00021512645,0.000057763864,0.00012295583],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014098376,0.000123642,0.0000846992,0.000043954093,0.000348705,0.000048598453,0.00012275019,0.00004850058,0.000007534916],"category_scores_gemma":[0.00007023073,0.00011719399,0.00004278154,0.00013252217,0.000057501078,0.000015144935,0.00016390612,0.000112150155,3.7986592e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009019188,0.00042142003,0.36264226,0.00048820485,0.00081864675,0.000030072259,0.0019915428,0.5599649,0.01815775,0.0016533989,0.016344095,0.0365858],"study_design_scores_gemma":[0.00129825,0.00034135947,0.33669773,0.000022845903,0.00017850105,0.00008490982,0.000731858,0.6566734,0.00062467216,0.00014728395,0.0026036403,0.0005955572],"about_ca_topic_score_codex":0.0000071117242,"about_ca_topic_score_gemma":0.000015614913,"teacher_disagreement_score":0.0967085,"about_ca_system_score_codex":0.000032367338,"about_ca_system_score_gemma":0.00006034842,"threshold_uncertainty_score":0.47790322},"labels":[],"label_agreement":null},{"id":"W4210808382","doi":"10.1093/bioinformatics/btac081","title":"SmMIP-tools: a computational toolset for processing and analysis of single-molecule molecular inversion probes-derived data","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Acute Myeloid Leukemia Research","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network; University of Toronto; Ontario Institute for Cancer Research","funders":"Canada First Research Excellence Fund","keywords":"Computer science; Source code; Modular design; Raw data; DNA sequencing; Set (abstract data type); Data mining; Scripting language; Computational biology; Biology; Genetics; Programming language; DNA","score_opus":0.07001876067722557,"score_gpt":0.3211005807529847,"score_spread":0.25108182007575913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210808382","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7443832,0.0003005791,0.2503107,0.000986616,0.000029842508,0.0015145328,0.0016599839,0.00006274776,0.0007517943],"genre_scores_gemma":[0.78802115,0.000011364649,0.20195854,0.0007661233,0.000013537446,0.00004950444,0.009103161,0.000021122543,0.000055475735],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986099,0.000027886852,0.00042422712,0.0001745383,0.00056603394,0.00019741346],"domain_scores_gemma":[0.9989511,0.00014131525,0.00021267022,0.00039031662,0.00021446799,0.00009016194],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048515343,0.00011041315,0.0003211953,0.0004113907,0.00015935753,0.000047110305,0.00026337986,0.000045512956,0.000031388685],"category_scores_gemma":[0.00034408536,0.00010411997,0.000071167226,0.00085753074,0.00008909291,0.00033343825,0.0006197314,0.00015267883,0.0000011279396],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006100533,0.0035716172,0.013945485,0.023973811,0.015375593,0.00023960676,0.034408547,0.08311735,0.27256817,0.0037363488,0.045676004,0.49728692],"study_design_scores_gemma":[0.0014173083,0.00035389548,0.00063052075,0.000036982812,0.0007740577,0.000021700936,0.0015749712,0.9917772,0.0017971256,0.000071621726,0.0014290552,0.0001155889],"about_ca_topic_score_codex":0.000007831004,"about_ca_topic_score_gemma":0.0000015805429,"teacher_disagreement_score":0.9086598,"about_ca_system_score_codex":0.00016230792,"about_ca_system_score_gemma":0.00043790723,"threshold_uncertainty_score":0.42458892},"labels":[],"label_agreement":null},{"id":"W4213201540","doi":"10.1093/bioinformatics/btac096","title":"CNGPLD: case–control copy-number analysis using Gaussian process latent difference","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomic variations and chromosomal abnormalities","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; National Institute of General Medical Sciences; National Institutes of Health; National Cancer Institute; Canadian Institutes of Health Research; Cancer Prevention and Research Institute of Texas; U.S. Department of Defense","keywords":"False discovery rate; Copy-number variation; Genome; Computational biology; Covariance; Selection (genetic algorithm); Biology; Somatic cell; Genetics; Computer science; Gene; Mathematics; Statistics; Artificial intelligence","score_opus":0.011863232954302026,"score_gpt":0.24514270016203954,"score_spread":0.2332794672077375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213201540","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9857584,0.00005165069,0.012413815,0.000030221292,0.00009841284,0.00015435254,0.00033411122,0.000015447105,0.0011435407],"genre_scores_gemma":[0.99675214,0.0000071754703,0.0022419721,0.0002340811,0.000058790825,0.00003336623,0.00015498497,0.000010842991,0.00050662743],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99907243,0.00004320359,0.00033681028,0.00013807061,0.00016925726,0.00024024912],"domain_scores_gemma":[0.99941236,0.000007293247,0.00016401464,0.00028217613,0.00006206114,0.000072108895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000148765,0.00014227514,0.00017571486,0.00007246092,0.00038341028,0.000049801063,0.00017499005,0.000056266777,0.000320249],"category_scores_gemma":[0.0000119634005,0.00013382664,0.00013296992,0.0002744239,0.000033481832,0.0000075598446,0.00013185994,0.00008953245,0.000009222231],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002479473,0.0003507047,0.8230465,0.00041521378,0.004938241,0.00026437873,0.009291076,0.14664158,0.008997583,0.00178078,0.0009836017,0.0030423813],"study_design_scores_gemma":[0.00721976,0.0013857927,0.07300492,0.00003732345,0.006718927,0.011594097,0.037302766,0.82359,0.021359485,0.0006381011,0.013121246,0.0040276083],"about_ca_topic_score_codex":0.000058070327,"about_ca_topic_score_gemma":0.000029941191,"teacher_disagreement_score":0.7500416,"about_ca_system_score_codex":0.00004151996,"about_ca_system_score_gemma":0.000100363366,"threshold_uncertainty_score":0.5457292},"labels":[],"label_agreement":null},{"id":"W4213235856","doi":"10.1093/bioinformatics/btac100","title":"Pre-training graph neural networks for link prediction in biomedical networks","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":90,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Research (Canada)","funders":"National Natural Science Foundation of China","keywords":"Computer science; Initialization; Graph; Artificial intelligence; Convolutional neural network; Machine learning; Artificial neural network; Node (physics); Encoder; Deep learning; Data mining; Theoretical computer science","score_opus":0.012200227654294996,"score_gpt":0.2334871319472515,"score_spread":0.22128690429295653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213235856","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06493451,0.0009735631,0.9283417,0.00038203792,0.0025157584,0.0014775884,0.00026993683,0.000083268766,0.0010216706],"genre_scores_gemma":[0.98521507,0.000116464435,0.008819008,0.0012673052,0.001105766,0.00033142575,0.0028569037,0.000043416938,0.00024465343],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99813694,0.00004271024,0.0007922446,0.00020877908,0.00021974153,0.00059957727],"domain_scores_gemma":[0.9991668,0.00003991517,0.00024808085,0.00035691945,0.000043548967,0.00014476015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007644488,0.00023138062,0.00024126437,0.00013942522,0.00031065292,0.00005419444,0.00036398674,0.00024909773,0.000029860545],"category_scores_gemma":[0.000037802507,0.00023523772,0.00016485094,0.0003078966,0.000093786235,0.000016920254,0.00032711477,0.00038266607,0.0000012586327],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037470483,0.000111360125,0.0013273873,0.00009276739,0.00010879859,0.0000027398064,0.001298242,0.8258178,0.00018698644,0.000420206,0.030524576,0.13973439],"study_design_scores_gemma":[0.001136927,0.0006173282,0.00053877773,0.000011509242,0.000018738712,0.000039730643,0.00059738953,0.9492218,0.000011021913,0.00015495464,0.047397185,0.00025466018],"about_ca_topic_score_codex":0.000005656182,"about_ca_topic_score_gemma":0.000012918305,"teacher_disagreement_score":0.9202806,"about_ca_system_score_codex":0.00004839575,"about_ca_system_score_gemma":0.00007968358,"threshold_uncertainty_score":0.95927155},"labels":[],"label_agreement":null},{"id":"W4214521759","doi":"10.1093/bioinformatics/btac134","title":"HAMdetector: a Bayesian regression model that integrates information to detect HLA-associated mutations","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"vaccines and immunoinformatics approaches","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"AIDS Vancouver; Simon Fraser University","funders":"Canadian Institutes of Health Research; Deutsche Forschungsgemeinschaft; Michael Smith Health Research BC","keywords":"Human leukocyte antigen; Major histocompatibility complex; CTL*; Computational biology; Biology; Epitope; Bayesian probability; Bayes' theorem; Population; Bayesian inference; Computer science; Genetics; CD8; Artificial intelligence; Immune system; Antigen","score_opus":0.016174406778392554,"score_gpt":0.2369433670564221,"score_spread":0.22076896027802956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214521759","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.65301853,0.00021618005,0.33432245,0.0006224955,0.00057045167,0.0017119956,0.00073135283,0.00021285437,0.008593654],"genre_scores_gemma":[0.9694584,0.000032493153,0.027142545,0.001066765,0.000025788404,0.00020575224,0.0016439409,0.000025024188,0.00039928197],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984765,0.000038808434,0.00064569275,0.00012067973,0.00036033816,0.00035800418],"domain_scores_gemma":[0.99892724,0.000014925738,0.0003636624,0.00044635092,0.00011893974,0.0001288612],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040312525,0.0002532057,0.00020407708,0.0002169166,0.00053241383,0.00013557298,0.00040691797,0.00011582309,0.000041782583],"category_scores_gemma":[0.00020935072,0.0002219699,0.00013782892,0.0003257357,0.00002460111,0.000081285645,0.00045675688,0.00020955887,0.000038725342],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014229633,0.00059409137,0.00287092,0.0007685295,0.0010563898,0.000004382631,0.046712127,0.42102683,0.06477216,0.0013426656,0.20756553,0.25186342],"study_design_scores_gemma":[0.0014306157,0.0009378948,0.00051280187,0.000044714157,0.000059078255,0.000044906566,0.009488048,0.9113364,0.030221539,0.0003687864,0.044753112,0.00080207555],"about_ca_topic_score_codex":0.000016499955,"about_ca_topic_score_gemma":0.000015858392,"teacher_disagreement_score":0.49030963,"about_ca_system_score_codex":0.00010673506,"about_ca_system_score_gemma":0.00015859932,"threshold_uncertainty_score":0.9051669},"labels":[],"label_agreement":null},{"id":"W4220970247","doi":"10.1093/bioinformatics/btac157","title":"RevUP: an online scoring system for regulatory variants implicated in rare diseases","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Children's Hospital; University of British Columbia","funders":"ZonMw","keywords":"Classifier (UML); Computer science; Source code; Scoring system; Phenotype; Data mining; Computational biology; Artificial intelligence; Biology; Genetics; Medicine; Gene","score_opus":0.017269702443983927,"score_gpt":0.2424494757252676,"score_spread":0.22517977328128366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220970247","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9962447,0.00046653915,0.00044296338,0.000029164295,0.00021054578,0.00044696007,0.0020269214,0.000029269815,0.0001029339],"genre_scores_gemma":[0.9942735,0.000021821223,0.0020158852,0.00015635106,0.00012803555,0.000109222245,0.003208893,0.000022328284,0.000063984975],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99915195,0.000027653476,0.0003238678,0.00017003843,0.00010342494,0.00022306548],"domain_scores_gemma":[0.99931806,0.000007718157,0.000120470846,0.00039845842,0.000045982022,0.00010932567],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012163442,0.00012211155,0.00013856408,0.000069134105,0.00016721475,0.000025338533,0.00024547285,0.000048447477,0.000006668748],"category_scores_gemma":[0.00003103149,0.00012403818,0.00007592902,0.00009564506,0.000019294785,0.000008822611,0.00018686008,0.000050063285,0.0000014729508],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.007929269,0.009120097,0.1301531,0.014124274,0.0014774416,0.00035381204,0.00560189,0.06805177,0.51950395,0.014609301,0.05476033,0.17431478],"study_design_scores_gemma":[0.021023536,0.005276604,0.46957192,0.00046412135,0.00054105965,0.00084203406,0.0435934,0.22534256,0.015062245,0.0006550855,0.21297309,0.004654368],"about_ca_topic_score_codex":0.000008984143,"about_ca_topic_score_gemma":0.000009375824,"teacher_disagreement_score":0.5044417,"about_ca_system_score_codex":0.000058353493,"about_ca_system_score_gemma":0.00013308437,"threshold_uncertainty_score":0.505813},"labels":[],"label_agreement":null},{"id":"W4221007687","doi":"10.1093/bioinformatics/btac128","title":"SomaticSiMu: a mutational signature simulator","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Western University","funders":"Compute Canada","keywords":"Python (programming language); Computer science; Visualization; Data mining; Signature (topology); Graphical user interface; Open source; Source code; Software; Computational biology; Artificial intelligence; Programming language; Biology","score_opus":0.008138215293260502,"score_gpt":0.222538426452493,"score_spread":0.2144002111592325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221007687","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9921866,0.0008002527,0.0020991904,0.00017404598,0.00038819102,0.00026447533,0.00022150156,0.000010547542,0.0038551935],"genre_scores_gemma":[0.9919293,0.000018547427,0.0064456854,0.0008357933,0.00011233074,0.000034740136,0.00015294917,0.0000133925205,0.0004572779],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.99931204,0.0000190424,0.00021694919,0.0001007658,0.00018390507,0.00016730031],"domain_scores_gemma":[0.9996008,0.000014724812,0.00009114182,0.00020022063,0.00004659572,0.0000465053],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000117448864,0.000108206725,0.00009203118,0.00003501331,0.0002678489,0.000017590966,0.00017752362,0.000042520984,0.000067902205],"category_scores_gemma":[0.000033972738,0.000107361775,0.000069552996,0.00007538017,0.00003338833,8.2233754e-7,0.0002786067,0.000081761325,0.000013451036],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004487415,0.000866444,0.013842115,0.00043088765,0.0014429654,0.00003106623,0.010124754,0.4502324,0.31600177,0.009837795,0.16587776,0.0308633],"study_design_scores_gemma":[0.0024293037,0.0011770771,0.00740787,0.000007791988,0.00007881448,0.00014070261,0.0049738334,0.09415801,0.014331157,0.0019730427,0.87224954,0.00107288],"about_ca_topic_score_codex":0.0000013297674,"about_ca_topic_score_gemma":0.000001346172,"teacher_disagreement_score":0.7063718,"about_ca_system_score_codex":0.000016622647,"about_ca_system_score_gemma":0.00007629414,"threshold_uncertainty_score":0.4378086},"labels":[],"label_agreement":null},{"id":"W4224287786","doi":"10.1093/bioinformatics/btac287","title":"SimPlot++: a Python application for representing sequence similarity and detecting recombination","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":155,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Agriculture and Agri-Food Canada; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Python (programming language); Computer science; Sequence (biology); Computational biology; Programming language; Biology; Genetics","score_opus":0.026194200691998164,"score_gpt":0.27159187954014335,"score_spread":0.2453976788481452,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224287786","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97892267,0.00022454317,0.019675586,0.00014320211,0.000101124875,0.00047959934,0.000054090087,0.0000093611725,0.00038984045],"genre_scores_gemma":[0.9871071,0.000053734024,0.012345639,0.0001537267,0.000047631056,0.0001596348,0.000074957905,0.000010176612,0.000047389345],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994659,0.000016265874,0.00018803972,0.00013202515,0.00006906424,0.00012871776],"domain_scores_gemma":[0.99960864,0.00002404824,0.00012728076,0.00016238248,0.000052979423,0.000024647168],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032405573,0.00007210411,0.000071148475,0.000025262036,0.00037102695,0.00001926536,0.00008392936,0.000032721517,9.5244985e-7],"category_scores_gemma":[0.0001112272,0.00007959645,0.000032238928,0.000054253924,0.000022078077,0.0000016902645,0.00022303758,0.000046324065,3.466335e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009295404,0.00006609602,0.011353052,0.00024405269,0.00009277006,3.04428e-7,0.0016276992,0.0017128306,0.7876749,0.0009038503,0.0008542518,0.19537722],"study_design_scores_gemma":[0.0033133696,0.0018690305,0.014236333,0.000019840816,0.0001378346,0.00013099323,0.007691904,0.40264514,0.20090844,0.008907749,0.3587684,0.0013709384],"about_ca_topic_score_codex":0.00000918257,"about_ca_topic_score_gemma":0.0000065291783,"teacher_disagreement_score":0.5867665,"about_ca_system_score_codex":0.00001615245,"about_ca_system_score_gemma":0.000022801312,"threshold_uncertainty_score":0.3245849},"labels":[],"label_agreement":null},{"id":"W4224289048","doi":"10.1093/bioinformatics/btac286","title":"Tightly integrated multiomics-based deep tensor survival model for time-to-event prediction","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Ferroptosis and cancer prognosis","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; Princess Margaret Cancer Centre; CancerCare Manitoba; Public Health Ontario; University of Toronto","funders":"","keywords":"Computer science; Data mining; Concordance; Machine learning; Artificial intelligence; Bioinformatics; Biology","score_opus":0.025212904911393164,"score_gpt":0.26451984591089206,"score_spread":0.2393069409994989,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224289048","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08707419,0.00006164591,0.90101564,0.0027726232,0.0006903283,0.0036423919,0.002120779,0.00042969434,0.002192681],"genre_scores_gemma":[0.75519687,0.000015988695,0.22507995,0.0067830803,0.0002577447,0.002355392,0.0032935948,0.00012268304,0.006894696],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987907,0.000017075476,0.00044789398,0.00013495886,0.00035520768,0.00025419955],"domain_scores_gemma":[0.9992673,0.000038462644,0.00011779453,0.0002449624,0.00017759154,0.00015389427],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002960781,0.00015338491,0.0002555179,0.00016331124,0.00020379068,0.000024345545,0.00011683949,0.000056684305,0.00035657955],"category_scores_gemma":[0.000062914,0.00013244963,0.00014490099,0.00024966281,0.000021504788,0.000075083284,0.00005419608,0.00014736269,0.000082795836],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004928485,0.0020623282,0.004331305,0.0013658374,0.0005488522,0.000004861847,0.0065893703,0.6667689,0.0053561674,0.00046914822,0.16701359,0.14056115],"study_design_scores_gemma":[0.0018669856,0.0007159947,0.00026082227,0.000029561596,0.00010241388,0.000003642656,0.00038054457,0.9658479,0.0006005655,0.000011605244,0.030041985,0.00013794086],"about_ca_topic_score_codex":0.000008278536,"about_ca_topic_score_gemma":0.0000032383796,"teacher_disagreement_score":0.67593575,"about_ca_system_score_codex":0.00033252948,"about_ca_system_score_gemma":0.00024146737,"threshold_uncertainty_score":0.5401139},"labels":[],"label_agreement":null},{"id":"W4224309355","doi":"10.1093/bioinformatics/btac276","title":"Kernel-based hierarchical structural component models for pathway analysis","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Kernel (algebra); Computer science; Kernel method; Computational biology; Software; Data mining; Pathway analysis; Component (thermodynamics); Machine learning; Artificial intelligence; Bioinformatics; Biology; Support vector machine; Mathematics; Genetics","score_opus":0.01322497955221346,"score_gpt":0.23123613584337055,"score_spread":0.21801115629115708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224309355","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15367408,0.00027385273,0.8418394,0.00023158295,0.00038385214,0.000749343,0.0010244744,0.000042053136,0.0017813584],"genre_scores_gemma":[0.9576917,0.000005720486,0.037719868,0.0011200019,0.00011424789,0.00011367822,0.003009316,0.00001995734,0.00020545725],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986873,0.00003132614,0.0005109203,0.00016822832,0.00024361991,0.0003585755],"domain_scores_gemma":[0.9991323,0.000026495052,0.00020746066,0.00044725186,0.00006365347,0.00012286559],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031804762,0.00019420212,0.00024713756,0.00013151325,0.00038472426,0.00005136289,0.00036609548,0.000095680414,0.000047718357],"category_scores_gemma":[0.000011762169,0.00018294847,0.0003444044,0.00023931965,0.00006422111,0.0000086258315,0.000254168,0.00015424922,0.0000030622057],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003834891,0.0000902398,0.00054830016,0.00013159559,0.00087272713,0.0000013324114,0.00061305106,0.96878475,0.0014274723,0.006464722,0.0072289105,0.0134534165],"study_design_scores_gemma":[0.00081881863,0.0002790403,0.00016916191,0.0000018504031,0.00011507502,0.0000059272975,0.00019473786,0.9703822,0.0006390066,0.0011808611,0.025935326,0.00027799798],"about_ca_topic_score_codex":0.000005416462,"about_ca_topic_score_gemma":0.000007842189,"teacher_disagreement_score":0.8041195,"about_ca_system_score_codex":0.00004378705,"about_ca_system_score_gemma":0.00013352113,"threshold_uncertainty_score":0.74604225},"labels":[],"label_agreement":null},{"id":"W4225351187","doi":"10.1093/bioinformatics/btac236","title":"Characterizing domain-specific open educational resources by linking ISCB Communities of Special Interest to Wikipedia","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Wikis in Education and Collaboration","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency","funders":"","keywords":"Computer science; Resource (disambiguation); Representation (politics); Data science; Domain (mathematical analysis); Systems biology; Computational biology; Biology; Mathematics","score_opus":0.05021417730920626,"score_gpt":0.3220012158937981,"score_spread":0.27178703858459186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225351187","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7875306,0.00005450763,0.00021455417,0.013030795,0.0026392688,0.0006389525,0.00014958256,0.000029977577,0.19571179],"genre_scores_gemma":[0.97509384,0.000101079895,0.01450684,0.0029661744,0.0026075998,0.0001701528,0.00046250812,0.000018434697,0.0040733963],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.998812,0.00016998331,0.00040031152,0.00006075338,0.00038762044,0.00016932812],"domain_scores_gemma":[0.9991668,0.0001477631,0.00026481098,0.0002000239,0.00014051114,0.00008012973],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008591096,0.00007785509,0.00012712092,0.00013108435,0.001181622,0.00035261086,0.00088524993,0.000033440545,0.0019214848],"category_scores_gemma":[0.00003462517,0.00008841075,0.00002743188,0.00050156575,0.00012930138,0.0005069299,0.00038273778,0.00014218032,0.000042210384],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003236679,0.00014591611,0.001499674,0.000016243852,0.000010789535,6.754321e-8,0.7047098,0.000008227429,0.00016195429,0.13071445,0.15496619,0.007734329],"study_design_scores_gemma":[0.000079083424,0.00003105776,0.0006136594,0.000016465157,0.0000018043746,3.5944458e-7,0.28889805,0.000007714521,0.000033441887,0.0006384867,0.70959985,0.00008004714],"about_ca_topic_score_codex":0.0002562515,"about_ca_topic_score_gemma":0.0008596624,"teacher_disagreement_score":0.5546337,"about_ca_system_score_codex":0.00021905944,"about_ca_system_score_gemma":0.00037553086,"threshold_uncertainty_score":0.9989909},"labels":[],"label_agreement":null},{"id":"W4225604045","doi":"10.1093/bioinformatics/btac283","title":"Continuous chromatin state feature annotation of the human epigenome","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Genome British Columbia; Michael Smith Health Research BC; Compute Canada; Genome Canada","keywords":"Epigenome; Chromatin; Epigenomics; Computer science; Annotation; Computational biology; Genome; Biology; Genetics; Artificial intelligence; Gene; DNA methylation; Gene expression","score_opus":0.004797717254827892,"score_gpt":0.20735783793867735,"score_spread":0.20256012068384946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225604045","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99729306,0.00010258709,0.00040515634,0.000089436304,0.0001497442,0.00022869236,0.000205877,0.0000074972772,0.0015179696],"genre_scores_gemma":[0.99613094,0.000013706128,0.002067467,0.00018278361,0.000028372282,0.000017240405,0.00025307812,0.000013782798,0.0012926304],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99928623,0.000035195488,0.00027829417,0.00008245068,0.00017066766,0.00014718196],"domain_scores_gemma":[0.9992644,0.000004696828,0.00029804846,0.00035364585,0.00005232306,0.000026861411],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001693122,0.00010010712,0.00011139582,0.00002657766,0.00025165,0.000016325333,0.00031830955,0.000041121846,0.000021095204],"category_scores_gemma":[0.000016825468,0.000082071245,0.00008597938,0.00010442031,0.00005341133,0.0000032470334,0.0003045229,0.000099407414,0.000002372993],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043447282,0.00022458172,0.010034474,0.00030958155,0.00019256271,0.000001886403,0.005801931,0.009199396,0.9483413,0.0016075446,0.017597355,0.0066459463],"study_design_scores_gemma":[0.0072126924,0.0038388341,0.20727178,0.00010385071,0.00024768876,0.00024379342,0.01919707,0.052638095,0.3600552,0.0050548376,0.3413547,0.0027814598],"about_ca_topic_score_codex":0.000008095404,"about_ca_topic_score_gemma":0.000010725178,"teacher_disagreement_score":0.5882861,"about_ca_system_score_codex":0.000026076941,"about_ca_system_score_gemma":0.00006466515,"threshold_uncertainty_score":0.33467683},"labels":[],"label_agreement":null},{"id":"W4225839207","doi":"10.1093/bioinformatics/btac259","title":"PhyloPGM: boosting regulatory function prediction accuracy using evolutionary information","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computational biology; Computer science; Boosting (machine learning); Context (archaeology); Probabilistic logic; Sequence (biology); Function (biology); Data mining; Extant taxon; Genomics; DNA binding site; Gene regulatory network; Machine learning; Biology; Genome; Gene; Artificial intelligence; Genetics; Gene expression; Evolutionary biology; Promoter","score_opus":0.008650630458668988,"score_gpt":0.20584923273597067,"score_spread":0.19719860227730168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225839207","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97069633,0.00014397429,0.025875669,0.000028169921,0.000720924,0.0002906686,0.00022331659,0.00004942601,0.0019715333],"genre_scores_gemma":[0.9866652,0.00002773395,0.010658633,0.0003862347,0.00017897335,0.00002972451,0.001945064,0.000016290067,0.000092134134],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989744,0.000030009183,0.0004377305,0.00009878946,0.00025754317,0.00020151718],"domain_scores_gemma":[0.9992531,0.000008878655,0.00030714797,0.00028994863,0.00008812875,0.000052791278],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021670897,0.00013088936,0.00008559242,0.00009315233,0.0005273294,0.000043060314,0.00015462625,0.000078786055,0.000041253956],"category_scores_gemma":[0.00006495061,0.00015003074,0.00007158219,0.00013187708,0.00003072929,0.00005494289,0.0002798961,0.00012486232,0.000012781618],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007560124,0.00039822608,0.023821807,0.000788525,0.0005215418,0.0000029339863,0.003529772,0.61196136,0.20202689,0.0037470828,0.0743661,0.07807973],"study_design_scores_gemma":[0.00087232975,0.0004457808,0.014380276,0.000014194072,0.0000560118,0.00014059787,0.0025291778,0.8346618,0.0011053963,0.00024256708,0.14515208,0.00039982752],"about_ca_topic_score_codex":0.000007619914,"about_ca_topic_score_gemma":8.582103e-7,"teacher_disagreement_score":0.22270039,"about_ca_system_score_codex":0.00013482413,"about_ca_system_score_gemma":0.00016027021,"threshold_uncertainty_score":0.6118076},"labels":[],"label_agreement":null},{"id":"W4226094768","doi":"10.1093/bioinformatics/btac266","title":"A graph neural network approach for molecule carcinogenicity prediction","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Machine learning; Artificial intelligence; Data mining; Source code; Graph; Theoretical computer science; Programming language","score_opus":0.0286934818020863,"score_gpt":0.25977673961487296,"score_spread":0.23108325781278666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226094768","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009454904,0.000060030794,0.98787624,0.000102054204,0.00052008487,0.00046474268,0.00006376697,0.00015480614,0.0013033553],"genre_scores_gemma":[0.15333797,0.0000013509953,0.8455536,0.0006228826,0.00010513686,0.00021186871,0.00011802673,0.000008958019,0.00004025143],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99876106,0.00009633113,0.00031990124,0.00016252697,0.00038723525,0.0002729213],"domain_scores_gemma":[0.99927485,0.00013552529,0.00013611306,0.00033184735,0.00005801174,0.00006366225],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006618169,0.00011031764,0.00012395732,0.00009119966,0.00043187532,0.0000983845,0.00064682035,0.000023545868,0.0000039087854],"category_scores_gemma":[0.00003309696,0.000114056566,0.00012423552,0.00058300403,0.000021828244,0.00044013705,0.0005219796,0.00013166563,0.0000014959397],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001074863,0.000037524474,0.00017203593,0.000029921286,0.000015171116,4.025899e-7,0.00062088546,0.9677839,0.00000607319,0.02050567,0.0051936093,0.005624054],"study_design_scores_gemma":[0.00027548298,0.00011579867,0.0008823257,0.0000010633936,0.000008154811,0.000028774199,0.00008505491,0.99265784,0.00003179723,0.004346556,0.001451006,0.00011617312],"about_ca_topic_score_codex":0.0000045936586,"about_ca_topic_score_gemma":2.6200547e-7,"teacher_disagreement_score":0.14388306,"about_ca_system_score_codex":0.00007713328,"about_ca_system_score_gemma":0.00009270149,"threshold_uncertainty_score":0.46510917},"labels":[],"label_agreement":null},{"id":"W4226119586","doi":"10.1093/bioinformatics/btac226","title":"Syotti: scalable bait design for DNA enrichment","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"National Human Genome Research Institute; National Institute of Allergy and Infectious Diseases; Natural Sciences and Engineering Research Council of Canada; Agencia Nacional de Investigación y Desarrollo; United States - Israel Binational Science Foundation; National Institutes of Health; National Science Foundation","keywords":"Metagenomics; Scalability; Computer science; Heuristic; Set (abstract data type); Computational biology; DNA; Process (computing); Protocol (science); Data mining; Algorithm; Biology; Database; Genetics; Artificial intelligence; Programming language; Gene","score_opus":0.02003392150478879,"score_gpt":0.23204389337318718,"score_spread":0.21200997186839837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226119586","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7160695,0.004544344,0.25954086,0.0008226599,0.0019930748,0.003456704,0.00077653443,0.000040677885,0.01275564],"genre_scores_gemma":[0.9025821,0.00023379955,0.092841305,0.0012209349,0.000213359,0.0005553044,0.0001904707,0.00003379546,0.0021289056],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99927473,0.000020364869,0.00022733527,0.00012371723,0.00011612956,0.00023771962],"domain_scores_gemma":[0.9995594,0.000020232264,0.000086694345,0.0002383829,0.000046163335,0.000049120168],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027080436,0.000116747186,0.00011181124,0.000030181525,0.00030959237,0.000020396896,0.0001961668,0.00003701731,0.00002588386],"category_scores_gemma":[0.000028511078,0.00011459484,0.00007836884,0.000058653044,0.000026572565,7.7831066e-7,0.0002565761,0.000039248232,0.00000831383],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00075712305,0.0006176676,0.0031849751,0.00042939838,0.0009983858,0.0000032855344,0.0029332624,0.0508595,0.43937373,0.003664198,0.46011478,0.03706369],"study_design_scores_gemma":[0.001135384,0.0013164819,0.00063616486,0.0000032637552,0.00004705364,0.000017969458,0.00084530824,0.013060083,0.04896261,0.0004870337,0.9330854,0.00040326704],"about_ca_topic_score_codex":0.0000024976748,"about_ca_topic_score_gemma":0.0000010063925,"teacher_disagreement_score":0.4729706,"about_ca_system_score_codex":0.00002551057,"about_ca_system_score_gemma":0.00007161343,"threshold_uncertainty_score":0.4673042},"labels":[],"label_agreement":null},{"id":"W4226329328","doi":"10.1093/bioinformatics/btac195","title":"ELIXIR biovalidator for semantic validation of life science metadata","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"Vlaamse regering; Fonds Wetenschappelijk Onderzoek; European Bioinformatics Institute","keywords":"Validator; Computer science; License; Schema (genetic algorithms); Elixir (programming language); Information retrieval; Metadata; JSON; Semantic integration; World Wide Web; Programming language; Semantic Web","score_opus":0.03119283094040965,"score_gpt":0.28790835011622395,"score_spread":0.2567155191758143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226329328","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9287149,0.00044704307,0.0687027,0.00031402058,0.0005385784,0.00041652672,0.0003970324,0.00003321556,0.00043599136],"genre_scores_gemma":[0.95742613,0.000023449413,0.041708637,0.00027586834,0.000055198358,0.000043618085,0.0002901875,0.0000080121,0.00016888275],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990975,0.000017305238,0.00030353997,0.00012651125,0.00027026454,0.00018485264],"domain_scores_gemma":[0.9993239,0.000023735513,0.0001713206,0.00032471656,0.000088892804,0.00006745013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007071899,0.000078852536,0.00012802467,0.00008418973,0.000204583,0.000027857699,0.00041372317,0.000042453063,0.000014500273],"category_scores_gemma":[0.0006157517,0.00006969745,0.00006201666,0.00022570317,0.00024531674,0.000011553638,0.00033054678,0.00004504666,0.0000020331895],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004529197,0.00046914024,0.0040491703,0.0009409454,0.00032572038,0.000001050717,0.0013810195,0.0007200683,0.8495335,0.0037852677,0.05635635,0.08198487],"study_design_scores_gemma":[0.0011566622,0.0010914669,0.0004141421,0.000011821443,0.00005929957,0.000014325628,0.0023614324,0.007987288,0.707563,0.00014236724,0.27886745,0.00033078156],"about_ca_topic_score_codex":0.000003701956,"about_ca_topic_score_gemma":6.046337e-7,"teacher_disagreement_score":0.22251111,"about_ca_system_score_codex":0.000012764227,"about_ca_system_score_gemma":0.00027765395,"threshold_uncertainty_score":0.28421795},"labels":[],"label_agreement":null},{"id":"W4229030659","doi":"10.1093/bioinformatics/btac309","title":"Targeted metabolomics analyses for brain tumor margin assessment during surgery","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Bruker BioSpin","keywords":"Brain tumor; Receiver operating characteristic; Biomarker; Metabolomics; Margin (machine learning); Computer science; Glioma; Magnetic resonance imaging; Artificial intelligence; Medicine; Chemistry; Machine learning; Bioinformatics; Radiology; Biology; Cancer research; Pathology","score_opus":0.02779288951151632,"score_gpt":0.30232438225387476,"score_spread":0.27453149274235844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4229030659","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98389786,0.0014865894,0.011107132,0.0005456271,0.0006680657,0.00058680755,0.0006166527,0.00004062128,0.001050633],"genre_scores_gemma":[0.93648344,0.00039970307,0.05792446,0.0014358893,0.00030601522,0.00045665383,0.0012758762,0.0000566339,0.0016613537],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986319,0.000056412744,0.0004951493,0.00021203695,0.00022156954,0.00038292352],"domain_scores_gemma":[0.9991512,0.00007563575,0.00027626695,0.00034812512,0.00007479076,0.00007403432],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062586705,0.00020550023,0.000359924,0.00018094994,0.00045708474,0.00004097742,0.0002210977,0.0000407312,0.0000706352],"category_scores_gemma":[0.00022138166,0.00019824828,0.00027603583,0.00023892583,0.000040512026,0.000008826361,0.00037378742,0.00010990628,0.0000023727762],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038935975,0.00032380066,0.006471129,0.0004425211,0.0014263559,0.0000084334015,0.0002443863,0.0018682312,0.85995597,0.0022613711,0.124561906,0.002046538],"study_design_scores_gemma":[0.0023831052,0.00053177745,0.018268202,0.000009831158,0.00027181694,0.00008382823,0.0031787376,0.011057545,0.22864437,0.00033962182,0.7339605,0.0012706767],"about_ca_topic_score_codex":0.0000058431615,"about_ca_topic_score_gemma":0.0000045320235,"teacher_disagreement_score":0.6313116,"about_ca_system_score_codex":0.000050495582,"about_ca_system_score_gemma":0.0001481919,"threshold_uncertainty_score":0.808433},"labels":[],"label_agreement":null},{"id":"W4232460051","doi":"10.4018/978-1-4666-3604-0.ch067","title":"The Impact of Genetic Testing and Genetic Information on Ethical, Legal and Social Issues in North America","year":2013,"lang":"en","type":"book-chapter","venue":"Bioinformatics","topic":"Reproductive Health and Technologies","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Genetic testing; Genetic discrimination; Eugenics; Autonomy; Legislation; Political science; Terminology; Internet privacy; Law; Computer science; Medicine","score_opus":0.030871836761586547,"score_gpt":0.304688814603027,"score_spread":0.27381697784144043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4232460051","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8965424,0.003093328,0.00011556888,0.0038638075,0.00012583334,0.0031181697,0.00008864874,0.00017238488,0.09287991],"genre_scores_gemma":[0.8602237,0.025739836,0.103404805,0.0023804724,0.00067022565,0.00013247227,0.00016410492,0.00012838833,0.007155988],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99885035,0.00000799789,0.00063801365,0.000088022076,0.00022020924,0.0001954011],"domain_scores_gemma":[0.9989343,0.00016536558,0.00045030282,0.00023546032,0.00016333917,0.000051198538],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009521646,0.00019884558,0.0003647515,0.00018555165,0.00011244806,0.00004684961,0.00007054327,0.00033666362,0.000005975772],"category_scores_gemma":[0.00050699594,0.0001223419,0.000043116135,0.000061952414,0.00042467963,0.00010319389,0.00007203474,0.000641585,0.000022705079],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001130042,0.000016520402,0.009461108,0.0015534223,0.00007381588,0.0000048991205,0.00210826,0.000027556913,0.000007081971,0.0022278246,0.0026569094,0.9817496],"study_design_scores_gemma":[0.0013768807,0.00410646,0.9131156,0.0007249769,0.00012041719,0.00017391992,0.0007946278,0.010203338,0.000020194699,0.0039025398,0.06489151,0.0005695028],"about_ca_topic_score_codex":0.00019608946,"about_ca_topic_score_gemma":0.000010068169,"teacher_disagreement_score":0.9811801,"about_ca_system_score_codex":0.000058269175,"about_ca_system_score_gemma":0.00016938124,"threshold_uncertainty_score":0.4988958},"labels":[],"label_agreement":null},{"id":"W4232856118","doi":"10.36255/exonpublications.bioinformatics.2021.cont","title":"List of Contributors","year":2021,"lang":"en","type":"book-chapter","venue":"Bioinformatics","topic":"Genetically Modified Organisms Research","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Library science; Humanities; Engineering; Art","score_opus":0.03265229458678334,"score_gpt":0.2262356959710034,"score_spread":0.19358340138422006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4232856118","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0056737834,0.00065582915,0.000026296111,0.00048222207,0.00019786808,0.00040353998,0.000733562,0.00005686576,0.99177],"genre_scores_gemma":[0.051728435,0.001399124,0.003882589,0.00040497578,0.0005982097,0.000008164831,0.0017520454,0.000008278521,0.94021815],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987208,0.000008898143,0.00046729247,0.000118483644,0.0004651353,0.00021936397],"domain_scores_gemma":[0.9991526,0.00015292499,0.00019738438,0.000108673965,0.00027173167,0.000116659205],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00014596811,0.00017796771,0.00032978598,0.000016129827,0.000055370354,0.000048354457,0.00031823147,0.00032918545,0.0044302],"category_scores_gemma":[0.00008297956,0.0000684761,0.0001568681,0.00005068057,0.00011815987,0.00003590885,0.00021326353,0.00021000455,0.00020135134],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005234474,0.0001358574,0.00016525245,0.0006747065,0.00034240232,0.00005036421,0.0003061159,0.0000039267275,0.059032824,0.38641217,0.031269625,0.5215544],"study_design_scores_gemma":[0.00017943604,0.00037932157,0.0011866108,0.00021447119,0.00005156909,0.00001692219,0.00014016853,0.00014629967,0.007191721,0.003054149,0.98692,0.00051930343],"about_ca_topic_score_codex":0.000018038987,"about_ca_topic_score_gemma":0.00006170163,"teacher_disagreement_score":0.9556504,"about_ca_system_score_codex":0.000029430294,"about_ca_system_score_gemma":0.000041186537,"threshold_uncertainty_score":0.99647987},"labels":[],"label_agreement":null},{"id":"W4233566421","doi":"10.1201/b16589-19","title":"Combined Analysis of Three Genome-Wide Association Studies on vWF and FVIII Plasma Levels","year":2014,"lang":"en","type":"book-chapter","venue":"Bioinformatics","topic":"Blood Coagulation and Thrombosis Mechanisms","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; Fondation pour la Recherche Médicale; Institut National de la Santé et de la Recherche Médicale; Canada Research Chairs; Heart and Stroke Foundation of Canada","keywords":"Genome-wide association study; Genetic association; Medicine; Computational biology; Internal medicine; Genetics; Biology; Single-nucleotide polymorphism; Genotype; Gene","score_opus":0.06007262892958733,"score_gpt":0.2769431802463115,"score_spread":0.21687055131672417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233566421","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061814502,0.0005875879,0.008367782,0.0029866758,0.0014222256,0.002952861,0.0007717667,0.0003770992,0.9207195],"genre_scores_gemma":[0.78807056,0.0011554915,0.0107066175,0.0060618934,0.00027286608,0.000026530877,0.0012667163,0.00015470108,0.19228463],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.998232,0.000010143767,0.00088421913,0.00014622956,0.0005725573,0.00015484374],"domain_scores_gemma":[0.99755824,0.0005156535,0.001134481,0.00036590174,0.00033128652,0.00009443288],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041826558,0.00028375976,0.0012384661,0.0006077017,0.00007212238,0.000018659264,0.00007622439,0.00036756948,0.00009787538],"category_scores_gemma":[0.000383285,0.00024472043,0.00025093535,0.000113627975,0.000056401448,0.000045614554,0.00006985279,0.00020584973,0.00006121266],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031303795,0.00020372545,0.011176848,0.0031101822,0.063736744,0.0000068200015,0.005844446,0.00032984745,0.00011428904,0.9003378,0.0042228866,0.010603368],"study_design_scores_gemma":[0.02946107,0.013339068,0.37354723,0.0064971726,0.16936843,0.000016077234,0.0026835606,0.1979459,0.0038407308,0.06563927,0.13170265,0.0059588607],"about_ca_topic_score_codex":0.0000015383941,"about_ca_topic_score_gemma":0.000037259426,"teacher_disagreement_score":0.83469856,"about_ca_system_score_codex":0.00014691285,"about_ca_system_score_gemma":0.00006428368,"threshold_uncertainty_score":0.99794096},"labels":[],"label_agreement":null},{"id":"W4239428642","doi":"10.1093/bioinformatics/btr647","title":"Sensitive and fast mapping of di-base encoded reads","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Chemical Synthesis and Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Base (topology); Software; Computational biology; Biology; Programming language; Mathematics","score_opus":0.016896724885756904,"score_gpt":0.20783175419916358,"score_spread":0.19093502931340667,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239428642","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9810174,0.00006164799,0.010685492,0.000015321057,0.000014332939,0.000047310026,0.000024053918,0.0000057281345,0.0081286775],"genre_scores_gemma":[0.9875928,0.000099918856,0.0121069765,0.00006254419,0.000023771318,0.0000014253958,0.000030011766,0.000004777402,0.00007777506],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99955773,0.000008209028,0.00020326767,0.00007318839,0.000059791142,0.00009779008],"domain_scores_gemma":[0.9996511,0.00000797435,0.00009530218,0.00014882404,0.00004650967,0.00005032097],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000079239835,0.00007591125,0.0001221062,0.000026282769,0.000023308168,0.0000053608896,0.000053379037,0.000067631576,0.000010548164],"category_scores_gemma":[0.00005184426,0.00006283294,0.00005787637,0.00005296195,0.000071814415,0.0000035770647,0.00006666405,0.000026950127,0.0000033903586],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003045411,0.00005249531,0.0029039064,0.00009673019,0.00011352845,0.000001309683,0.0013043627,0.0000022138095,0.97665745,0.0001214366,0.00026826907,0.018447869],"study_design_scores_gemma":[0.0001348286,0.000045783378,0.0011674969,0.00002099472,0.000025665198,0.000005310872,0.0008507592,0.0015764014,0.9954087,0.000023840767,0.0006364204,0.00010379503],"about_ca_topic_score_codex":0.000016516044,"about_ca_topic_score_gemma":0.0000036559306,"teacher_disagreement_score":0.018751279,"about_ca_system_score_codex":0.0000030596368,"about_ca_system_score_gemma":0.000011938422,"threshold_uncertainty_score":0.25622532},"labels":[],"label_agreement":null},{"id":"W4241029082","doi":"10.1093/bioinformatics/btr601","title":"Automated workflows for accurate mass-based putative metabolite identification in LC/MS-derived metabolomic datasets","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Discovery Centre; University of Alberta","funders":"Biotechnology and Biological Sciences Research Council; Directorate for Biological Sciences; National Institute for Health and Care Research; Cancer Research UK; Wellcome Trust","keywords":"Metabolomics; Workflow; Identification (biology); Metabolite; Computer science; Computational biology; Chromatography; Chemistry; Data mining; Biology; Biochemistry; Database","score_opus":0.030480199805048347,"score_gpt":0.28736586061543684,"score_spread":0.2568856608103885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4241029082","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6825063,0.0035786333,0.2982742,0.00025909668,0.0014206799,0.0036930747,0.0076274252,0.00033889606,0.00230168],"genre_scores_gemma":[0.82621306,0.000596234,0.16513817,0.00042673486,0.00009190443,0.0003293889,0.0070440513,0.00004681897,0.00011363729],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983586,0.000058078273,0.00073241396,0.00029540906,0.00014207435,0.00041340178],"domain_scores_gemma":[0.9988561,0.000034260178,0.00039480216,0.0004953275,0.0001345748,0.000084919855],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005517408,0.00027739597,0.0003732909,0.00021748611,0.00010783916,0.000053935106,0.00032461158,0.00015700478,0.000016068037],"category_scores_gemma":[0.0002868743,0.00025137037,0.00013163406,0.0002977819,0.00009199632,0.0000346694,0.000090061716,0.000086407,0.000025809908],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010215547,0.00039976783,0.0012725422,0.00035093984,0.00077244214,0.000004576625,0.0014428038,0.0006112392,0.97863084,0.0027395235,0.006337856,0.0064159073],"study_design_scores_gemma":[0.0031059799,0.0002549745,0.020339135,0.000019352445,0.0002196772,0.0000036547438,0.0006394792,0.086519375,0.8620716,0.00079271104,0.025270892,0.0007631765],"about_ca_topic_score_codex":0.000018759192,"about_ca_topic_score_gemma":0.000021965176,"teacher_disagreement_score":0.14370674,"about_ca_system_score_codex":0.000024219446,"about_ca_system_score_gemma":0.00009461383,"threshold_uncertainty_score":0.99999386},"labels":[],"label_agreement":null},{"id":"W4243450674","doi":"10.1093/bioinformatics/btab790","title":"Theory of local k-mer selection with applications to long-read alignment","year":2021,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Selection (genetic algorithm); Computer science; Algorithm; Artificial intelligence","score_opus":0.009314820077001981,"score_gpt":0.22851076394630696,"score_spread":0.21919594386930497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4243450674","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28345427,0.0003484391,0.7125371,0.00008350288,0.000035848756,0.00023857807,0.00002970255,0.0000034150448,0.0032691583],"genre_scores_gemma":[0.9692147,0.00008286848,0.029651793,0.00029758568,0.000055278317,0.000050006274,0.00004657578,0.00000908301,0.00059213646],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99955344,0.000010755595,0.00016173285,0.000088954985,0.00007785579,0.00010728473],"domain_scores_gemma":[0.99958485,0.000006895857,0.00005488045,0.00018328261,0.000125538,0.000044561766],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000068981484,0.00007730026,0.00008572179,0.000017951794,0.000053969106,0.0000074693203,0.000063276224,0.000042771608,0.000011838321],"category_scores_gemma":[0.0000063431453,0.0000645932,0.000030510953,0.000082635415,0.00004712179,5.970225e-7,0.00006607728,0.000021394284,0.0000104522815],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045638377,0.000667767,0.021671226,0.0005736872,0.0014444398,0.0000035134917,0.0020376483,0.015518202,0.65799946,0.026785735,0.0054547614,0.26738718],"study_design_scores_gemma":[0.00062691636,0.00065825944,0.014142542,0.000027087153,0.00009149517,0.000050995488,0.0016105236,0.0003449223,0.9048313,0.0004042637,0.07685609,0.00035559823],"about_ca_topic_score_codex":0.0000020009584,"about_ca_topic_score_gemma":0.000019014722,"teacher_disagreement_score":0.6857604,"about_ca_system_score_codex":0.000009120446,"about_ca_system_score_gemma":0.00006766788,"threshold_uncertainty_score":0.26340345},"labels":[],"label_agreement":null},{"id":"W4244443336","doi":"10.1093/bioinformatics/btt670","title":"ISCB/SPRINGER series in computational biology","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Computational Physics and Python Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Series (stratigraphy); Computer science; Computational biology; Biology","score_opus":0.01424726321169884,"score_gpt":0.24695382801820068,"score_spread":0.23270656480650184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4244443336","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010451015,0.000013485021,0.9789504,0.0028040744,0.00009792943,0.00019048697,0.0000039158813,0.00007645395,0.0074122814],"genre_scores_gemma":[0.5609169,0.0000031274653,0.4383374,0.0005679297,0.00002625192,0.000043874043,0.00002408451,0.0000032888258,0.00007716772],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994276,0.000010079311,0.00024607178,0.000087354194,0.00009415131,0.00013474241],"domain_scores_gemma":[0.9995484,0.000073738054,0.00006728469,0.00018487994,0.00008321646,0.000042505708],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000067749614,0.00007080913,0.00007927138,0.000089928915,0.000054102038,0.00011534949,0.00032279477,0.000028552315,0.000027615777],"category_scores_gemma":[0.000008658543,0.00006555974,0.000025220317,0.0002925514,0.00003175662,0.0006968526,0.00013629376,0.000060886458,0.00069351675],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.9288375e-7,0.00002605793,0.0006382287,0.000007847557,0.0000037396483,1.2709317e-7,0.0004989933,0.0049677626,0.000020874217,0.96165,0.0013509878,0.030835051],"study_design_scores_gemma":[0.000110227375,0.000014998603,0.021658774,0.0000039746756,4.415383e-7,0.0000041082762,0.000025780739,0.6799095,0.000020923757,0.29304036,0.0051155696,0.0000952993],"about_ca_topic_score_codex":0.000024336918,"about_ca_topic_score_gemma":0.0000028128648,"teacher_disagreement_score":0.6749418,"about_ca_system_score_codex":0.000019718373,"about_ca_system_score_gemma":0.00005203238,"threshold_uncertainty_score":0.8913986},"labels":[],"label_agreement":null},{"id":"W4246220398","doi":"10.1093/bioinformatics/btt046","title":"A system for exact and approximate genetic linkage analysis of SNP data in large pedigrees","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Pedigree chart; Linkage (software); SNP; Computer science; Genetics; Genetic linkage; Genetic data; Computational biology; Biology; Data mining; Single-nucleotide polymorphism; Genotype; Population; Medicine; Gene","score_opus":0.02390971813834013,"score_gpt":0.27855223092193776,"score_spread":0.2546425127835976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4246220398","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94081455,0.00036700311,0.05767912,0.000041542407,0.000039932853,0.00038226327,0.0004053285,0.0000062910694,0.00026398306],"genre_scores_gemma":[0.9595329,0.00016212126,0.039220754,0.00005698162,0.000031737556,0.00003880227,0.0009037573,0.000007189234,0.000045721565],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990342,0.00003150899,0.00049416913,0.00015531768,0.00006247363,0.00022233154],"domain_scores_gemma":[0.99909467,0.000046463418,0.0002292234,0.00050964055,0.000073027404,0.000046957943],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004416332,0.00010116389,0.00029077558,0.000124782,0.000035284265,0.000015389425,0.00021963326,0.00014139384,0.000005864351],"category_scores_gemma":[0.00018859481,0.00008767368,0.000057597437,0.0001686507,0.000032019416,0.000008061051,0.00020111454,0.00003348764,0.0000025320167],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033827328,0.00017518125,0.97393817,0.0013534148,0.0015621546,6.395959e-7,0.0010538675,0.0017391797,0.0055360002,0.00032738745,0.0039050668,0.010375119],"study_design_scores_gemma":[0.00056798605,0.000104746556,0.35384384,0.000015364574,0.00026055987,0.0000025257325,0.0012046058,0.64257586,0.00027560623,0.000023034396,0.000975492,0.00015038313],"about_ca_topic_score_codex":0.000056950597,"about_ca_topic_score_gemma":0.00011333428,"teacher_disagreement_score":0.64083666,"about_ca_system_score_codex":0.000008992702,"about_ca_system_score_gemma":0.000029757375,"threshold_uncertainty_score":0.35752288},"labels":[],"label_agreement":null},{"id":"W4250891669","doi":"10.1093/bioinformatics/btn204","title":"<i>Editorial</i>","year":2008,"lang":"he","type":"article","venue":"Bioinformatics","topic":"Earthquake and Disaster Impact Studies","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.03853453417813308,"score_gpt":0.286133681234586,"score_spread":0.24759914705645292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4250891669","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051423322,0.0012281049,0.00019228822,0.0015666082,0.18005599,0.0004797358,0.000079871555,0.00021272685,0.7647613],"genre_scores_gemma":[0.6838835,0.016934033,0.0037322065,0.0035685168,0.26196626,0.000015981212,0.000027116785,0.00004980852,0.029822586],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978259,0.00006187777,0.00052551826,0.00010824177,0.0008753415,0.0006030972],"domain_scores_gemma":[0.99889684,0.00016132047,0.00022209031,0.00027315764,0.00017579942,0.0002707719],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00041219202,0.00021765295,0.00029890885,0.000065340915,0.0014525348,0.0001033479,0.00030182296,0.0002281015,0.0003159675],"category_scores_gemma":[0.0003272123,0.00019256282,0.00015053866,0.000396564,0.0006483877,0.0006784282,0.00012085993,0.00019139244,0.0052892254],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008576726,0.000044579647,0.0015303723,0.000042150226,0.000033407952,0.0000024086314,0.1424366,0.0000014875545,0.0000018373336,0.00066486566,0.8529507,0.002283034],"study_design_scores_gemma":[0.0003904289,0.00011012952,0.0014825234,0.000037512382,0.000032127504,0.000005567499,0.025265723,0.00007094819,0.00001376897,0.00013341158,0.9721706,0.00028726296],"about_ca_topic_score_codex":0.0003092097,"about_ca_topic_score_gemma":0.000077790966,"teacher_disagreement_score":0.73493874,"about_ca_system_score_codex":0.0000620373,"about_ca_system_score_gemma":0.00041529458,"threshold_uncertainty_score":0.9998474},"labels":[],"label_agreement":null},{"id":"W4280528542","doi":"10.1093/bioinformatics/btac304","title":"deepSimDEF: deep neural embeddings of gene products and gene ontology terms for functional analysis of genes","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute; University of Ottawa; Dalhousie University; Montreal Heart Institute","funders":"Fonds de Recherche du Québec - Santé; Institut de Valorisation des Données; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Gene ontology; Gene; Computational biology; Computer science; Genetics; Biology; Artificial intelligence; Gene expression","score_opus":0.01238335273723722,"score_gpt":0.22635082858919084,"score_spread":0.2139674758519536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280528542","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92540896,0.0014221645,0.07161244,0.000096777774,0.000305007,0.0004620805,0.00042072087,0.000009109621,0.0002627534],"genre_scores_gemma":[0.9557949,0.00009255243,0.0422749,0.00023922842,0.00008909624,0.00005180874,0.0013585581,0.000014521886,0.00008447097],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998853,0.000018451223,0.0006084506,0.00014920953,0.00015318536,0.00021769879],"domain_scores_gemma":[0.9990543,0.000023968489,0.00042879942,0.00030330181,0.00013718438,0.00005240676],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028130988,0.00014773147,0.00032804743,0.00017441467,0.00012511598,0.000010606705,0.00017538105,0.00008956218,0.000017810326],"category_scores_gemma":[0.000033409888,0.00014108603,0.00015361472,0.00027387645,0.00011005229,0.000009454734,0.00019912596,0.00006420324,2.5749574e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001996874,0.0005905401,0.03274742,0.0016399851,0.008770561,0.0000025671877,0.0062263585,0.17002492,0.63383347,0.0029078803,0.005537327,0.13572207],"study_design_scores_gemma":[0.0018613373,0.001324564,0.008824077,0.000004719301,0.0013320595,0.00008894885,0.0011235418,0.8750778,0.094110265,0.0001829001,0.015498062,0.00057176093],"about_ca_topic_score_codex":0.0000068284885,"about_ca_topic_score_gemma":0.000016164233,"teacher_disagreement_score":0.70505285,"about_ca_system_score_codex":0.000013672279,"about_ca_system_score_gemma":0.000049877657,"threshold_uncertainty_score":0.5753321},"labels":[],"label_agreement":null},{"id":"W4280553929","doi":"10.1093/bioinformatics/btac327","title":"Assessing and assuring interoperability of a genomics file format","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto; Princess Margaret Cancer Centre; University Health Network","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Software; Suite; Interoperability; Test suite; File format; Fuzz testing; Software engineering; Correctness; Test case; Database; Programming language; Operating system; Machine learning","score_opus":0.017293559913787802,"score_gpt":0.24105137407473362,"score_spread":0.2237578141609458,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280553929","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9967504,0.00039803595,0.00043830753,0.000027649297,0.00008418791,0.00010196631,0.00020729995,0.0000024090368,0.0019897562],"genre_scores_gemma":[0.9901735,0.00008869888,0.009477956,0.000101073194,0.000022792998,0.000016397302,0.00006521124,0.000007641477,0.00004670741],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99945325,0.000019671581,0.00025076262,0.00008250518,0.000073791736,0.000120040226],"domain_scores_gemma":[0.9996327,0.000013733337,0.00011219741,0.00017936091,0.000032239175,0.000029778525],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018454634,0.00008069498,0.000113329304,0.000025353522,0.00014708178,0.000024078841,0.00011021835,0.000025776268,0.000059067825],"category_scores_gemma":[0.0000313065,0.00007861013,0.000040643266,0.00003447846,0.000053691772,0.000002111829,0.00052922574,0.000054542863,9.97983e-7],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026104855,0.00043556097,0.036739934,0.0012367538,0.0007134329,0.000003242973,0.0140086245,0.003930177,0.7485416,0.0004700025,0.034054104,0.1596055],"study_design_scores_gemma":[0.0021077846,0.0016213225,0.073013514,0.00003895753,0.00009730979,0.00017742525,0.024758743,0.021805726,0.074752174,0.0003212048,0.80022407,0.0010817834],"about_ca_topic_score_codex":0.0000071638824,"about_ca_topic_score_gemma":0.0000023803595,"teacher_disagreement_score":0.76616997,"about_ca_system_score_codex":0.000016461643,"about_ca_system_score_gemma":0.00003452943,"threshold_uncertainty_score":0.3205628},"labels":[],"label_agreement":null},{"id":"W4281636170","doi":"10.1093/bioinformatics/btac345","title":"Deep structure integrative representation of multi-omics data for cancer subtyping","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Natural Science Foundation of China","keywords":"Subtyping; Computer science; Subspace topology; Omics; Representation (politics); External Data Representation; Cluster analysis; Data mining; Machine learning; Nonlinear dimensionality reduction; Artificial intelligence; Data science; Bioinformatics; Biology; Dimensionality reduction","score_opus":0.029297918903950445,"score_gpt":0.30043188300237283,"score_spread":0.2711339640984224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281636170","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09796886,0.0016324818,0.88975537,0.00021987669,0.0012468481,0.0016571621,0.00700603,0.000026639029,0.00048672975],"genre_scores_gemma":[0.78246415,0.0004963304,0.20115295,0.00076888234,0.00029378457,0.00012168346,0.014309877,0.000044640554,0.00034769627],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990958,0.000020291545,0.00043673106,0.00014493497,0.00012184894,0.00018038739],"domain_scores_gemma":[0.9988673,0.000021326201,0.0003533312,0.0006160645,0.00010181872,0.000040203875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018274467,0.00012913746,0.00017324487,0.000045568027,0.00016242667,0.000019867104,0.0005095385,0.000078161574,0.00002793701],"category_scores_gemma":[0.000069953094,0.00011775686,0.00006408609,0.000117421936,0.00005118924,0.000016683325,0.0005682304,0.000111426794,5.056453e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018133981,0.00046738636,0.006410355,0.0016379997,0.0019438375,0.0000016545307,0.019032376,0.24752726,0.1219158,0.0048698066,0.09386923,0.5005109],"study_design_scores_gemma":[0.00092066935,0.0001644551,0.00013523777,0.000010410268,0.000047755606,0.000008258005,0.0038635738,0.94300616,0.01188596,0.00020657656,0.039523687,0.0002272646],"about_ca_topic_score_codex":0.000026818623,"about_ca_topic_score_gemma":0.00012148925,"teacher_disagreement_score":0.6954789,"about_ca_system_score_codex":0.000028558557,"about_ca_system_score_gemma":0.00011275618,"threshold_uncertainty_score":0.48019853},"labels":[],"label_agreement":null},{"id":"W4281909951","doi":"10.1093/bioinformatics/btac355","title":"MAFFIN: metabolomics sample normalization using maximal density fold change with high-quality metabolic features and corrected signal intensities","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation","keywords":"Normalization (sociology); Computer science; Fold (higher-order function); Statistics; Mathematics","score_opus":0.025487399599166252,"score_gpt":0.24640956952106405,"score_spread":0.22092216992189778,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281909951","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98191124,0.0017887304,0.0151169365,0.0000857123,0.00026078528,0.00034098537,0.00037797014,0.000030586805,0.00008707182],"genre_scores_gemma":[0.9627931,0.0006304137,0.03478259,0.00089970895,0.000166026,0.000040997813,0.0005896123,0.000026748014,0.00007081754],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99875265,0.00009149147,0.00034236623,0.0002275203,0.00026661038,0.0003193483],"domain_scores_gemma":[0.99917257,0.000030372032,0.00028017917,0.00026261172,0.00017640834,0.00007785517],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036117338,0.00024917081,0.00038359675,0.00012827193,0.00046958184,0.00006463442,0.00014572887,0.00007916076,0.000028103117],"category_scores_gemma":[0.000086636595,0.00021786215,0.000065465574,0.00025201446,0.00011480925,0.00002684538,0.00050312566,0.00015607142,6.4286706e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008313505,0.0013355546,0.1909857,0.0015908211,0.0066758557,0.00005121924,0.018304432,0.005082521,0.6081516,0.10939634,0.011478677,0.03863378],"study_design_scores_gemma":[0.010140427,0.0037339819,0.42218563,0.00006135662,0.0021858802,0.0016257211,0.029878458,0.032370485,0.3823273,0.001445094,0.10896146,0.0050842077],"about_ca_topic_score_codex":0.00043192826,"about_ca_topic_score_gemma":0.00015091579,"teacher_disagreement_score":0.23119994,"about_ca_system_score_codex":0.000026575632,"about_ca_system_score_gemma":0.00006274905,"threshold_uncertainty_score":0.88841605},"labels":[],"label_agreement":null},{"id":"W4281964006","doi":"10.1093/bioinformatics/btac383","title":"Looking at the BiG picture: incorporating bipartite graphs in drug response prediction","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"Natural Sciences and Engineering Research Council of Canada; Institut de Valorisation des Données; Merck Canada","keywords":"Bipartite graph; Drug response; Computer science; Leverage (statistics); Pharmacogenomics; Python (programming language); Drug; Graph; Big data; Machine learning; Artificial intelligence; Computational biology; Theoretical computer science; Data mining; Bioinformatics; Biology","score_opus":0.018610616020080822,"score_gpt":0.2560658220336284,"score_spread":0.23745520601354755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281964006","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7499081,0.000099017285,0.24578643,0.0014514192,0.0012108985,0.00037951279,0.000033491044,0.0001607201,0.00097041024],"genre_scores_gemma":[0.9419345,0.0000033992212,0.05662007,0.0010625231,0.00004430383,0.00007943173,0.000022817703,0.000010711206,0.00022222157],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99798465,0.00055263296,0.00049401436,0.00015607859,0.0005959012,0.00021671501],"domain_scores_gemma":[0.9984558,0.00074984494,0.00025785188,0.000456186,0.00003648207,0.000043802935],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031294064,0.00012018352,0.00011187617,0.00027010994,0.0005499876,0.00014776058,0.00070966367,0.000021558511,0.000010704693],"category_scores_gemma":[0.0001867292,0.00009706475,0.000061152,0.00124587,0.00005226823,0.0005089467,0.0012497553,0.00026542018,0.00001591824],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018082367,0.00007916713,0.006409284,0.00004563134,0.000024035755,0.000019483661,0.025422525,0.8747681,0.00034517547,0.030920796,0.0038433743,0.057941638],"study_design_scores_gemma":[0.00029660683,0.000049747603,0.011699178,0.000013467735,0.0000035218243,0.00004623679,0.000665282,0.9711447,0.00029894087,0.00870697,0.006939806,0.00013558584],"about_ca_topic_score_codex":0.000017717864,"about_ca_topic_score_gemma":0.00003201159,"teacher_disagreement_score":0.19202642,"about_ca_system_score_codex":0.0002726723,"about_ca_system_score_gemma":0.00019817376,"threshold_uncertainty_score":0.42301154},"labels":[],"label_agreement":null},{"id":"W4282834074","doi":"10.1093/bioinformatics/btac391","title":"SPEAR: Systematic ProtEin AnnotatoR","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"vaccines and immunoinformatics approaches","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Réseau Québécois de Recherche sur les Médicaments","keywords":"Spear; Python (programming language); Computer science; Annotation; Documentation; Visualization; Computational biology; Data mining; Biology; Programming language; Artificial intelligence; Archaeology","score_opus":0.011090178579655609,"score_gpt":0.21049638583135297,"score_spread":0.19940620725169736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4282834074","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96674556,0.0014738555,0.0067466516,0.00030451253,0.0005368706,0.0031346928,0.000152741,0.00011453886,0.020790592],"genre_scores_gemma":[0.9842852,0.00003108054,0.010943428,0.00058395445,0.00010838881,0.00046379628,0.0003475149,0.000039999562,0.0031966444],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99873924,0.00004686449,0.00055576523,0.00010742902,0.00028011252,0.00027058052],"domain_scores_gemma":[0.99910456,0.0000057754264,0.00025357344,0.00052451034,0.000044233886,0.00006736472],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041775842,0.00017020878,0.00021004793,0.00006966233,0.00028691324,0.000060281676,0.0003828298,0.000050527673,0.00007067077],"category_scores_gemma":[0.00006148069,0.00015102801,0.00011333523,0.00015713893,0.000023717774,0.000012740776,0.00043130098,0.00012735986,0.00007128304],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016901117,0.00323165,0.0041875467,0.18169293,0.0037825475,0.000057720146,0.03267964,0.0129473,0.3929169,0.03768656,0.31589565,0.013231458],"study_design_scores_gemma":[0.0102239605,0.007970562,0.00088487193,0.0018589068,0.0004858262,0.0018820415,0.09388746,0.22814156,0.11848313,0.0008649807,0.5294285,0.005888213],"about_ca_topic_score_codex":0.0000031005968,"about_ca_topic_score_gemma":6.998944e-7,"teacher_disagreement_score":0.27443376,"about_ca_system_score_codex":0.000031569274,"about_ca_system_score_gemma":0.00008221167,"threshold_uncertainty_score":0.6158744},"labels":[],"label_agreement":null},{"id":"W4283659942","doi":"10.1093/bioinformatics/btac420","title":"Improving candidate Biosynthetic Gene Clusters in fungi through reinforcement learning","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; Université du Québec à Montréal","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Université du Québec à Montréal","keywords":"Candidate gene; Aspergillus nidulans; Computer science; Task (project management); Reinforcement learning; Genome; Computational biology; Gene; Artificial intelligence; Biology; Genetics; Engineering","score_opus":0.007802561118249228,"score_gpt":0.21366434891964242,"score_spread":0.2058617878013932,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283659942","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7340065,0.0025138988,0.22842608,0.00046023823,0.001983875,0.0020764703,0.000110090106,0.00014477069,0.030278066],"genre_scores_gemma":[0.99019414,0.0002303884,0.007199204,0.00095491356,0.00009316472,0.00006044911,0.00048540792,0.00002868393,0.00075363735],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99843186,0.000044319026,0.00063048373,0.00017326279,0.0002449407,0.00047514157],"domain_scores_gemma":[0.9992306,0.00001225908,0.00028286563,0.00037236672,0.000027867416,0.00007399404],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045788987,0.00021320669,0.00019047876,0.000093049086,0.00030884714,0.00005268178,0.00032571665,0.00009712591,0.00007560088],"category_scores_gemma":[0.000025614889,0.00021866622,0.000095725234,0.00019299678,0.00004967698,0.000019205843,0.0006425088,0.00030736375,0.000022671935],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048844895,0.0001753811,0.0030269802,0.00044136896,0.00023108456,0.000022614435,0.008186378,0.8571467,0.03764211,0.0009825184,0.0089218365,0.082734615],"study_design_scores_gemma":[0.002635068,0.001078882,0.00018314,0.00003393156,0.00004468329,0.00014108336,0.005933264,0.8214869,0.011380036,0.000120035016,0.15589754,0.0010654313],"about_ca_topic_score_codex":0.000071793336,"about_ca_topic_score_gemma":0.000026760561,"teacher_disagreement_score":0.25618765,"about_ca_system_score_codex":0.00010566847,"about_ca_system_score_gemma":0.00011789345,"threshold_uncertainty_score":0.89169496},"labels":[],"label_agreement":null},{"id":"W4283716699","doi":"10.1093/bioinformatics/btac429","title":"RAPPPID: towards generalizable protein interaction prediction with AWD-LSTM twin networks","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"Compute Canada; Natural Sciences and Engineering Research Council of Canada; McGill University","keywords":"Computer science; Regularization (linguistics); Machine learning; Artificial intelligence; Source code; Code (set theory); Training set; Set (abstract data type); Data mining","score_opus":0.008924453457807548,"score_gpt":0.21018700338334148,"score_spread":0.20126254992553394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283716699","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31364393,0.0007750723,0.65472513,0.00042642505,0.0017048414,0.0023039686,0.00028488477,0.00019655733,0.025939202],"genre_scores_gemma":[0.96713746,0.00012234096,0.025238017,0.0013619218,0.00072464807,0.00039474427,0.002129346,0.00006481803,0.0028266967],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99861723,0.00004660842,0.00049489224,0.00018222767,0.00028015228,0.00037887206],"domain_scores_gemma":[0.99909806,0.000004298562,0.00028243024,0.00043470078,0.000071838906,0.00010864722],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036929667,0.00023085004,0.0001788495,0.00008042855,0.00037521461,0.00009102843,0.0002691604,0.00012749094,0.00011771242],"category_scores_gemma":[0.000009264012,0.00020507991,0.00008833943,0.00020801934,0.000054577682,0.000031515654,0.0002936995,0.00028548238,0.0000120794875],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014003335,0.00043795045,0.0010344329,0.00030291427,0.0006206151,0.000010269514,0.001781608,0.7338839,0.00988368,0.0013232337,0.17431393,0.07500713],"study_design_scores_gemma":[0.0013618477,0.0013159948,0.00015427978,0.000028569551,0.000042922893,0.0001491516,0.0012278015,0.6045501,0.0031634492,0.000068148016,0.38746497,0.00047277415],"about_ca_topic_score_codex":0.000026386248,"about_ca_topic_score_gemma":0.000012696978,"teacher_disagreement_score":0.6534935,"about_ca_system_score_codex":0.00007723392,"about_ca_system_score_gemma":0.0001306228,"threshold_uncertainty_score":0.8362916},"labels":[],"label_agreement":null},{"id":"W4288429604","doi":"10.1093/bioinformatics/btac497","title":"BioCaster in 2021: automatic disease outbreaks detection from global news media","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; McGill University","funders":"Economic and Social Research Council","keywords":"Computer science; Upgrade; Outbreak; Infectious disease (medical specialty); Dashboard; Machine translation; Visualization; Artificial neural network; Ontology; Data science; Cloud computing; Semantics (computer science); World Wide Web; Artificial intelligence; Disease; Medicine; Programming language","score_opus":0.01273902401072915,"score_gpt":0.24822163088394172,"score_spread":0.23548260687321257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4288429604","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.987617,0.00036842684,0.001716239,0.0006757217,0.0010318534,0.0008129737,0.004256615,0.00024321915,0.0032779456],"genre_scores_gemma":[0.99266624,0.00002255382,0.0040010335,0.0014348911,0.00014579872,0.00008312721,0.0015746806,0.000019016708,0.000052678693],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9983156,0.000070384755,0.0005809953,0.00017470495,0.0005687865,0.00028956644],"domain_scores_gemma":[0.99883,0.000068410074,0.00016849097,0.0005784907,0.000030907973,0.000323672],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00017698543,0.00018042306,0.00029999219,0.00012691901,0.00008228568,0.000035991587,0.00018492302,0.000058122685,0.0012216639],"category_scores_gemma":[0.00028414073,0.00017275815,0.000102259415,0.0004900733,0.000047053156,0.0002312055,0.0002565265,0.0002496143,0.0004495045],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009799814,0.0007356653,0.31366113,0.0005435342,0.00017296738,0.0004528847,0.0028148007,0.00035400433,0.00010684432,0.00006469405,0.0182579,0.6618556],"study_design_scores_gemma":[0.0036475766,0.00014631033,0.72971183,0.00011861542,0.0001604719,0.000033459797,0.0026804665,0.23426932,0.00003390545,0.00036321185,0.028412959,0.00042189387],"about_ca_topic_score_codex":0.00021633394,"about_ca_topic_score_gemma":0.0002962276,"teacher_disagreement_score":0.6614337,"about_ca_system_score_codex":0.00039569568,"about_ca_system_score_gemma":0.00018920412,"threshold_uncertainty_score":0.99969137},"labels":[],"label_agreement":null},{"id":"W4292961172","doi":"10.1093/bioinformatics/btac564","title":"ntHash2: recursive spaced seed hashing for nucleotide sequences","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"National Institutes of Health","keywords":"Hash function; Computer science; Dynamic perfect hashing; Universal hashing; Sequence (biology); Linear hashing; Algorithm; Hash table; Theoretical computer science; Perfect hash function; Double hashing; Biology; Genetics; Programming language","score_opus":0.022581972130463614,"score_gpt":0.25195325326204365,"score_spread":0.22937128113158003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292961172","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0042365375,0.000059973805,0.991018,0.0011122277,0.0009393115,0.00040560003,0.00011440941,0.0002010275,0.0019128892],"genre_scores_gemma":[0.029001368,0.000012605005,0.9693454,0.0010338012,0.00009112994,0.00008905225,0.000089567024,0.000012167362,0.00032489924],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989079,0.000027481165,0.00028293612,0.00015566543,0.00034774782,0.00027827467],"domain_scores_gemma":[0.99907213,0.00012625208,0.00020519286,0.00045510227,0.000060155304,0.00008114479],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038392254,0.0001176658,0.0001404773,0.00009249529,0.0006488346,0.00023444969,0.0010385395,0.0000271843,0.000023014796],"category_scores_gemma":[0.00006475785,0.00010523287,0.00006779752,0.00026086956,0.000028021335,0.0011065297,0.00078056805,0.0001338337,0.000024281377],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012250111,0.0003751252,0.0007900332,0.0004752686,0.00017020317,0.00004903406,0.046869166,0.0149929775,0.001662485,0.3858577,0.22312789,0.3255076],"study_design_scores_gemma":[0.00043798794,0.0002069586,0.00017146632,0.000020374968,0.000006488808,0.000023652266,0.0015151467,0.87587893,0.00048861286,0.0044126837,0.11659682,0.000240893],"about_ca_topic_score_codex":0.000019826006,"about_ca_topic_score_gemma":0.0000019488953,"teacher_disagreement_score":0.8608859,"about_ca_system_score_codex":0.00007678084,"about_ca_system_score_gemma":0.00010313956,"threshold_uncertainty_score":0.49903768},"labels":[],"label_agreement":null},{"id":"W4294631394","doi":"10.1093/bioinformatics/btac599","title":"CCPLS reveals cell-type-specific spatial dependence of transcriptomes in single cells","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Genetics; Japan Society for the Promotion of Science; Research Organization of Information and Systems","keywords":"Cell type; Transcriptome; Cell; Interpretability; Context (archaeology); Computational biology; Biology; Gene expression; Computer science; Gene; Genetics; Artificial intelligence","score_opus":0.018084635621990055,"score_gpt":0.21369034047721464,"score_spread":0.19560570485522458,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294631394","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9903248,0.00074575644,0.004954328,0.00002785599,0.0007077774,0.0002977459,0.00010508707,0.0000150248625,0.0028216378],"genre_scores_gemma":[0.99505734,0.0002375557,0.0040185614,0.00015212246,0.000058991045,0.000011937929,0.000116559066,0.000022022901,0.0003249208],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985912,0.000059347552,0.00059234677,0.00018190028,0.00028823284,0.00028699776],"domain_scores_gemma":[0.99934113,0.000018271447,0.00017334033,0.0003417677,0.000060808652,0.000064657215],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027039394,0.00017375381,0.00023411628,0.00010987303,0.00008820716,0.00001929348,0.00036452245,0.00010458118,0.000103788734],"category_scores_gemma":[0.000013044286,0.00018490033,0.00010838726,0.0002265311,0.000068654896,0.000010686585,0.000092964176,0.00016796046,0.000008621596],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015208563,0.00027749693,0.0015629586,0.00010893255,0.000011099759,0.0000033083045,0.0007623883,0.00088985026,0.9925863,0.000023403449,0.001383314,0.0022388739],"study_design_scores_gemma":[0.0013002335,0.0009293609,0.0006723078,0.00002094521,0.000014602125,0.0000128584525,0.00092542724,0.0011180188,0.9636712,0.000046118697,0.030931765,0.00035715752],"about_ca_topic_score_codex":0.000052994917,"about_ca_topic_score_gemma":0.00003364249,"teacher_disagreement_score":0.029548451,"about_ca_system_score_codex":0.00003784725,"about_ca_system_score_gemma":0.00008064602,"threshold_uncertainty_score":0.7540017},"labels":[],"label_agreement":null},{"id":"W4295681693","doi":"10.1093/bioinformatics/btac628","title":"SQuAPP—simple quantitative analysis of proteins and PTMs","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Children's Hospital; University of British Columbia","funders":"Michael Cuccione Foundation; Natural Sciences and Engineering Research Council of Canada; Michael Smith Health Research BC","keywords":"Computer science; Workflow; Proteomics; Proteome; Pipeline (software); Visualization; Software; Quantitative proteomics; Data science; Data mining; Computational biology; Bioinformatics; Database; Chemistry; Biology; Programming language","score_opus":0.020229492025920257,"score_gpt":0.29578866180857577,"score_spread":0.2755591697826555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4295681693","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7580296,0.000113648566,0.21978828,0.000121624034,0.000008625179,0.0004335838,0.0011372631,0.00015589887,0.020211497],"genre_scores_gemma":[0.74512696,0.000030003845,0.2541538,0.000047720256,0.00000443976,0.000262185,0.00020049643,0.000008734932,0.00016568191],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994284,0.0000041181365,0.00027656707,0.000069520924,0.0001274676,0.00009393689],"domain_scores_gemma":[0.9994579,0.000036751426,0.00021417956,0.00022784327,0.000032799973,0.000030554867],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000077413664,0.00006784208,0.00015890847,0.00009859468,0.0001404966,0.000009082961,0.00012358393,0.000023510534,0.00034335887],"category_scores_gemma":[0.000018235709,0.00006779853,0.000058790072,0.00042289746,0.000047209778,0.000064856365,0.00014931927,0.00009810314,0.0000011886706],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002506845,0.0009391575,0.022127917,0.0018523582,0.0032765425,0.0000046173873,0.023169085,0.015991993,0.23903966,0.6329995,0.0041028447,0.056245636],"study_design_scores_gemma":[0.00074749463,0.00026099774,0.00065533136,0.000020246947,0.0009214709,0.000010104177,0.013473967,0.7233939,0.16283709,0.019157007,0.077809714,0.00071267714],"about_ca_topic_score_codex":0.000028469141,"about_ca_topic_score_gemma":0.0000039340694,"teacher_disagreement_score":0.70740193,"about_ca_system_score_codex":0.000029360102,"about_ca_system_score_gemma":0.000014886793,"threshold_uncertainty_score":0.37595388},"labels":[],"label_agreement":null},{"id":"W4296780664","doi":"10.1093/bioinformatics/btac478","title":"GNN-SubNet: disease subnetwork detection with explainable graph neural networks","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":68,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Austrian Science Fund; European Commission","keywords":"Subnetwork; Subnet; Interpretability; Computer science; Python (programming language); Graph; Machine learning; Artificial intelligence; Data mining; Theoretical computer science; Computer network","score_opus":0.005619933380862117,"score_gpt":0.188813731602062,"score_spread":0.18319379822119988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4296780664","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42877492,0.003093586,0.5575492,0.0002663759,0.0020046383,0.0018298888,0.00016636877,0.00022139879,0.006093632],"genre_scores_gemma":[0.99553025,0.00010488938,0.0017875856,0.0010400398,0.00035748753,0.00014653592,0.0005431969,0.00004256797,0.00044745064],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984175,0.000050650073,0.0004489618,0.00021757395,0.00029930816,0.00056602],"domain_scores_gemma":[0.9988377,0.00001400438,0.00026034325,0.0005750777,0.00006461415,0.00024823245],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00025811463,0.0002825677,0.00019269441,0.000085768654,0.0006834901,0.000089291665,0.0003554573,0.0000957313,0.000056450295],"category_scores_gemma":[0.0000106928255,0.00025588766,0.00012964901,0.0003405546,0.00009346227,0.000023276045,0.00034610915,0.00030027074,0.000007570255],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014954438,0.0001772028,0.002636941,0.00015060097,0.00023101938,0.000025363548,0.00047724284,0.9246007,0.00041539106,0.00045639163,0.01967558,0.049658105],"study_design_scores_gemma":[0.0013119371,0.0010295677,0.001124462,0.000013295985,0.0000789434,0.00011645782,0.0009597778,0.9099409,0.00024246828,0.00020931354,0.08421799,0.0007549047],"about_ca_topic_score_codex":0.000009360194,"about_ca_topic_score_gemma":0.000026101141,"teacher_disagreement_score":0.5667553,"about_ca_system_score_codex":0.00004772078,"about_ca_system_score_gemma":0.00007349462,"threshold_uncertainty_score":0.99998933},"labels":[],"label_agreement":null},{"id":"W4298125100","doi":"10.1093/bioinformatics/btac655","title":"Integrating phylogenetic and functional data in microbiome studies","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; Tel Aviv University; Israel Science Foundation","keywords":"Phylogenetic tree; Microbiome; Computational biology; Metagenomics; Biology; Computer science; Evolutionary biology; Data science; Bioinformatics; Genetics; Gene","score_opus":0.04460253469201658,"score_gpt":0.29736789798655766,"score_spread":0.2527653632945411,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4298125100","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9952407,0.0033852065,0.0003311215,0.0002030305,0.00020662633,0.00016809533,0.00018748525,0.000007357252,0.00027039956],"genre_scores_gemma":[0.98719066,0.0005425563,0.009739132,0.0010341686,0.00007811759,0.000017893704,0.0011309998,0.000011713438,0.00025478133],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993744,0.000028454246,0.0002341169,0.0001428578,0.000063588304,0.00015661128],"domain_scores_gemma":[0.9995794,0.000010707329,0.000068055306,0.00029132568,0.000021978301,0.000028512386],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002884104,0.00008588694,0.00010028633,0.00006175524,0.00014730572,0.000013311822,0.0001544713,0.00003167189,0.000016983075],"category_scores_gemma":[0.00004183784,0.000081086575,0.000013323054,0.00009447923,0.000052511896,0.000005174858,0.000814958,0.000096378215,0.0000036618555],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010591787,0.00015101892,0.021994157,0.00045662286,0.00013941927,0.00000513755,0.0025425847,0.00017824821,0.91900635,0.00035231712,0.042654857,0.012413403],"study_design_scores_gemma":[0.006382924,0.002128449,0.11482872,0.0001426763,0.00010310827,0.0010662326,0.04953326,0.01590501,0.01819885,0.0003917687,0.78940123,0.0019177427],"about_ca_topic_score_codex":0.000009224532,"about_ca_topic_score_gemma":0.000054700486,"teacher_disagreement_score":0.90080744,"about_ca_system_score_codex":0.00002410756,"about_ca_system_score_gemma":0.00007951085,"threshold_uncertainty_score":0.33066145},"labels":[],"label_agreement":null},{"id":"W4304757181","doi":"10.1093/bioinformatics/btac649","title":"METAbolomics data Balancing with Over-sampling Algorithms (META-BOA): an online resource for addressing class imbalance","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Overfitting; Sampling (signal processing); Class (philosophy); Data mining; Machine learning; Sample (material); Visualization; Random forest; Resource (disambiguation); Artificial intelligence; Algorithm; Artificial neural network","score_opus":0.1940735828464191,"score_gpt":0.3426043390083074,"score_spread":0.1485307561618883,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4304757181","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008626782,0.00018212218,0.9944239,0.00049598934,0.00015046707,0.00063195644,0.002376019,0.000699202,0.00017765447],"genre_scores_gemma":[0.0060134744,0.0000212582,0.98790926,0.0018813825,0.0001137959,0.00016068338,0.003788806,0.00003872508,0.000072626404],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99732876,0.000092059214,0.0007538872,0.0005830904,0.0007032741,0.0005389275],"domain_scores_gemma":[0.9954299,0.00025286782,0.0006969867,0.0033431337,0.000134509,0.00014262079],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014541211,0.00030917913,0.000490038,0.00021120303,0.0007263645,0.00045732077,0.004167087,0.00007237141,0.0000125393135],"category_scores_gemma":[0.00014663833,0.0002683201,0.000078853074,0.0006764086,0.00008076401,0.0028180722,0.0019197961,0.0003851502,0.0000024820763],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00050541776,0.0023869001,0.0014466551,0.0015111323,0.0027563574,0.000040901192,0.010170514,0.031132126,0.0064052735,0.10164551,0.13882138,0.70317787],"study_design_scores_gemma":[0.00043147933,0.00015929308,0.00017669733,0.000015612295,0.00011212924,0.000039735136,0.0004443669,0.80101293,0.0004976821,0.00021282081,0.1965528,0.00034443353],"about_ca_topic_score_codex":0.000014596421,"about_ca_topic_score_gemma":0.000010957745,"teacher_disagreement_score":0.76988083,"about_ca_system_score_codex":0.00015337353,"about_ca_system_score_gemma":0.00023838802,"threshold_uncertainty_score":0.9999769},"labels":[],"label_agreement":null},{"id":"W4307091043","doi":"10.1093/bioinformatics/btac692","title":"Defining the extent of gene function using ROC curvature","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"U.S. National Library of Medicine; National Institute of Mental Health; National Institutes of Health","keywords":"Genome; Biology; Computational biology; Robustness (evolution); Gene; Generalizability theory; Context (archaeology); Computer science; Function (biology); Genetics; Mathematics","score_opus":0.009905996297909917,"score_gpt":0.21944269434356733,"score_spread":0.20953669804565742,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307091043","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5633375,0.017513847,0.40169477,0.00034602958,0.0032682766,0.0013896486,0.00048602684,0.00006476337,0.011899095],"genre_scores_gemma":[0.98578954,0.000061455365,0.01254725,0.00096260075,0.00013880289,0.000017627432,0.00029462247,0.00001814818,0.00016996842],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991453,0.000026009682,0.000375528,0.00007543873,0.00019063105,0.0001870513],"domain_scores_gemma":[0.999293,0.000010183506,0.00027301512,0.0003399692,0.000049031038,0.00003476685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034637208,0.00011214197,0.00010925507,0.00003393518,0.00029650808,0.000019935098,0.0002375502,0.00006792483,0.000032061373],"category_scores_gemma":[0.00001495908,0.00008593036,0.000094132716,0.00013141701,0.000040136914,0.000006477953,0.0002528789,0.00015571673,0.0000041576177],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014567246,0.0006023421,0.0056016897,0.00088330865,0.002106383,0.0000059294152,0.010408945,0.44865274,0.16657852,0.05865708,0.115901336,0.189145],"study_design_scores_gemma":[0.0020696567,0.0015525996,0.0016888902,0.000041962274,0.0003956832,0.00032807718,0.008809463,0.5058036,0.023244329,0.001303278,0.45372644,0.0010360088],"about_ca_topic_score_codex":0.0000055032906,"about_ca_topic_score_gemma":0.0000021652388,"teacher_disagreement_score":0.422452,"about_ca_system_score_codex":0.000018392715,"about_ca_system_score_gemma":0.000082795625,"threshold_uncertainty_score":0.35041383},"labels":[],"label_agreement":null},{"id":"W4310594072","doi":"10.1093/bioinformatics/btac779","title":"DeepCellEss: cell line-specific essential protein prediction with attention-based interpretable deep learning","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"National Natural Science Foundation of China","keywords":"Interpretability; Computer science; Artificial intelligence; Benchmark (surveying); Source code; Machine learning; Convolutional neural network; Deep learning; Code (set theory); Data mining","score_opus":0.004123358410521841,"score_gpt":0.19876093933838215,"score_spread":0.19463758092786032,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310594072","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.525099,0.0002540197,0.46207425,0.000099096236,0.00033586746,0.0009662776,0.00006512066,0.00017597359,0.010930411],"genre_scores_gemma":[0.96130824,0.000022666149,0.03505035,0.00016413117,0.00014071347,0.0001663876,0.0013934834,0.000051149327,0.0017028822],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982858,0.00010178077,0.0005532446,0.00021490728,0.00047196477,0.00037231878],"domain_scores_gemma":[0.9989248,0.000017360304,0.0004089841,0.00043522107,0.00011373636,0.00009989896],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00038900244,0.00026086546,0.00019041078,0.00013412522,0.0005581589,0.00011229373,0.00035474557,0.00011054365,0.00021902451],"category_scores_gemma":[0.000039805705,0.0002460299,0.00011291075,0.0002423191,0.00008158101,0.000025444408,0.00027186592,0.00049629225,0.00004655827],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013392452,0.00072321086,0.014781177,0.0012227899,0.00022785409,0.000014086211,0.0026265362,0.8498707,0.1127407,0.00025679512,0.0055711023,0.010625824],"study_design_scores_gemma":[0.0021590923,0.0021992389,0.00029796964,0.000050264713,0.00004855103,0.00004567998,0.002322951,0.82347393,0.02242374,0.000007744162,0.14639048,0.0005803395],"about_ca_topic_score_codex":0.000006432938,"about_ca_topic_score_gemma":0.0000046296377,"teacher_disagreement_score":0.43620926,"about_ca_system_score_codex":0.00006399156,"about_ca_system_score_gemma":0.00011808761,"threshold_uncertainty_score":0.99999917},"labels":[],"label_agreement":null},{"id":"W4311575706","doi":"10.1093/bioinformatics/btac809","title":"Efficient computation of contributional diversity metrics from microbiome data with <i>FuncDiv</i>","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Dalhousie University; McGill Genome Centre","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"License; Metagenomics; Computer science; Microbiome; ENCODE; Diversity (politics); Function (biology); Alpha diversity; Data mining; Computational biology; Data science; Biology; Bioinformatics; Biodiversity; Genetics; Gene; Ecology","score_opus":0.01919680741520582,"score_gpt":0.24245384039659265,"score_spread":0.22325703298138683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311575706","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9546444,0.0002976967,0.03806938,0.00008375344,0.00014484151,0.00020945058,0.006408545,0.000009622361,0.00013231517],"genre_scores_gemma":[0.98069537,0.000012560977,0.010390106,0.00030633388,0.000026303427,0.0000016213369,0.008544344,0.0000053110057,0.000018040952],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992669,0.000029068176,0.00022953333,0.00013595313,0.00019339198,0.00014514575],"domain_scores_gemma":[0.99932927,0.000016194315,0.00019804167,0.00031393117,0.000096754324,0.000045797042],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023261321,0.00008489312,0.0001218444,0.000060567225,0.00028174906,0.000009429295,0.00033922752,0.00004059118,0.000021982856],"category_scores_gemma":[0.000020229396,0.000078681966,0.000027721368,0.00020010507,0.00005814707,0.0000036113352,0.0013947639,0.00007429013,0.0000048648053],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023034348,0.0024695548,0.07095859,0.0007494112,0.0012468335,0.000016325761,0.004905015,0.060577236,0.68453693,0.00081787974,0.16336389,0.008054879],"study_design_scores_gemma":[0.025323903,0.006275467,0.12358969,0.00015225462,0.0008745473,0.0003080012,0.008526997,0.4363188,0.083225034,0.00021261918,0.31210262,0.0030900347],"about_ca_topic_score_codex":0.00008043398,"about_ca_topic_score_gemma":0.000009850681,"teacher_disagreement_score":0.6013119,"about_ca_system_score_codex":0.00003680876,"about_ca_system_score_gemma":0.00014657993,"threshold_uncertainty_score":0.32085574},"labels":[],"label_agreement":null},{"id":"W4312018781","doi":"10.1093/bioinformatics/btac813","title":"Integrative chromatin domain annotation through graph embedding of Hi-C data","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Compute Canada","keywords":"Annotation; Chromatin; Computational biology; Genome; Embedding; Domain (mathematical analysis); Pairwise comparison; Epigenomics; Genomics; Computer science; Graph; Biology; Genetics; Theoretical computer science; Artificial intelligence; Gene; DNA methylation; Gene expression; Mathematics","score_opus":0.01531051330598558,"score_gpt":0.26775388303336095,"score_spread":0.25244336972737536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312018781","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92626065,0.0003591612,0.06845138,0.00008053944,0.00024314126,0.0002988281,0.0009936428,0.000017256709,0.003295392],"genre_scores_gemma":[0.82465607,0.00018315468,0.17101045,0.00021542727,0.000056727375,0.000025511497,0.0037221618,0.000023193852,0.00010728943],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998972,0.00004547259,0.0004473729,0.00016349657,0.00020155858,0.00017011187],"domain_scores_gemma":[0.99887973,0.00001486457,0.00033274587,0.0006821297,0.000060014416,0.000030494359],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002952884,0.00014022048,0.0001605947,0.000047618545,0.00016588619,0.000020695745,0.00057111407,0.000055615223,0.000037404276],"category_scores_gemma":[0.000036208567,0.00013385885,0.000060505732,0.00016422161,0.00006856642,0.000018077273,0.0007372899,0.00010225252,0.0000037307248],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045205222,0.001048199,0.002089111,0.0010512497,0.0010472105,0.00001273466,0.04168734,0.040150903,0.70928556,0.023524774,0.14846979,0.031181075],"study_design_scores_gemma":[0.0050244015,0.0029223312,0.0015093108,0.0001365005,0.00014942735,0.00024372031,0.08237776,0.5329017,0.069437705,0.011940558,0.29121128,0.0021452757],"about_ca_topic_score_codex":0.000011777138,"about_ca_topic_score_gemma":0.000008151129,"teacher_disagreement_score":0.6398479,"about_ca_system_score_codex":0.000026915002,"about_ca_system_score_gemma":0.00008321652,"threshold_uncertainty_score":0.5458605},"labels":[],"label_agreement":null},{"id":"W4316494517","doi":"10.1093/bioinformatics/btad031","title":"Cytoscape.js 2023 update: a graph theory library for visualization and analysis","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":165,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sinai Health System; Princess Margaret Cancer Centre; Lunenfeld-Tanenbaum Research Institute; University Health Network; University of Toronto","funders":"National Center for Research Resources; National Institute of General Medical Sciences; National Cancer Institute; National Human Genome Research Institute; National Institutes of Health","keywords":"Computer science; JavaScript; Visualization; Documentation; Source code; Graph; Software; Graph drawing; Web application; Programming language; World Wide Web; Information retrieval; Data mining; Theoretical computer science","score_opus":0.007757637779909554,"score_gpt":0.23830022338613036,"score_spread":0.2305425856062208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4316494517","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11745666,0.0010495735,0.8728458,0.00034242804,0.00045042371,0.001163876,0.0011018367,0.0002767175,0.005312652],"genre_scores_gemma":[0.841512,0.011404864,0.071251884,0.0077568055,0.0012571096,0.0004021388,0.053694554,0.00025655437,0.012464072],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99906707,0.000020091056,0.00039927269,0.00014065627,0.0000971358,0.00027580513],"domain_scores_gemma":[0.99938935,0.00003419879,0.00015484978,0.0002872304,0.00003853831,0.0000958369],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003488586,0.00016082711,0.00019301551,0.00023438208,0.00013880857,0.00010296902,0.00016006388,0.00017966924,0.000024270768],"category_scores_gemma":[0.00003604107,0.00014452745,0.00014939248,0.0006781943,0.00006455675,0.000026790174,0.0001690467,0.00004631122,0.00003682785],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008652658,0.00017259324,0.008111459,0.0013847908,0.005779768,0.000004521865,0.0034998981,0.0032610202,0.004579041,0.14585394,0.67162687,0.15486085],"study_design_scores_gemma":[0.0021016204,0.000530334,0.0038096332,0.000042601172,0.000997025,0.00001524031,0.0022554526,0.66112465,0.0076099024,0.016332641,0.3039806,0.0012003491],"about_ca_topic_score_codex":5.7136975e-7,"about_ca_topic_score_gemma":0.0000029788423,"teacher_disagreement_score":0.80159396,"about_ca_system_score_codex":0.0000036090619,"about_ca_system_score_gemma":0.000039098304,"threshold_uncertainty_score":0.58936584},"labels":[],"label_agreement":null},{"id":"W4316926479","doi":"10.1093/bioinformatics/btad032","title":"JBrowse Jupyter: a Python interface to JBrowse 2","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"National Institute of General Medical Sciences; National Human Genome Research Institute; National Institutes of Health","keywords":"Python (programming language); Computer science; Programming language; Interface (matter); Operating system","score_opus":0.014844535896914578,"score_gpt":0.26097935467307,"score_spread":0.2461348187761554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4316926479","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9908715,0.00021786605,0.0022068599,0.00041849233,0.00043469487,0.00028213533,0.00006130578,0.00003515928,0.0054719765],"genre_scores_gemma":[0.98822784,0.00032078134,0.0076296953,0.00083254406,0.00021515533,0.00004047388,0.00005965505,0.00003219354,0.0026416597],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.999108,0.000012387901,0.00027651133,0.00016346834,0.00011721018,0.00032239934],"domain_scores_gemma":[0.9993628,0.000010868331,0.000059638063,0.00038328776,0.0000621767,0.0001212253],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015879271,0.00016345928,0.00014053067,0.00008318116,0.000089007095,0.000038493516,0.00023458965,0.00008927615,0.00001024935],"category_scores_gemma":[0.0000804937,0.0001505265,0.000076761666,0.00021198444,0.00003573199,0.0000013793433,0.00037608118,0.000050284856,0.00068471115],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015770274,0.000074735704,0.0032237347,0.00020310988,0.00025905535,0.0000066743246,0.0054797726,0.002294838,0.6726219,0.00023790747,0.27569553,0.03974505],"study_design_scores_gemma":[0.00066855823,0.00065720757,0.007112324,0.00003440572,0.000028382268,0.000019534122,0.0017132862,0.0024205663,0.13627164,0.0001316422,0.85034627,0.0005961658],"about_ca_topic_score_codex":0.0000061981923,"about_ca_topic_score_gemma":0.000015498717,"teacher_disagreement_score":0.57465076,"about_ca_system_score_codex":0.000011468832,"about_ca_system_score_gemma":0.000035416084,"threshold_uncertainty_score":0.8800805},"labels":[],"label_agreement":null},{"id":"W4317212859","doi":"10.1093/bioinformatics/btad036","title":"HelixGAN a deep-learning methodology for conditional <i>de novo</i> design of α-helix structures","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Chemical Synthesis and Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Computational biology; Peptide; Synthetic biology; Peptidomimetic; Computer science; Protein design; Helix (gastropod); Deep learning; Protein structure; Chemistry; Biology; Artificial intelligence; Biochemistry","score_opus":0.044930952105651935,"score_gpt":0.3029639355541699,"score_spread":0.25803298344851794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317212859","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13202927,0.00013066083,0.8672278,0.000100934085,0.00003800277,0.00016847483,0.00008227474,0.000029275696,0.00019334552],"genre_scores_gemma":[0.6583569,0.00027336684,0.33922285,0.00034675456,0.00020646308,0.000047487316,0.0012091037,0.00002547443,0.0003116011],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992717,0.0000517979,0.0002799975,0.000099356184,0.00009172919,0.00020544585],"domain_scores_gemma":[0.9994188,0.00018958063,0.00013566134,0.0001254033,0.00007841326,0.000052118758],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004424563,0.000097355776,0.00017777894,0.000054214383,0.00006232379,0.00001125521,0.000131275,0.00013199402,0.000029758085],"category_scores_gemma":[0.00067267107,0.00008559872,0.00013403644,0.00012356942,0.00006180673,0.000003380834,0.000054775403,0.000049604183,0.0000071121253],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007485781,0.000016432245,0.00025420616,0.00013426995,0.00015591274,5.058255e-7,0.000182757,0.008365991,0.97966427,0.00066565804,0.002416204,0.0080689555],"study_design_scores_gemma":[0.00052379153,0.00020311013,0.00030527177,0.000010207036,0.00008422652,0.000015225492,0.00051334297,0.049014654,0.92731535,0.0027836487,0.019015687,0.00021550732],"about_ca_topic_score_codex":0.0000020466844,"about_ca_topic_score_gemma":0.0000011326741,"teacher_disagreement_score":0.52800494,"about_ca_system_score_codex":0.000007902569,"about_ca_system_score_gemma":0.000038414062,"threshold_uncertainty_score":0.34906146},"labels":[],"label_agreement":null},{"id":"W4317869953","doi":"10.1093/bioinformatics/btad055","title":"Binding peptide generation for MHC Class I proteins with deep reinforcement learning","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"vaccines and immunoinformatics approaches","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; University of Ottawa","funders":"National Science Foundation","keywords":"Reinforcement learning; Computational biology; Class (philosophy); Computer science; Peptide; MHC class I; Artificial intelligence; Major histocompatibility complex; Chemistry; Biology; Biochemistry; Gene","score_opus":0.02448110864336796,"score_gpt":0.23952572503999564,"score_spread":0.21504461639662767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317869953","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73356205,0.000063357526,0.25872776,0.00020854715,0.00019743644,0.001807422,0.000013236482,0.00014453904,0.005275625],"genre_scores_gemma":[0.9502312,0.00022125737,0.039006617,0.00023666122,0.0004008526,0.0004400567,0.0040771714,0.00006443078,0.0053217337],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99892354,0.0000099456765,0.00040986552,0.0001278783,0.00017421639,0.00035457546],"domain_scores_gemma":[0.99933124,0.000010145304,0.00021456729,0.00027103475,0.000109329536,0.000063695974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030631237,0.00018781371,0.0001461326,0.00010471854,0.00027921057,0.000105151434,0.00015679903,0.00011566715,0.000006282022],"category_scores_gemma":[0.00008487181,0.00015058403,0.00007814975,0.00019619497,0.00002455164,0.000029391796,0.000100076424,0.00008749111,0.000060831215],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006295279,0.00012885514,0.0025318922,0.0021076472,0.00087081577,0.000003231642,0.0068694223,0.44788283,0.45097917,0.0028144894,0.045001544,0.040180583],"study_design_scores_gemma":[0.001179973,0.0009819478,0.00009527464,0.000034013552,0.000031577492,0.00001320486,0.001977226,0.87887645,0.05225659,0.000007867951,0.06418567,0.00036023124],"about_ca_topic_score_codex":0.0000025934548,"about_ca_topic_score_gemma":0.000009065636,"teacher_disagreement_score":0.43099362,"about_ca_system_score_codex":0.00002511455,"about_ca_system_score_gemma":0.00006710521,"threshold_uncertainty_score":0.61406386},"labels":[],"label_agreement":null},{"id":"W4318193482","doi":"10.1093/bioinformatics/btad057","title":"How to optimally sample a sequence for rapid analysis","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Japan Science and Technology Agency; U.S. National Library of Medicine; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Sequence (biology); Computer science; Source code; Sampling (signal processing); Sample (material); Sequence analysis; Sequence alignment; Algorithm; Biology; Peptide sequence; Genetics; DNA; Programming language","score_opus":0.03516069343064127,"score_gpt":0.2718266799308762,"score_spread":0.23666598650023496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318193482","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74896616,0.00026637895,0.24500985,0.0023610578,0.00028105313,0.000907314,0.0013728974,0.000038171722,0.00079708226],"genre_scores_gemma":[0.75504625,0.00036842836,0.24138397,0.0010734439,0.00020224415,0.00016068066,0.0007083431,0.000023915183,0.0010327023],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993509,0.0000059803856,0.000167463,0.00013994268,0.000082468694,0.00025323304],"domain_scores_gemma":[0.99944735,0.00003253659,0.000058094494,0.00028462903,0.00009814606,0.00007926452],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015645113,0.00011363442,0.000150473,0.00011439991,0.00009567597,0.000060329785,0.00017808967,0.00005975316,0.000002471783],"category_scores_gemma":[0.00020621085,0.000103768674,0.0001485066,0.00040870786,0.000025568788,0.000001172533,0.00013335046,0.000019090226,0.00001453528],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030535102,0.000098019314,0.011997428,0.00046524408,0.005573063,0.0000032336795,0.0040071397,0.02907521,0.69345796,0.0015268297,0.13619307,0.11729745],"study_design_scores_gemma":[0.00080343947,0.0010382942,0.008400133,0.000009469387,0.0004517578,0.0000036312772,0.0017649187,0.05127095,0.042625096,0.00033809294,0.8925115,0.00078273466],"about_ca_topic_score_codex":0.0000045103116,"about_ca_topic_score_gemma":0.000023235947,"teacher_disagreement_score":0.7563184,"about_ca_system_score_codex":0.000007807207,"about_ca_system_score_gemma":0.000038305265,"threshold_uncertainty_score":0.42315638},"labels":[],"label_agreement":null},{"id":"W4318391569","doi":"10.1093/bioinformatics/btad063","title":"Efficient penalized generalized linear mixed models for variable selection and genetic risk prediction in high-dimensional data","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Medical Research Council; Compute Canada","keywords":"Generalized linear mixed model; Lasso (programming language); Feature selection; Genome-wide association study; Curse of dimensionality; Linear model; Generalized linear model; Computer science; Mixed model; Binary number; Model selection; Covariance; Mathematics; Statistics; Artificial intelligence; Biology; Single-nucleotide polymorphism","score_opus":0.025862531734247348,"score_gpt":0.2652881851989897,"score_spread":0.23942565346474237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318391569","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81157076,0.00010043606,0.18708684,0.000066370034,0.00019108543,0.0003757696,0.00055060186,0.000027153186,0.00003094976],"genre_scores_gemma":[0.50976557,0.00034089715,0.48423144,0.00014465653,0.0002148965,0.00008590043,0.004893073,0.000026625006,0.00029694775],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988164,0.00007934401,0.00047380128,0.00024710025,0.000104879924,0.0002785259],"domain_scores_gemma":[0.9993118,0.000059153102,0.00018034768,0.00029910466,0.00009019005,0.000059413538],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007368076,0.000127645,0.00018695243,0.00010015047,0.00013433812,0.000014851209,0.00013427233,0.00019447073,0.000005821822],"category_scores_gemma":[0.00034915737,0.00012011688,0.000030978208,0.0002055995,0.00002705961,0.0000063671764,0.000187404,0.00006718906,0.0000089429],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000090798734,0.000043148488,0.0061325524,0.00004921412,0.000069739915,2.4135548e-7,0.00006755425,0.97588444,0.004016983,0.00020177045,0.011966203,0.0014773279],"study_design_scores_gemma":[0.0014037684,0.00012023998,0.016302025,0.000007782591,0.000038183844,0.000006735571,0.00003478477,0.9794391,0.00017825168,0.0008256307,0.0015211811,0.00012232158],"about_ca_topic_score_codex":0.000094250776,"about_ca_topic_score_gemma":0.000053955166,"teacher_disagreement_score":0.30180526,"about_ca_system_score_codex":0.000021039426,"about_ca_system_score_gemma":0.00008947246,"threshold_uncertainty_score":0.48982242},"labels":[],"label_agreement":null},{"id":"W4320817603","doi":"10.1093/bioinformatics/btad087","title":"Generalizations of the genomic rank distance to indels","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Foreign, Commonwealth and Development Office; Fundação de Amparo à Pesquisa do Estado de São Paulo; Medical Research Council; Alfred P. Sloan Foundation","keywords":"Indel; Rank (graph theory); Computer science; Genetics; Biology; Computational biology; Mathematics; Combinatorics; Single-nucleotide polymorphism; Gene; Genotype","score_opus":0.013477248210070252,"score_gpt":0.23895492266185675,"score_spread":0.2254776744517865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320817603","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9626412,0.00009051235,0.033136457,0.00039782695,0.0003073256,0.00046878957,0.000114657814,0.000026198974,0.0028170662],"genre_scores_gemma":[0.9875557,0.00014439691,0.00878691,0.00043260033,0.00011212914,0.000030271895,0.00015493477,0.000021068869,0.0027620294],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99946123,0.000010813602,0.00020446058,0.00006696488,0.00011476593,0.00014174829],"domain_scores_gemma":[0.99947655,0.0000035372002,0.00009241206,0.00034054715,0.000049407285,0.000037547332],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010086171,0.00007010646,0.00006866316,0.00004098302,0.000057388203,0.000011300601,0.00024326431,0.000045126697,0.0000102837275],"category_scores_gemma":[0.00004902401,0.000053079864,0.000053425287,0.00029984908,0.00003142626,0.0000025416425,0.00017726599,0.00002403597,0.00007260018],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044091084,0.000088057655,0.024829207,0.00036397285,0.00026233256,9.849475e-7,0.003932688,0.031773448,0.81868464,0.002912293,0.097169094,0.019939179],"study_design_scores_gemma":[0.0017304184,0.0003082269,0.15194131,0.00007647476,0.00008137737,0.000010574513,0.0012324058,0.033254273,0.23185015,0.00042241454,0.57822317,0.0008691934],"about_ca_topic_score_codex":0.000002897002,"about_ca_topic_score_gemma":0.00000998037,"teacher_disagreement_score":0.5868345,"about_ca_system_score_codex":0.000009722144,"about_ca_system_score_gemma":0.0000400052,"threshold_uncertainty_score":0.2164534},"labels":[],"label_agreement":null},{"id":"W4321611764","doi":"10.1093/bioinformatics/btad099","title":"CLAIRE: contrastive learning-based batch correction framework for better balance between batch mixing and preservation of cellular heterogeneity","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"National Natural Science Foundation of China","keywords":"Computer science; Benchmark (surveying); Source code; Code (set theory); Artificial intelligence; Machine learning; Programming language","score_opus":0.02165348175230125,"score_gpt":0.2564710270575074,"score_spread":0.23481754530520615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321611764","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61801046,0.000034520534,0.3814137,0.00006533296,0.0001886695,0.00020467737,0.000036832676,0.000022542374,0.000023247547],"genre_scores_gemma":[0.98895425,0.00003364359,0.010023853,0.000101996666,0.0001648942,0.00002131975,0.0006271623,0.000018139232,0.000054718028],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992027,0.000029306546,0.00031451744,0.0001417668,0.00011425877,0.00019742119],"domain_scores_gemma":[0.99940956,0.00011832274,0.00016790623,0.00014470969,0.00010934209,0.0000501791],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022979951,0.00013086578,0.00017977708,0.000044319353,0.0001057055,0.000025535439,0.00009043527,0.00022009738,0.0000017235348],"category_scores_gemma":[0.00020480814,0.00013072201,0.00007541202,0.00012081451,0.000061116545,0.000013934388,0.000028882998,0.000110298424,0.0000022323654],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004562954,0.00009585788,0.7026096,0.0011544365,0.0002636935,6.843881e-7,0.0008961039,0.0042011356,0.26860738,0.000106092026,0.0019153393,0.019693373],"study_design_scores_gemma":[0.0012569607,0.0007137363,0.04078095,0.00013277291,0.00007580607,8.5282323e-7,0.00017889193,0.26732603,0.68533695,0.00033360187,0.003523923,0.0003395246],"about_ca_topic_score_codex":0.000010853912,"about_ca_topic_score_gemma":0.000005651407,"teacher_disagreement_score":0.66182864,"about_ca_system_score_codex":0.000010948896,"about_ca_system_score_gemma":0.000035377896,"threshold_uncertainty_score":0.5330689},"labels":[],"label_agreement":null},{"id":"W4323353510","doi":"10.1093/bioinformatics/btad118","title":"NDEx IQuery: a multi-method network gene set analysis leveraging the Network Data Exchange","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Cancer Institute; National Human Genome Research Institute; Advanced Research Projects Agency; Defense Advanced Research Projects Agency; National Institutes of Health","keywords":"Computer science; Java; Context (archaeology); Set (abstract data type); Biological network; JavaScript; Task (project management); Network analysis; Variety (cybernetics); Software; Gene regulatory network; Data mining; Computational biology; World Wide Web; Artificial intelligence; Programming language; Gene; Biology","score_opus":0.05488798261072136,"score_gpt":0.306567996007621,"score_spread":0.25168001339689966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323353510","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0073340447,0.0016334831,0.9861805,0.0006407407,0.0007812869,0.0007536154,0.00045752703,0.00016799344,0.0020508214],"genre_scores_gemma":[0.19142628,0.008163079,0.7398866,0.011809527,0.00760768,0.00018702932,0.035179008,0.00022708636,0.0055137626],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99762154,0.00011686909,0.0007610133,0.00034069503,0.00028016212,0.00087972014],"domain_scores_gemma":[0.99718964,0.000095201096,0.0003734455,0.0020973694,0.000086818225,0.00015750455],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002540365,0.00033602727,0.00038474397,0.00008427551,0.00047438018,0.00018076117,0.0012973768,0.00028378822,0.000032996028],"category_scores_gemma":[0.00007138321,0.00025318773,0.00023116688,0.0015049976,0.00009158187,0.000027727465,0.0016697049,0.00026274723,0.00012911201],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006276653,0.000032936507,0.0041871956,0.0001450929,0.0024824622,0.000007734919,0.0013079502,0.27271608,0.00019989011,0.00022963877,0.6784125,0.040215753],"study_design_scores_gemma":[0.0003874845,0.000041714553,0.0023342145,0.000015766804,0.00031637598,0.000014920249,0.00047797782,0.8234657,0.00005046859,0.00008713528,0.17245232,0.0003559411],"about_ca_topic_score_codex":0.000033072636,"about_ca_topic_score_gemma":0.00015820592,"teacher_disagreement_score":0.5507496,"about_ca_system_score_codex":0.000021548314,"about_ca_system_score_gemma":0.00010191936,"threshold_uncertainty_score":0.999992},"labels":[],"label_agreement":null},{"id":"W4323810601","doi":"10.1093/bioinformatics/btad126","title":"RNAget: an API to securely retrieve RNA quantifications","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Genomics; McGill University; Ontario Institute for Cancer Research","funders":"National Human Genome Research Institute; European Regional Development Fund; Medical Research Council; National Institutes of Health; Generalitat de Catalunya; Ministerio de Ciencia e Innovación; Centres de Recerca de Catalunya; Canadian Institutes of Health Research; Genome Canada","keywords":"Computer science; Genomics; Slicing; DNA microarray; Computational biology; Data mining; World Wide Web; Genome; Biology; Genetics; Gene; Gene expression","score_opus":0.034816919898544706,"score_gpt":0.3055031289160492,"score_spread":0.2706862090175045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323810601","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92780006,0.00011526342,0.044743963,0.0024941394,0.0009876586,0.0007563296,0.000120698336,0.00029425157,0.02268763],"genre_scores_gemma":[0.9885522,0.0001441728,0.0054067764,0.00091467315,0.00018913297,0.000057167617,0.0007359454,0.0000231837,0.003976753],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99920774,0.000019670493,0.00025316398,0.00016467857,0.00016015286,0.00019457033],"domain_scores_gemma":[0.9991146,0.000005338661,0.000082510225,0.00055007706,0.00009420063,0.00015332311],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019117039,0.00010335923,0.00007663803,0.00011779847,0.00011612654,0.00005519118,0.0002459636,0.000108923035,0.000022249707],"category_scores_gemma":[0.00009330906,0.0000972352,0.00004412209,0.00046483733,0.000024268578,0.000010913219,0.00007637231,0.000053913205,0.0005726026],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004756811,0.00005054083,0.00018990308,0.00004069784,0.000023706787,6.5128546e-7,0.0017417616,0.0002993697,0.73029625,0.0019866354,0.24516046,0.020162476],"study_design_scores_gemma":[0.0003436136,0.0002656434,0.006083749,0.000020026708,0.000012815151,0.00000424232,0.0019627362,0.0058599603,0.2714181,0.00015595848,0.7135195,0.00035362312],"about_ca_topic_score_codex":0.0000032565622,"about_ca_topic_score_gemma":0.000007861453,"teacher_disagreement_score":0.46835908,"about_ca_system_score_codex":0.000012294381,"about_ca_system_score_gemma":0.000068700574,"threshold_uncertainty_score":0.7359839},"labels":[],"label_agreement":null},{"id":"W4327682542","doi":"10.1093/bioinformatics/btad136","title":"GENLIB: new function to simulate haplotype transmission in large complex genealogies","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hôpital Maisonneuve-Rosemont; Université du Québec à Chicoutimi; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation; Canadian Institutes of Health Research; University of Ottawa; Canarie","keywords":"Haplotype; R package; Computer science; Function (biology); Transmission (telecommunications); Proband; Genealogy; Theoretical computer science; Biology; Mutation; Genetics; Programming language; History; Telecommunications; Gene","score_opus":0.036914413292160185,"score_gpt":0.29490424534431,"score_spread":0.2579898320521498,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327682542","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85043865,0.00015735687,0.14586219,0.0013389488,0.0002740785,0.00039989088,0.000040565137,0.00011013653,0.0013781715],"genre_scores_gemma":[0.9634109,0.0003806975,0.03140858,0.0019087055,0.00017867693,0.000015737216,0.00084437354,0.000027923248,0.0018243735],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99904406,0.00003229942,0.00034971215,0.00013935285,0.00008974677,0.0003448009],"domain_scores_gemma":[0.9995568,0.00002111276,0.000067795976,0.00021041342,0.000035271547,0.00010864212],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030404358,0.0001184876,0.00015401808,0.000113090864,0.000071671275,0.0000144003825,0.00012722606,0.000164026,0.000030375375],"category_scores_gemma":[0.00012097336,0.00010951578,0.000058460664,0.0002881734,0.000011955948,0.000004939842,0.00009180161,0.00005763503,0.0003123456],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004245604,0.00018678556,0.08784419,0.00020259162,0.00022329332,0.000006833455,0.0033395486,0.10753536,0.10456778,0.0005345717,0.4157943,0.27934018],"study_design_scores_gemma":[0.0009811817,0.0003419015,0.4791264,0.0000144825,0.000017522716,0.0000023260015,0.00046316432,0.08244781,0.000774843,0.0005089468,0.4350188,0.0003026185],"about_ca_topic_score_codex":0.000021747936,"about_ca_topic_score_gemma":0.00006179059,"teacher_disagreement_score":0.3912822,"about_ca_system_score_codex":0.000017787925,"about_ca_system_score_gemma":0.000066572386,"threshold_uncertainty_score":0.4465924},"labels":[],"label_agreement":null},{"id":"W4328048262","doi":"10.1093/bioinformatics/btad139","title":"The hidden factor: accounting for covariate effects in power and sample size computation for a binary trait","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"Covariate; Biobank; Sample size determination; Computer science; Trait; Statistics; Sample (material); Logistic regression; Binary number; Data mining; Replication (statistics); Econometrics; Mathematics; Biology; Bioinformatics","score_opus":0.019299697030622898,"score_gpt":0.2859291187542457,"score_spread":0.2666294217236228,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4328048262","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94936913,0.00007811554,0.048797373,0.00049117126,0.00021017934,0.00080039114,0.00017708314,0.000018051205,0.00005851814],"genre_scores_gemma":[0.9389931,0.00007553353,0.06019786,0.00025682512,0.00006092704,0.00014132075,0.00018904921,0.000013134046,0.00007225027],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99935454,0.000023163835,0.00025707722,0.00009198463,0.000042274398,0.00023095847],"domain_scores_gemma":[0.99818754,0.0015317163,0.00011928575,0.00008598924,0.00005086749,0.000024583012],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046001707,0.00008297563,0.00011566616,0.00002885344,0.00016157197,0.000030876916,0.00007190397,0.00010940851,5.525845e-7],"category_scores_gemma":[0.0023072395,0.000064192645,0.00005007686,0.00007676687,0.000027898164,0.0000048744273,0.00004979527,0.000031034888,0.0000017537845],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012790804,0.0003083304,0.20890948,0.003117662,0.0012236635,0.000002439462,0.014942955,0.008358592,0.07220308,0.0063729463,0.15629138,0.5269904],"study_design_scores_gemma":[0.0034890794,0.00095580146,0.6529585,0.000037571,0.0000401765,0.0000038773087,0.0016359336,0.29688725,0.0006099793,0.013343229,0.029597962,0.00044061954],"about_ca_topic_score_codex":0.00000954428,"about_ca_topic_score_gemma":0.000025859234,"teacher_disagreement_score":0.52654976,"about_ca_system_score_codex":0.0000114350105,"about_ca_system_score_gemma":0.000035388068,"threshold_uncertainty_score":0.27621478},"labels":[],"label_agreement":null},{"id":"W4362657842","doi":"10.1093/bioinformatics/btad177","title":"MARSY: a multitask deep-learning framework for prediction of drug combination synergy scores","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Institut de Valorisation des Données; Merck Canada; Canada First Research Excellence Fund; Compute Canada; Government of Canada; McGill University","keywords":"Python (programming language); Machine learning; Computer science; Artificial intelligence; Multi-task learning; Deep learning; Drug; Encoder; Drug repositioning; Task (project management); Medicine; Pharmacology","score_opus":0.022969270557317737,"score_gpt":0.29107115244868986,"score_spread":0.26810188189137213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362657842","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02803499,0.000021344536,0.97039896,0.00019771859,0.0005528842,0.00026317543,0.000026677411,0.00028774835,0.00021648628],"genre_scores_gemma":[0.22980964,0.000022705322,0.7698258,0.000055995453,0.00004199435,0.000042138243,0.000109140325,0.000010504559,0.0000820739],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998825,0.000065891225,0.00043468818,0.00012537748,0.00035350252,0.0001955521],"domain_scores_gemma":[0.99803984,0.0012300601,0.0002595809,0.00023959659,0.00018280609,0.0000480872],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076701154,0.000104842075,0.00014986955,0.00027212343,0.00012468804,0.00009023654,0.00038961944,0.000062557876,0.000002546823],"category_scores_gemma":[0.0008561523,0.00010422096,0.000082056526,0.0007455119,0.000034808083,0.00071615813,0.00019728985,0.000107416425,0.00002769007],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018702103,0.000074720105,0.0014659949,0.00045198665,0.000053529748,8.993383e-7,0.006858533,0.21962716,0.00006051734,0.62229246,0.0012870749,0.14780842],"study_design_scores_gemma":[0.0002817018,0.00006818972,0.009364202,0.000073656614,0.0000069007224,0.0000016882241,0.00026873837,0.93392134,0.00043033255,0.05494234,0.0005543322,0.00008658024],"about_ca_topic_score_codex":0.0000045757097,"about_ca_topic_score_gemma":9.905871e-7,"teacher_disagreement_score":0.7142942,"about_ca_system_score_codex":0.00004425714,"about_ca_system_score_gemma":0.00006023799,"threshold_uncertainty_score":0.42500076},"labels":[],"label_agreement":null},{"id":"W4365444089","doi":"10.1093/bioinformatics/btad189","title":"Structure-aware protein self-supervised learning","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Pairwise comparison; Leverage (statistics); Graph; Supervised learning; Artificial neural network; Theoretical computer science","score_opus":0.007098345358430243,"score_gpt":0.2367498723285093,"score_spread":0.22965152697007907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4365444089","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98174554,0.000038624716,0.0065393145,0.00020593584,0.00028491748,0.0007280287,0.00005375586,0.0007627664,0.009641139],"genre_scores_gemma":[0.94066006,0.00007629182,0.053314954,0.00041991874,0.0003403173,0.000040873347,0.001653968,0.00007954453,0.0034140805],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99851847,0.00005019768,0.00047947018,0.00016581222,0.0003198718,0.0004661755],"domain_scores_gemma":[0.9990985,0.000016134263,0.00019594593,0.00045830855,0.000101935984,0.00012916885],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000291348,0.0002581594,0.00018736615,0.00014204587,0.00023133722,0.000093732204,0.000363216,0.00024438585,0.00006765454],"category_scores_gemma":[0.00025188664,0.00023548723,0.00010155159,0.0003807853,0.00004984011,0.000019076419,0.0002968168,0.00030107016,0.000483977],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00059821806,0.00045984832,0.073690936,0.009458076,0.0019841816,0.000073580624,0.031084895,0.06977375,0.40234354,0.0052341563,0.19609791,0.20920089],"study_design_scores_gemma":[0.0014390239,0.00064714847,0.002101151,0.00007915552,0.000039810373,0.000057219804,0.0016876708,0.7189814,0.033850852,0.00011583996,0.2400074,0.0009933145],"about_ca_topic_score_codex":0.000004326531,"about_ca_topic_score_gemma":0.0000046351106,"teacher_disagreement_score":0.64920765,"about_ca_system_score_codex":0.000022245054,"about_ca_system_score_gemma":0.00010013436,"threshold_uncertainty_score":0.960289},"labels":[],"label_agreement":null},{"id":"W4366351318","doi":"10.1093/bioinformatics/btad255","title":"ConsAlign: simultaneous RNA structural aligner based on rich transfer learning and thermodynamic ensemble model of alignment scoring","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Genetics","keywords":"Computer science; Ensemble learning; Artificial intelligence; Software; Machine learning; Programming language","score_opus":0.01284406087212039,"score_gpt":0.23595095961090834,"score_spread":0.22310689873878795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366351318","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95384103,0.000038612718,0.044338904,0.00003169084,0.00005381076,0.00021779905,0.000025288435,0.000030480822,0.0014224005],"genre_scores_gemma":[0.9956336,0.0000790679,0.0038441492,0.00009268846,0.000020375968,0.0000112912785,0.000049296897,0.000020695208,0.00024882148],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99915695,0.000032598353,0.00026727084,0.00013736231,0.00018870285,0.00021713886],"domain_scores_gemma":[0.99960876,0.000052182197,0.00006234017,0.00018087147,0.000037819744,0.000058021455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019377595,0.00015723161,0.0001599939,0.00006508474,0.00008693199,0.000019849838,0.00009979176,0.00011991586,0.0000075092626],"category_scores_gemma":[0.000055287666,0.0001331775,0.000056596964,0.00007426642,0.000043475527,0.0000052150544,0.00003678262,0.00005482295,0.0000070163464],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006545818,0.000007410334,0.000044695495,0.000092952694,0.00002705702,0.0000016137983,0.0002502141,0.1044444,0.8851285,0.00021609134,0.000015311922,0.009706294],"study_design_scores_gemma":[0.00024886755,0.00016971683,0.000006839934,0.000027347449,0.000012145545,0.0000018462714,0.0001429998,0.5941443,0.404974,0.00009728456,0.00005813681,0.0001165187],"about_ca_topic_score_codex":0.000002924023,"about_ca_topic_score_gemma":0.0000014320241,"teacher_disagreement_score":0.4896999,"about_ca_system_score_codex":0.000009984918,"about_ca_system_score_gemma":0.000039872673,"threshold_uncertainty_score":0.54308206},"labels":[],"label_agreement":null},{"id":"W4366549780","doi":"10.1093/bioinformatics/btad180","title":"The DynaSig-ML Python package: automated learning of biomolecular dynamics–function relationships","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Institute for Research in Immunology and Cancer","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Compute Canada; Genome Canada","keywords":"Python (programming language); Computer science; R package; Programming language; Artificial intelligence","score_opus":0.00876049196145396,"score_gpt":0.23710940974201583,"score_spread":0.22834891778056188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366549780","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6870266,0.000489055,0.3032887,0.00042926005,0.0008988917,0.0007806758,0.000087410415,0.00078723574,0.006212151],"genre_scores_gemma":[0.9958458,0.00016598904,0.0021300688,0.00003796035,0.00005132517,0.0000146719985,0.0009871664,0.000025714644,0.00074129214],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990119,0.000074142146,0.00037366775,0.00011491198,0.00018675646,0.00023864298],"domain_scores_gemma":[0.99920404,0.000045787405,0.00021617698,0.00037096118,0.00011293435,0.000050124396],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045836967,0.00013595504,0.00011193021,0.000078468795,0.00033769762,0.00004143328,0.0001854461,0.00019649407,0.0000019220768],"category_scores_gemma":[0.00041310617,0.000104151826,0.00008923018,0.00039930732,0.00010447789,0.000010309234,0.00012249465,0.00017121868,0.000042199914],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010031901,0.00016221158,0.04006274,0.0013054318,0.0015723787,0.000025520143,0.003126866,0.03425217,0.60864645,0.07151701,0.036003094,0.20232293],"study_design_scores_gemma":[0.0005083016,0.00034570464,0.010730552,0.000031035535,0.000053461175,0.000019813806,0.0015020048,0.95730925,0.014652896,0.0010723874,0.013466939,0.00030768054],"about_ca_topic_score_codex":0.0000061063183,"about_ca_topic_score_gemma":0.000024802212,"teacher_disagreement_score":0.9230571,"about_ca_system_score_codex":0.000022493834,"about_ca_system_score_gemma":0.000062909836,"threshold_uncertainty_score":0.42471883},"labels":[],"label_agreement":null},{"id":"W4366721767","doi":"10.1093/bioinformatics/btad276","title":"spongEffects: ceRNA modules offer patient-specific insights into the miRNA regulatory landscape","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"MicroRNA in disease regulation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Genome British Columbia","funders":"Bundesministerium für Bildung und Forschung; Deutsche Forschungsgemeinschaft; European Commission","keywords":"microRNA; Computational biology; Computer science; Competing endogenous RNA; Data science; Biology; Gene; Genetics","score_opus":0.007984792714195431,"score_gpt":0.21192679396232234,"score_spread":0.2039420012481269,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366721767","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9961507,0.0014841153,0.00036619324,0.00009830018,0.0002889879,0.0003195505,0.0000113727165,0.000064111366,0.0012167027],"genre_scores_gemma":[0.9978346,0.00043449443,0.000640267,0.00018250581,0.00020729292,0.000028732182,0.0004237576,0.000026316975,0.00022202583],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990243,0.000046804635,0.00030606866,0.00015699236,0.00024110418,0.00022475088],"domain_scores_gemma":[0.99908906,0.000023594444,0.00013332696,0.00059703836,0.000075454045,0.00008153341],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013290653,0.00017082131,0.00011456894,0.000082529,0.00016486258,0.00005363397,0.0002449437,0.0001390059,0.000020987703],"category_scores_gemma":[0.000046687386,0.000119655444,0.00010074781,0.00022838546,0.00009035673,0.000014186303,0.00018370103,0.000071058734,0.0002916541],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003413529,0.00015465973,0.0024654444,0.0005115811,0.0003484162,0.000018430599,0.009265849,0.0023895707,0.53013504,0.0018621096,0.3156256,0.1368819],"study_design_scores_gemma":[0.0010801094,0.00029609344,0.072626464,0.00009268984,0.00004675174,0.00001703421,0.0014761278,0.021229342,0.20013396,0.00062229566,0.7016757,0.00070339313],"about_ca_topic_score_codex":0.0000029264825,"about_ca_topic_score_gemma":0.0000070468495,"teacher_disagreement_score":0.3860501,"about_ca_system_score_codex":0.00002235428,"about_ca_system_score_gemma":0.000035184043,"threshold_uncertainty_score":0.48794076},"labels":[],"label_agreement":null},{"id":"W4366992370","doi":"10.1093/bioinformatics/btad163","title":"Correction to: Continuous chromatin state feature annotation of the human epigenome","year":2023,"lang":"en","type":"erratum","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Michael Smith Health Research BC; Compute Canada; Genome Canada","keywords":"Epigenome; Chromatin; Feature (linguistics); Annotation; Computer science; State (computer science); Computational biology; Artificial intelligence; Biology; Genetics; DNA methylation; Programming language; DNA; Gene","score_opus":0.006974353029127545,"score_gpt":0.2547317770100916,"score_spread":0.24775742398096404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366992370","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18392454,0.0016846718,0.022120647,0.002837797,0.34729877,0.013068909,0.005391295,0.0012301359,0.42244324],"genre_scores_gemma":[0.0097892,0.0003110219,0.0070311045,0.000985999,0.0018070968,0.00009043031,0.008662861,0.00023312499,0.9710892],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979796,0.00007339393,0.0008645983,0.00020273996,0.0005009128,0.0003787788],"domain_scores_gemma":[0.9975178,0.000031311978,0.0011454234,0.0009164793,0.00029264198,0.00009629273],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00040456027,0.00040134613,0.00042972653,0.00017492511,0.00022728859,0.00008009225,0.0007004401,0.00051969825,0.000013912343],"category_scores_gemma":[0.00074026646,0.00031426153,0.00024468557,0.00042521197,0.00010651107,0.000011079152,0.00044397303,0.00074694806,0.00011859742],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010486678,0.000017344879,0.00022504535,0.00053160056,0.0000841945,4.1113077e-7,0.0012380619,0.00051731436,0.0018145258,0.000011521723,0.9930583,0.0024911538],"study_design_scores_gemma":[0.00046357035,0.00061644224,0.011809063,0.00076964725,0.00009934429,0.00002016629,0.00062497135,0.008210149,0.0048722886,0.00004414931,0.97170097,0.0007692227],"about_ca_topic_score_codex":0.000052590887,"about_ca_topic_score_gemma":0.00018144178,"teacher_disagreement_score":0.5486459,"about_ca_system_score_codex":0.00006513208,"about_ca_system_score_gemma":0.00028098753,"threshold_uncertainty_score":0.9999309},"labels":[],"label_agreement":null},{"id":"W4367836399","doi":"10.1093/bioinformatics/btad210","title":"Signed Distance Correlation (SiDCo): an online implementation of distance correlation and partial distance correlation for data-driven network analysis","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; National Research Council Canada","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pearson product-moment correlation coefficient; Distance correlation; Partial correlation; Correlation; Covariance; Covariance and correlation; Linear correlation; Software; Computer science; Correlation coefficient; Distance measures; Data mining; Linear model; Mathematics; Statistics; Artificial intelligence; Random variable","score_opus":0.027772411800048722,"score_gpt":0.30760081987860377,"score_spread":0.279828408078555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367836399","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14535744,0.00030637215,0.85207504,0.000060958515,0.0002574824,0.0004797347,0.0013927913,0.000027550754,0.000042611682],"genre_scores_gemma":[0.948566,0.0006260957,0.022265872,0.000038108,0.00018500419,0.000031776322,0.028142367,0.000018389575,0.00012638008],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984892,0.00004136925,0.0006856048,0.00030416058,0.00020522453,0.0002744261],"domain_scores_gemma":[0.99860734,0.00006616523,0.0005965798,0.0005068747,0.0001548571,0.00006818044],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039477483,0.00018886894,0.000316935,0.000109436034,0.00020521788,0.000042010306,0.00018591218,0.00011400259,0.000007688957],"category_scores_gemma":[0.000108158754,0.00018545667,0.00008032761,0.00065472693,0.00008124451,0.00007319271,0.0001303316,0.00006190316,0.0000018376373],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015539167,0.00039139358,0.51841724,0.0008078762,0.0030683824,0.0000019918543,0.0031968225,0.3323527,0.0078062518,0.03498223,0.015667455,0.08175375],"study_design_scores_gemma":[0.0008094017,0.00024776117,0.04276209,0.00001377964,0.0004423336,5.8180416e-7,0.0008334101,0.9448489,0.00026207932,0.00020867589,0.009334761,0.00023624496],"about_ca_topic_score_codex":0.000020628351,"about_ca_topic_score_gemma":0.0007871336,"teacher_disagreement_score":0.8298092,"about_ca_system_score_codex":0.000024840223,"about_ca_system_score_gemma":0.00004493287,"threshold_uncertainty_score":0.75627035},"labels":[],"label_agreement":null},{"id":"W4375955770","doi":"10.1093/bioinformatics/btad309","title":"Genome mining for anti-CRISPR operons using machine learning","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"CRISPR and Genetic Engineering","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institutes of Health; National Institute of General Medical Sciences; National Institute of Allergy and Infectious Diseases; University of Nebraska-Lincoln; University of Toronto; U.S. Department of Agriculture","keywords":"CRISPR; Genome; Operon; Computational biology; Context (archaeology); Computer science; Python (programming language); Gene; Biology; Genetics; Programming language","score_opus":0.02191280019472707,"score_gpt":0.3098302355894656,"score_spread":0.2879174353947385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4375955770","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83434296,0.00036650393,0.16437337,0.0000341462,0.00020805164,0.00022990389,0.000048379014,0.000075139724,0.00032154637],"genre_scores_gemma":[0.937066,0.00027427007,0.06079191,0.00008545339,0.00027007237,0.000019190755,0.000674068,0.00005092976,0.00076808815],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99925435,0.000007116564,0.00023574762,0.000117601856,0.00008260038,0.00030260795],"domain_scores_gemma":[0.9996468,0.00001427646,0.00005432447,0.00017824897,0.00004100834,0.000065342676],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018842173,0.00013120272,0.00012487364,0.000079985824,0.00014093137,0.000035468704,0.00012861118,0.00008916124,0.0000061325404],"category_scores_gemma":[0.00009421749,0.00013115158,0.00007872621,0.00013920355,0.00002105867,0.000005500395,0.00011359036,0.00005644648,0.000018177709],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001921406,0.000016586268,0.0030420022,0.00027081175,0.00009497427,0.0000021112883,0.0008583393,0.109733425,0.88214535,0.000024809826,0.0006440766,0.0031482782],"study_design_scores_gemma":[0.00073839293,0.00021002303,0.0018898643,0.000027392374,0.000040907522,0.00002708554,0.000996263,0.784853,0.09368828,0.000005868796,0.11709722,0.0004257335],"about_ca_topic_score_codex":0.000004365931,"about_ca_topic_score_gemma":0.000003915827,"teacher_disagreement_score":0.7884571,"about_ca_system_score_codex":0.000009587713,"about_ca_system_score_gemma":0.000032358697,"threshold_uncertainty_score":0.5348206},"labels":[],"label_agreement":null},{"id":"W4377086801","doi":"10.1093/bioinformatics/btad328","title":"GIL: a python package for designing custom indexing primers","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; University of British Columbia; Western Canada Research Grid; Stem Cell Network; Canadian Institutes of Health Research; Compute Canada","keywords":"Python (programming language); Search engine indexing; Programming language; Computer science; R package; Information retrieval","score_opus":0.03511654673081748,"score_gpt":0.27567387795689735,"score_spread":0.24055733122607986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377086801","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00075023324,0.000018531566,0.9969819,0.00013351125,0.00039669365,0.0002579722,0.000015558167,0.0005214252,0.0009241423],"genre_scores_gemma":[0.008843798,0.000020360818,0.99035805,0.00027745203,0.000087925044,0.000033716737,0.00006302705,0.000015185519,0.00030048605],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99900293,0.000012375935,0.00027947812,0.00013496859,0.00023617224,0.00033407268],"domain_scores_gemma":[0.9991378,0.00014633495,0.00012531599,0.00045020354,0.00005241349,0.000087894594],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041891437,0.00011612277,0.00012613463,0.00015728897,0.00022794836,0.00022013723,0.0006059634,0.00006452478,0.0000023362907],"category_scores_gemma":[0.00008107491,0.00009785484,0.00005695167,0.00047183994,0.000019723051,0.0010318949,0.00038575524,0.00008130132,0.00018070657],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018479152,0.000050032133,0.00022900171,0.0004229295,0.000051983523,0.000016622536,0.0108929,0.000860657,0.0025666514,0.031426195,0.121830635,0.8316339],"study_design_scores_gemma":[0.00032973173,0.00005746892,0.00022130727,0.00006217392,0.000004581818,0.0000053748568,0.00026866447,0.95319086,0.0038346492,0.0010109721,0.040822174,0.00019203192],"about_ca_topic_score_codex":0.000004098001,"about_ca_topic_score_gemma":4.067939e-7,"teacher_disagreement_score":0.95233023,"about_ca_system_score_codex":0.000028076884,"about_ca_system_score_gemma":0.00006549209,"threshold_uncertainty_score":0.39904046},"labels":[],"label_agreement":null},{"id":"W4378782144","doi":"10.1093/bioinformatics/btad353","title":"MRGCN: cancer subtyping with multi-reconstruction graph convolutional network using full and partial multi-omics dataset","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Xi'an Municipal Bureau of Science and Technology; Education Department of Shaanxi Province; Xi'an Polytechnic University; National Natural Science Foundation of China","keywords":"Subtyping; Omics; Computer science; Graph; Rank (graph theory); Computational biology; Data mining; Bioinformatics; Biology; Theoretical computer science; Mathematics","score_opus":0.02777623596967806,"score_gpt":0.264301826644408,"score_spread":0.23652559067472992,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378782144","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5906571,0.0010848264,0.40332067,0.00010495983,0.0012851253,0.00078392756,0.0025654589,0.00009672813,0.00010115877],"genre_scores_gemma":[0.40980148,0.0053615347,0.5576956,0.0020484768,0.002787935,0.000112485766,0.02172203,0.00017134269,0.00029908912],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998855,0.000017986498,0.00040876624,0.00017679161,0.00011964075,0.0004218164],"domain_scores_gemma":[0.9992962,0.000012587608,0.0002278924,0.00025670027,0.000081572725,0.00012503788],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025085604,0.00021207304,0.00018288412,0.000065376065,0.00024953188,0.00007330649,0.0001271224,0.00018862919,0.000010500265],"category_scores_gemma":[0.000015831478,0.00018815375,0.000044822445,0.00020584145,0.00019225312,0.00003061489,0.00016411407,0.00013068941,0.000015681022],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022388513,0.00034434517,0.07755253,0.0019116976,0.002743176,0.000025771375,0.0024814664,0.6419385,0.030769408,0.0024614085,0.10302403,0.13450882],"study_design_scores_gemma":[0.0015117,0.00009661251,0.0015427095,0.000056694196,0.00006051453,0.00010244556,0.00033195113,0.9840111,0.0005019051,0.000026322876,0.011365201,0.00039285742],"about_ca_topic_score_codex":0.000029342295,"about_ca_topic_score_gemma":0.00012389327,"teacher_disagreement_score":0.34207258,"about_ca_system_score_codex":0.000023669063,"about_ca_system_score_gemma":0.00012727882,"threshold_uncertainty_score":0.7672687},"labels":[],"label_agreement":null},{"id":"W4380869524","doi":"10.1093/bioinformatics/btad381","title":"GRETTA: an R package for mapping <i>in silico</i> genetic interaction and essentiality networks","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; Genome British Columbia; University of British Columbia","funders":"University of British Columbia; University of Alabama at Birmingham; Canada Research Chairs; Broad Institute; University of Alabama; Canadian Institutes of Health Research; Canada's Michael Smith Genome Sciences Centre","keywords":"DECIPHER; In silico; Computer science; MIT License; Documentation; Computational biology; Source code; Biology; Genetics; Gene; Software; Programming language","score_opus":0.017506506091304393,"score_gpt":0.26022353994634445,"score_spread":0.24271703385504007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380869524","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7860469,0.00023113926,0.2115032,0.00012617385,0.0005751843,0.00068691425,0.000049394388,0.00005862289,0.0007224681],"genre_scores_gemma":[0.9871578,0.0005232723,0.010469921,0.00049763895,0.00037484287,0.00005567559,0.00075668754,0.000027968885,0.00013615264],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989068,0.00002118732,0.00047743376,0.00016495527,0.00007940509,0.00035020182],"domain_scores_gemma":[0.99937576,0.000024871959,0.0001466977,0.00031263134,0.00004244384,0.000097573546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003809483,0.00016463223,0.0001655419,0.00009056943,0.000101191006,0.000085148204,0.00014122376,0.00019557052,0.0000029515654],"category_scores_gemma":[0.000029412246,0.00016306357,0.0000612218,0.00017052845,0.00005254908,0.000025639481,0.00012332192,0.00010007137,0.000008778875],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00069142424,0.0004161176,0.04085842,0.0028275077,0.00052613707,0.000019330322,0.008965468,0.052657988,0.04984031,0.0028420489,0.08694295,0.7534123],"study_design_scores_gemma":[0.0013031581,0.00026863848,0.013648528,0.000060415838,0.00002339552,0.000030022371,0.0019392081,0.9507687,0.0015056789,0.00056247134,0.029375905,0.0005138973],"about_ca_topic_score_codex":0.000009164136,"about_ca_topic_score_gemma":0.000049076,"teacher_disagreement_score":0.8981107,"about_ca_system_score_codex":0.0000143925645,"about_ca_system_score_gemma":0.000027130642,"threshold_uncertainty_score":0.66495395},"labels":[],"label_agreement":null},{"id":"W4380871602","doi":"10.1093/bioinformatics/btad390","title":"Interpretable deep learning architectures for improving drug response prediction performance: myth or reality?","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Institut de Valorisation des Données; Merck Canada; Canada First Research Excellence Fund; Government of Canada; Génome Québec; Compute Canada","keywords":"Interpretability; Computer science; Generalizability theory; Machine learning; Artificial intelligence; Baseline (sea); Random forest; Deep learning; Overfitting; Perceptron; Predictive modelling; Data mining; Artificial neural network; Statistics; Mathematics","score_opus":0.02475005689958606,"score_gpt":0.29803671581054364,"score_spread":0.2732866589109576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380871602","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25836784,0.000012537908,0.7394581,0.00037424755,0.00046025286,0.00035193126,0.000015681251,0.0006000636,0.0003593916],"genre_scores_gemma":[0.61289597,0.0000139025915,0.38478437,0.00032274547,0.00014081172,0.00011779645,0.0000536952,0.000025824598,0.0016449088],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983529,0.00016219674,0.00049907144,0.00021390388,0.00037519826,0.00039671586],"domain_scores_gemma":[0.9978152,0.0014074228,0.00020555178,0.00036689936,0.00011432678,0.00009058126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025944386,0.00017024981,0.00018608331,0.000360592,0.00034706722,0.0002671624,0.00058334426,0.00005704517,0.0000050546128],"category_scores_gemma":[0.0011185759,0.00013985393,0.00008686463,0.0007612993,0.000040405484,0.0006087423,0.00040062008,0.00020796453,0.00004023294],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048840157,0.000016173102,0.00017383073,0.00038552724,0.000021132577,0.0000019633947,0.011985462,0.62528646,0.00011820722,0.00049489277,0.001308893,0.35971907],"study_design_scores_gemma":[0.0003448644,0.00020850645,0.0030486928,0.00004873926,0.0000084621015,0.00002053769,0.00041857592,0.99023175,0.00055335567,0.00072533306,0.0042228373,0.00016833212],"about_ca_topic_score_codex":0.0000063434522,"about_ca_topic_score_gemma":0.0000031445068,"teacher_disagreement_score":0.36494532,"about_ca_system_score_codex":0.000103349645,"about_ca_system_score_gemma":0.00021490446,"threshold_uncertainty_score":0.57030773},"labels":[],"label_agreement":null},{"id":"W4382631279","doi":"10.1093/bioinformatics/btad253","title":"Robust reconstruction of single-cell RNA-seq data with iterative gene weight updates","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Defense Advanced Research Projects Agency; Azrieli Foundation; Israel Science Foundation; European Commission; U.S. Department of Energy; National Science Foundation","keywords":"RNA-Seq; Computer science; Computational biology; Gene; Algorithm; Gene expression; Data mining; Biology; Transcriptome; Genetics","score_opus":0.03678924505138624,"score_gpt":0.2210204430184372,"score_spread":0.18423119796705095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382631279","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9651356,0.00018712893,0.028358096,0.00008977812,0.0004278828,0.00026759598,0.00048344338,0.00006041338,0.00499008],"genre_scores_gemma":[0.87816435,0.00070842647,0.1137248,0.00019143717,0.00033704002,0.000010403751,0.0058467523,0.000056546916,0.00096026843],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990857,0.000018971043,0.00035629334,0.00018839879,0.00014412942,0.00020646103],"domain_scores_gemma":[0.9990641,0.000015016125,0.00018102476,0.00056963495,0.000110270834,0.000059941427],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014156115,0.00015994665,0.00016874383,0.00007679504,0.00006981893,0.000035940528,0.000313945,0.00012434235,0.000015379846],"category_scores_gemma":[0.000026932397,0.00012994066,0.000040473606,0.00021311393,0.00011810833,0.00002946481,0.00012265355,0.00006948147,0.000023317578],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020161083,0.00014505166,0.0030935104,0.00025396678,0.00014207496,0.0000038504413,0.00055225415,0.0009159862,0.9733958,0.00004000278,0.0061443215,0.015111523],"study_design_scores_gemma":[0.0010180203,0.000503846,0.00017673094,0.000056453955,0.000053360465,0.000039641287,0.0004564645,0.023472134,0.9655963,0.000022585953,0.008291016,0.00031341045],"about_ca_topic_score_codex":0.000011065406,"about_ca_topic_score_gemma":0.000023962404,"teacher_disagreement_score":0.08697126,"about_ca_system_score_codex":0.000010041812,"about_ca_system_score_gemma":0.00007439928,"threshold_uncertainty_score":0.5298826},"labels":[],"label_agreement":null},{"id":"W4382631507","doi":"10.1093/bioinformatics/btad250","title":"PlasBin-flow: a flow-based MILP algorithm for plasmid contigs binning","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Vedecká Grantová Agentúra MŠVVaŠ SR a SAV; European Commission; Genome Canada","keywords":"Contig; Plasmid; Genetics; Biology; Computer science; Computational biology; Sequence assembly; Genome; Algorithm; DNA; Gene","score_opus":0.01611820032584436,"score_gpt":0.24090628305546335,"score_spread":0.224788082729619,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382631507","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5553096,0.0007595489,0.4329059,0.0006826477,0.0021373155,0.001829551,0.0034392595,0.00013445927,0.0028017499],"genre_scores_gemma":[0.10451186,0.00074286107,0.882064,0.002909646,0.0011510535,0.00053928635,0.0050404617,0.0001587178,0.002882135],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99896735,0.000009965991,0.00033624313,0.00017736558,0.00012464703,0.00038441227],"domain_scores_gemma":[0.9993841,0.000045915054,0.00010509969,0.0002739675,0.000106498774,0.00008440494],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020182793,0.00019767118,0.0001948674,0.00008382099,0.00017578718,0.0000404953,0.00018748778,0.00014090128,0.00000552887],"category_scores_gemma":[0.00007362856,0.00018606303,0.00014658943,0.00014329802,0.00006395663,0.0000015785478,0.00011104721,0.00004457902,0.00004966875],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028726712,0.00018289563,0.0022091812,0.0007024041,0.00094397774,0.000010402951,0.0017696589,0.016960185,0.24467336,0.00013952018,0.29977152,0.43234965],"study_design_scores_gemma":[0.0012882529,0.00028579304,0.0004179613,0.000019201478,0.000028770211,0.0000031486672,0.00022560338,0.62798893,0.030970521,0.00003846771,0.3384374,0.00029591564],"about_ca_topic_score_codex":0.0000022420236,"about_ca_topic_score_gemma":0.000007787774,"teacher_disagreement_score":0.6110288,"about_ca_system_score_codex":0.000012288202,"about_ca_system_score_gemma":0.00009556128,"threshold_uncertainty_score":0.75874305},"labels":[],"label_agreement":null},{"id":"W4382631688","doi":"10.1093/bioinformatics/btad249","title":"PPAD: a deep learning architecture to predict progression of Alzheimer’s disease","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; National Institute of General Medical Sciences; Northern California Institute for Research and Education; University of North Texas; Pfizer; Novartis Pharmaceuticals Corporation; University of Southern California; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; BioClinica; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; National Institute on Aging; Alzheimer's Association","keywords":"Autoencoder; Dementia; Recurrent neural network; Disease; Alzheimer's disease; Neuroimaging; Artificial intelligence; Deep learning; Cognitive impairment; Electronic health record; Medicine; Computer science; Machine learning; Gerontology; Artificial neural network; Psychiatry; Health care; Internal medicine","score_opus":0.022478761562064423,"score_gpt":0.31194538166756747,"score_spread":0.28946662010550306,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382631688","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07169878,0.0005975029,0.90960824,0.008729922,0.0010201696,0.0019445319,0.000024153589,0.0030221667,0.0033545266],"genre_scores_gemma":[0.67455983,0.00003121921,0.32439902,0.00057455996,0.00012132347,0.00007661732,0.00005404983,0.000030199584,0.00015318932],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984337,0.00007918651,0.0004279311,0.00016677791,0.0005329319,0.00035946642],"domain_scores_gemma":[0.9987467,0.00010777716,0.00020098638,0.00052737974,0.00008968899,0.00032748302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043031728,0.0001419259,0.00017532875,0.00030628714,0.00014563154,0.000065531545,0.00065696187,0.000056850335,0.000008831934],"category_scores_gemma":[0.00048399222,0.00011695136,0.00006697263,0.00097578403,0.000029214716,0.00021176576,0.0005529089,0.00028823456,0.00019935031],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023590525,0.000028244529,0.021006154,0.00062358694,0.00002500252,0.000018294857,0.013043534,0.056561377,0.000021066679,0.0021970754,0.0016122784,0.9048398],"study_design_scores_gemma":[0.00014976657,0.00023154022,0.03448543,0.00019942336,0.000010558857,0.000005189156,0.00011494136,0.9545472,0.000070829614,0.00029480553,0.009727485,0.00016280214],"about_ca_topic_score_codex":0.000008619788,"about_ca_topic_score_gemma":0.000002014769,"teacher_disagreement_score":0.904677,"about_ca_system_score_codex":0.000018170334,"about_ca_system_score_gemma":0.000100607016,"threshold_uncertainty_score":0.4769138},"labels":[],"label_agreement":null},{"id":"W4382631698","doi":"10.1093/bioinformatics/btad266","title":"Reference panel-guided super-resolution inference of Hi-C data","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Fonds de recherche du Québec – Nature et technologies; Institut de Valorisation des Données","keywords":"Computer science; Inference; Focus (optics); Data mining; DNA sequencing; Chromatin; Task (project management); Computational biology; Resolution (logic); Genome; Artificial intelligence; DNA; Biology; Gene; Genetics; Physics","score_opus":0.08873438610513366,"score_gpt":0.3032298105770997,"score_spread":0.214495424471966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382631698","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9897264,0.0000666165,0.005718352,0.00007721383,0.00015099985,0.00016015503,0.0005116036,0.000038870352,0.0035497602],"genre_scores_gemma":[0.98504907,0.00058937666,0.009584407,0.00007049764,0.000049207174,0.000004907352,0.0042747273,0.000013266599,0.0003645266],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99908453,0.000014598499,0.0003931875,0.000149233,0.0001468709,0.00021160378],"domain_scores_gemma":[0.99876755,0.000016432517,0.00014475759,0.0009222748,0.00009510918,0.000053896187],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025074297,0.00011615535,0.00013079871,0.000055889195,0.000051623203,0.000021043776,0.0005800488,0.00013011578,0.000012258782],"category_scores_gemma":[0.00018334723,0.000109532804,0.000031193635,0.00016370138,0.000065551074,0.000011508541,0.0006116822,0.000059805003,0.00007825655],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001461073,0.00034218776,0.017870246,0.0019376465,0.00044346007,0.000009630326,0.0021387402,0.01060837,0.7231525,0.009497979,0.18246743,0.051385704],"study_design_scores_gemma":[0.0011947475,0.00043338956,0.018180717,0.00009522344,0.000063209096,0.000029857449,0.0011204258,0.8646798,0.027065177,0.00058596075,0.08578468,0.0007668017],"about_ca_topic_score_codex":0.00002322875,"about_ca_topic_score_gemma":0.00002572848,"teacher_disagreement_score":0.85407144,"about_ca_system_score_codex":0.000009490203,"about_ca_system_score_gemma":0.00011433604,"threshold_uncertainty_score":0.44666183},"labels":[],"label_agreement":null},{"id":"W4382632303","doi":"10.1093/bioinformatics/btad242","title":"SpatialSort: a Bayesian model for clustering and cell population annotation of spatial proteomics data","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Terry Fox Research Institute; BC Cancer Agency","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Cancer Research UK; BC Cancer Foundation; Terry Fox Research Institute; Michael Smith Health Research BC; V Foundation for Cancer Research","keywords":"Cluster analysis; Computer science; Annotation; Bayesian probability; Data mining; Spatial analysis; Source code; Profiling (computer programming); Population; Context (archaeology); Consensus clustering; Artificial intelligence; Machine learning; Fuzzy clustering; CURE data clustering algorithm; Geography; Mathematics; Statistics","score_opus":0.037640320235041845,"score_gpt":0.2650842334166531,"score_spread":0.22744391318161125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382632303","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33322993,0.00001571616,0.6659092,0.000024264798,0.00007929726,0.00039037975,0.00027950166,0.000016352064,0.000055396904],"genre_scores_gemma":[0.9139072,0.00007518419,0.082683496,0.00003942168,0.00007808713,0.000015965308,0.0031121587,0.000018459594,0.000070032576],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99924797,0.000008959604,0.00035047112,0.00014706615,0.00009528722,0.00015023065],"domain_scores_gemma":[0.99941784,0.000011305365,0.00015507096,0.0003177993,0.000056543548,0.00004142159],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020920897,0.000107908476,0.0001296759,0.000059751357,0.000064512154,0.000024151963,0.00015565807,0.0001145239,6.361231e-7],"category_scores_gemma":[0.000057005178,0.00010873473,0.000032647316,0.00006108061,0.00002651074,0.000019512694,0.00011465056,0.000033712953,9.038133e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00083636574,0.0001913023,0.018041223,0.0036232737,0.000112067355,7.644374e-7,0.0030863804,0.0875159,0.8052537,0.00012612065,0.0018717019,0.0793412],"study_design_scores_gemma":[0.0005817936,0.000113371454,0.0011123628,0.000017140925,0.000020824331,0.0000010868753,0.000060286187,0.9771473,0.020604674,0.00007939283,0.00013457384,0.00012722742],"about_ca_topic_score_codex":0.00007586827,"about_ca_topic_score_gemma":0.00019521103,"teacher_disagreement_score":0.8896314,"about_ca_system_score_codex":0.0000061132546,"about_ca_system_score_gemma":0.00004087868,"threshold_uncertainty_score":0.44340733},"labels":[],"label_agreement":null},{"id":"W4383186166","doi":"10.1093/bioinformatics/btad423","title":"MEDIPIPE: an automated and comprehensive pipeline for cfMeDIP-seq data quality control and analysis","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Epigenetics and DNA Methylation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research; University of Toronto; Princess Margaret Cancer Centre; University Health Network","funders":"Ontario Institute for Cancer Research; Cancer Research Institute","keywords":"Computer science; MIT License; Pipeline (software); Software; Bioconductor; Data mining; Source code; Operating system; Biology","score_opus":0.05855120257903918,"score_gpt":0.37471489919629397,"score_spread":0.3161636966172548,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383186166","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8966626,0.0010964634,0.09936129,0.0003085872,0.00013105842,0.0004908448,0.0017373575,0.0001323151,0.000079486505],"genre_scores_gemma":[0.96830374,0.0013339444,0.015962878,0.00031960444,0.00015998214,0.00001932781,0.013786145,0.000018930681,0.000095437914],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99902576,0.00004736407,0.00038581065,0.0002226641,0.0001294587,0.00018893574],"domain_scores_gemma":[0.99894875,0.00009619339,0.00014995843,0.00053229264,0.0001487737,0.00012403315],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057773944,0.00013081415,0.00023415017,0.00010481553,0.000101465535,0.0000537049,0.00016109408,0.00013308247,0.00000171499],"category_scores_gemma":[0.00026916456,0.00011690247,0.00003776131,0.00022327316,0.00008210168,0.000016328442,0.00016130658,0.000037464055,0.0000023162588],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010922038,0.0003588661,0.08775164,0.002174204,0.004802233,0.000006636135,0.0035542287,0.0042258836,0.5614274,0.0008676334,0.033407535,0.30033153],"study_design_scores_gemma":[0.0012111757,0.0001392179,0.03559042,0.0000047043022,0.00027148865,9.3822877e-7,0.0003409102,0.94521075,0.002863051,0.00008573913,0.014079844,0.00020175184],"about_ca_topic_score_codex":0.00001754826,"about_ca_topic_score_gemma":0.00005787636,"teacher_disagreement_score":0.94098485,"about_ca_system_score_codex":0.0000038727776,"about_ca_system_score_gemma":0.000032752818,"threshold_uncertainty_score":0.47671443},"labels":[],"label_agreement":null},{"id":"W4385237450","doi":"10.1093/bioinformatics/btad457","title":"LegNet: a best-in-class deep learning model for short DNA regulatory regions","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Ministry of Science and Higher Education of the Russian Federation; Russian Science Foundation","keywords":"Computer science; Gene regulatory network; Python (programming language); Computational biology; Scripting language; Deep learning; Artificial intelligence; Gene; Data mining; Gene expression; Biology; Genetics; Programming language","score_opus":0.0159666890867824,"score_gpt":0.2420830472253247,"score_spread":0.2261163581385423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385237450","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9345113,0.000110541325,0.0618359,0.00012302701,0.00013380483,0.00041777405,0.000038406975,0.000055083507,0.0027741813],"genre_scores_gemma":[0.9797698,0.00036170002,0.015524221,0.00015830647,0.000094356015,0.000080892816,0.0006597214,0.000045882305,0.0033051027],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999025,0.000009798191,0.00035069874,0.00015903111,0.000109164735,0.00034634682],"domain_scores_gemma":[0.99945956,0.000014878795,0.000076848315,0.00031819966,0.00005641121,0.00007410177],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022839522,0.00015322337,0.00014986399,0.000098056014,0.000113924085,0.000032826443,0.00019797092,0.00018379273,0.0000015604114],"category_scores_gemma":[0.000063502506,0.000160265,0.000106252395,0.00013851073,0.000044863318,0.000007714258,0.00012236228,0.000091614245,0.000025876814],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016374339,0.0002307543,0.004313666,0.000907782,0.00023996999,0.0000094758825,0.0045265905,0.8162229,0.0990476,0.008758665,0.018451078,0.047127772],"study_design_scores_gemma":[0.00032501484,0.00011000642,0.00032722487,0.000017793285,0.000013492669,0.0000061139417,0.0006379855,0.9892098,0.00096094003,0.00038385566,0.007792438,0.00021538312],"about_ca_topic_score_codex":0.0000018536741,"about_ca_topic_score_gemma":0.00006928837,"teacher_disagreement_score":0.17298685,"about_ca_system_score_codex":0.000030981202,"about_ca_system_score_gemma":0.00008095184,"threshold_uncertainty_score":0.6535417},"labels":[],"label_agreement":null},{"id":"W4385453913","doi":"10.1093/bioinformatics/btad477","title":"<i>USNAP</i>: fast unique dense region detection and its application to lung cancer","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; Discovery Centre; University Health Network","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Scalability; Computer science; Time complexity; Graph; Theoretical computer science; Dynamic programming; Algorithm","score_opus":0.008048395387785028,"score_gpt":0.24074019103440478,"score_spread":0.23269179564661974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385453913","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66267663,0.0006505015,0.33210778,0.0007312796,0.00043425616,0.001346878,0.000054954166,0.00014876905,0.0018489317],"genre_scores_gemma":[0.9956913,0.001180009,0.0010508182,0.00092581875,0.00022742162,0.00014158252,0.00012423626,0.000023131854,0.00063567073],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992463,0.000010664866,0.00027784338,0.00013291244,0.000089273686,0.00024300764],"domain_scores_gemma":[0.9994573,0.00000700518,0.00010746033,0.00023050583,0.00007457661,0.00012316612],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015897235,0.00013876968,0.0001059207,0.00008309976,0.00012326006,0.000038707964,0.0001136868,0.00016465127,0.0000018639322],"category_scores_gemma":[0.000020049361,0.00013385143,0.000036422814,0.0002459663,0.000019756942,0.000012973453,0.00014146278,0.00007541388,0.000042388285],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030885078,0.000053915817,0.0014970064,0.0010892274,0.0002506486,0.0000046132704,0.0038603512,0.011101372,0.25375158,0.0018943981,0.05019603,0.675992],"study_design_scores_gemma":[0.0007378393,0.00023668549,0.0017477578,0.00007206788,0.00005268989,0.000055484856,0.00044669755,0.79425794,0.057733364,0.0001417037,0.14387196,0.00064579124],"about_ca_topic_score_codex":0.000009832746,"about_ca_topic_score_gemma":0.00005281649,"teacher_disagreement_score":0.7831566,"about_ca_system_score_codex":0.000023011495,"about_ca_system_score_gemma":0.000035415913,"threshold_uncertainty_score":0.54583025},"labels":[],"label_agreement":null},{"id":"W4385897776","doi":"10.1093/bioinformatics/btad508","title":"<i>i</i>DeLUCS: a deep learning interactive tool for alignment-free clustering of DNA sequences","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Cluster analysis; Computer science; Metagenomics; DNA sequencing; Data mining; Artificial intelligence; Scalability; Genomics; Software; Set (abstract data type); Genome; Unsupervised learning; Identifier; Computational biology; Pattern recognition (psychology); Machine learning; DNA; Biology; Database; Genetics; Gene","score_opus":0.01482127274179808,"score_gpt":0.25078210115095595,"score_spread":0.23596082840915786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385897776","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97811717,0.00026197394,0.019317396,0.000072825635,0.0002729392,0.00037608438,0.00008698031,0.000015404294,0.0014792385],"genre_scores_gemma":[0.98219615,0.0005617416,0.016626377,0.0000832818,0.00009897377,0.00005480687,0.000097462056,0.00001639251,0.00026478266],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99930125,0.000011502923,0.00029465917,0.00010651506,0.00008734933,0.0001987123],"domain_scores_gemma":[0.99948156,0.000040052084,0.00015569897,0.000217859,0.00007779973,0.000027038604],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000178924,0.00011287148,0.00014201007,0.000046092333,0.00006962125,0.000017911065,0.00020445258,0.000062449355,0.0000025920174],"category_scores_gemma":[0.00017800112,0.0001038158,0.00009000118,0.00007869912,0.00004836131,0.0000024393837,0.00028140284,0.000035518206,0.0000065466506],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002886033,0.000057297355,0.0035069913,0.0007606338,0.0006630065,0.0000017278531,0.009523402,0.016656663,0.8931152,0.00027431373,0.0048188763,0.07033325],"study_design_scores_gemma":[0.004073843,0.0027512584,0.005138761,0.00021319019,0.00019009743,0.000028131293,0.02434524,0.22569707,0.5699905,0.0013898456,0.16484976,0.0013323022],"about_ca_topic_score_codex":0.0000034280579,"about_ca_topic_score_gemma":0.000009597163,"teacher_disagreement_score":0.3231247,"about_ca_system_score_codex":0.000009196206,"about_ca_system_score_gemma":0.000018736606,"threshold_uncertainty_score":0.42334855},"labels":[],"label_agreement":null},{"id":"W4385898657","doi":"10.1093/bioinformatics/btad498","title":"Adjusting for gene-specific covariates to improve RNA-seq analysis","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Food and Agriculture; Genome Alberta; Genome Canada; U.S. Department of Agriculture","keywords":"Covariate; Estimator; Null (SQL); Type I and type II errors; Context (archaeology); Computer science; Null hypothesis; Variable (mathematics); Null model; Statistics; Multiple comparisons problem; Data mining; Mathematics; Biology","score_opus":0.026445728465342967,"score_gpt":0.28277570739909486,"score_spread":0.25632997893375187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385898657","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25176606,0.00025631284,0.74122876,0.0007948887,0.0009983906,0.0010712397,0.00042885533,0.00017166429,0.0032838364],"genre_scores_gemma":[0.8782928,0.00047534434,0.11008031,0.0012973992,0.0008304715,0.00046707934,0.003075431,0.000056105004,0.0054250914],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99916744,0.0000093618555,0.0002932436,0.00018002764,0.00011889209,0.00023103906],"domain_scores_gemma":[0.9992923,0.000015018362,0.00011109179,0.00036734034,0.000116875206,0.000097369266],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021804482,0.0001118997,0.00012891532,0.00018931346,0.000106536965,0.000050017075,0.00017868844,0.00009838451,0.000011879217],"category_scores_gemma":[0.000085939166,0.000102615086,0.00013209583,0.00065284135,0.000014620741,0.0000053811063,0.00008682654,0.00003165945,0.00007566256],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052718602,0.000014552989,0.00020244883,0.000047810772,0.00016110658,1.90313e-7,0.00032373617,0.0022828989,0.9244694,0.00026117652,0.047189478,0.02499447],"study_design_scores_gemma":[0.00068826776,0.00022247565,0.0024608336,0.000011665633,0.00015683661,0.0000010615485,0.0009891139,0.045988802,0.5942887,0.00010437257,0.35468283,0.0004050393],"about_ca_topic_score_codex":0.0000028029658,"about_ca_topic_score_gemma":0.0000036790827,"teacher_disagreement_score":0.63114846,"about_ca_system_score_codex":0.000016014006,"about_ca_system_score_gemma":0.00004385488,"threshold_uncertainty_score":0.41845217},"labels":[],"label_agreement":null},{"id":"W4386084463","doi":"10.1093/bioinformatics/btad523","title":"metGWAS 1.0: an R workflow for network-driven over-representation analysis between independent metabolomic and meta-genome-wide association studies","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto General Hospital; University of Toronto; Canadian Institute for Advanced Research","funders":"National Heart, Lung, and Blood Institute; Banting and Best Diabetes Centre, University of Toronto; Natural Sciences and Engineering Research Council of Canada; Diabetes Canada; Canadian Institutes of Health Research; U.S. Department of Veterans Affairs","keywords":"Metabolomics; Genome-wide association study; Computational biology; Workflow; Genetic association; Biology; Single-nucleotide polymorphism; Genomics; Computer science; Bioinformatics; Genome; Genetics; Gene; Database; Genotype","score_opus":0.049196344753754735,"score_gpt":0.3230295530492259,"score_spread":0.2738332082954712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386084463","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9769853,0.004637675,0.015825232,0.00078442856,0.0002585365,0.0008608196,0.0004396127,0.00008158815,0.00012685376],"genre_scores_gemma":[0.9440792,0.010091658,0.039072927,0.0008858791,0.0007279716,0.000340071,0.0032894558,0.00005311832,0.0014596786],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984007,0.00007814509,0.0005430589,0.00029698326,0.00026725334,0.0004138865],"domain_scores_gemma":[0.9986523,0.00031002623,0.00041355865,0.00033037554,0.00019747361,0.00009631433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00096368033,0.00024555452,0.00078773056,0.0002608728,0.00024578528,0.0000838016,0.00016728217,0.00016411037,0.00000895106],"category_scores_gemma":[0.00066322787,0.00020794653,0.00033306688,0.0007869353,0.000042069558,0.000032530497,0.00023336035,0.00007836598,0.0000064207557],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023754426,0.00012479225,0.69675726,0.000351875,0.21908282,0.0000023948714,0.0026156665,0.024761692,0.0076086256,0.0009017774,0.04006832,0.0074872063],"study_design_scores_gemma":[0.0029528886,0.0008550209,0.7634515,0.00000718316,0.09054742,0.0000010883163,0.0032772834,0.020111633,0.007031854,0.0039220834,0.10624243,0.0015995796],"about_ca_topic_score_codex":0.000010073093,"about_ca_topic_score_gemma":0.00011676467,"teacher_disagreement_score":0.1285354,"about_ca_system_score_codex":0.000042173015,"about_ca_system_score_gemma":0.00002675199,"threshold_uncertainty_score":0.84798133},"labels":[],"label_agreement":null},{"id":"W4386554491","doi":"10.1093/bioinformatics/btad552","title":"μ- PBWT: a lightweight r-indexing of the PBWT for storing and querying UK Biobank data","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"National Human Genome Research Institute; European Commission; Natural Sciences and Engineering Research Council of Canada; Japan Society for the Promotion of Science; National Institutes of Health; National Science Foundation","keywords":"Computer science; Biobank; Search engine indexing; Leverage (statistics); Set (abstract data type); Data structure; Haplotype; Data mining; Index (typography); Computation; Theoretical computer science; Information retrieval; Algorithm; Artificial intelligence; Bioinformatics; Biology; Genotype; Genetics","score_opus":0.046232991827891444,"score_gpt":0.2960578176711589,"score_spread":0.24982482584326746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386554491","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97963315,0.0005178176,0.016507464,0.0008015859,0.00059909583,0.0004898074,0.0003314738,0.000026465015,0.0010931639],"genre_scores_gemma":[0.98136765,0.00036030638,0.017109474,0.00019306807,0.00017158798,0.00001801734,0.0003062141,0.000014305412,0.0004593548],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99924153,0.00002229422,0.00031864332,0.00013061053,0.0000755723,0.00021132942],"domain_scores_gemma":[0.9991334,0.00006418399,0.0001947724,0.00051948044,0.00005379613,0.000034337467],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055204704,0.00009138968,0.00014501945,0.000038411985,0.00014380594,0.0000135513665,0.00030973245,0.00011943439,0.0000013813725],"category_scores_gemma":[0.0004948369,0.00006660442,0.000049061437,0.00012721516,0.000053641776,0.0000057986504,0.00046885898,0.00004585575,0.0000027924125],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001486973,0.00012587919,0.5415142,0.0018015559,0.0011030308,0.0000014491484,0.0050524515,0.0019356662,0.15309498,0.007724059,0.19593899,0.09155904],"study_design_scores_gemma":[0.0030785615,0.00055642246,0.18459381,0.00027483932,0.00029170726,0.00003772759,0.0040429854,0.2646189,0.04986459,0.0020814603,0.4893728,0.0011862012],"about_ca_topic_score_codex":0.000011535045,"about_ca_topic_score_gemma":0.000021833095,"teacher_disagreement_score":0.3569204,"about_ca_system_score_codex":0.000008429649,"about_ca_system_score_gemma":0.000055620534,"threshold_uncertainty_score":0.27160496},"labels":[],"label_agreement":null},{"id":"W4386979606","doi":"10.1093/bioinformatics/btad590","title":"Using a novel structure/function approach to select diverse swine major histocompatibility complex 1 alleles to predict epitopes for vaccine development","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Animal Virus Infections Studies","field":"Agricultural and Biological Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Alliance de recherche numérique du Canada; Innovation Saskatchewan; Ministry of Agriculture - Saskatchewan; University of Saskatchewan","keywords":"Epitope; Biology; Major histocompatibility complex; Docking (animal); Computational biology; Homology modeling; Allele; Human leukocyte antigen; Genetics; Homology (biology); Amino acid; Antigen; Gene; Biochemistry; Medicine","score_opus":0.13127981398610575,"score_gpt":0.28298871093904376,"score_spread":0.15170889695293802,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386979606","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9614827,0.0000057066263,0.035669684,0.00019033375,0.00013014795,0.001691738,0.00028763228,0.00024448725,0.00029757508],"genre_scores_gemma":[0.79162854,0.0000015511301,0.20733263,0.00032899203,0.00019645576,0.000117526186,0.00029790917,0.0000023983248,0.00009398625],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9988703,0.00001382993,0.00038393226,0.00020173061,0.000207666,0.00032254923],"domain_scores_gemma":[0.9994844,0.00008167309,0.0000946436,0.00006691714,0.00016155107,0.00011076639],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026750998,0.00017946014,0.00023615372,0.000051528365,0.00063415687,0.00004965284,0.00016927296,0.00005799022,0.00004115968],"category_scores_gemma":[0.00012448277,0.00007990502,0.000058880294,0.0006903403,0.000016823085,0.00012737684,0.00022243183,0.00005544241,0.000042238567],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012030802,0.0013781809,0.08100286,0.0010100562,0.000893754,6.185659e-7,0.013469262,0.014547942,0.5473623,0.0013832604,0.09395914,0.24378952],"study_design_scores_gemma":[0.0005983157,0.00093121844,0.8200573,0.000039659826,0.00007862457,0.000005309072,0.0026790742,0.04899365,0.0018414054,0.00010412384,0.12407371,0.0005976144],"about_ca_topic_score_codex":0.00013343904,"about_ca_topic_score_gemma":0.00071080006,"teacher_disagreement_score":0.73905444,"about_ca_system_score_codex":0.0001604907,"about_ca_system_score_gemma":0.000017962595,"threshold_uncertainty_score":0.4877486},"labels":[],"label_agreement":null},{"id":"W4387300238","doi":"10.1093/bioinformatics/btad608","title":"Surfaces: a software to quantify and visualize interactions within and between proteins and ligands","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Surface Chemistry and Catalysis","field":"Engineering","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada; Genome Canada","keywords":"Visualization; Computer science; Scripting language; Documentation; Software; Software visualization; Computational science; Surface (topology); Computer graphics (images); Data mining; Programming language; Software development; Component-based software engineering; Mathematics","score_opus":0.02404851307661481,"score_gpt":0.267226260133734,"score_spread":0.2431777470571192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387300238","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9973798,0.00007690091,0.001787631,0.00005949655,0.000045718363,0.0001262295,0.000057541358,0.0003067933,0.00015990701],"genre_scores_gemma":[0.9933966,0.00010048239,0.0062259184,0.000019596293,0.000020847514,0.000015674274,0.000047293797,0.000015160515,0.00015841905],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995102,0.0000022676172,0.00020136064,0.0000728764,0.00007896724,0.00013427726],"domain_scores_gemma":[0.9996506,0.00007959847,0.000025385181,0.00011080751,0.000016792226,0.000116802345],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011382684,0.000110950496,0.0001431612,0.00006740829,0.00007580037,0.00009039187,0.000042901884,0.00005379454,0.0000047975013],"category_scores_gemma":[0.00007601006,0.00010463458,0.0000140457305,0.0002478225,0.00002882535,0.00020405048,0.00006608739,0.00008550214,0.000024847881],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011394635,0.0001036219,0.36872327,0.020100513,0.0023440067,0.00004545719,0.22898038,0.01900041,0.17705823,0.00029751364,0.022867812,0.16036484],"study_design_scores_gemma":[0.0018770783,0.00026943706,0.09857193,0.0010716988,0.00040699297,0.00010280906,0.026046578,0.2814478,0.56736535,0.00038645332,0.02020126,0.0022525932],"about_ca_topic_score_codex":0.0000064748847,"about_ca_topic_score_gemma":0.000008046195,"teacher_disagreement_score":0.39030713,"about_ca_system_score_codex":0.000010402173,"about_ca_system_score_gemma":0.000006438172,"threshold_uncertainty_score":0.42668742},"labels":[],"label_agreement":null},{"id":"W4387359355","doi":"10.1093/bioinformatics/btag207","title":"Segzoo: a turnkey system that summarizes genome annotations","year":2023,"lang":"en","type":"preprint","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Python (programming language); Annotation; Turnkey; Upload; Visualization; MIT License; JSON; Genome; Source code; Unix; Download; Software; Data mining; Operating system; Database; Artificial intelligence; Biology","score_opus":0.03593523873103464,"score_gpt":0.2498236841964263,"score_spread":0.21388844546539168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387359355","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94480205,0.0065031936,0.016532777,0.00062377116,0.0058324984,0.0026255215,0.0051600086,0.00025203187,0.01766817],"genre_scores_gemma":[0.9719061,0.0024591738,0.019231714,0.00025120715,0.000780795,0.00023628361,0.0026933234,0.00011093723,0.0023304452],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985366,0.000031243337,0.0005187795,0.00032382115,0.00021727537,0.00037231593],"domain_scores_gemma":[0.9985701,0.000022729479,0.00034141057,0.000801546,0.00015528519,0.00010891649],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00022888609,0.0003754944,0.00036368181,0.00011346191,0.00017550908,0.00012721278,0.00046998527,0.00041891015,0.00000377759],"category_scores_gemma":[0.0000441171,0.00035701194,0.00023719651,0.00007200986,0.00008477628,0.0000011622853,0.0013609859,0.00021486948,0.00016968908],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00086778606,0.0010381548,0.064837225,0.049558613,0.023166431,0.00019427034,0.042737506,0.12207109,0.37913603,0.009871975,0.27741623,0.029104695],"study_design_scores_gemma":[0.0046362723,0.0013792715,0.14235716,0.0014729196,0.0017699691,0.0002179855,0.028716393,0.051215738,0.028601678,0.0022505305,0.72846097,0.008921096],"about_ca_topic_score_codex":0.00004277924,"about_ca_topic_score_gemma":0.00005076521,"teacher_disagreement_score":0.45104474,"about_ca_system_score_codex":0.00005015441,"about_ca_system_score_gemma":0.00019472706,"threshold_uncertainty_score":0.9998882},"labels":[],"label_agreement":null},{"id":"W4387363064","doi":"10.1093/bioinformatics/btad613","title":"SBILib: a handle for protein modeling and engineering","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Children's Hospital; University of British Columbia","funders":"Agencia Estatal de Investigación; Ministerio de Ciencia e Innovación","keywords":"Python (programming language); Computer science; Parsing; Structural bioinformatics; File format; Programming language; Simple (philosophy); Computational biology; Software engineering; Protein structure; Chemistry; Biology; Biochemistry","score_opus":0.008994534504336108,"score_gpt":0.2203856039355147,"score_spread":0.2113910694311786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387363064","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7880168,0.00010762793,0.21111426,0.000049195583,0.000058712507,0.00042885967,0.000029567993,0.000057349538,0.00013762659],"genre_scores_gemma":[0.93391365,0.00004598099,0.06527254,0.00007109676,0.00011906468,0.00010054905,0.00017216272,0.000022286313,0.0002827007],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99957746,0.0000018968034,0.00013386874,0.00007854196,0.000048913378,0.00015932032],"domain_scores_gemma":[0.9997724,0.0000034609734,0.000025344765,0.00012900132,0.00002867361,0.000041078918],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009353436,0.00008125134,0.000070077454,0.000036471145,0.00004732232,0.000025089326,0.000061172934,0.000082998886,4.1699863e-7],"category_scores_gemma":[0.00007730436,0.000073830655,0.00003149332,0.00005938384,0.0000110956435,0.000005221097,0.00006636832,0.00003044026,0.0000032015942],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015103741,0.000022146958,0.00020141732,0.0015369268,0.00014596057,0.000002080831,0.0010067066,0.042035982,0.919149,0.0049372804,0.0018432345,0.028968256],"study_design_scores_gemma":[0.0003030005,0.000087124936,0.000020981002,0.000017180486,0.0000056910176,0.0000049147275,0.000060052407,0.9805748,0.012902809,0.00032710092,0.005568061,0.00012832],"about_ca_topic_score_codex":0.0000012718789,"about_ca_topic_score_gemma":0.0000017048247,"teacher_disagreement_score":0.9385388,"about_ca_system_score_codex":0.0000037620187,"about_ca_system_score_gemma":0.000021066453,"threshold_uncertainty_score":0.3010727},"labels":[],"label_agreement":null},{"id":"W4387796811","doi":"10.1093/bioinformatics/btad639","title":"Privacy-preserving federated genome-wide association studies via dynamic sampling","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"U.S. National Library of Medicine; National Institute of General Medical Sciences; University of Texas Health Science Center at Houston; Cisco Systems; National Science Foundation; National Institutes of Health; Cancer Prevention and Research Institute of Texas","keywords":"Computer science; Robustness (evolution); Data mining; Source code; Genome-wide association study; Data sharing; Single-nucleotide polymorphism","score_opus":0.05433862897628468,"score_gpt":0.30878861326997387,"score_spread":0.2544499842936892,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387796811","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054609418,0.00033899132,0.8976425,0.038882736,0.0010986209,0.00050313724,0.000036917052,0.0061461437,0.00074157165],"genre_scores_gemma":[0.07736475,0.0011661274,0.919663,0.0010669382,0.000054041655,0.00006269161,0.00018210274,0.00004079551,0.00039955226],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99754864,0.000051337858,0.0007052131,0.00031770667,0.00064694847,0.000730137],"domain_scores_gemma":[0.9929379,0.0015213654,0.0004866411,0.004697712,0.0002792914,0.00007705825],"candidate_categories":["metaresearch","metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0013007841,0.00025699622,0.00032956342,0.00040464266,0.00048628496,0.00052145123,0.01580734,0.00020408022,0.0000062520667],"category_scores_gemma":[0.08450305,0.00024688148,0.000075789605,0.0017957991,0.000047430225,0.0019004241,0.080796316,0.00032808652,0.0006696228],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012660019,0.00010128408,0.01813295,0.0012164525,0.0009567967,0.000060661725,0.006876334,0.001499241,0.001348361,0.0005742568,0.89461154,0.074609436],"study_design_scores_gemma":[0.00023203752,0.000033606877,0.005546517,0.00007315692,0.00001147795,0.0000045153242,0.0005342778,0.9372542,0.00029633543,0.051142566,0.004535736,0.00033559438],"about_ca_topic_score_codex":0.000008269573,"about_ca_topic_score_gemma":0.000010889069,"teacher_disagreement_score":0.93575495,"about_ca_system_score_codex":0.0006766705,"about_ca_system_score_gemma":0.000080570266,"threshold_uncertainty_score":0.99999833},"labels":[],"label_agreement":null},{"id":"W4388556708","doi":"10.1093/bioinformatics/btad673","title":"hipFG: high-throughput harmonization and integration pipeline for functional genomics data","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Weston Brain Institute; National Institute on Aging; Alzheimer’s Research UK; Alzheimer's Association","keywords":"Pipeline (software); Harmonization; Throughput; Computer science; Genomics; Functional genomics; Data integration; Computational biology; Data mining; Biology; Programming language; Genome; Operating system; Gene; Genetics","score_opus":0.05108167327523701,"score_gpt":0.28346035393168745,"score_spread":0.23237868065645045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388556708","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15898837,0.00009875466,0.8387131,0.00093738234,0.00035950195,0.00029733093,0.0004274919,0.000035218534,0.000142852],"genre_scores_gemma":[0.79893094,0.0015078649,0.14811037,0.0011252204,0.00082705455,0.00006192101,0.047720525,0.000035497782,0.0016806137],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999316,0.000017395323,0.00028802035,0.00016040937,0.000058717615,0.0001594908],"domain_scores_gemma":[0.9993898,0.00004114096,0.00012362296,0.00030382266,0.000103254024,0.000038315666],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004134685,0.00009185017,0.00010276932,0.000044900473,0.000119310746,0.000024819492,0.00012029963,0.00010925317,0.0000044300928],"category_scores_gemma":[0.00043583618,0.00008543156,0.000019969455,0.00009311949,0.00003481197,0.000012030606,0.00017071367,0.000035963156,0.000021990534],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018592949,0.00009311296,0.008482717,0.00016519551,0.00018802744,3.7574785e-7,0.00041927575,0.004809456,0.042456534,0.003183853,0.8014701,0.13854541],"study_design_scores_gemma":[0.0011728592,0.00025919577,0.026106335,0.000008771379,0.000057580284,0.000008690981,0.0005078407,0.8520218,0.0026439496,0.0012439201,0.11567987,0.0002891792],"about_ca_topic_score_codex":0.0000087453345,"about_ca_topic_score_gemma":0.000025669833,"teacher_disagreement_score":0.8472124,"about_ca_system_score_codex":0.000014366329,"about_ca_system_score_gemma":0.00005950199,"threshold_uncertainty_score":0.3483798},"labels":[],"label_agreement":null},{"id":"W4388608496","doi":"10.1093/bioinformatics/btad684","title":"PiDeeL: metabolic pathway-informed deep learning model for survival analysis and pathological classification of gliomas","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Glioma Diagnosis and Treatment","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Bilim Akademisi; Centre National de la Recherche Scientifique","keywords":"Computer science; Recall; Artificial intelligence; Deep learning; Machine learning; Pathological; Index (typography); Concordance; Mechanism (biology); Pathology; Bioinformatics; Medicine; Biology; Psychology; Cognitive psychology","score_opus":0.06304541078609775,"score_gpt":0.3137776443325855,"score_spread":0.2507322335464877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388608496","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9632984,0.00014765898,0.034949355,0.00019334485,0.000039396848,0.00049611187,0.00004477534,0.00012295257,0.0007080249],"genre_scores_gemma":[0.9808732,0.00037056836,0.018159477,0.000034321227,0.000017415097,0.00008729293,0.00038186487,0.000010191704,0.00006565967],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989196,0.00001524562,0.0004987787,0.00011112092,0.00023752147,0.00021770634],"domain_scores_gemma":[0.9991161,0.00021923025,0.00022164636,0.00019645365,0.00013898041,0.00010756864],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034478836,0.0001334396,0.0004599213,0.00046761867,0.00008389546,0.000021187056,0.000049873797,0.00010132793,0.0000062113522],"category_scores_gemma":[0.0003751903,0.00009688101,0.00019927867,0.000901105,0.00005517738,0.00010885576,0.000040110186,0.00006404948,0.000013374357],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005290868,0.0008144836,0.6079556,0.0018088864,0.004101674,0.000037052556,0.013394215,0.016423767,0.007810008,0.032040592,0.0004387463,0.3146459],"study_design_scores_gemma":[0.0010189769,0.0001343923,0.20699552,0.000012518848,0.0007859871,0.0000044071126,0.0008685167,0.7887554,0.00093544216,0.00013385412,0.00027379883,0.00008114096],"about_ca_topic_score_codex":0.0000053929225,"about_ca_topic_score_gemma":0.000018259825,"teacher_disagreement_score":0.77233166,"about_ca_system_score_codex":0.000022723083,"about_ca_system_score_gemma":0.000047245772,"threshold_uncertainty_score":0.3950693},"labels":[],"label_agreement":null},{"id":"W4388706662","doi":"10.1093/bioinformatics/btad679","title":"ReGeNNe: genetic pathway-based deep neural network using canonical correlation regularizer for disease prediction","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; Public Health Ontario; University of Toronto; University Health Network","funders":"","keywords":"Interpretability; Computer science; Artificial intelligence; Correlation; Machine learning; Robustness (evolution); Artificial neural network; Canonical correlation; Generalizability theory; Convolutional neural network; Novelty; Gene; Biology; Mathematics; Genetics; Statistics","score_opus":0.01467302902274496,"score_gpt":0.2301602004368411,"score_spread":0.21548717141409615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388706662","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14033397,0.00040663863,0.8559671,0.00016707895,0.0012919654,0.0011477979,0.00032918638,0.00012974469,0.00022651914],"genre_scores_gemma":[0.874511,0.0000970553,0.113996826,0.0013419965,0.0020789201,0.00016655818,0.007197904,0.0001101582,0.0004995713],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984644,0.00002791683,0.0006063923,0.00019672832,0.0001928894,0.00051165355],"domain_scores_gemma":[0.99893713,0.000033358596,0.00023878146,0.00046034702,0.00011355079,0.00021683052],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031534466,0.00022506762,0.00017603916,0.000069518974,0.0002706069,0.00007026874,0.0001891604,0.00024936194,0.00000702734],"category_scores_gemma":[0.000061320716,0.00021926094,0.0001790312,0.00024526299,0.00007449877,0.000016347052,0.00009948715,0.000105535815,0.00002051695],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029405046,0.000031891548,0.0028223956,0.00022889709,0.00006764764,0.0000025915251,0.00009142829,0.96513546,0.0014241554,0.00030610466,0.012195829,0.017399576],"study_design_scores_gemma":[0.0008092952,0.00015008912,0.0021536434,0.000027472892,0.000059643207,0.0000064637607,0.00004051994,0.9822702,0.00015626344,0.00032956552,0.013744045,0.00025283243],"about_ca_topic_score_codex":0.0000028448683,"about_ca_topic_score_gemma":0.000010958476,"teacher_disagreement_score":0.7419703,"about_ca_system_score_codex":0.000042002095,"about_ca_system_score_gemma":0.00022059493,"threshold_uncertainty_score":0.89412016},"labels":[],"label_agreement":null},{"id":"W4389452578","doi":"10.1093/bioinformatics/btad739","title":"Local Disordered Region Sampling (LDRS) for ensemble modeling of proteins with experimentally undetermined or low confidence prediction segments","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"College of Family Physicians of Canada; Hospital for Sick Children; University of Toronto","funders":"National Institutes of Health; National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Sampling (signal processing); Confidence interval; Computer science; Artificial intelligence; Computational biology; Pattern recognition (psychology); Statistics; Biology; Mathematics; Computer vision","score_opus":0.02603965739753545,"score_gpt":0.269981924206933,"score_spread":0.24394226680939757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389452578","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26270345,0.000020824262,0.73645496,0.000011285073,0.000046166253,0.0006237686,0.000035203277,0.000027339824,0.00007699159],"genre_scores_gemma":[0.9620536,0.000051554394,0.03717601,0.00004210191,0.00003686568,0.00010796371,0.00038571883,0.000019062976,0.00012712175],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99919033,0.0000075462503,0.0003167035,0.00013916289,0.00014329766,0.00020295591],"domain_scores_gemma":[0.99946886,0.000009905006,0.00014379281,0.00023916787,0.00009152218,0.00004677303],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000080115096,0.00013688586,0.00013984906,0.000049728977,0.00008053664,0.000019036554,0.00012347438,0.000119227094,0.0000010095986],"category_scores_gemma":[0.00003537501,0.000105133855,0.00004765673,0.00010744865,0.0000559205,0.000016630482,0.00006381736,0.000039146846,0.0000011294569],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0056750313,0.0002146732,0.0006641298,0.0029090995,0.00042959463,0.0000079690635,0.0033413062,0.20687045,0.7442602,0.00083440455,0.00054756005,0.03424559],"study_design_scores_gemma":[0.0011824722,0.00089814846,0.000022969152,0.00013918124,0.000019969186,0.000018987228,0.0012224907,0.84052056,0.15549861,0.00017923459,0.00012220895,0.00017515023],"about_ca_topic_score_codex":0.000009200181,"about_ca_topic_score_gemma":0.000023422994,"teacher_disagreement_score":0.6993502,"about_ca_system_score_codex":0.000018812076,"about_ca_system_score_gemma":0.000108660126,"threshold_uncertainty_score":0.4287234},"labels":[],"label_agreement":null},{"id":"W4389452890","doi":"10.1093/bioinformatics/btad720","title":"NMJ Analyser: a novel method to quantify neuromuscular junction morphology in zebrafish","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Zebrafish Biomedical Research Applications","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Institut National de la Recherche Scientifique","funders":"Fonds de Recherche du Québec - Santé; Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Fondation Brain Canada","keywords":"Neuromuscular junction; Zebrafish; Postsynaptic potential; Biology; Neuroscience; Neuromuscular transmission; Cell biology; Genetics; Receptor","score_opus":0.03480099033414182,"score_gpt":0.3513222281535572,"score_spread":0.3165212378194154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389452890","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4868722,0.000027684655,0.5072345,0.0033432967,0.00017689841,0.00079543417,0.00007918739,0.000110156085,0.0013606617],"genre_scores_gemma":[0.63689834,0.00025444035,0.34751886,0.008749283,0.0005541301,0.00082912383,0.0029134066,0.00013563312,0.0021467744],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99845564,0.00005611155,0.0004317141,0.00027405942,0.00031709255,0.0004653831],"domain_scores_gemma":[0.99900526,0.000050590646,0.000073195144,0.00053306454,0.00009544992,0.00024245142],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008545707,0.00014936678,0.00018470186,0.00039699106,0.00006507253,0.000038301234,0.00036185654,0.00020065471,0.000027483924],"category_scores_gemma":[0.000709616,0.00014359811,0.00009433704,0.0014454783,0.000063595195,0.000010336985,0.00031482326,0.00016371897,0.00051453616],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057969617,0.00012439759,0.00073007564,0.00006709698,0.000057457353,0.000008458153,0.00016374276,0.0006734443,0.94167393,0.00042421854,0.03974905,0.016270166],"study_design_scores_gemma":[0.002908259,0.001059057,0.11338041,0.000054813358,0.000056595443,0.000109797256,0.00092301005,0.11430602,0.121995,0.00047429916,0.64371717,0.0010155599],"about_ca_topic_score_codex":0.00007107606,"about_ca_topic_score_gemma":0.00006209714,"teacher_disagreement_score":0.8196789,"about_ca_system_score_codex":0.00002947582,"about_ca_system_score_gemma":0.00010963825,"threshold_uncertainty_score":0.6613493},"labels":[],"label_agreement":null},{"id":"W4389453022","doi":"10.1093/bioinformatics/btad726","title":"invMap: a sensitive mapping tool for long noisy reads with inversion structural variants","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Science Basic Research Program of Shaanxi Province; Natural Sciences and Engineering Research Council of Canada; Education Department of Shaanxi Province; China Scholarship Council","keywords":"Chaining; Nanopore sequencing; Computer science; Inversion (geology); Benchmark (surveying); Software; Algorithm; Data mining; Artificial intelligence; Genome; Genetics; Biology; Cartography","score_opus":0.014794007641766662,"score_gpt":0.22759963580796688,"score_spread":0.21280562816620022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389453022","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99273735,0.00003255012,0.006073492,0.00010149628,0.00015349299,0.00035077857,0.00009581986,0.000013772977,0.00044125304],"genre_scores_gemma":[0.9840482,0.00008326561,0.014802141,0.0002985432,0.00014093092,0.000020494155,0.00027525268,0.000017917047,0.0003132885],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9992985,0.000009633826,0.00019867384,0.00013973896,0.00009565004,0.00025779955],"domain_scores_gemma":[0.9995285,0.000020758183,0.00009348448,0.00020184519,0.0001106239,0.0000447338],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012495021,0.00014368715,0.0001331414,0.00005619679,0.00015396498,0.000029623508,0.00009486844,0.00008491389,0.0000012495269],"category_scores_gemma":[0.000049024333,0.00011609372,0.000054202977,0.0001309941,0.000051965635,0.0000027176675,0.00013188903,0.000038935577,0.000015052877],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016057116,0.000083848856,0.09214323,0.0019246669,0.0024349592,0.00005682111,0.018144008,0.0046185176,0.74237335,0.001438463,0.057014246,0.07816215],"study_design_scores_gemma":[0.009727461,0.003441088,0.51066345,0.0003480363,0.00031524955,0.00024699405,0.013605733,0.16069883,0.23071013,0.0009161017,0.06608143,0.0032455318],"about_ca_topic_score_codex":0.00000528943,"about_ca_topic_score_gemma":0.000012861306,"teacher_disagreement_score":0.51166326,"about_ca_system_score_codex":0.000012620649,"about_ca_system_score_gemma":0.000052892945,"threshold_uncertainty_score":0.47341642},"labels":[],"label_agreement":null},{"id":"W4389799054","doi":"10.1093/bioinformatics/btad750","title":"Rarity: discovering rare cell populations from single-cell imaging data","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; Medical Research Council; University of Toronto; King's Health Partners; King's College London; UK Research and Innovation; European Commission; Alan Turing Institute; Wellcome Trust; Francis Crick Institute; Cancer Research UK","keywords":"Computer science; Computational biology; Data mining; Biology","score_opus":0.05919013795234787,"score_gpt":0.259301637795228,"score_spread":0.20011149984288015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389799054","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.934136,0.0005448827,0.052444022,0.00022341879,0.0011823103,0.00031292238,0.001607818,0.00019143791,0.009357225],"genre_scores_gemma":[0.96562994,0.00013380208,0.020561846,0.00032005837,0.00032567716,0.000005252771,0.012290392,0.000043830212,0.0006892174],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988738,0.00001881036,0.00036902155,0.00025395892,0.00017347325,0.00031096826],"domain_scores_gemma":[0.99884707,0.000018599776,0.00011242466,0.0008906678,0.00003699642,0.00009421843],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012584457,0.00018747352,0.00014965732,0.000067386754,0.00016179353,0.00013699871,0.0005283881,0.00010467852,0.000018416284],"category_scores_gemma":[0.000045067827,0.00018770379,0.00007045994,0.00017834287,0.000047220794,0.000043733555,0.00041040246,0.00010655853,0.00011553911],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000077727316,0.00033560608,0.042819273,0.00032996322,0.00006521374,0.00001887637,0.0014405376,0.0013272462,0.87909985,0.000047267265,0.05137854,0.023059921],"study_design_scores_gemma":[0.0035017892,0.00020972792,0.006713253,0.00014202592,0.00020745902,0.000014818731,0.0033765489,0.42995536,0.33532423,0.00041325012,0.21833362,0.0018079362],"about_ca_topic_score_codex":0.00013065025,"about_ca_topic_score_gemma":0.00007703083,"teacher_disagreement_score":0.5437756,"about_ca_system_score_codex":0.000016114449,"about_ca_system_score_gemma":0.000058243513,"threshold_uncertainty_score":0.76543385},"labels":[],"label_agreement":null},{"id":"W4390345333","doi":"10.1093/bioinformatics/btad783","title":"ESQmodel: biologically informed evaluation of 2-D cell segmentation quality in multiplexed tissue images","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia; BC Children's Hospital; BC Cancer Agency","funders":"Canadian Institutes of Health Research; BC Cancer Foundation; Natural Sciences and Engineering Research Council of Canada; Cancer Research UK; Michael Smith Health Research BC","keywords":"Computer science; Segmentation; Quality (philosophy); Computer vision; Biological tissue; Artificial intelligence; Multiplexing; Biomedical engineering; Medicine","score_opus":0.06053723972205262,"score_gpt":0.3398534103869885,"score_spread":0.2793161706649359,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390345333","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9946115,0.00005483988,0.0027790673,0.000025725607,0.00011679334,0.00041229452,0.00005687554,0.00002532788,0.0019175533],"genre_scores_gemma":[0.98859715,0.00018047502,0.010155854,0.000064494736,0.000026826625,0.000027364888,0.00085562415,0.000008514041,0.00008367625],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99881,0.00007193117,0.00056122075,0.00011077579,0.00026382867,0.00018222336],"domain_scores_gemma":[0.999377,0.000033478373,0.00018376978,0.00019874923,0.00016915807,0.000037842838],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008856409,0.00011710352,0.00015167007,0.00009899166,0.00003197951,0.0000150434635,0.0001338318,0.0001498817,0.000012917009],"category_scores_gemma":[0.0002283263,0.0001038985,0.000063314525,0.0002126313,0.00005402952,0.000015342443,0.00004708283,0.000054019783,0.000022322181],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000061543404,0.00006296956,0.0037877022,0.0001377595,0.000011972757,1.6401188e-7,0.0005237998,0.0026598233,0.9773197,0.000013072345,0.00028406447,0.015137393],"study_design_scores_gemma":[0.0021466436,0.00023500044,0.01993083,0.000021171414,0.00002360615,7.3925685e-7,0.00092810247,0.037761223,0.9381426,0.00009475663,0.0004948656,0.00022046905],"about_ca_topic_score_codex":0.00004697089,"about_ca_topic_score_gemma":0.000076334305,"teacher_disagreement_score":0.039177142,"about_ca_system_score_codex":0.000029013296,"about_ca_system_score_gemma":0.00012472495,"threshold_uncertainty_score":0.4236858},"labels":[],"label_agreement":null},{"id":"W4390793818","doi":"10.1093/bioinformatics/btad738","title":"Seq-InSite: sequence supersedes structure for protein interaction site prediction","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Computer science; Sequence (biology); Source code; Matching (statistics); Code (set theory); Quality (philosophy); Data mining; Artificial intelligence; Machine learning; Programming language; Biology","score_opus":0.010736573104246281,"score_gpt":0.25635788674873794,"score_spread":0.24562131364449166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390793818","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.872546,0.0003281987,0.1229594,0.00014330876,0.0008856001,0.0010332586,0.0013177149,0.00013125884,0.000655257],"genre_scores_gemma":[0.9737004,0.000034249806,0.023671133,0.0001280693,0.00031753743,0.0000493555,0.0016307423,0.000022450473,0.00044602898],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99927837,0.000009892823,0.00025374108,0.00016633897,0.00010987432,0.00018176317],"domain_scores_gemma":[0.99959975,0.0000066782013,0.000052796815,0.00021484263,0.00007527174,0.00005065544],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000082612474,0.00015170363,0.00009549886,0.000060352388,0.00008239617,0.00011559305,0.000096334974,0.00019403342,0.000011196999],"category_scores_gemma":[0.00005736763,0.00012882029,0.00008287285,0.000090814545,0.00004013475,0.00003450864,0.00004631926,0.000105701794,0.000010410274],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009517755,0.000008417675,0.00016049243,0.0007944998,0.00008201548,0.0000015905235,0.00055619155,0.00035158906,0.9740693,0.0012659105,0.0030200968,0.019594695],"study_design_scores_gemma":[0.00074649876,0.00094012404,0.00019533819,0.00032590813,0.00010082303,0.00024877125,0.0006347291,0.30748776,0.45750743,0.002467071,0.22867025,0.0006752741],"about_ca_topic_score_codex":0.000005564416,"about_ca_topic_score_gemma":0.000015660455,"teacher_disagreement_score":0.51656187,"about_ca_system_score_codex":0.000036459784,"about_ca_system_score_gemma":0.00008586821,"threshold_uncertainty_score":0.5253139},"labels":[],"label_agreement":null},{"id":"W4390946662","doi":"10.1093/bioinformatics/btae022","title":"Concurrent prediction of RNA secondary structures with pseudoknots and local 3D motifs in an integer programming framework","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada","keywords":"Integer programming; Computer science; Integer (computer science); Nucleic acid secondary structure; RNA; Computational biology; Theoretical computer science; Algorithm; Biology; Genetics; Programming language; Gene","score_opus":0.009611091094722876,"score_gpt":0.24205697556432612,"score_spread":0.23244588446960324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390946662","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71746105,0.0012719502,0.2804731,0.000019462661,0.00024326507,0.0002944044,0.000041763407,0.00002362634,0.00017135084],"genre_scores_gemma":[0.96796745,0.00007383555,0.03177738,0.00002894823,0.00005827286,0.000015124068,0.00005620318,0.000011998913,0.000010767338],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99937254,0.000020593094,0.00024266484,0.00012446784,0.000106242114,0.0001335146],"domain_scores_gemma":[0.99969906,0.00001303015,0.000055105233,0.00014871101,0.000031732372,0.00005237465],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013138868,0.00011643435,0.00011620459,0.000059431524,0.000023347582,0.000046966332,0.00007502242,0.00015487391,0.000013052167],"category_scores_gemma":[0.000020105546,0.00008713906,0.00002274698,0.00007408439,0.00009010539,0.000018826986,0.000040380804,0.00012163749,9.697643e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052685038,0.000035232246,0.00061528495,0.000741631,0.0000599403,0.000004366358,0.0015775593,0.00014220198,0.029292764,0.0023570939,0.00007077517,0.96505046],"study_design_scores_gemma":[0.001324033,0.0047239065,0.0035186708,0.0018946083,0.00013050901,0.00019492685,0.0043585487,0.084019564,0.87710446,0.0036617557,0.018182063,0.0008869678],"about_ca_topic_score_codex":0.0000049807645,"about_ca_topic_score_gemma":0.00000997775,"teacher_disagreement_score":0.9641635,"about_ca_system_score_codex":0.000009458287,"about_ca_system_score_gemma":0.00006648911,"threshold_uncertainty_score":0.35534275},"labels":[],"label_agreement":null},{"id":"W4391261909","doi":"10.1093/bioinformatics/btae051","title":"TKSM: highly modular, user-customizable, and scalable transcriptomic sequencing long-read simulator","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"RNA modifications and cancer","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Michael Smith Health Research BC","keywords":"Computer science; Modular design; Scalability; Software; Human–computer interaction; Operating system; Computer architecture","score_opus":0.012109639831769402,"score_gpt":0.2418908974974867,"score_spread":0.2297812576657173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391261909","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93426293,0.0057342444,0.055563428,0.00021095542,0.00041456026,0.00030132607,0.000089251465,0.00008901776,0.003334306],"genre_scores_gemma":[0.9908864,0.00092355587,0.0039703767,0.0002520765,0.00014121774,0.000022333441,0.000114302886,0.000029393363,0.0036603496],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99912596,0.000013195898,0.00029260543,0.00019946833,0.00012324745,0.0002455343],"domain_scores_gemma":[0.99946874,0.000009356933,0.00004225496,0.00032418515,0.00005360123,0.00010187416],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015400336,0.00016606326,0.0001355284,0.00007032222,0.00010313683,0.00016452228,0.00013564774,0.00015096842,0.000034429104],"category_scores_gemma":[0.000015850535,0.00014660295,0.00007038318,0.00013405371,0.000071727896,0.00003037117,0.00004287917,0.00009342317,0.000051994797],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002214748,0.00015944424,0.0026577495,0.0032642595,0.0008914705,0.000040455714,0.0026479089,0.028448114,0.7866852,0.01079333,0.05677242,0.10741816],"study_design_scores_gemma":[0.0011953651,0.00027308738,0.00096642866,0.00023467877,0.00016058354,0.00011210992,0.0004993361,0.49316707,0.08475839,0.00023473418,0.41752124,0.0008769476],"about_ca_topic_score_codex":0.000019477888,"about_ca_topic_score_gemma":0.000015504924,"teacher_disagreement_score":0.7019268,"about_ca_system_score_codex":0.000049068152,"about_ca_system_score_gemma":0.00016213383,"threshold_uncertainty_score":0.5978295},"labels":[],"label_agreement":null},{"id":"W4391335182","doi":"10.1093/bioinformatics/btae264","title":"TA-RNN: an attention-based time-aware recurrent neural network architecture for electronic health records","year":2024,"lang":"en","type":"preprint","venue":"Bioinformatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; National Institute of General Medical Sciences; Northern California Institute for Research and Education; University of North Texas; Pfizer; Novartis Pharmaceuticals Corporation; University of Southern California; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; BioClinica; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; National Institute on Aging; Alzheimer's Association","keywords":"Recurrent neural network; Computer science; Architecture; Health records; Electronic health record; Artificial neural network; Artificial intelligence; History; Health care; Political science","score_opus":0.021397708566468953,"score_gpt":0.3124257444798212,"score_spread":0.29102803591335225,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391335182","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026166127,0.0017555648,0.9630698,0.020162426,0.006668371,0.0034603376,0.00031412602,0.0017079435,0.00024484994],"genre_scores_gemma":[0.06280394,0.00021218887,0.91385216,0.010268369,0.00434769,0.0011919999,0.006096526,0.00030949604,0.00091761054],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956646,0.00031403455,0.0012862406,0.0007478854,0.0006224251,0.0013648241],"domain_scores_gemma":[0.99642634,0.00027086385,0.00089461636,0.0017699072,0.00023819845,0.00040007898],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00151514,0.00062808924,0.0007151935,0.0003282954,0.00039200505,0.00066450646,0.0019886116,0.00041353525,0.00002053029],"category_scores_gemma":[0.00009879328,0.00057604833,0.00041214182,0.00050015835,0.000045847104,0.00017049251,0.0012468784,0.0027032269,0.00011132363],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040801486,0.000077363584,0.0003748085,0.01021323,0.00008875122,0.00000355616,0.0017768539,0.336289,2.3979962e-7,0.003728847,0.039782554,0.607624],"study_design_scores_gemma":[0.00022050236,0.00086059776,0.00023970485,0.0007993144,0.000023664468,0.00001533458,0.000015842974,0.9689835,4.85009e-7,0.008336503,0.01997955,0.0005250116],"about_ca_topic_score_codex":0.00010452458,"about_ca_topic_score_gemma":0.0001961128,"teacher_disagreement_score":0.6326945,"about_ca_system_score_codex":0.00063441385,"about_ca_system_score_gemma":0.0026936943,"threshold_uncertainty_score":0.9996691},"labels":[],"label_agreement":null},{"id":"W4391389830","doi":"10.1093/bioinformatics/btae056","title":"PERFUMES: pipeline to extract RNA functional motifs and exposed structures","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Montreal Clinical Research Institute; McGill University","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Institut de Valorisation des Données; Compute Canada","keywords":"RNA; Computational biology; Structural motif; Computer science; Circular RNA; Pipeline (software); Python (programming language); Base pair; Biology; Gene; Genetics; Biochemistry; Programming language","score_opus":0.016611471485229144,"score_gpt":0.23920252842017242,"score_spread":0.22259105693494327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391389830","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.642223,0.0037869473,0.34507388,0.0008305885,0.0011884399,0.00057458057,0.00011847973,0.00011249823,0.0060916054],"genre_scores_gemma":[0.970488,0.00018192957,0.02570211,0.0008446383,0.00047385402,0.000020311703,0.000103421415,0.00002565751,0.0021600442],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99934375,0.00001251177,0.00020790027,0.00014554558,0.0001324004,0.00015790205],"domain_scores_gemma":[0.99963975,0.000015444011,0.0000274063,0.00018341106,0.00003289025,0.00010112481],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014205134,0.00013425254,0.000092072194,0.00005939317,0.00006291764,0.00010178911,0.00008516371,0.00010971602,0.00009949605],"category_scores_gemma":[0.0000641391,0.000107742686,0.000049746166,0.00006203396,0.000023458766,0.0000100198895,0.00006615769,0.000055341956,0.00006160316],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058794794,0.000012731867,0.000020561221,0.00016306034,0.000048304715,0.000003871992,0.00038938748,0.000085108375,0.80756915,0.0010884305,0.023623275,0.16693735],"study_design_scores_gemma":[0.00022976888,0.0002839059,0.0002581698,0.000049252063,0.000028907914,0.00007917408,0.00033422036,0.0049950313,0.73067874,0.0007802635,0.26194382,0.00033873075],"about_ca_topic_score_codex":0.0000017247969,"about_ca_topic_score_gemma":0.0000017949644,"teacher_disagreement_score":0.32826504,"about_ca_system_score_codex":0.000007759781,"about_ca_system_score_gemma":0.000047660607,"threshold_uncertainty_score":0.43936193},"labels":[],"label_agreement":null},{"id":"W4391390112","doi":"10.1093/bioinformatics/btae034","title":"GeNLP: a web tool for NLP-based exploration and prediction of microbial gene function","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Azrieli Foundation; Israel Science Foundation","keywords":"Computer science; MIT License; Context (archaeology); Function (biology); License; Source code; Interface (matter); Semantics (computer science); World Wide Web; Artificial intelligence; Web application; Natural language processing; Programming language; Biology; Genetics","score_opus":0.011154803564037847,"score_gpt":0.23325216432045523,"score_spread":0.2220973607564174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391390112","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24782622,0.00034299213,0.74942905,0.00016425338,0.0006222232,0.0006534818,0.00044470446,0.00008115333,0.00043594316],"genre_scores_gemma":[0.8807448,0.00021632138,0.115196474,0.00032831178,0.00044122775,0.00008452115,0.0026345064,0.000040322273,0.0003134954],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99921083,0.000013742391,0.00041939356,0.00010794413,0.00011090164,0.0001371925],"domain_scores_gemma":[0.99954724,0.000022843047,0.00011704438,0.00018535795,0.00009312544,0.000034382974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026953616,0.00012964879,0.00011096001,0.00009732095,0.00006223588,0.000060852533,0.00006624616,0.0001515409,0.000006818615],"category_scores_gemma":[0.00009371231,0.00011956661,0.00007337843,0.000089927584,0.000049681657,0.00003294927,0.000037060177,0.00006629655,0.0000068435043],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000596433,0.00010127911,0.0011641248,0.0049983156,0.00028399428,5.8616735e-7,0.0012210343,0.005857409,0.8824775,0.0013586653,0.035491243,0.0664494],"study_design_scores_gemma":[0.0008447273,0.000891924,0.0002795705,0.00007747868,0.00009072254,0.0000143716625,0.000106706204,0.8192417,0.07720463,0.0000871953,0.100968264,0.00019272834],"about_ca_topic_score_codex":0.0000011739768,"about_ca_topic_score_gemma":0.000002095732,"teacher_disagreement_score":0.8133843,"about_ca_system_score_codex":0.000014471222,"about_ca_system_score_gemma":0.00011542903,"threshold_uncertainty_score":0.48757848},"labels":[],"label_agreement":null},{"id":"W4391897827","doi":"10.1093/bioinformatics/btae066","title":"VariantDetective: an accurate all-in-one pipeline for detecting consensus bacterial SNPs and SVs","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Food Inspection Agency","funders":"Canadian Food Inspection Agency","keywords":"MIT License; Single-nucleotide polymorphism; Source code; Computational biology; Benchmarking; Pipeline (software); SNP; Biology; Computer science; Genetics; Data mining; Software; Gene; Genotype; Programming language","score_opus":0.036520477259258666,"score_gpt":0.28541033089839296,"score_spread":0.2488898536391343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391897827","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9906201,0.0009006367,0.0070560826,0.00011293423,0.00042192757,0.00038155535,0.0001437347,0.00001210377,0.00035096493],"genre_scores_gemma":[0.98467326,0.0002457978,0.014520607,0.000098650824,0.00030646435,0.00002832309,0.000052406096,0.00001925108,0.000055265773],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992093,0.000017591206,0.00029461944,0.00018007868,0.00005071777,0.0002476945],"domain_scores_gemma":[0.99962616,0.00004740631,0.000053106927,0.00016022963,0.000049368897,0.00006373562],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028979263,0.00014222361,0.00014637633,0.00005177439,0.00006715087,0.00008381488,0.00007692277,0.00010855597,0.0000030138665],"category_scores_gemma":[0.000113089736,0.00013354806,0.000041387073,0.000053190004,0.00004885556,0.0000025610514,0.00008528848,0.000058936454,0.000002507003],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002745234,0.000050233702,0.00023379669,0.00041672183,0.00020662106,0.000004288776,0.0015764021,0.00012286167,0.9200897,0.000312563,0.0005176561,0.07619462],"study_design_scores_gemma":[0.0061103697,0.0031192503,0.007226913,0.00024934774,0.00036034957,0.00026286775,0.003651674,0.35097197,0.43424875,0.0024981387,0.18920696,0.0020934192],"about_ca_topic_score_codex":0.000011299389,"about_ca_topic_score_gemma":0.000078556535,"teacher_disagreement_score":0.48584095,"about_ca_system_score_codex":0.000011538493,"about_ca_system_score_gemma":0.000057202098,"threshold_uncertainty_score":0.5445932},"labels":[],"label_agreement":null},{"id":"W4392103664","doi":"10.1093/bioinformatics/btae067","title":"Phenotype prediction from single-cell RNA-seq data using attention-based neural networks","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; University of British Columbia; Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Cancer Research Society","keywords":"Artificial neural network; Phenotype; Computer science; RNA-Seq; Artificial intelligence; Computational biology; Deep neural networks; Software; Machine learning; Data mining; Pattern recognition (psychology); Biology; Gene; Genetics; Transcriptome; Gene expression","score_opus":0.03938044047685513,"score_gpt":0.2431787984064393,"score_spread":0.20379835792958417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392103664","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46491688,0.0015666011,0.52961016,0.00005887956,0.0021218155,0.00020663114,0.00063393463,0.000109151086,0.00077594724],"genre_scores_gemma":[0.97702605,0.000054087875,0.015754836,0.0003070304,0.0008471074,0.0000028004479,0.0058708973,0.00004066416,0.00009651508],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889976,0.000024998835,0.00038818768,0.00027043832,0.00016633932,0.00025025057],"domain_scores_gemma":[0.999149,0.000024701721,0.00007816623,0.00061194826,0.000051276107,0.00008491144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012688653,0.00019453227,0.00013363744,0.000051885072,0.000103920655,0.00018424251,0.00034024217,0.00020906716,0.000024708224],"category_scores_gemma":[0.000022385822,0.00018392569,0.000087727276,0.0001314999,0.00005965835,0.000033593376,0.00011057874,0.00014973903,0.000015944019],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002356991,0.00034410492,0.0035403776,0.00046111466,0.00023946926,0.00001351868,0.00020776017,0.062670894,0.87838644,0.000023331864,0.0101830745,0.04369424],"study_design_scores_gemma":[0.00040005628,0.000104837345,0.00011585413,0.000054740827,0.00009209283,0.0000029088249,0.00004304762,0.9845941,0.0077117234,0.000009168758,0.0066675036,0.00020397142],"about_ca_topic_score_codex":0.00007448237,"about_ca_topic_score_gemma":0.000024398385,"teacher_disagreement_score":0.9219232,"about_ca_system_score_codex":0.00002935593,"about_ca_system_score_gemma":0.00008669338,"threshold_uncertainty_score":0.7500272},"labels":[],"label_agreement":null},{"id":"W4392563655","doi":"10.1093/bioinformatics/btae136","title":"EpiVar Browser: advanced exploration of epigenomics data under controlled access","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Epigenetics and DNA Methylation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Institute of General Medical Sciences; Genome Canada; Canadian Institutes of Health Research; Alliance de recherche numérique du Canada; Ministry of Education, Culture, Sports, Science and Technology; National Institute of Diabetes and Digestive and Kidney Diseases; McGill University","keywords":"Computer science; Epigenomics; Software; Data exploration; World Wide Web; Programming language; Data mining; Biology; Visualization","score_opus":0.06283079410161505,"score_gpt":0.339123684800046,"score_spread":0.276292890698431,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392563655","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31894317,0.009225083,0.6634558,0.00037777415,0.0009194296,0.0008767626,0.0003066975,0.000056039207,0.0058392296],"genre_scores_gemma":[0.98044664,0.003607523,0.013735828,0.00009470363,0.00017267441,0.000017185628,0.0016102956,0.000026695669,0.00028845703],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99901056,0.000025887166,0.0004947264,0.0001773878,0.00014421224,0.00014722417],"domain_scores_gemma":[0.99903643,0.000036261772,0.00014533992,0.0006414473,0.00009093127,0.000049585],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034687918,0.0001285146,0.00018931276,0.00007188261,0.00004338997,0.000090564914,0.00040611465,0.00011623352,0.000012940714],"category_scores_gemma":[0.00010919151,0.00011244222,0.000065918015,0.00012074816,0.000042781743,0.00007883684,0.0002692932,0.000057389127,0.00001638949],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011830566,0.00027261666,0.00060112483,0.0014988775,0.000948534,0.0000042271054,0.0013775785,0.03569929,0.6778977,0.011092127,0.004840307,0.26458457],"study_design_scores_gemma":[0.0047531407,0.00063791126,0.0007420773,0.00017362616,0.00023484493,0.000004388418,0.0008170784,0.2902926,0.5421879,0.0062442296,0.15307084,0.00084133726],"about_ca_topic_score_codex":0.0000049424516,"about_ca_topic_score_gemma":0.000014506416,"teacher_disagreement_score":0.66150343,"about_ca_system_score_codex":0.000012470575,"about_ca_system_score_gemma":0.00012885159,"threshold_uncertainty_score":0.45852607},"labels":[],"label_agreement":null},{"id":"W4392564168","doi":"10.1093/bioinformatics/btae135","title":"iNGNN-DTI: prediction of drug–target interaction with interpretable nested graph neural network and pretrained molecule models","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Children’s Health Research Institute; Lawson Health Research Institute; University of Toronto; University of Manitoba; Western University","funders":"Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Discriminative model; Computer science; Machine learning; Artificial intelligence; Graph; ENCODE; Generalization; Artificial neural network; Feature (linguistics); Benchmark (surveying); Interaction network; Set (abstract data type); Pattern recognition (psychology); Theoretical computer science","score_opus":0.017053019806671173,"score_gpt":0.2544432196605,"score_spread":0.2373901998538288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392564168","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07478094,0.00021582938,0.92258453,0.000115924966,0.0004864093,0.00021567628,0.000015185938,0.0001918939,0.0013936182],"genre_scores_gemma":[0.74647146,0.00001299267,0.253326,0.000079909805,0.000039171286,0.000011187695,0.000021024005,0.00000984146,0.000028395463],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988819,0.00006756754,0.00040537168,0.00017501005,0.00027954183,0.0001906429],"domain_scores_gemma":[0.999272,0.00021453439,0.00012435905,0.0002325429,0.000092239425,0.00006435762],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003679315,0.0001486461,0.00016777891,0.00019274796,0.000059728427,0.0002540776,0.00023397806,0.000042203737,0.0000027208362],"category_scores_gemma":[0.00002264435,0.00012255034,0.000048808553,0.0006716233,0.000053592445,0.0025121868,0.0001667332,0.0001584595,0.000001975049],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037088153,0.000024417133,0.00016255504,0.0003354339,0.00007021061,0.0000037445488,0.006185184,0.95830685,0.00005072998,0.022417217,0.0007716334,0.0116349645],"study_design_scores_gemma":[0.00015335622,0.00011256801,0.0004045085,0.00022907474,0.000016664568,0.000052278418,0.00013412205,0.98909706,0.00026245337,0.009326399,0.00010146939,0.0001100387],"about_ca_topic_score_codex":0.000010499104,"about_ca_topic_score_gemma":0.0000025034187,"teacher_disagreement_score":0.6716905,"about_ca_system_score_codex":0.00003657719,"about_ca_system_score_gemma":0.00008539152,"threshold_uncertainty_score":0.49974576},"labels":[],"label_agreement":null},{"id":"W4394582173","doi":"10.1093/bioinformatics/btae190","title":"Improving the performance of supervised deep learning for regulatory genomics using phylogenetic augmentation","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Genomics; Phylogenetic tree; Computer science; Deep learning; Source code; Set (abstract data type); Artificial intelligence; Sequence (biology); Function (biology); Machine learning; Code (set theory); Computational genomics; Functional genomics; Biological data; Computational biology; Genome; Biology; Bioinformatics; Genetics; Gene","score_opus":0.008751119482387123,"score_gpt":0.22010876798226825,"score_spread":0.21135764849988112,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394582173","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9544782,0.00078107003,0.04421228,0.000008797444,0.0001788406,0.00026895766,0.00001237576,0.000011044864,0.000048415775],"genre_scores_gemma":[0.9727121,0.00018682097,0.026746187,0.000036848294,0.00010733869,0.000012843307,0.000112244576,0.000024693676,0.00006091903],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99929476,0.000012698889,0.00032852677,0.00010871316,0.000087030145,0.00016824705],"domain_scores_gemma":[0.9995655,0.00001889023,0.00011894849,0.00020675846,0.000062999025,0.000026926964],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024629617,0.00011501291,0.0000960387,0.00004003035,0.0001289583,0.000051055704,0.00015712187,0.00008487019,0.0000027001022],"category_scores_gemma":[0.00002114753,0.000093116716,0.00008619222,0.00006681463,0.000056978377,0.0000085851325,0.000075744676,0.000061983505,0.0000019588676],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002635642,0.000010046692,0.0005323181,0.0007880449,0.00006816296,1.1266724e-7,0.0007644795,0.04696667,0.91536754,0.00010420693,0.000026843862,0.035345245],"study_design_scores_gemma":[0.00019386977,0.00016177855,0.00040843894,0.000023623965,0.000042812266,0.000009211279,0.000489879,0.92550445,0.072188266,0.000011611852,0.00084992667,0.00011614621],"about_ca_topic_score_codex":0.0000034804723,"about_ca_topic_score_gemma":0.0000028744848,"teacher_disagreement_score":0.8785378,"about_ca_system_score_codex":0.00003678792,"about_ca_system_score_gemma":0.00010363118,"threshold_uncertainty_score":0.37971893},"labels":[],"label_agreement":null},{"id":"W4394675060","doi":"10.1093/bioinformatics/btae192","title":"VirusPredictor: XGBoost-based software to predict virus-related sequences in human data","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier Universitaire Sainte-Justine","funders":"National Institute of Allergy and Infectious Diseases; National Institutes of Health; Open Medicine Foundation; U.S. Department of Defense","keywords":"Python (programming language); Contig; Genome; Metagenomics; Biology; Sanger sequencing; Computational biology; Software; Genetics; DNA sequencing; Genomics; Human genome; Computer science; Gene","score_opus":0.023752742637846082,"score_gpt":0.274237705772119,"score_spread":0.2504849631342729,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394675060","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.986547,0.0032988829,0.004346248,0.00025587293,0.0009115345,0.0005846029,0.001734052,0.00006447258,0.0022573317],"genre_scores_gemma":[0.98985934,0.00017447303,0.008233069,0.000467045,0.00013702457,0.00002746279,0.00086944166,0.000028146256,0.0002040021],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988081,0.000020722398,0.00043962925,0.00029162204,0.00016120727,0.0002787606],"domain_scores_gemma":[0.99912435,0.000022462322,0.00004822171,0.0006724118,0.000035163175,0.00009741526],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028687727,0.00019038573,0.00016145827,0.00011977379,0.00008217991,0.00007902732,0.0005366797,0.00014114456,0.000014216924],"category_scores_gemma":[0.00009205863,0.00017043368,0.000051565807,0.0001986639,0.000076540055,0.0000049765335,0.0004034101,0.000103644416,0.000043965774],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015801347,0.00028597907,0.032270003,0.0012211222,0.0008301729,0.00006906211,0.0034641651,0.007920874,0.74763995,0.00073922495,0.14919513,0.056206323],"study_design_scores_gemma":[0.0017969072,0.0017334296,0.017022364,0.0005836024,0.00017236616,0.000034337445,0.00078813836,0.0546087,0.09199524,0.0006216945,0.8289309,0.0017122861],"about_ca_topic_score_codex":0.00005119099,"about_ca_topic_score_gemma":0.0002789621,"teacher_disagreement_score":0.67973584,"about_ca_system_score_codex":0.00002438586,"about_ca_system_score_gemma":0.00015337962,"threshold_uncertainty_score":0.69500834},"labels":[],"label_agreement":null},{"id":"W4394745991","doi":"10.1093/bioinformatics/btae182","title":"Pacybara: accurate long-read sequencing for barcoded mutagenized allelic libraries","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; University of Toronto","funders":"National Institute of General Medical Sciences; National Human Genome Research Institute; National Heart, Lung, and Blood Institute; Canadian Institutes of Health Research; National Institutes of Health","keywords":"Barcode; Identification (biology); Biology; Genetics; Computational biology; Identifier; DNA sequencing; Computer science; Gene; Programming language","score_opus":0.021092162970628367,"score_gpt":0.2625775321882256,"score_spread":0.24148536921759722,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394745991","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87786514,0.012135848,0.101909645,0.0007725779,0.0012929852,0.0013088633,0.000890665,0.00024676556,0.0035774854],"genre_scores_gemma":[0.9743758,0.00076744845,0.019832037,0.0008391057,0.00047962004,0.00009153974,0.0014959335,0.00005978122,0.0020587544],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991266,0.000011184534,0.00031157132,0.00017696994,0.00009045284,0.00028323068],"domain_scores_gemma":[0.9994686,0.000030474946,0.000058548492,0.00027378945,0.000059555598,0.000108989225],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011675249,0.0001810817,0.00014343491,0.00004153831,0.00011094791,0.00024845338,0.0001953555,0.00012459407,0.000032103697],"category_scores_gemma":[0.00009114181,0.00015108466,0.00017468618,0.0000810539,0.000056822064,0.000023031103,0.0001065271,0.00006847161,0.00004572844],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017894104,0.00041989397,0.0012566852,0.011747335,0.0041708765,0.00036775018,0.013826837,0.0049278536,0.43153387,0.03248059,0.22699386,0.27048504],"study_design_scores_gemma":[0.0031031587,0.0009831985,0.00067007414,0.00042659626,0.00040033102,0.00028305408,0.0033323315,0.16957106,0.15530013,0.0033847173,0.6604547,0.0020906853],"about_ca_topic_score_codex":0.0000062297086,"about_ca_topic_score_gemma":0.000010161095,"teacher_disagreement_score":0.43346083,"about_ca_system_score_codex":0.000019411156,"about_ca_system_score_gemma":0.00031713131,"threshold_uncertainty_score":0.6161054},"labels":[],"label_agreement":null},{"id":"W4394759342","doi":"10.1093/bioinformatics/btae161","title":"phylaGAN: data augmentation through conditional GANs and autoencoders for improving disease prediction accuracy using microbiome data","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; Public Health Ontario; University of Toronto; University Health Network","funders":"","keywords":"Autoencoder; Machine learning; Artificial intelligence; Computer science; Microbiome; Deep learning; Generative grammar; Subspace topology; Pattern recognition (psychology); Bioinformatics","score_opus":0.0742748241898758,"score_gpt":0.35470221034668203,"score_spread":0.28042738615680624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394759342","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1082338,0.0023298801,0.8493488,0.0006898196,0.00081769074,0.0010645997,0.037376147,0.00008185922,0.00005743294],"genre_scores_gemma":[0.5181706,0.0008371847,0.25783718,0.0013640611,0.0009857642,0.000023880637,0.22054914,0.00006682348,0.0001653845],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99915266,0.000011205382,0.00028369488,0.00029048417,0.0000736863,0.00018826542],"domain_scores_gemma":[0.999209,0.00002336944,0.00008472535,0.0005719852,0.00003899876,0.000071944174],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001935545,0.00012354615,0.00008127728,0.00004029735,0.00016695498,0.00014283317,0.00026498517,0.00007734649,0.0000069748535],"category_scores_gemma":[0.00007589889,0.00011868434,0.000023031454,0.000059925886,0.00006760623,0.00013698384,0.00034015032,0.000054576052,0.00000418914],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001863274,0.00010871214,0.00037990452,0.0055979374,0.00023710553,0.000003828824,0.0010670719,0.0003473775,0.8934414,0.0007228697,0.085393265,0.012514229],"study_design_scores_gemma":[0.0008585534,0.00012166792,0.0008332155,0.00011467603,0.0002029354,0.00005448572,0.0005477756,0.91845423,0.0036301664,0.00022702567,0.0746564,0.00029890132],"about_ca_topic_score_codex":0.00001611087,"about_ca_topic_score_gemma":0.00001078538,"teacher_disagreement_score":0.91810685,"about_ca_system_score_codex":0.000027201244,"about_ca_system_score_gemma":0.0003983737,"threshold_uncertainty_score":0.4839807},"labels":[],"label_agreement":null},{"id":"W4394769874","doi":"10.1093/bioinformatics/btae196","title":"Effect of tokenization on transformers for biological sequences","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Tel Aviv University; Azrieli Foundation; Israel Science Foundation","keywords":"Lexical analysis; Computer science; Artificial intelligence; Natural language processing; Biological network; Inference; Security token; Machine learning; Computational biology; Biology","score_opus":0.009661397653894933,"score_gpt":0.2905729843578977,"score_spread":0.28091158670400274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394769874","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73067147,0.00044915028,0.2509752,0.0002148511,0.0008066813,0.0013327765,0.00021669529,0.00013254555,0.015200628],"genre_scores_gemma":[0.9914115,0.00015694032,0.007494724,0.00013632957,0.00011206434,0.000036390058,0.00048134147,0.0000160827,0.00015461698],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999221,0.000030633473,0.00035278115,0.00009998439,0.00012447487,0.00017110104],"domain_scores_gemma":[0.99960977,0.00011416038,0.00007425448,0.00011844656,0.000039993567,0.000043388023],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048193248,0.00014927675,0.00015847679,0.00007657011,0.000046863242,0.00003243941,0.00012335464,0.00016518762,0.00001243461],"category_scores_gemma":[0.00023561704,0.00010182254,0.00013197157,0.00011399437,0.00007814601,0.000010434945,0.00002078402,0.000079205456,0.000019236972],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018605442,0.00012951884,0.0033180104,0.012153691,0.00063975,0.00000282062,0.0023874226,0.0055032843,0.10392743,0.0116519,0.022442082,0.8359836],"study_design_scores_gemma":[0.001263536,0.014036489,0.00016174022,0.00029518924,0.00009400266,0.000034376335,0.00019513356,0.29477412,0.5435262,0.00010620904,0.1449502,0.0005628031],"about_ca_topic_score_codex":0.0000011201664,"about_ca_topic_score_gemma":5.676803e-7,"teacher_disagreement_score":0.8354207,"about_ca_system_score_codex":0.000012083636,"about_ca_system_score_gemma":0.000043207587,"threshold_uncertainty_score":0.41522026},"labels":[],"label_agreement":null},{"id":"W4396561183","doi":"10.1093/bioinformatics/btae295","title":"SharePro: an accurate and efficient genetic colocalization method accounting for multiple causal signals","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Université de Montréal; McGill University; Montreal Heart Institute","funders":"Canada First Research Excellence Fund","keywords":"Colocalization; Genome-wide association study; Linkage disequilibrium; Computational biology; Computer science; Locus (genetics); Genetic association; Statistical power; False positive paradox; Biology; Machine learning; Statistics; Genetics; Neuroscience; Allele; Mathematics; Genotype; Single-nucleotide polymorphism; Gene; Haplotype","score_opus":0.025460759315474625,"score_gpt":0.32263423724643114,"score_spread":0.2971734779309565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396561183","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36535603,0.00047372482,0.6333974,0.000076942044,0.00015465615,0.0003413946,0.00009166998,0.000027479693,0.000080678954],"genre_scores_gemma":[0.812426,0.00008181041,0.18637918,0.000303597,0.00018525159,0.00007560672,0.0004250959,0.000021479094,0.00010201973],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990711,0.000048663078,0.0003619677,0.00021376893,0.000071243834,0.00023323204],"domain_scores_gemma":[0.9994455,0.00011009848,0.00009982514,0.0001733169,0.000104534665,0.000066718065],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060962565,0.00012677533,0.00014025437,0.000052180796,0.00012149759,0.00009188354,0.000089124725,0.00016602053,0.000007869718],"category_scores_gemma":[0.00041663743,0.00011321931,0.000049971237,0.000084700805,0.000030422601,0.000008149839,0.0000692595,0.000044889817,0.000006970638],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026436325,0.00035012883,0.044879843,0.002638762,0.00091137824,0.000006813352,0.0057032844,0.37067783,0.23372145,0.0022068217,0.03249315,0.30614617],"study_design_scores_gemma":[0.00024732496,0.00019859248,0.004825808,0.000017288943,0.000038279686,0.000013386267,0.0002459507,0.9785979,0.0031138551,0.00011355511,0.012422565,0.00016551046],"about_ca_topic_score_codex":0.000010328814,"about_ca_topic_score_gemma":0.000015137229,"teacher_disagreement_score":0.60792005,"about_ca_system_score_codex":0.00001567094,"about_ca_system_score_gemma":0.00007257207,"threshold_uncertainty_score":0.46169496},"labels":[],"label_agreement":null},{"id":"W4396745594","doi":"10.1093/bioinformatics/btae444","title":"A curated rotamer library for common post-translational modifications of proteins","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children; University of Toronto","funders":"National Institutes of Health; National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Protein Data Bank (RCSB PDB); Dihedral angle; Conformational isomerism; Computational biology; Intrinsically disordered proteins; Computer science; Protein structure; Conformational ensembles; Database; Bioinformatics; Chemistry; Biology; Biochemistry; Molecule","score_opus":0.009658113960087922,"score_gpt":0.24955730278967478,"score_spread":0.23989918882958686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396745594","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23154421,0.002499272,0.747759,0.0018513366,0.00039389593,0.0028290648,0.004557937,0.00018384213,0.008381439],"genre_scores_gemma":[0.91328174,0.00005399083,0.082763776,0.00019847197,0.000109638786,0.00010152909,0.003020758,0.000024407049,0.00044571442],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99947315,0.0000071611307,0.00025921702,0.00008213381,0.000074995325,0.000103336446],"domain_scores_gemma":[0.9996449,0.000013868427,0.000070701244,0.0001771077,0.000060283037,0.000033187313],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000044536715,0.000087667,0.000085091124,0.000049736445,0.00003972946,0.00003239872,0.00011465651,0.00010446669,0.000011786686],"category_scores_gemma":[0.000022609014,0.00007491026,0.00008187989,0.0001001066,0.000048273225,0.000019715713,0.000027004784,0.00004709536,0.000004839817],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00054476777,0.00023312676,0.00085387204,0.0036943236,0.0006773262,0.000002283046,0.002183969,0.0018880963,0.679097,0.13699889,0.024386369,0.14943998],"study_design_scores_gemma":[0.0010409866,0.00089455175,0.0013858419,0.00020130684,0.000120264325,0.000042141684,0.00028854693,0.33316284,0.36599013,0.008777269,0.28740934,0.00068680604],"about_ca_topic_score_codex":0.0000024226576,"about_ca_topic_score_gemma":0.0000032535133,"teacher_disagreement_score":0.6817375,"about_ca_system_score_codex":0.0000026308583,"about_ca_system_score_gemma":0.00014319208,"threshold_uncertainty_score":0.30547518},"labels":[],"label_agreement":null},{"id":"W4399117787","doi":"10.1093/bioinformatics/btae342","title":"Representations of lipid nanoparticles using large language models for transfection efficiency prediction","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"RNA Interference and Gene Delivery","field":"Biochemistry, Genetics and Molecular Biology","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sanofi (Canada)","funders":"Sanofi","keywords":"Payload (computing); Transfection; Nanoparticle; Gene delivery; Computer science; Messenger RNA; Chemistry; Nanotechnology; Computational biology; Cell biology; Biochemistry; Biology; Materials science; Gene; Computer network","score_opus":0.01932988650558984,"score_gpt":0.2876306062438401,"score_spread":0.2683007197382503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399117787","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6549594,0.0002796719,0.34394732,0.000010306478,0.00017555062,0.00013868025,0.0001548096,0.000015535092,0.00031876087],"genre_scores_gemma":[0.99656385,0.00007415644,0.0030026168,0.000020516301,0.00010414075,0.000012943021,0.00012530052,0.0000073709984,0.000089087494],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995181,0.000007885045,0.00021611241,0.00008348667,0.00006538333,0.00010900746],"domain_scores_gemma":[0.99976915,0.000009072178,0.000029780544,0.00011811873,0.000052570318,0.000021333992],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011483769,0.000059837133,0.000060280647,0.00005078825,0.00004584505,0.000022122731,0.00005213683,0.000059078047,0.0000049697574],"category_scores_gemma":[0.000017856426,0.000054109503,0.00007517248,0.00008020707,0.000019906294,0.000020769141,0.000014480438,0.000024148203,0.0000023970513],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003277363,0.000044518685,0.000054138927,0.00023161914,0.000043231135,2.2417436e-7,0.0017729347,0.008030534,0.9854004,0.00043539982,0.0007554256,0.0031988495],"study_design_scores_gemma":[0.00014785712,0.0001630467,0.00001822194,0.000034226287,0.000024565286,0.0000053856706,0.0007787088,0.5739243,0.42425433,0.00004990373,0.0005489692,0.00005050688],"about_ca_topic_score_codex":0.0000067699416,"about_ca_topic_score_gemma":0.000005367569,"teacher_disagreement_score":0.56589377,"about_ca_system_score_codex":0.000007537763,"about_ca_system_score_gemma":0.000041039395,"threshold_uncertainty_score":0.22065215},"labels":[],"label_agreement":null},{"id":"W4400128023","doi":"10.1093/bioinformatics/btae229","title":"Median and small parsimony problems on RNA trees","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Agence Nationale de la Recherche; Institut Polytechnique de Paris","keywords":"RNA; Biology; Computational biology; Nucleic acid secondary structure; Nucleic acid structure; Non-coding RNA; Evolutionary biology; Homologous chromosome; Genetics; RNA editing; Protein secondary structure; Structural motif; Gene","score_opus":0.016641647047241314,"score_gpt":0.22389361941666736,"score_spread":0.20725197236942605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400128023","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9014614,0.007420309,0.027891748,0.002361247,0.00143816,0.0012509944,0.00013039501,0.00023806175,0.05780766],"genre_scores_gemma":[0.9847156,0.0012291153,0.011300865,0.0005524908,0.00027812543,0.000042131574,0.00007239443,0.000030625033,0.001778671],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994392,0.00001380939,0.00017300346,0.00012357518,0.00008879332,0.00016166299],"domain_scores_gemma":[0.9996729,0.000017370101,0.000030606585,0.00018764319,0.000014362689,0.00007713766],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016000491,0.00012207769,0.000087276385,0.000046238183,0.000047137313,0.000080228754,0.00009891032,0.000118832846,0.000015488884],"category_scores_gemma":[0.000036012763,0.0000948888,0.000044423883,0.000048431117,0.00003573749,0.0000049275645,0.000047390164,0.000050923805,0.00006542191],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005094277,0.000049521856,0.000097573495,0.0006062063,0.00015564101,0.000011734483,0.0011810559,0.000046833866,0.43049958,0.0048613283,0.009106228,0.55333334],"study_design_scores_gemma":[0.0003274321,0.0008738472,0.00013938706,0.00027733506,0.000039096452,0.000033972523,0.00030347618,0.005056486,0.62748545,0.0018144092,0.3631813,0.00046779012],"about_ca_topic_score_codex":0.0000033644822,"about_ca_topic_score_gemma":0.000016797057,"teacher_disagreement_score":0.55286556,"about_ca_system_score_codex":0.0000054042994,"about_ca_system_score_gemma":0.000031820207,"threshold_uncertainty_score":0.38694528},"labels":[],"label_agreement":null},{"id":"W4400140691","doi":"10.1093/bioinformatics/btae252","title":"Floria: fast and accurate strain haplotyping in metagenomes","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Metagenomics; Strain (injury); Computer science; Pipeline (software); Workflow; Computational biology; Set (abstract data type); Haplotype; Genome; Data mining; Biology; Genetics; Database; Gene; Allele; Operating system; Programming language","score_opus":0.015796229212360697,"score_gpt":0.2470699199430443,"score_spread":0.2312736907306836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400140691","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97797143,0.013751115,0.002955126,0.00029399816,0.000512291,0.0002373007,0.00012039275,0.000014594612,0.0041437265],"genre_scores_gemma":[0.992964,0.0018818269,0.0045951945,0.00011076472,0.00017440582,0.000010852163,0.000029505043,0.000013492127,0.00021992878],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994492,0.000008923132,0.00020758988,0.000119689095,0.00004995242,0.00016465061],"domain_scores_gemma":[0.9997915,0.000011936656,0.000024461537,0.00012050622,0.000014609505,0.00003698234],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014425823,0.00011107009,0.0001065277,0.000057141882,0.00003805701,0.00006812806,0.00007262101,0.00006391281,0.0000041074322],"category_scores_gemma":[0.000021486065,0.00009625231,0.00003399819,0.00007410152,0.00004227499,0.000002296514,0.000107520966,0.00005463283,0.000011440247],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000077419696,0.000053963806,0.0060996795,0.0012947371,0.00080015574,0.00003446083,0.009452637,0.0012318814,0.4692394,0.008347091,0.0033439398,0.5000246],"study_design_scores_gemma":[0.0022974936,0.00093097123,0.07726159,0.00033398834,0.00020855786,0.0001341502,0.009272424,0.094856314,0.041763246,0.0030752965,0.76767963,0.002186362],"about_ca_topic_score_codex":0.0000047144745,"about_ca_topic_score_gemma":0.000026357031,"teacher_disagreement_score":0.7643357,"about_ca_system_score_codex":0.0000072458633,"about_ca_system_score_gemma":0.000036459332,"threshold_uncertainty_score":0.39250553},"labels":[],"label_agreement":null},{"id":"W4400140816","doi":"10.1093/bioinformatics/btae263","title":"Adaptive digital tissue deconvolution","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Bundesministerium für Bildung und Forschung; Deutsche Forschungsgemeinschaft; European Commission; Trond Mohn stiftelse; Ministère de l'Économie, de la Science et de l'Innovation - Québec; California Department of Fish and Game","keywords":"Deconvolution; Computer science; Blind deconvolution; Algorithm; Artificial intelligence","score_opus":0.013059272636809205,"score_gpt":0.23184750945628338,"score_spread":0.21878823681947418,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400140816","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4282871,0.0040797987,0.49780372,0.00023077618,0.0024096763,0.0005169484,0.00032473225,0.00026804098,0.06607921],"genre_scores_gemma":[0.994351,0.00009079336,0.0035816305,0.000109835026,0.0002309354,0.00000489509,0.00020604607,0.00001549342,0.001409325],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99949193,0.000004186706,0.00017398475,0.00010131929,0.000080723614,0.00014785981],"domain_scores_gemma":[0.99975425,0.000006733208,0.000020656087,0.00013613753,0.000029497061,0.00005273092],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000048500977,0.00010121133,0.00006794967,0.000035029218,0.000040412324,0.000117559306,0.00009050148,0.00010008785,0.000015222743],"category_scores_gemma":[0.000016865408,0.00008999244,0.000054805438,0.00006590398,0.000043633485,0.00001724585,0.00003130774,0.000057922643,0.00019850874],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000215272,0.00020128912,0.0012355195,0.00062091684,0.00039351537,0.000026467884,0.0018674526,0.00033234997,0.20114441,0.006003008,0.06512254,0.72283727],"study_design_scores_gemma":[0.00049520354,0.0008304631,0.0003281406,0.000101255435,0.000043669992,0.000087257344,0.00040430226,0.06078252,0.1225485,0.00044181294,0.8133424,0.00059449015],"about_ca_topic_score_codex":0.0000036406361,"about_ca_topic_score_gemma":0.0000045640427,"teacher_disagreement_score":0.74821985,"about_ca_system_score_codex":0.0000146457605,"about_ca_system_score_gemma":0.000057661426,"threshold_uncertainty_score":0.36697853},"labels":[],"label_agreement":null},{"id":"W4400140828","doi":"10.1093/bioinformatics/btae237","title":"Predicting protein functions using positive-unlabeled ranking with ontology-based priors","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"King Abdullah University of Science and Technology","keywords":"Computer science; Prior probability; Benchmark (surveying); Classifier (UML); Ranking (information retrieval); Artificial intelligence; Machine learning; Data mining; Source code; Gene ontology; Function (biology); Ontology; Pattern recognition (psychology); Bayesian probability","score_opus":0.015018811350751586,"score_gpt":0.2557952577102794,"score_spread":0.2407764463595278,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400140828","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83816147,0.000615301,0.15934922,0.00021796994,0.00020456077,0.00030217803,0.000035325254,0.00015576265,0.0009582308],"genre_scores_gemma":[0.91449857,0.000005450493,0.08464466,0.00021624319,0.0001542934,0.00002652455,0.00012687783,0.00002455371,0.00030283554],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990707,0.000028841507,0.00026205022,0.00018652693,0.00016523992,0.00028662613],"domain_scores_gemma":[0.9995725,0.0000274235,0.000073231226,0.00019220547,0.00006120366,0.00007340077],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020031487,0.00016840993,0.00014454957,0.00008836018,0.00016153297,0.00007702003,0.00012051233,0.00020201124,0.000010958547],"category_scores_gemma":[0.00009715319,0.0001254894,0.0000656138,0.00019362704,0.0001776821,0.000009327844,0.000050981194,0.00016103138,0.000013965361],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013224249,0.00038292387,0.029934412,0.003236671,0.0018645737,0.00018984213,0.0039887666,0.003117381,0.6015276,0.00087290286,0.0054193577,0.34814316],"study_design_scores_gemma":[0.003966751,0.0039677056,0.0030749775,0.0026121184,0.0004992938,0.00053131586,0.003674775,0.7399904,0.16364208,0.0000775431,0.076185495,0.0017775465],"about_ca_topic_score_codex":0.000016338112,"about_ca_topic_score_gemma":0.00002272885,"teacher_disagreement_score":0.73687303,"about_ca_system_score_codex":0.000029635692,"about_ca_system_score_gemma":0.00026484,"threshold_uncertainty_score":0.5117309},"labels":[],"label_agreement":null},{"id":"W4400497719","doi":"10.1093/bioinformatics/btae405","title":"Geometric epitope and paratope prediction","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"vaccines and immunoinformatics approaches","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"H2020 European Research Council; Sapienza Università di Roma; European Commission","keywords":"Paratope; Epitope; Computer science; Computational biology; Artificial intelligence; Biology; Antibody; Genetics","score_opus":0.012131777674846557,"score_gpt":0.22608040107793448,"score_spread":0.21394862340308793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400497719","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.913222,0.020580156,0.043196183,0.00032392686,0.001092951,0.0005712059,0.00014111152,0.00017051148,0.020701932],"genre_scores_gemma":[0.98703706,0.003777404,0.007512851,0.00020050516,0.00024582748,0.00001999113,0.00027093664,0.000021375723,0.0009140651],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993622,0.0000060811767,0.00027839563,0.0000967682,0.000094646595,0.00016192373],"domain_scores_gemma":[0.9996727,0.000008817755,0.000036863432,0.00019564666,0.00002925551,0.000056731435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017155638,0.00011846887,0.00009028098,0.00011602516,0.00006520761,0.00015239202,0.000088754,0.00010173296,0.000011342426],"category_scores_gemma":[0.000039314553,0.00009542882,0.000045287405,0.00021118353,0.000027888382,0.000024473205,0.00010054082,0.00007258342,0.000057183923],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009044734,0.00011603795,0.005556467,0.0025170967,0.0005961706,0.00000673623,0.0022038051,0.0002910068,0.02399235,0.005778806,0.1614422,0.7974089],"study_design_scores_gemma":[0.0006087035,0.00062091317,0.005315289,0.000095477764,0.00007236309,0.00025108058,0.00082243886,0.13157783,0.019268319,0.00017528863,0.84070486,0.00048745298],"about_ca_topic_score_codex":0.000002137164,"about_ca_topic_score_gemma":5.6680335e-7,"teacher_disagreement_score":0.79692143,"about_ca_system_score_codex":0.000007971045,"about_ca_system_score_gemma":0.000038363665,"threshold_uncertainty_score":0.38914743},"labels":[],"label_agreement":null},{"id":"W4400597743","doi":"10.1093/bioinformatics/btae448","title":"isolateR: an R package for generating microbial libraries from Sanger sequencing data","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan; University of Guelph","funders":"Breakthrough T1D Canada; Canada First Research Excellence Fund; National Institute of General Medical Sciences; Canada Research Chairs","keywords":"Cataloging; Sanger sequencing; Benchmarking; Computer science; Biology; Pipeline (software); Computational biology; Information retrieval; DNA sequencing; World Wide Web; Genetics; Programming language; Gene","score_opus":0.04105578436180538,"score_gpt":0.26225966537620315,"score_spread":0.22120388101439778,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400597743","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93398803,0.0050367215,0.05629983,0.00011382059,0.0008384193,0.00030913734,0.0029630812,0.000029258681,0.00042168924],"genre_scores_gemma":[0.6886088,0.00036209694,0.3026009,0.0007699339,0.001842081,0.000022841845,0.0054908153,0.000055320765,0.00024716384],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992059,0.000012213448,0.00027191412,0.00024137796,0.000056137374,0.00021248969],"domain_scores_gemma":[0.9992631,0.000023738365,0.000048594153,0.0005788535,0.00003147624,0.000054202093],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001333619,0.00015269649,0.00012504678,0.000026893355,0.00013162517,0.00026456636,0.0003397196,0.000105380845,0.000009224346],"category_scores_gemma":[0.000037459256,0.00013427147,0.000051094044,0.00003911369,0.000045291716,0.000012752981,0.0003363933,0.000049606733,0.000011641802],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001811613,0.000008347145,0.00012088338,0.00009714375,0.00014447825,0.000001239282,0.0012080801,0.00004346078,0.9714688,0.0001290884,0.015174565,0.011585799],"study_design_scores_gemma":[0.0006446909,0.0004598281,0.0001989701,0.000088865556,0.00016077214,0.00002234016,0.001782368,0.19442217,0.39498332,0.0006448338,0.40573916,0.00085267646],"about_ca_topic_score_codex":0.0000221679,"about_ca_topic_score_gemma":0.00004066008,"teacher_disagreement_score":0.5764855,"about_ca_system_score_codex":0.000010447274,"about_ca_system_score_gemma":0.0001256157,"threshold_uncertainty_score":0.54754317},"labels":[],"label_agreement":null},{"id":"W4400920210","doi":"10.1093/bioinformatics/btae446","title":"Adaptive space search-based molecular evolution optimization algorithm","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Key Research and Development Program of China; Natural Science Foundation of Anhui Province; National Natural Science Foundation of China; Institute for Catastrophic Loss Reduction","keywords":"Computer science; Space (punctuation); Optimization problem; Process (computing); Encoder; Chemical space; Algorithm; Mathematical optimization; Theoretical computer science; Mathematics; Drug discovery; Bioinformatics","score_opus":0.017765906789825977,"score_gpt":0.2777247315030628,"score_spread":0.25995882471323684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400920210","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009138846,0.00020716053,0.99587923,0.0006738936,0.0004268352,0.00019491468,0.000014481555,0.00036048426,0.0021516094],"genre_scores_gemma":[0.025010085,0.000003675859,0.9747114,0.00015151789,0.000037236056,0.000008948082,0.000023623641,0.000010431672,0.000043084296],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99877185,0.000087617474,0.00025095008,0.00017866507,0.00049335335,0.00021759311],"domain_scores_gemma":[0.9992613,0.00018401134,0.000044326873,0.00029658966,0.0001309581,0.000082815866],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004557534,0.00013182177,0.00010152374,0.0002681499,0.00007549752,0.00037634597,0.00037866223,0.000056221117,0.00000980591],"category_scores_gemma":[0.00004424432,0.00012637883,0.00007823491,0.00084993296,0.000045630557,0.0011105388,0.00015027188,0.00013181103,0.00013185067],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013361015,0.000011569736,7.622505e-7,0.000035256617,0.000011766894,0.000008636741,0.00025923358,0.8290707,0.000008494231,0.112636186,0.0002128902,0.05774319],"study_design_scores_gemma":[0.00010979611,0.00005796101,0.00002736961,0.000058435733,0.0000069854705,0.000010667527,0.00004872642,0.99492544,0.00059868087,0.0035665915,0.00043547517,0.0001538953],"about_ca_topic_score_codex":0.000009355035,"about_ca_topic_score_gemma":2.2683508e-7,"teacher_disagreement_score":0.16585474,"about_ca_system_score_codex":0.0002168829,"about_ca_system_score_gemma":0.0004385774,"threshold_uncertainty_score":0.5153579},"labels":[],"label_agreement":null},{"id":"W4401322700","doi":"10.1093/bioinformatics/btae483","title":"Cellular proliferation biases clonal lineage tracing and trajectory inference","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Yale University","keywords":"Python (programming language); Computer science; Inference; Tracing; Probabilistic logic; Source code; Skew; Sampling bias; Theoretical computer science; Computational biology; Algorithm; Biology; Artificial intelligence; Statistics; Programming language; Mathematics; Sample size determination","score_opus":0.02444510163836968,"score_gpt":0.2530713318885632,"score_spread":0.2286262302501935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401322700","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9510496,0.0014182475,0.046110395,0.00004436618,0.0002939926,0.00014624331,0.00003382466,0.00004726102,0.0008560591],"genre_scores_gemma":[0.9940265,0.00028078852,0.0048979986,0.00014624723,0.0002537577,0.0000070282485,0.0001824617,0.000013223542,0.0001919866],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994007,0.000012920664,0.0002294825,0.00012330923,0.00009464969,0.00013897748],"domain_scores_gemma":[0.99974465,0.000024566823,0.000028050215,0.00011393807,0.000030519677,0.000058253314],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011597617,0.00011988197,0.00008794406,0.000047740676,0.000066523964,0.00011790255,0.00006257343,0.000113299204,0.000009124175],"category_scores_gemma":[0.00005473028,0.0001052887,0.00004709153,0.00005987512,0.000050393548,0.000016025162,0.000022331686,0.00008851373,0.000010321681],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007374652,0.00009391526,0.0036129153,0.0010048796,0.00010497914,0.000012817451,0.0019721317,0.00064743427,0.957043,0.00051053334,0.0016213579,0.0333023],"study_design_scores_gemma":[0.00050923397,0.00046067373,0.0008767892,0.00023265385,0.000060154765,0.00004072381,0.00024516875,0.21082665,0.7608441,0.0000359841,0.025373675,0.00049421383],"about_ca_topic_score_codex":0.0000047303083,"about_ca_topic_score_gemma":0.000011816268,"teacher_disagreement_score":0.21017921,"about_ca_system_score_codex":0.0000075694606,"about_ca_system_score_gemma":0.00007913904,"threshold_uncertainty_score":0.42935488},"labels":[],"label_agreement":null},{"id":"W4401666005","doi":"10.1093/bioinformatics/btae517","title":"Spaln3: improvement in speed and accuracy of genome mapping and spliced alignment of protein query sequences","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Genetics; National Institute of Advanced Industrial Science and Technology","keywords":"Vectorization (mathematics); Computer science; SIMD; Genome; Multiple sequence alignment; Sequence (biology); Smith–Waterman algorithm; Dynamic programming; Sequence alignment; Alignment-free sequence analysis; Speedup; Computational biology; Reference genome; Parallel computing; Gene; Algorithm; Genetics; Biology; Peptide sequence","score_opus":0.014101316815504597,"score_gpt":0.23624416687569055,"score_spread":0.22214285006018597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401666005","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.995193,0.0038571055,0.00021189521,0.000064928856,0.000030010284,0.0003059359,0.000033321532,0.0000014437524,0.00030233822],"genre_scores_gemma":[0.9941909,0.0013665977,0.004338505,0.00003059123,0.000019987123,0.000007884224,0.000008663282,0.000005049605,0.000031851632],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993977,0.0000066218417,0.00032305307,0.000098399825,0.0000669751,0.00010725958],"domain_scores_gemma":[0.9997408,0.000011240852,0.00008998499,0.00010967443,0.000022636857,0.000025713214],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015888766,0.00009048709,0.00013530786,0.000054472748,0.000015100046,0.000014170626,0.00005570843,0.000046973546,0.0000014400263],"category_scores_gemma":[0.000020544756,0.00007679163,0.000023684921,0.000053340103,0.0000741941,0.000002164203,0.00013205303,0.000027507538,3.4354045e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000913116,0.000010563967,0.00074719364,0.0006238727,0.000051003935,6.3337194e-7,0.00080664956,0.000020801324,0.9907558,0.00016693122,0.000007721191,0.0067997305],"study_design_scores_gemma":[0.0011116816,0.0011535734,0.030356975,0.00047663692,0.000049063237,0.000017259972,0.0049337526,0.0070766425,0.94401497,0.00086569856,0.009425496,0.0005182809],"about_ca_topic_score_codex":0.00005279938,"about_ca_topic_score_gemma":0.000012551846,"teacher_disagreement_score":0.04674083,"about_ca_system_score_codex":0.0000074408636,"about_ca_system_score_gemma":0.000040050705,"threshold_uncertainty_score":0.31314716},"labels":[],"label_agreement":null},{"id":"W4401835088","doi":"10.1093/bioinformatics/btae525","title":"FateNet: an integration of dynamical systems and deep learning for cell fate prediction","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of Waterloo","funders":"Fonds de recherche du Québec – Nature et technologies","keywords":"Computer science; Deep learning; Artificial intelligence; Machine learning","score_opus":0.012743921212909527,"score_gpt":0.23074258807812947,"score_spread":0.21799866686521996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401835088","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62915075,0.0007170711,0.36928853,0.000006500981,0.00029149008,0.0001926398,0.000036513014,0.000024586107,0.00029192676],"genre_scores_gemma":[0.9948749,0.0002420829,0.0041566608,0.000009477009,0.00008845378,0.000011152403,0.00047093304,0.000012303451,0.00013403357],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995108,0.000013458418,0.00023259113,0.00009071098,0.00005912741,0.00009331535],"domain_scores_gemma":[0.9997764,0.000010225198,0.000045064866,0.00007949743,0.000050836617,0.00003795882],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011893457,0.00008109139,0.000084972875,0.000038692204,0.00004049034,0.000053484007,0.000046009915,0.000115729556,7.297275e-7],"category_scores_gemma":[0.000015387624,0.00006907025,0.000036939055,0.000036277674,0.000030589497,0.000013700605,0.000011850536,0.00005529609,8.820356e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009988261,0.000054649045,0.00088783505,0.0012838526,0.00004636457,3.3742288e-7,0.0012670045,0.0025198972,0.9506425,0.0005050237,0.00009746093,0.04259518],"study_design_scores_gemma":[0.00024734772,0.00061432825,0.00020918496,0.000047276877,0.000028138344,0.0000060644115,0.0005209486,0.9517313,0.04291782,0.00001890828,0.0035701098,0.00008857338],"about_ca_topic_score_codex":0.00001100366,"about_ca_topic_score_gemma":0.000008822695,"teacher_disagreement_score":0.9492114,"about_ca_system_score_codex":0.000008314729,"about_ca_system_score_gemma":0.000018130746,"threshold_uncertainty_score":0.28166032},"labels":[],"label_agreement":null},{"id":"W4402253411","doi":"10.1093/bioinformatics/btae398","title":"skandiver: a divergence-based analysis tool for identifying intercellular mobile genetic elements","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bacteriophages and microbial interactions","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Carnegie Mellon University","keywords":"Mobile genetic elements; Genome; Scalability; Transposable element; Plasmid; Computational biology; Annotation; Biology; Computer science; Genetics; Gene; Database","score_opus":0.017636749436864878,"score_gpt":0.2702004668755518,"score_spread":0.25256371743868694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402253411","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.650939,0.00006825323,0.34717342,0.000026156718,0.00053542753,0.0004856385,0.00017940448,0.00008258312,0.0005101132],"genre_scores_gemma":[0.9528493,0.000035124427,0.045336682,0.00019219592,0.00003573241,0.00010029617,0.00012701662,0.000012351813,0.0013112967],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991728,0.000010346898,0.00035783325,0.00014200667,0.000108634435,0.00020838785],"domain_scores_gemma":[0.9996579,0.000038425394,0.0000646243,0.00018000812,0.000009172988,0.00004983561],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00014384695,0.00011461938,0.00012056118,0.000107076856,0.00013030568,0.00020937933,0.00017251393,0.000041716943,0.0042457255],"category_scores_gemma":[0.00001012278,0.000101065365,0.00022788963,0.00038440817,0.000041618598,0.0003303362,0.00011937454,0.000060360537,0.0010110001],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014985066,0.00067225035,0.058015864,0.0021120787,0.0039271573,0.00006288498,0.015541534,0.044534586,0.39133856,0.00014813032,0.0742059,0.4092912],"study_design_scores_gemma":[0.00033395985,0.00015925018,0.027366672,0.00008026911,0.0010283142,0.0000047133126,0.0003875057,0.79328674,0.008474647,0.000054155193,0.16839749,0.00042625566],"about_ca_topic_score_codex":0.00006505147,"about_ca_topic_score_gemma":0.000040196337,"teacher_disagreement_score":0.7487522,"about_ca_system_score_codex":0.000132942,"about_ca_system_score_gemma":0.0000099966255,"threshold_uncertainty_score":0.9997668},"labels":[],"label_agreement":null},{"id":"W4402253482","doi":"10.1093/bioinformatics/btae391","title":"GGTyper: genotyping complex structural variants using short-read sequencing data","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Amgen (Canada)","funders":"Berlin Institute of Health","keywords":"Genotyping; Computer science; Computational biology; Genetics; Biology; Genotype; Gene","score_opus":0.09498124191876284,"score_gpt":0.3235446239675812,"score_spread":0.22856338204881838,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402253482","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9769155,0.002183044,0.017277727,0.000033771077,0.0007108682,0.00021654456,0.0008109632,0.000059852904,0.0017917508],"genre_scores_gemma":[0.972511,0.000100120604,0.024765855,0.00019437411,0.00033381343,0.0000012211422,0.0020030136,0.000025441102,0.000065188266],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999131,0.000012650301,0.0002798244,0.00021480145,0.000113807575,0.0002479009],"domain_scores_gemma":[0.99922967,0.0000075558573,0.000036306,0.00059673743,0.000041777646,0.000087975495],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012428159,0.0001546121,0.000116490366,0.00005066528,0.00013052771,0.00016124902,0.0003762712,0.0000922161,0.000045241664],"category_scores_gemma":[0.00003488329,0.00013442921,0.00005506149,0.0000851035,0.000043884324,0.000023483693,0.00040270056,0.00007033398,0.00002345059],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009909982,0.000038824997,0.0015496205,0.0016185418,0.0009957014,0.00017055958,0.0016105009,0.0051365127,0.86610824,0.0018353721,0.014671705,0.10616532],"study_design_scores_gemma":[0.00015210372,0.00005103736,0.0010744449,0.00008186243,0.00010202897,0.0003151855,0.00057865604,0.96550196,0.0020939787,0.00010208287,0.029510396,0.00043626002],"about_ca_topic_score_codex":0.000023127706,"about_ca_topic_score_gemma":0.000013824024,"teacher_disagreement_score":0.9603655,"about_ca_system_score_codex":0.00003600644,"about_ca_system_score_gemma":0.00024815826,"threshold_uncertainty_score":0.54818636},"labels":[],"label_agreement":null},{"id":"W4402348973","doi":"10.1093/bioinformatics/btae546","title":"Bin2cell reconstructs cells from high resolution Visium HD data","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":75,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; Medical Research Council; UK Research and Innovation; Wellcome Trust; Canadian Institute for Advanced Research","keywords":"Python (programming language); Computer science; Software; Documentation; Segmentation; Open source; Image resolution; Artificial intelligence; Data mining; Information retrieval; Computer graphics (images); Computer vision; Operating system","score_opus":0.023994808084351116,"score_gpt":0.23487815531196674,"score_spread":0.21088334722761562,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402348973","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90961367,0.003538109,0.06682969,0.000372863,0.0069304416,0.0004696643,0.0034964995,0.00022874524,0.008520298],"genre_scores_gemma":[0.93095165,0.0012045543,0.058356676,0.00051353185,0.001119483,0.0000053771773,0.006740862,0.000052876363,0.0010550024],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99896896,0.000020715837,0.00036043825,0.00026930607,0.0001473474,0.00023323743],"domain_scores_gemma":[0.999033,0.000021720965,0.000058289792,0.00076516066,0.000037186925,0.00008466085],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016126777,0.00016955532,0.00013788744,0.000052227664,0.00007027177,0.00014453426,0.0004292763,0.00020469895,0.000053846037],"category_scores_gemma":[0.000026593174,0.00015468273,0.000056708366,0.0001062684,0.000073090356,0.000025737265,0.00018677636,0.00012414157,0.00021801019],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000102001715,0.000080403435,0.0002414648,0.00033796334,0.00020907377,0.0000128132515,0.00036807364,0.0001423995,0.8423796,0.0003478244,0.08967322,0.06610513],"study_design_scores_gemma":[0.0006917182,0.00022581822,0.00020223741,0.00013890579,0.00011147125,0.000019499439,0.0001999569,0.1166507,0.4155276,0.000337024,0.46528235,0.00061269273],"about_ca_topic_score_codex":0.00012858228,"about_ca_topic_score_gemma":0.00005523751,"teacher_disagreement_score":0.42685202,"about_ca_system_score_codex":0.000017817272,"about_ca_system_score_gemma":0.0001165898,"threshold_uncertainty_score":0.6307779},"labels":[],"label_agreement":null},{"id":"W4402947492","doi":"10.1093/bioinformatics/btae561","title":"RetroCaptioner: beyond attention in end-to-end retrosynthesis transformer via contrastively captioned learnable graph representation","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Young Scientists Fund; National Natural Science Foundation of China; Central South University; Institute for Catastrophic Loss Reduction","keywords":"Computer science; Encoder; Transformer; Artificial intelligence; Graph; Natural language processing; Theoretical computer science; Engineering","score_opus":0.012636624051815783,"score_gpt":0.2618396766940532,"score_spread":0.24920305264223744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402947492","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7068011,0.00006309303,0.2860239,0.0011297574,0.0013319072,0.0006151221,0.000100159756,0.00033702864,0.003597897],"genre_scores_gemma":[0.96266866,0.000036753987,0.036265384,0.00017974799,0.00010458532,0.00006706943,0.00006932908,0.00002802958,0.0005804673],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99739146,0.00014583209,0.0008508379,0.00038941734,0.0007107621,0.0005116874],"domain_scores_gemma":[0.999154,0.00014285957,0.00015901307,0.00030659005,0.00009594141,0.00014165381],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0017788443,0.00024101629,0.00030913702,0.00053590944,0.0002076995,0.00055193226,0.00032606648,0.00013020498,0.0015627688],"category_scores_gemma":[0.00026851744,0.0002174132,0.00009779,0.0009469861,0.00012611577,0.0015117344,0.000045342087,0.00020753432,0.0016966462],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007621308,0.000039118928,0.0015032872,0.00025043407,0.00001033978,0.000010932409,0.0024153418,0.005041349,0.9811993,0.0015229107,0.0007532555,0.007177501],"study_design_scores_gemma":[0.0014403241,0.0006306241,0.1024184,0.0008960451,0.00014181023,0.00016282775,0.0028016432,0.6401425,0.23891737,0.0063313777,0.0044930405,0.0016240488],"about_ca_topic_score_codex":0.00046384297,"about_ca_topic_score_gemma":0.00012672249,"teacher_disagreement_score":0.742282,"about_ca_system_score_codex":0.0001879409,"about_ca_system_score_gemma":0.000083428706,"threshold_uncertainty_score":0.99934995},"labels":[],"label_agreement":null},{"id":"W4403113340","doi":"10.1093/bioinformatics/btae589","title":"Learning to explain is a good biomedical few-shot learner","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Natural Science Foundation of China; Fundamental Research Funds for the Central Universities; Institute for Catastrophic Loss Reduction","keywords":"Computer science; Shot (pellet); One shot; Artificial intelligence; Chemistry; Engineering; Mechanical engineering","score_opus":0.035562380217422467,"score_gpt":0.29649448069667717,"score_spread":0.2609321004792547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403113340","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012516186,0.00018953565,0.9557982,0.0070677237,0.0012557029,0.00032057555,0.0000061762353,0.0010348755,0.02181103],"genre_scores_gemma":[0.68541676,0.000098615594,0.2954409,0.006416241,0.0005269985,0.00008907572,0.00002210421,0.000066246175,0.011923065],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979529,0.000040738276,0.0005378892,0.00029382465,0.00059773144,0.000576917],"domain_scores_gemma":[0.9988585,0.00018262268,0.000056647303,0.0005071816,0.00007729267,0.00031773842],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00068423885,0.00020506528,0.00018907216,0.00038232392,0.00021225504,0.0008585477,0.0009559494,0.00012224662,0.00016881239],"category_scores_gemma":[0.0002237391,0.0001779664,0.00010190538,0.0013730344,0.00006360257,0.0011763547,0.0004868513,0.0003638254,0.009011252],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008806258,0.00010227287,0.000099361874,0.00035725092,0.00007211043,0.0001520492,0.10038531,0.00082361,0.0013289938,0.13824886,0.08174791,0.6766735],"study_design_scores_gemma":[0.000037257898,0.00023701174,0.000012082659,0.0001007346,0.0000050507283,0.000034191027,0.0021034537,0.54781,0.004902814,0.0009027354,0.4436105,0.00024415128],"about_ca_topic_score_codex":0.00003027955,"about_ca_topic_score_gemma":0.0000052500827,"teacher_disagreement_score":0.67642933,"about_ca_system_score_codex":0.000104503415,"about_ca_system_score_gemma":0.00017054021,"threshold_uncertainty_score":0.9917604},"labels":[],"label_agreement":null},{"id":"W4403299283","doi":"10.1093/bioinformatics/btae601","title":"MNBC: a multithreaded Minimizer-based Naïve Bayes Classifier for improved metagenomic sequence classification","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Agency of Canada; University of Manitoba; Agriculture and Agri-Food Canada; Canadian Food Inspection Agency","funders":"Public Health Agency; Public Health Agency of Canada; Agriculture and Agri-Food Canada; Canadian Food Inspection Agency; University of Lethbridge","keywords":"Metagenomics; Naive Bayes classifier; Classifier (UML); Computer science; Bayes' theorem; Artificial intelligence; Bayes classifier; Pattern recognition (psychology); Sequence (biology); Machine learning; Computational biology; Bayesian probability; Biology; Support vector machine; Genetics","score_opus":0.05319947061359019,"score_gpt":0.29396832035820253,"score_spread":0.24076884974461232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403299283","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6323965,0.007983851,0.34366742,0.0025981122,0.0027696425,0.0036981767,0.0022101516,0.00014593119,0.004530198],"genre_scores_gemma":[0.9047497,0.00028005932,0.09274755,0.000504222,0.00026335934,0.0002313277,0.00043051149,0.00004348296,0.0007497887],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989656,0.0000159482,0.00039437096,0.00026528278,0.00007710482,0.00028166067],"domain_scores_gemma":[0.99931043,0.00005574178,0.00010262241,0.00035102514,0.00010656735,0.000073610776],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020425522,0.00021698636,0.00018675993,0.00007061778,0.000114272545,0.00010322353,0.00019898247,0.00016436848,0.000007077058],"category_scores_gemma":[0.00008366531,0.00018754732,0.00017975294,0.00008813557,0.000097917204,0.0000036559986,0.00005645135,0.00006674754,0.000025660882],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000084137784,0.000033169123,0.000060098788,0.00027152587,0.00020914568,4.602289e-7,0.00026932667,0.00009873966,0.9706784,0.00050221523,0.0051488443,0.02264397],"study_design_scores_gemma":[0.0012583893,0.00049825426,0.00075436156,0.00005211767,0.00018155607,0.000009311759,0.000588608,0.49961174,0.17331791,0.00032134584,0.32277912,0.00062728033],"about_ca_topic_score_codex":0.0000050595427,"about_ca_topic_score_gemma":0.00001774937,"teacher_disagreement_score":0.7973605,"about_ca_system_score_codex":0.000035815287,"about_ca_system_score_gemma":0.00020803542,"threshold_uncertainty_score":0.7647958},"labels":[],"label_agreement":null},{"id":"W4403597831","doi":"10.1093/bioinformatics/btae634","title":"PONYTA: prioritization of phenotype-related genes from mouse KO events using PU learning on a biological network","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; Seoul National University; National Research Foundation","keywords":"False positive paradox; Cutoff; Phenotype; Transcriptome; Computational biology; Gene; Benchmark (surveying); Biology; Prioritization; Gene regulatory network; Computer science; Genetics; Gene expression; Machine learning; Physics","score_opus":0.015840838371398647,"score_gpt":0.24211639001666194,"score_spread":0.22627555164526328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403597831","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9583658,0.0029865587,0.035925407,0.000032719578,0.0006999214,0.0003129792,0.000076401586,0.00007042309,0.0015298027],"genre_scores_gemma":[0.9826708,0.001061979,0.014632727,0.00013038074,0.0004066712,0.000004915356,0.0008456267,0.000030956373,0.00021595422],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99876046,0.00004017586,0.00060265564,0.00016467423,0.00015031635,0.00028173416],"domain_scores_gemma":[0.99940485,0.000035006975,0.00019283117,0.00023864889,0.000057481946,0.000071180424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025165238,0.00020178931,0.00021261864,0.00005751566,0.0001013215,0.000046954774,0.00017022509,0.00032735718,0.000027999047],"category_scores_gemma":[0.000040214232,0.00016950912,0.00012210773,0.00018287246,0.000057257726,0.00001504364,0.00013099346,0.00018884684,0.000039087936],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00076826254,0.00038983644,0.011445184,0.00094555813,0.0022440813,0.00001603944,0.0037725812,0.41284925,0.28580394,0.01111328,0.010746744,0.25990522],"study_design_scores_gemma":[0.0011864427,0.0010013125,0.001582771,0.0005367343,0.00012062472,0.000021689439,0.0005310504,0.93290913,0.013684947,0.0023336103,0.045142952,0.0009487104],"about_ca_topic_score_codex":0.0000116190095,"about_ca_topic_score_gemma":0.0000032114478,"teacher_disagreement_score":0.5200599,"about_ca_system_score_codex":0.00002692096,"about_ca_system_score_gemma":0.000076236596,"threshold_uncertainty_score":0.6912381},"labels":[],"label_agreement":null},{"id":"W4403597865","doi":"10.1093/bioinformatics/btae622","title":"Biologically-informed killer cell immunoglobulin-like receptor gene annotation tool","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Immune Cell Function and Interaction","field":"Immunology and Microbiology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"National Cancer Institute; National Institutes of Health","keywords":"Genotyping; Annotation; Computational biology; Computer science; Gene; Identification (biology); Biology; Genetics; Genotype","score_opus":0.013490382800119905,"score_gpt":0.23653785458795284,"score_spread":0.22304747178783293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403597865","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60253894,0.02060013,0.040436137,0.002421724,0.16221128,0.002802754,0.00019109985,0.004154663,0.16464327],"genre_scores_gemma":[0.779688,0.0032708654,0.011967503,0.0038852934,0.00033737932,0.00013523045,0.0067624147,0.000081194135,0.1938721],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987575,0.000045567434,0.0006505063,0.00016086778,0.00005307326,0.00033249482],"domain_scores_gemma":[0.99936354,0.00013833502,0.0001323351,0.00026078924,0.00008493801,0.000020042233],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00020637391,0.00022204155,0.0002010862,0.00017856598,0.00018688373,0.00011020733,0.00017123,0.00033470555,0.0042252988],"category_scores_gemma":[0.00006911649,0.00017035102,0.0001570649,0.00022745614,0.000088542845,0.00053293566,0.00006873092,0.00034193997,0.026439525],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033008712,0.00014278998,0.00012861974,0.0002854177,0.00030051696,0.0000031283287,0.0026671868,0.00003634491,0.2767324,0.0010857552,0.6780381,0.040249668],"study_design_scores_gemma":[0.0005278205,0.00021752523,0.0003979324,0.000051898653,0.000034797267,0.00005227014,0.0004928233,0.00073733786,0.06286163,0.000020170535,0.9343454,0.0002603789],"about_ca_topic_score_codex":0.000011717488,"about_ca_topic_score_gemma":7.476846e-7,"teacher_disagreement_score":0.2563073,"about_ca_system_score_codex":0.00012307867,"about_ca_system_score_gemma":0.000113568654,"threshold_uncertainty_score":0.99668497},"labels":[],"label_agreement":null},{"id":"W4403680155","doi":"10.1093/bioinformatics/btae636","title":"EuDockScore: Euclidean graph neural networks for scoring protein–protein interfaces","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Monoclonal and Polyclonal Antibodies Research","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto; University of New Brunswick","funders":"Canadian Institutes of Health Research; Alliance de recherche numérique du Canada","keywords":"Computer science; Macromolecular docking; Docking (animal); Artificial intelligence; Machine learning; Artificial neural network; Graph; Protein–protein interaction; Computational biology; Protein structure; Theoretical computer science; Biology","score_opus":0.03702823887180946,"score_gpt":0.31701686099494925,"score_spread":0.2799886221231398,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403680155","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95233035,0.0033368072,0.030771162,0.00347654,0.00073042826,0.003124488,0.00007402237,0.0004173206,0.005738851],"genre_scores_gemma":[0.9740282,0.00009699019,0.016022071,0.00032940967,0.00071887,0.00019432603,0.000082892824,0.000046728033,0.008480495],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984901,0.000014807108,0.00047885836,0.00017397739,0.00034132952,0.0005009421],"domain_scores_gemma":[0.9993317,0.00008912616,0.000056795478,0.0002229897,0.000098637276,0.00020074948],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030199846,0.0002157877,0.00027691448,0.00019491905,0.00014043348,0.00017625923,0.00016934487,0.000101531194,0.00007883073],"category_scores_gemma":[0.000082435145,0.00015389273,0.00019670412,0.00030571528,0.00011291034,0.00025861076,0.000117421696,0.00036354148,0.00008221998],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0030030708,0.00045790154,0.0022787396,0.025803084,0.0012399404,0.000361658,0.0042033275,0.0010762645,0.018614389,0.03557979,0.043019287,0.86436254],"study_design_scores_gemma":[0.0007340692,0.0013894363,0.00032866324,0.0017435051,0.000072006,0.00014446279,0.00034355395,0.932017,0.009923775,0.00091983954,0.052009396,0.00037428833],"about_ca_topic_score_codex":0.000032100525,"about_ca_topic_score_gemma":0.000006982388,"teacher_disagreement_score":0.93094075,"about_ca_system_score_codex":0.00004135935,"about_ca_system_score_gemma":0.00007676075,"threshold_uncertainty_score":0.6275563},"labels":[],"label_agreement":null},{"id":"W4404091271","doi":"10.1093/bioinformatics/btae660","title":"ADTGP: correcting single-cell antibody sequencing data using Gaussian process regression","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Interpretability; Computer science; R package; Isotype; Raw data; Regression; Process (computing); Count data; Data mining; Algorithm; Computational biology; Statistics; Mathematics; Artificial intelligence; Antibody; Biology; Immunology; Computational science","score_opus":0.06228579374345745,"score_gpt":0.3170366147317804,"score_spread":0.25475082098832297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404091271","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9124051,0.0016491001,0.07865328,0.000036403435,0.0014529328,0.00025648403,0.00010507566,0.00012900005,0.0053126505],"genre_scores_gemma":[0.9825511,0.00009227285,0.01557225,0.00013474018,0.00043712833,0.0000019947695,0.00088209735,0.00005161278,0.00027682178],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986179,0.000025477888,0.0004461057,0.00033672256,0.00021908521,0.00035473704],"domain_scores_gemma":[0.99904794,0.000019679572,0.000116691874,0.0006429946,0.000067582165,0.000105102314],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028796482,0.00024797875,0.00018220101,0.000090674526,0.00017747967,0.00022358418,0.0004680261,0.00020808779,0.000011936192],"category_scores_gemma":[0.00007834714,0.00020776018,0.00007050674,0.00021914595,0.00006367006,0.00005612036,0.00019367592,0.00019671021,0.000019791461],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033631884,0.000050118466,0.0010855806,0.0010372502,0.00004314932,0.000016976954,0.0009895551,0.0003612292,0.9819454,0.000008957878,0.00087163533,0.013556518],"study_design_scores_gemma":[0.00046259194,0.00023472893,0.000026831802,0.0009415872,0.000101507314,0.00024281688,0.0019416464,0.50441605,0.48146287,0.000025433063,0.009488948,0.0006550094],"about_ca_topic_score_codex":0.000027902315,"about_ca_topic_score_gemma":0.000012770809,"teacher_disagreement_score":0.50405484,"about_ca_system_score_codex":0.000052988347,"about_ca_system_score_gemma":0.00028308266,"threshold_uncertainty_score":0.84722143},"labels":[],"label_agreement":null},{"id":"W4404185145","doi":"10.1093/bioinformatics/btae666","title":"MR Corge: sensitivity analysis of Mendelian randomization based on the core gene hypothesis for polygenic exposures","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Montreal Heart Institute","funders":"Japan Society for the Promotion of Science; Canadian Institutes of Health Research; Compute Canada; Division of Graduate Education; University of Wisconsin-Madison","keywords":"Mendelian randomization; Sensitivity (control systems); Computational biology; Mendelian inheritance; Biology; Core (optical fiber); Genetics; Gene; Computer science; Statistics; Mathematics; Genetic variants; Genotype","score_opus":0.027509506983968125,"score_gpt":0.2652732472096275,"score_spread":0.2377637402256594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404185145","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6631386,0.00024986026,0.33407283,0.00081713323,0.00019340422,0.0005111346,0.0005636152,0.000020653879,0.00043275292],"genre_scores_gemma":[0.98798734,0.00007325375,0.01075905,0.0005367444,0.000057022356,0.00003204166,0.0004139603,0.000010399327,0.00013016669],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99918795,0.00007809433,0.00036357276,0.00012050794,0.00009949098,0.00015040128],"domain_scores_gemma":[0.998954,0.0004905933,0.00014599969,0.00028215282,0.00009671754,0.000030555282],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00088302227,0.00011011145,0.00023072475,0.00012847257,0.00007811645,0.000017618655,0.00007915396,0.00012330322,0.000015557423],"category_scores_gemma":[0.00069533335,0.00007439841,0.0002757516,0.00029031886,0.000046774257,0.0000026005714,0.000021403706,0.000037495098,0.0000037461148],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019343665,0.00044784838,0.045409262,0.0007043374,0.013675754,0.0000033842605,0.0017776638,0.42312586,0.3625225,0.003967009,0.09468912,0.05174287],"study_design_scores_gemma":[0.0005443397,0.00016445806,0.008135719,0.00001024125,0.0006722297,9.955284e-7,0.00013313207,0.96894604,0.019081036,0.00007735301,0.0021083334,0.00012611826],"about_ca_topic_score_codex":0.000009296651,"about_ca_topic_score_gemma":0.00003165716,"teacher_disagreement_score":0.5458202,"about_ca_system_score_codex":0.000015470257,"about_ca_system_score_gemma":0.0000761438,"threshold_uncertainty_score":0.30338794},"labels":[],"label_agreement":null},{"id":"W4404607640","doi":"10.1093/bioinformatics/btae701","title":"Sparse Neighbor Joining: rapid phylogenetic inference using a sparse distance matrix","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Vetenskapsrådet","keywords":"Distance matrix; Python (programming language); Computer science; Sparse matrix; Distance matrices in phylogeny; Phylogenetic tree; Inference; Computation; Matrix (chemical analysis); Set (abstract data type); Tree (set theory); Algorithm; Theoretical computer science; Data mining; Combinatorics; Artificial intelligence; Mathematics; Biology","score_opus":0.030483514826302148,"score_gpt":0.2807530257646901,"score_spread":0.25026951093838795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404607640","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93348676,0.01855364,0.042054392,0.00011842923,0.0010542949,0.00042991783,0.0001987599,0.000041233077,0.004062604],"genre_scores_gemma":[0.9761104,0.0015650741,0.02136079,0.00019172224,0.00032003564,0.000016077189,0.000046687903,0.000036854275,0.00035238973],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986752,0.000022988084,0.00045321896,0.00027721366,0.00017058618,0.0004007797],"domain_scores_gemma":[0.9992318,0.00002892689,0.00010381388,0.00044553855,0.00007493351,0.00011494491],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00017206544,0.0002806445,0.0002247263,0.00008022985,0.00013010613,0.00014075219,0.0002501943,0.00014229491,0.000027723003],"category_scores_gemma":[0.00006740726,0.0002530804,0.00013322289,0.0001879837,0.00011919688,0.0000041833164,0.00022463329,0.00010841376,0.00006574015],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019923238,0.00020820803,0.012132728,0.0016746774,0.0010745163,0.000060022543,0.0035784803,0.008027098,0.8821164,0.0067216307,0.011591227,0.072615795],"study_design_scores_gemma":[0.0013157782,0.0009604467,0.0050186263,0.00040524433,0.0003322067,0.00018949293,0.0011856146,0.26746213,0.06868645,0.0010296407,0.6513681,0.0020462768],"about_ca_topic_score_codex":0.000008481519,"about_ca_topic_score_gemma":0.000009494375,"teacher_disagreement_score":0.81342995,"about_ca_system_score_codex":0.000027431219,"about_ca_system_score_gemma":0.00018060619,"threshold_uncertainty_score":0.99999213},"labels":[],"label_agreement":null},{"id":"W4404691004","doi":"10.1093/bioinformatics/btae707","title":"<i>lefser</i>: implementation of metagenomic biomarker discovery tool, <i>LEfSe</i>, in R","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Population and Public Health","funders":"National Cancer Institute; National Institutes of Health","keywords":"Bioconductor; Python (programming language); Metagenomics; Computer science; Software; Data mining; Source code; JavaScript; Benchmarking; Visualization; Population; Data science; Biology; World Wide Web; Operating system","score_opus":0.01587551541960474,"score_gpt":0.29522894954475254,"score_spread":0.2793534341251478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404691004","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97787976,0.0014513879,0.01710249,0.00025921626,0.0004824998,0.00030279244,0.00008126764,0.0000212977,0.0024192627],"genre_scores_gemma":[0.99723405,0.00048156164,0.0014823107,0.00015298516,0.000042355518,0.000023581628,0.00021781455,0.000011214687,0.00035413873],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999236,0.000019702,0.00038544476,0.00012394099,0.0001121252,0.00012277388],"domain_scores_gemma":[0.9996505,0.0000071667287,0.000077432196,0.00021723099,0.000024863282,0.000022839762],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019018882,0.000093776434,0.000091809736,0.00011702419,0.000018639006,0.000048613983,0.00010589616,0.000068141984,0.000028355922],"category_scores_gemma":[0.000010069515,0.00008128695,0.00006816099,0.0001862752,0.000027917522,0.000030677846,0.00005404518,0.000039853687,0.000015027411],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035561097,0.000031659703,0.0020586697,0.00024474616,0.000051183848,8.6879635e-7,0.00043429495,0.000044657496,0.92949176,0.0014080396,0.016544873,0.049653705],"study_design_scores_gemma":[0.00088374334,0.00016304593,0.025503706,0.00010972112,0.000041768657,0.000011174402,0.0020040777,0.0033790744,0.72145915,0.00025488218,0.24581805,0.00037161115],"about_ca_topic_score_codex":0.000013118479,"about_ca_topic_score_gemma":0.000021175125,"teacher_disagreement_score":0.22927319,"about_ca_system_score_codex":0.000020210218,"about_ca_system_score_gemma":0.0001209787,"threshold_uncertainty_score":0.33147857},"labels":[],"label_agreement":null},{"id":"W4405218992","doi":"10.1093/bioinformatics/btae715","title":"VSS-Hi-C: variance-stabilized signals for chromatin contacts","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Variance (accounting); Computer science; Chromatin; Biology; Genetics; DNA; Business","score_opus":0.011047146874385268,"score_gpt":0.24874267685226964,"score_spread":0.23769552997788437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405218992","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7328436,0.002243423,0.2498627,0.00052967254,0.001520913,0.0016719989,0.0007615218,0.00019088222,0.010375331],"genre_scores_gemma":[0.9299527,0.00028105063,0.065944575,0.00054526736,0.00041558794,0.00012550072,0.00083895697,0.00006564398,0.0018307394],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989271,0.000013429037,0.00044003542,0.00019388231,0.000118314914,0.00030721948],"domain_scores_gemma":[0.9993477,0.00004778106,0.00009276072,0.00033652308,0.00008196551,0.000093302995],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027237006,0.00019843946,0.00019151178,0.000050541057,0.00008750225,0.0001580584,0.00021685446,0.00017489327,0.00004016787],"category_scores_gemma":[0.00010063956,0.00017853495,0.00016138847,0.00008947256,0.00004516783,0.000011701289,0.00008401761,0.00006784605,0.00006324537],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020349691,0.00018298492,0.000102306454,0.003200986,0.00063809956,0.000009168647,0.001762355,0.0017032517,0.8656073,0.011038816,0.081310265,0.034240954],"study_design_scores_gemma":[0.0019278373,0.00090763095,0.00018145204,0.00020943068,0.00012498705,0.00008624736,0.0005936289,0.4123192,0.121625684,0.0028181563,0.45826197,0.0009437449],"about_ca_topic_score_codex":0.0000030171425,"about_ca_topic_score_gemma":0.000008306215,"teacher_disagreement_score":0.74398166,"about_ca_system_score_codex":0.000031657248,"about_ca_system_score_gemma":0.00018296037,"threshold_uncertainty_score":0.7280444},"labels":[],"label_agreement":null},{"id":"W4405221092","doi":"10.1093/bioinformatics/btae719","title":"PheWAS analysis on large-scale biobank data with PheTK","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Human Genome Research Institute; National Institutes of Health","keywords":"Biobank; Computer science; Scale (ratio); Data science; Bioinformatics; Biology; Geography; Cartography","score_opus":0.01748673113263469,"score_gpt":0.2820495558834093,"score_spread":0.2645628247507746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405221092","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5623994,0.0021815535,0.39578286,0.0018522374,0.00070467545,0.0005217705,0.0022683034,0.00017858084,0.034110628],"genre_scores_gemma":[0.95217025,0.00035676712,0.039860956,0.0010475429,0.00026224012,0.000013104233,0.00463627,0.000024270284,0.0016286242],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99904865,0.000029207493,0.00027359044,0.00025247224,0.0001269453,0.00026915516],"domain_scores_gemma":[0.9989509,0.000027424448,0.00007182043,0.0008395075,0.000041486925,0.00006886592],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038486614,0.00014138827,0.00018619506,0.00010579523,0.000078895995,0.00005155376,0.00030831076,0.00013769543,0.00004826757],"category_scores_gemma":[0.000060894123,0.000102951955,0.00008258618,0.0003838174,0.00004184048,0.000007753111,0.00017091424,0.00008348917,0.0001264611],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003364129,0.00081876456,0.14216383,0.00066893816,0.014026663,0.000035135807,0.003032689,0.01695341,0.0038005689,0.0039985985,0.7420889,0.0720761],"study_design_scores_gemma":[0.00048266017,0.0005138408,0.015048965,0.000033173383,0.00079724274,0.000014852526,0.0008290463,0.31478968,0.00079899636,0.000049693786,0.6661792,0.00046268158],"about_ca_topic_score_codex":0.000009698892,"about_ca_topic_score_gemma":0.00013873873,"teacher_disagreement_score":0.38977084,"about_ca_system_score_codex":0.000010311672,"about_ca_system_score_gemma":0.000077570025,"threshold_uncertainty_score":0.4198259},"labels":[],"label_agreement":null},{"id":"W4405231346","doi":"10.1093/bioinformatics/btae729","title":"A BLAST from the past: revisiting blastp’s <i>E</i>-value","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Value (mathematics); Computer science; History; Psychology; Machine learning","score_opus":0.009638727986995934,"score_gpt":0.22526681105481872,"score_spread":0.21562808306782277,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405231346","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.956918,0.016640466,0.00695034,0.0022509391,0.0010717977,0.00037324792,0.00031089215,0.000037326987,0.015446964],"genre_scores_gemma":[0.98873097,0.0011380877,0.0064485115,0.0012961902,0.0018711593,0.000016827138,0.000094908115,0.000027296122,0.00037605202],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992789,0.000019131845,0.00025153015,0.00014336868,0.00010912908,0.00019791783],"domain_scores_gemma":[0.99952024,0.000051755014,0.000047257698,0.00030579502,0.000032743712,0.00004218451],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016413187,0.00014185885,0.00010157852,0.000014852445,0.00012539698,0.00012292423,0.000210181,0.00006883269,0.000010952352],"category_scores_gemma":[0.000043980584,0.0000946342,0.00009918322,0.00008057078,0.00006502034,0.0000014825587,0.00019667765,0.00008413793,0.00010095754],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012528061,0.00007832708,0.016690934,0.0007745721,0.0021179984,0.00002595095,0.010115798,0.00149823,0.36972108,0.008361496,0.30075902,0.28973132],"study_design_scores_gemma":[0.00021442761,0.000107653366,0.0040531824,0.000110795714,0.00007651965,0.000020787003,0.0009122858,0.008517909,0.00680122,0.00030905387,0.9785711,0.00030504732],"about_ca_topic_score_codex":0.000016368862,"about_ca_topic_score_gemma":0.000007333944,"teacher_disagreement_score":0.6778121,"about_ca_system_score_codex":0.000008227548,"about_ca_system_score_gemma":0.00004719234,"threshold_uncertainty_score":0.38590705},"labels":[],"label_agreement":null},{"id":"W4405356247","doi":"10.1093/bioinformatics/btae738","title":"DiffPaSS—high-performance differentiable pairing of protein sequences using soft scores","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Infection and Immunity","funders":"H2020 European Research Council; European Commission; Cancer Research UK","keywords":"Python (programming language); Hyperparameter; Computer science; Differentiable function; Pairing; Benchmark (surveying); Artificial intelligence; Similarity (geometry); Machine learning; Theoretical computer science; Graph; Data mining; Mathematics","score_opus":0.013342887466565215,"score_gpt":0.2266625405328697,"score_spread":0.21331965306630446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405356247","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9595784,0.0009887717,0.0380736,0.000020791844,0.0002511707,0.0002714448,0.000036276968,0.000037000525,0.00074252835],"genre_scores_gemma":[0.9818252,0.00013898384,0.017325182,0.00004431902,0.00016802218,0.000011921782,0.00007627296,0.000021955993,0.0003881733],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998793,0.000012419391,0.00054843404,0.00013968431,0.00019077625,0.00031566506],"domain_scores_gemma":[0.9993966,0.000011076693,0.00015066545,0.0003145796,0.000057859408,0.00006919234],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021598965,0.00020245208,0.00020300991,0.00008798632,0.00009238211,0.00009670749,0.00024452174,0.00016220425,0.000020668964],"category_scores_gemma":[0.000017198287,0.00016549282,0.00008789519,0.00015688829,0.00012275024,0.00003302262,0.000166675,0.00012303884,0.000018221617],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024118308,0.00023476985,0.00799331,0.013412343,0.0011123678,0.000010797531,0.0023826708,0.027646268,0.7602105,0.0076805227,0.005297699,0.17377757],"study_design_scores_gemma":[0.0004326488,0.0003983432,0.00073747634,0.00092906714,0.00007153462,0.00003885241,0.00024714024,0.7812956,0.20754573,0.0005494461,0.007164512,0.0005896618],"about_ca_topic_score_codex":0.000019116167,"about_ca_topic_score_gemma":0.0000047351077,"teacher_disagreement_score":0.75364935,"about_ca_system_score_codex":0.000021260117,"about_ca_system_score_gemma":0.00012879427,"threshold_uncertainty_score":0.6748601},"labels":[],"label_agreement":null},{"id":"W4405596815","doi":"10.1093/bioinformatics/btae748","title":"CParty: hierarchically constrained partition function of RNA pseudoknots","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Agence Nationale de la Recherche","keywords":"Pseudoknot; Partition function (quantum field theory); Algorithm; Partition (number theory); Partition problem; Computer science; Dynamic programming; Function (biology); Time complexity; Nucleic acid secondary structure; Mathematics; RNA; Combinatorics; Physics","score_opus":0.011570003130580743,"score_gpt":0.23340572108363922,"score_spread":0.22183571795305848,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405596815","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.606516,0.0013008905,0.35672376,0.00046307067,0.0011861945,0.0005804006,0.00013630287,0.00012765781,0.03296573],"genre_scores_gemma":[0.99070144,0.00012550561,0.00836605,0.00014879392,0.00013353114,0.000015977248,0.00010784653,0.000011775061,0.0003890836],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993369,0.00002130764,0.00028453374,0.000097980934,0.00012553301,0.00013375426],"domain_scores_gemma":[0.9996503,0.000015461199,0.000059231777,0.00018143986,0.00004343354,0.000050160113],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019756785,0.00009607235,0.00009770434,0.00004968729,0.000034417633,0.000031020107,0.000078490295,0.00011915055,0.00007518629],"category_scores_gemma":[0.00004976343,0.00008193294,0.000082483166,0.000078948586,0.000060733477,0.000009291247,0.000031897263,0.000050234084,0.000055763867],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000065256194,0.000022809252,0.000014725953,0.00025257745,0.00007301292,0.000001410403,0.00010767111,0.000026735843,0.8965563,0.008951973,0.002736897,0.09119062],"study_design_scores_gemma":[0.00028639418,0.0006698425,0.00012700434,0.0001288196,0.000057788213,0.000022236578,0.00012249651,0.004983454,0.92617273,0.0033205403,0.063866705,0.00024196222],"about_ca_topic_score_codex":0.0000013277585,"about_ca_topic_score_gemma":0.0000014329144,"teacher_disagreement_score":0.38418543,"about_ca_system_score_codex":0.0000053382537,"about_ca_system_score_gemma":0.000075752,"threshold_uncertainty_score":0.33411285},"labels":[],"label_agreement":null},{"id":"W4405625946","doi":"10.1093/bioinformatics/btag415","title":"Fitness translocation: improving variant effect prediction with biologically-grounded data augmentation","year":2024,"lang":"en","type":"preprint","venue":"Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Bottleneck; Fitness function; Computer science; Fitness landscape; Sequence (biology); Function (biology); Machine learning; Selection (genetic algorithm); Computational biology; Artificial intelligence; Biology; Genetics; Medicine; Genetic algorithm; Population","score_opus":0.02251479689590924,"score_gpt":0.2593764694314939,"score_spread":0.23686167253558466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405625946","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14885816,0.00236754,0.8385136,0.00039475274,0.0021561151,0.0030843627,0.0018548046,0.00027247562,0.0024981673],"genre_scores_gemma":[0.9036783,0.0006219892,0.074955195,0.0001882008,0.00091923383,0.00042506563,0.01878686,0.00008499423,0.00034014712],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984203,0.000092946524,0.0004988112,0.000502886,0.0002517584,0.00023327727],"domain_scores_gemma":[0.99839133,0.000026591983,0.0002627553,0.0011686662,0.00007547099,0.000075183394],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00072581746,0.00035086978,0.00027560984,0.000072527895,0.000101870726,0.0002358012,0.0006132376,0.0005459122,0.000019485073],"category_scores_gemma":[0.000067691326,0.00025257532,0.000079803176,0.00008784762,0.000062586936,0.000016373728,0.0008162822,0.00027113815,0.000031613887],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012832565,0.00019432677,0.000099969984,0.008687719,0.0015094108,0.00003784657,0.0009689135,0.0020373152,0.2913992,0.0009306229,0.0028932046,0.6899582],"study_design_scores_gemma":[0.004156947,0.006378142,0.0005063579,0.0029735519,0.0018858677,0.0005132994,0.00081439735,0.2272853,0.72845453,0.0041322066,0.019689199,0.0032101863],"about_ca_topic_score_codex":0.000029205923,"about_ca_topic_score_gemma":0.00001474512,"teacher_disagreement_score":0.76355845,"about_ca_system_score_codex":0.000037154416,"about_ca_system_score_gemma":0.0002345596,"threshold_uncertainty_score":0.99999267},"labels":[],"label_agreement":null},{"id":"W4406170484","doi":"10.1093/bioinformatics/btaf009","title":"BetaAlign: a deep learning approach for multiple sequence alignment","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Tel Aviv University; Azrieli Foundation; Israel Science Foundation","keywords":"Computer science; Artificial intelligence; Inference; Subspace topology; Multiple sequence alignment; Chunking (psychology); Sequence (biology); Sequence alignment; Smith–Waterman algorithm; Machine learning; Deep learning; Set (abstract data type); Phylogenomics; Phylogenetic tree; Biology","score_opus":0.025010616289056334,"score_gpt":0.25447387497717366,"score_spread":0.22946325868811734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406170484","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33873728,0.007902363,0.642973,0.00014192137,0.00066746655,0.0012237082,0.00016558892,0.00006062881,0.008128027],"genre_scores_gemma":[0.9122586,0.00032254338,0.086253904,0.000119745906,0.00018653601,0.00009816431,0.00020239479,0.000020298223,0.0005377987],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99930775,0.000009653517,0.00021627605,0.00016070665,0.00008353848,0.00022207823],"domain_scores_gemma":[0.99968815,0.000020986468,0.000040552466,0.00015946032,0.000040568797,0.000050275215],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001644416,0.00013429845,0.000108101245,0.000030115203,0.000107462496,0.00006199322,0.00012242777,0.000080942606,0.000001962631],"category_scores_gemma":[0.00004809358,0.00011664223,0.00009991575,0.000045166915,0.00004218015,0.0000015334373,0.00009057071,0.00004915073,0.000009871234],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015239688,0.00017915874,0.0038270352,0.0026249427,0.0013618175,0.0000048522365,0.005952908,0.02840487,0.77356935,0.0065078125,0.01000575,0.16740912],"study_design_scores_gemma":[0.000593079,0.00053733937,0.00022064889,0.000030182051,0.00008024334,0.000029675575,0.00096825714,0.5657169,0.04665251,0.00027788212,0.3843735,0.0005197847],"about_ca_topic_score_codex":0.0000028161548,"about_ca_topic_score_gemma":0.000001639912,"teacher_disagreement_score":0.7269168,"about_ca_system_score_codex":0.000015545498,"about_ca_system_score_gemma":0.00003448657,"threshold_uncertainty_score":0.4756532},"labels":[],"label_agreement":null},{"id":"W4406213027","doi":"10.1093/bioinformatics/btaf010","title":"FlowPacker: protein side-chain packing with torsional flow matching","year":2025,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Canadian Institutes of Health Research; Alliance de recherche numérique du Canada","keywords":"Computer science; Side chain; Matching (statistics); Graph; Algorithm; Source code; Folding (DSP implementation); Code (set theory); Chain (unit); Sequence (biology); Flow (mathematics); Set (abstract data type); Theoretical computer science; Programming language; Chemistry; Mathematics; Engineering; Biochemistry","score_opus":0.003672734255921913,"score_gpt":0.21323902876353262,"score_spread":0.20956629450761072,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406213027","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.556598,0.00028718644,0.42494866,0.00034141197,0.00024382077,0.0007349698,0.000057146797,0.00006928495,0.016719516],"genre_scores_gemma":[0.7728228,0.000019885578,0.22384442,0.0010513365,0.00016988895,0.000045518187,0.0003038861,0.00002472546,0.0017175141],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99915385,0.000016917893,0.00026101945,0.00015106627,0.00016490059,0.0002522328],"domain_scores_gemma":[0.99943537,0.000008186721,0.00008870197,0.00033569333,0.000072831805,0.000059214308],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013677856,0.00018234142,0.00014220478,0.00006296104,0.00013826214,0.00005707242,0.00018602643,0.00015376449,0.000007976705],"category_scores_gemma":[0.000043623906,0.00014231034,0.000060882663,0.00012964371,0.00005815896,0.000012101319,0.00014083993,0.00012033714,0.000010259334],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017804551,0.00032151197,0.0054791844,0.0026268181,0.0013109995,0.000056162837,0.0027392337,0.016091846,0.62300855,0.046234954,0.015631042,0.28471926],"study_design_scores_gemma":[0.008032513,0.0019072416,0.004407542,0.0019577127,0.00025924953,0.000269193,0.0033443214,0.17149737,0.5659974,0.023907226,0.21474549,0.003674719],"about_ca_topic_score_codex":0.0000082250235,"about_ca_topic_score_gemma":0.000032374188,"teacher_disagreement_score":0.28104454,"about_ca_system_score_codex":0.000023844319,"about_ca_system_score_gemma":0.00015821737,"threshold_uncertainty_score":0.5803247},"labels":[],"label_agreement":null},{"id":"W4406292104","doi":"10.1093/bioinformatics/btaf014","title":"PhyloMix: enhancing microbiome-trait association prediction through phylogeny-mixing augmentation","year":2025,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Microbiome; Computer science; Trait; Sample (material); Set (abstract data type); Machine learning; Phylogenetic tree; Raw data; Artificial intelligence; Phylogenetics; Data mining; Biology; Bioinformatics","score_opus":0.006999816828427663,"score_gpt":0.25921222452973497,"score_spread":0.2522124077013073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406292104","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8720597,0.00045646954,0.11070412,0.00045694577,0.0015689087,0.0007628845,0.0002639225,0.000097878125,0.01362916],"genre_scores_gemma":[0.96253055,0.00039815978,0.028148439,0.002728866,0.00035023747,0.000032907297,0.0016768744,0.000025331547,0.0041086297],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989616,0.000032355943,0.00045879712,0.00015949122,0.000103440165,0.00028426398],"domain_scores_gemma":[0.9994039,0.000014995195,0.00023500672,0.00020083904,0.000110834546,0.000034452936],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028618932,0.00014577378,0.00013776195,0.000075323966,0.00019405442,0.000057610363,0.00011423446,0.0002309448,0.000014529625],"category_scores_gemma":[0.00006996991,0.00015225085,0.00008134632,0.00018900138,0.00002159703,0.000021883525,0.00006480094,0.00009854532,0.00003091389],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002155855,0.000036322665,0.0017309085,0.00018804477,0.000073559866,1.2396603e-7,0.0005095596,0.00003280192,0.9789893,0.00014694175,0.016553694,0.001717191],"study_design_scores_gemma":[0.002140046,0.00025209607,0.026631279,0.00019569944,0.00011162857,0.000009430784,0.001374883,0.0013028464,0.836987,0.00020628305,0.13036074,0.00042805495],"about_ca_topic_score_codex":0.000021921098,"about_ca_topic_score_gemma":0.00004129296,"teacher_disagreement_score":0.14200228,"about_ca_system_score_codex":0.00018440257,"about_ca_system_score_gemma":0.00015764234,"threshold_uncertainty_score":0.620861},"labels":[],"label_agreement":null},{"id":"W4406887020","doi":"10.1093/bioinformatics/btaf042","title":"Multidimensional scaling improves distance-based clustering for microbiome data","year":2025,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Institute of General Medical Sciences; School of Medicine and Public Health, University of Wisconsin-Madison","keywords":"Cluster analysis; Computer science; Multidimensional scaling; Medoid; Microbiome; Data mining; Clustering high-dimensional data; Dimensionality reduction; Artificial intelligence; Pattern recognition (psychology); Machine learning; Bioinformatics; Biology","score_opus":0.021011993475996037,"score_gpt":0.29725787483098987,"score_spread":0.27624588135499384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406887020","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.098500356,0.0006511173,0.8972729,0.0005796239,0.0007218355,0.00079871196,0.00092244404,0.000040363368,0.00051268237],"genre_scores_gemma":[0.39643878,0.00009399211,0.5891304,0.004562966,0.00023888022,0.000038754897,0.008034578,0.000037033544,0.0014245876],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99917454,0.000008790689,0.00032175166,0.0001927845,0.000046914345,0.00025525148],"domain_scores_gemma":[0.9992026,0.000022070606,0.00009105409,0.00056493585,0.00007120039,0.000048152637],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020985666,0.00012978441,0.00012947126,0.000056870867,0.00015034282,0.000032609925,0.00028817297,0.000118353106,0.0000026340474],"category_scores_gemma":[0.00006259606,0.00011999174,0.000053712396,0.000075002456,0.000050849256,0.000008429996,0.00025098768,0.000050644692,0.0000060430352],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014493233,0.000057632915,0.00015738964,0.00080237957,0.000047730813,2.1533481e-7,0.000042008298,0.00014580338,0.9679503,0.00015268676,0.02187432,0.00862459],"study_design_scores_gemma":[0.0026767235,0.00015033623,0.0009809445,0.00021603769,0.000052744606,0.000004703197,0.00019801981,0.25083253,0.13082181,0.000023073995,0.6136195,0.00042355273],"about_ca_topic_score_codex":0.0000060736984,"about_ca_topic_score_gemma":0.00002643427,"teacher_disagreement_score":0.8371285,"about_ca_system_score_codex":0.000021487234,"about_ca_system_score_gemma":0.00023252843,"threshold_uncertainty_score":0.4893121},"labels":[],"label_agreement":null},{"id":"W4407388488","doi":"10.1093/bioinformatics/btaf060","title":"ImmunoTar—integrative prioritization of cell surface targets for cancer immunotherapy","year":2025,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Cancer Immunotherapy and Biomarkers","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia; Spinal Cord Injury BC","funders":"National Cancer Institute; Cancer Research UK; National Institutes of Health; Michael Smith Health Research BC; Mark Foundation For Cancer Research","keywords":"Identification (biology); Chimeric antigen receptor; Prioritization; Immunotherapy; Computational biology; Cancer immunotherapy; Cancer; Computer science; Proteomics; Bioinformatics; Biology; Gene","score_opus":0.010638015712514907,"score_gpt":0.29056213018331295,"score_spread":0.27992411447079807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407388488","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5891412,0.046063215,0.31960988,0.0035679922,0.003420579,0.00788907,0.00070834626,0.0005027901,0.029096952],"genre_scores_gemma":[0.7964291,0.015053126,0.1699719,0.0034185175,0.00010753521,0.00019992265,0.00033683205,0.00009871749,0.014384357],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99904734,0.000011238266,0.00053183467,0.00008825021,0.00014181445,0.00017952922],"domain_scores_gemma":[0.9991382,0.00007787947,0.00022318315,0.00023723903,0.00029863615,0.00002489676],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018095516,0.00015309323,0.00031779366,0.00009850412,0.000059249953,0.000015896445,0.00010077798,0.00010305806,0.00005207249],"category_scores_gemma":[0.000025301424,0.000119010925,0.00017365061,0.00030032004,0.00008310223,0.000118450254,0.000014460894,0.00007828797,0.0000018353443],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010726666,0.0007079027,0.007956355,0.0045749685,0.001622956,0.0000010812489,0.011986193,0.00015234016,0.80014735,0.0018173667,0.031684864,0.12862198],"study_design_scores_gemma":[0.010127745,0.00069284765,0.0087929135,0.0009844825,0.00019167068,0.00000314293,0.0028274232,0.013516694,0.80644715,0.00023389186,0.15584393,0.0003380899],"about_ca_topic_score_codex":0.00010991929,"about_ca_topic_score_gemma":0.000014280268,"teacher_disagreement_score":0.20728791,"about_ca_system_score_codex":0.000113793845,"about_ca_system_score_gemma":0.0003778651,"threshold_uncertainty_score":0.48531246},"labels":[],"label_agreement":null},{"id":"W4407578746","doi":"10.1093/bioinformatics/btaf071","title":"<i>PNL</i>: a software to build polygenic risk scores using a super learner approach based on PairNet, a Convolutional Neural Network","year":2025,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Academia Sinica; Institute of Biomedical Sciences, Academia Sinica; Natural Sciences and Engineering Research Council of Canada; National Science and Technology Council","keywords":"Convolutional neural network; Computer science; Polygenic risk score; Software; Artificial intelligence; Machine learning; Artificial neural network; Programming language; Biology; Single-nucleotide polymorphism; Genetics","score_opus":0.019815162476490098,"score_gpt":0.2710087187799389,"score_spread":0.25119355630344875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407578746","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028300611,0.00015346016,0.9678803,0.0010656846,0.0006324616,0.00059578725,0.000022148492,0.00043186988,0.00091768254],"genre_scores_gemma":[0.2260857,0.00000294757,0.7643342,0.009198646,0.0001519334,0.00003443884,0.000023850183,0.000017647108,0.000150661],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976287,0.00020260709,0.00059611327,0.00035027904,0.000549932,0.0006724032],"domain_scores_gemma":[0.9981892,0.00034837966,0.00018614014,0.0008739373,0.00018694118,0.00021539563],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00066478667,0.00028800775,0.00029298666,0.00030463908,0.0004930005,0.0002458711,0.00094612554,0.00014596869,0.000013861964],"category_scores_gemma":[0.0006121851,0.000257509,0.00014287588,0.0012008986,0.00006240681,0.0003226935,0.00041740225,0.0005828709,0.00005360636],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004375853,0.000057416335,0.079369895,0.00024775666,0.00002584441,0.000002506253,0.00072649104,0.8876671,0.0000015636896,0.0051208506,0.008695811,0.01804097],"study_design_scores_gemma":[0.00039531686,0.00013200092,0.014691061,0.00013150614,0.000014847743,0.000009493488,0.000041592662,0.9810179,0.000003850659,0.00017935799,0.0031230166,0.00026004747],"about_ca_topic_score_codex":0.00026244967,"about_ca_topic_score_gemma":0.000017137168,"teacher_disagreement_score":0.2035461,"about_ca_system_score_codex":0.00016392935,"about_ca_system_score_gemma":0.00049903797,"threshold_uncertainty_score":0.9999877},"labels":[],"label_agreement":null},{"id":"W4407613286","doi":"10.1093/bioinformatics/btag199","title":"Refining sequence-to-expression modelling with chromatin accessibility","year":2025,"lang":"en","type":"preprint","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada","keywords":"Refining (metallurgy); Sequence (biology); Chromatin; Expression (computer science); Computational biology; Computer science; Process engineering; Chemistry; Engineering; Biology; Programming language; DNA; Biochemistry","score_opus":0.025698479143283957,"score_gpt":0.2758157139084285,"score_spread":0.2501172347651446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407613286","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69246227,0.00010353308,0.30003944,0.00006216112,0.00025638728,0.0004078367,0.0003559218,0.000049982442,0.006262473],"genre_scores_gemma":[0.4484603,0.0001157851,0.54835594,0.00040213641,0.00015093283,0.00009295591,0.0014330298,0.000038057697,0.0009508458],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982265,0.000032683613,0.0006674391,0.00045983924,0.0002538005,0.00035972596],"domain_scores_gemma":[0.9980676,0.000014647271,0.00040161316,0.0011820033,0.00018758641,0.00014652094],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00029445768,0.00041124737,0.0003708317,0.00010856079,0.00014552036,0.00016362866,0.00071157975,0.00050071353,0.000007778601],"category_scores_gemma":[0.000035693138,0.00035032906,0.00011901772,0.00011940534,0.000057864563,0.0000078106,0.0015487095,0.00035262565,0.000011789173],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002270117,0.0001488873,0.0014879724,0.0032457546,0.00023327043,0.0000050545164,0.0013714654,0.93652,0.045217644,0.0002183432,0.002370506,0.008954109],"study_design_scores_gemma":[0.00094308215,0.000407068,0.00033568026,0.0021678363,0.00012072615,0.000016742571,0.0004280429,0.9212494,0.058652245,0.00049457,0.013617355,0.0015672622],"about_ca_topic_score_codex":0.000029861942,"about_ca_topic_score_gemma":0.00002829998,"teacher_disagreement_score":0.24831648,"about_ca_system_score_codex":0.00008415089,"about_ca_system_score_gemma":0.0005505089,"threshold_uncertainty_score":0.99989486},"labels":[],"label_agreement":null},{"id":"W4408212560","doi":"10.1093/bioinformatics/btaf094","title":"ENACT: End-to-End Analysis of Visium High Definition (HD) Data","year":2025,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sanofi (Canada)","funders":"","keywords":"End-to-end principle; Computer science; End user; Operating system; Computer network","score_opus":0.02679882034336073,"score_gpt":0.261496189409761,"score_spread":0.23469736906640026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408212560","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78541934,0.00028405743,0.19051817,0.00035273648,0.00060958386,0.00034419895,0.0017659275,0.000037555328,0.020668387],"genre_scores_gemma":[0.97920406,0.00013573183,0.015869468,0.0007038983,0.00004593223,0.000004027769,0.0038190244,0.000007816904,0.00021006555],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990787,0.000016652459,0.00042630604,0.00016742192,0.00014255736,0.00016837139],"domain_scores_gemma":[0.99893034,0.000022341512,0.00010815292,0.0007939754,0.00008826731,0.000056950106],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019518458,0.00012595837,0.00023441738,0.00022743219,0.00005123456,0.00002911235,0.00041761,0.00012757922,0.000039059283],"category_scores_gemma":[0.00008946861,0.000118816984,0.00009791041,0.0005115531,0.000048316037,0.000011173166,0.00018908625,0.000056253382,0.000010956711],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00080125686,0.0010645986,0.023563523,0.0012231383,0.0082272645,0.000005154119,0.0017228357,0.0037159473,0.7489494,0.010879171,0.041827254,0.15802042],"study_design_scores_gemma":[0.0032203933,0.00095483917,0.036099758,0.00019118785,0.005582727,0.000005970598,0.0011864714,0.09952293,0.6557191,0.000638585,0.19538143,0.001496601],"about_ca_topic_score_codex":0.0001091506,"about_ca_topic_score_gemma":0.00015865835,"teacher_disagreement_score":0.19378465,"about_ca_system_score_codex":0.000012996978,"about_ca_system_score_gemma":0.00008648796,"threshold_uncertainty_score":0.4845216},"labels":[],"label_agreement":null},{"id":"W4408884143","doi":"10.1093/bioinformatics/btaf129","title":"AI-augmented physics-based docking for antibody-antigen complex prediction","year":2025,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Monoclonal and Polyclonal Antibodies Research","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Ste. Anne's Hospital; National Research Council Canada","funders":"","keywords":"Docking (animal); Computer science; Computational biology; Macromolecular docking; Epitope; Artificial intelligence; Antigen; Biology; Protein structure","score_opus":0.0501294460679583,"score_gpt":0.38286061444346187,"score_spread":0.33273116837550354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408884143","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15722841,0.00036364785,0.7763811,0.015225948,0.0009984644,0.0040116617,0.0010368441,0.00048576485,0.04426817],"genre_scores_gemma":[0.88267696,0.00026185517,0.08122478,0.020503238,0.00094024494,0.00016570871,0.0071616415,0.000060317197,0.00700528],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988185,0.000012607684,0.00040928466,0.00012082787,0.0003108104,0.00032794895],"domain_scores_gemma":[0.9992208,0.00010725601,0.00007867574,0.00023286886,0.00026429092,0.00009611002],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018107815,0.00015273645,0.00027083975,0.00014841747,0.00021692748,0.00005332745,0.00011666529,0.00007710737,0.000061431274],"category_scores_gemma":[0.000066073415,0.00012280175,0.00016085045,0.00028952438,0.0000874462,0.00013147586,0.000054682987,0.00014904939,0.000042920223],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0052599255,0.0018205744,0.24406497,0.01672849,0.0019687954,0.00002891204,0.0014530696,0.0017614085,0.07205332,0.036651034,0.349203,0.26900652],"study_design_scores_gemma":[0.0022732231,0.00029840454,0.030027753,0.00035923938,0.00008063035,0.00000561186,0.00010270976,0.7045082,0.008035234,0.00038911137,0.25378248,0.00013740279],"about_ca_topic_score_codex":0.000023145218,"about_ca_topic_score_gemma":0.0000020660893,"teacher_disagreement_score":0.72544855,"about_ca_system_score_codex":0.0000621667,"about_ca_system_score_gemma":0.00021980368,"threshold_uncertainty_score":0.500771},"labels":[],"label_agreement":null},{"id":"W4408956502","doi":"10.1093/bioinformatics/btaf137","title":"scMUSCL: multi-source transfer learning for clustering scRNA-seq data","year":2025,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Transfer of learning; Cluster analysis; Computer science; Transfer (computing); Data source; Artificial intelligence; Data mining; Parallel computing","score_opus":0.04198762505065439,"score_gpt":0.27984129734352414,"score_spread":0.23785367229286974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408956502","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05682503,0.0002455925,0.9408913,0.0000934192,0.00033932604,0.00032599183,0.000055113465,0.000044670585,0.001179549],"genre_scores_gemma":[0.8809788,0.00034294443,0.108076535,0.001417686,0.0002831171,0.000036380723,0.0019517192,0.0000606707,0.0068521127],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99908787,0.000016716787,0.0003406462,0.00020570615,0.000082494145,0.0002665756],"domain_scores_gemma":[0.9993293,0.000021562175,0.000038694285,0.0004897299,0.00006438854,0.0000563102],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023598614,0.00016364967,0.00015739177,0.000057977406,0.00017390183,0.00007068372,0.0004556982,0.00016617078,0.000004890981],"category_scores_gemma":[0.00011314381,0.0001585368,0.00008215643,0.00008513336,0.000052671665,0.000014720553,0.00015189227,0.00011537818,0.000006283633],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00084102794,0.0004975926,0.009089558,0.002840007,0.0007131376,0.0000021221454,0.002051116,0.022414312,0.57266974,0.00033854338,0.014418922,0.37412393],"study_design_scores_gemma":[0.0021410524,0.00015520069,0.0003120123,0.000092208276,0.00006961805,0.0000044991493,0.0004018283,0.5723156,0.0364153,0.0000071522827,0.38774148,0.0003440735],"about_ca_topic_score_codex":0.000017158713,"about_ca_topic_score_gemma":0.000075291486,"teacher_disagreement_score":0.83281475,"about_ca_system_score_codex":0.000012050467,"about_ca_system_score_gemma":0.000077433484,"threshold_uncertainty_score":0.64649427},"labels":[],"label_agreement":null},{"id":"W4409567869","doi":"10.1093/bioinformatics/btaf173","title":"argNorm: normalization of antibiotic resistance gene annotations to the Antibiotic Resistance Ontology (ARO)","year":2025,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Pharmaceutical and Antibiotic Environmental Impacts","field":"Environmental Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"National Health and Medical Research Council; Institut National de la Santé et de la Recherche Médicale; Medical Research Council; Università degli Studi di Trento; European Molecular Biology Laboratory; University of Pretoria; International Development Research Centre; Joint Programming Initiative on Antimicrobial Resistance","keywords":"Antibiotics; Antibiotic resistance; Normalization (sociology); Gene ontology; Gene; Computer science; Computational biology; Biology; Microbiology; Genetics; Gene expression; Sociology","score_opus":0.015642746211059447,"score_gpt":0.2729083488235146,"score_spread":0.2572656026124552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409567869","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68659014,0.00063094567,0.05672257,0.0126083875,0.0008956153,0.0018641751,0.00022125362,0.00014776092,0.24031915],"genre_scores_gemma":[0.9776797,0.00014038403,0.0146126235,0.0026915593,0.000017056946,0.0000016250564,0.000024641953,0.00000976134,0.004822648],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984952,0.00005292465,0.00056479685,0.0001873891,0.0003206556,0.00037903176],"domain_scores_gemma":[0.9991422,0.00009188122,0.00018437314,0.0004423011,0.000015801803,0.00012339781],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029404034,0.0001839127,0.00022427349,0.0000726776,0.00024514526,0.000036275265,0.00043607803,0.00008136408,0.00011908739],"category_scores_gemma":[0.00015549305,0.00013678639,0.00006659945,0.0007720776,0.0003637326,0.00030065593,0.00023543216,0.00012198375,0.0003977594],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009034058,0.0027571737,0.33676282,0.00317317,0.0005441904,0.000053248696,0.014166151,0.036397517,0.19985409,0.044577762,0.3181651,0.042645406],"study_design_scores_gemma":[0.0014032664,0.0001679182,0.61683923,0.00059373444,0.00022021835,0.000013024431,0.00095980405,0.012907783,0.2298804,0.001090988,0.13510206,0.0008215661],"about_ca_topic_score_codex":0.000033005508,"about_ca_topic_score_gemma":0.00045285368,"teacher_disagreement_score":0.29108956,"about_ca_system_score_codex":0.00013398482,"about_ca_system_score_gemma":0.000025303423,"threshold_uncertainty_score":0.5577987},"labels":[],"label_agreement":null},{"id":"W4409886452","doi":"10.1093/bioinformatics/btaf269","title":"PICRUSt2-SC: an update to the reference database used for functional prediction within PICRUSt2","year":2025,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada","keywords":"Database; Computer science; Source code; Code (set theory); Process (computing); Genome; Information retrieval; Set (abstract data type); Programming language; Biology","score_opus":0.027568846823798364,"score_gpt":0.2633363834784288,"score_spread":0.23576753665463043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409886452","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8208442,0.0004022394,0.17089705,0.0013418397,0.0015239468,0.0013165923,0.001705258,0.0000239395,0.0019449854],"genre_scores_gemma":[0.9643146,0.00018476816,0.028495966,0.0036357155,0.00039605837,0.00022345294,0.0015962536,0.000018415782,0.0011347701],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99925464,0.000016338941,0.00028870004,0.0001672806,0.00009443344,0.00017859548],"domain_scores_gemma":[0.9992723,0.000016728225,0.00007690743,0.00044774482,0.00012850692,0.000057852278],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002565386,0.00013117917,0.000100407095,0.000042578886,0.000233741,0.000046983463,0.00021729703,0.000080350175,0.000005384798],"category_scores_gemma":[0.000081167884,0.000096956996,0.000042669282,0.00009501525,0.000041653722,0.000003943195,0.0001591071,0.000058982325,0.000013158899],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013138133,0.00042098682,0.009992079,0.0004922157,0.0010314349,8.1556016e-7,0.003769747,0.01690023,0.5113789,0.023907995,0.40083143,0.029960362],"study_design_scores_gemma":[0.0014172515,0.00072604365,0.015743889,0.00004773344,0.00012846068,0.000006306954,0.0014168876,0.018137475,0.058543533,0.000369262,0.9030539,0.00040926866],"about_ca_topic_score_codex":0.00000970889,"about_ca_topic_score_gemma":0.00011321102,"teacher_disagreement_score":0.5022225,"about_ca_system_score_codex":0.000013677131,"about_ca_system_score_gemma":0.00011485566,"threshold_uncertainty_score":0.39537916},"labels":[],"label_agreement":null},{"id":"W4410812090","doi":"10.1093/bioinformatics/btaf325","title":"HSDSnake: a user-friendly SnakeMake pipeline for analysis of duplicate genes in eukaryotic genomes","year":2025,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Pipeline (software); Workflow; Genome; Novelty; Gene duplication; Gene; KEGG; Computational biology; Data mining; Similarity (geometry); Information retrieval; Database; Biology; Genetics; Gene ontology; Artificial intelligence; Programming language","score_opus":0.012807122185724927,"score_gpt":0.2637024476158325,"score_spread":0.25089532543010756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410812090","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94514734,0.006098987,0.04529264,0.00022279304,0.00017630607,0.0006623444,0.0003219312,0.0000062569234,0.002071424],"genre_scores_gemma":[0.97711366,0.0017800867,0.019496594,0.00028037746,0.00004045973,0.00007430654,0.00023493332,0.000012654303,0.0009669342],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99894834,0.000012078186,0.0005692277,0.00016882816,0.00007296016,0.00022858675],"domain_scores_gemma":[0.99925786,0.00003360088,0.00016035467,0.00038452653,0.00012958956,0.000034047996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020285678,0.00015599339,0.00035378666,0.0002815352,0.000048607297,0.000014093031,0.00021502541,0.00010436574,0.0000038038809],"category_scores_gemma":[0.000060777344,0.00014183843,0.00020243599,0.0005109659,0.00006503575,0.0000013584588,0.00013726368,0.00003343996,0.0000013717049],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009186337,0.00089465483,0.47790638,0.0030608552,0.01047262,0.0000030441088,0.0020587693,0.037433654,0.30332857,0.00961684,0.021374553,0.13293143],"study_design_scores_gemma":[0.005502181,0.00093703973,0.22868347,0.00012223443,0.003685079,0.0000046643245,0.0026964028,0.2143021,0.14755426,0.0007184424,0.3943001,0.0014940058],"about_ca_topic_score_codex":0.000015076021,"about_ca_topic_score_gemma":0.00019230966,"teacher_disagreement_score":0.37292555,"about_ca_system_score_codex":0.000013933437,"about_ca_system_score_gemma":0.00008208582,"threshold_uncertainty_score":0.5784003},"labels":[],"label_agreement":null},{"id":"W4411279248","doi":"10.1093/bioinformatics/btaf344","title":"PhyClone: accurate Bayesian reconstruction of cancer phylogenies from bulk sequencing","year":2025,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"Natural Sciences and Engineering Research Council of Canada; BC Cancer Foundation; Michael Smith Health Research BC","keywords":"Bayesian probability; Computer science; Computational biology; DNA sequencing; Biology; Artificial intelligence; Genetics; Gene","score_opus":0.009649039802931908,"score_gpt":0.252707724374754,"score_spread":0.24305868457182206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411279248","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9781746,0.0017051848,0.015154999,0.00009935126,0.0007579284,0.00016600291,0.00035780953,0.000012047168,0.003572065],"genre_scores_gemma":[0.9877425,0.0019540698,0.009514197,0.00033999834,0.00015275076,0.000015364318,0.00011776289,0.000008975738,0.00015441622],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999339,0.000008419652,0.00033466148,0.00011244737,0.00006596963,0.00013950684],"domain_scores_gemma":[0.99942964,0.0000261859,0.00016973127,0.00024209729,0.00009743246,0.000034938923],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000057530855,0.00011336758,0.00014584573,0.00005258856,0.000053036434,0.000023717284,0.00013302585,0.000112613496,0.000023370256],"category_scores_gemma":[0.00008678974,0.000112572234,0.00006931541,0.000101824364,0.00007163695,0.000006464636,0.00008297664,0.000051916504,0.000002691718],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024354478,0.000060910545,0.020887004,0.00044420437,0.0007020141,0.0000016944867,0.0010255397,0.0063703004,0.66629094,0.0015669888,0.009049384,0.29335746],"study_design_scores_gemma":[0.0010714438,0.00012276054,0.0038153848,0.00021070066,0.00013488047,0.0000050197186,0.0015714074,0.019995816,0.95146143,0.0008902696,0.020322293,0.00039859823],"about_ca_topic_score_codex":0.0003350119,"about_ca_topic_score_gemma":0.00031760553,"teacher_disagreement_score":0.29295886,"about_ca_system_score_codex":0.000044685425,"about_ca_system_score_gemma":0.00027653307,"threshold_uncertainty_score":0.45905626},"labels":[],"label_agreement":null},{"id":"W4411297467","doi":"10.1093/bioinformatics/btaf345","title":"Securing diagonal integration of multimodal single-cell data against ambiguous mapping","year":2025,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Diagonal; Computer science; Software; Artificial intelligence; Computational biology; Mathematics; Biology; Programming language; Geometry","score_opus":0.030690999028713445,"score_gpt":0.24716306605043412,"score_spread":0.21647206702172067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411297467","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7793801,0.00044945802,0.20917253,0.000054637105,0.00049787073,0.00022995792,0.00015154309,0.000027944043,0.010035965],"genre_scores_gemma":[0.9693021,0.00018696026,0.028723376,0.00033405123,0.00008928782,0.0000036241681,0.0011507528,0.000011923218,0.00019787715],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99906665,0.000018009941,0.0004463869,0.00016633197,0.00011981626,0.00018281254],"domain_scores_gemma":[0.99918747,0.000013210543,0.00014049893,0.00054133876,0.00007674691,0.000040737606],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016219474,0.0001479166,0.00015889076,0.00008509093,0.0000648743,0.000035244444,0.00040441024,0.00014434518,0.000003235329],"category_scores_gemma":[0.000078003206,0.00014261874,0.000063990825,0.0001240788,0.000066906214,0.000018319446,0.00020538483,0.00009608038,0.0000037669108],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047426052,0.0001861427,0.0005288172,0.00023606351,0.000049668837,6.866715e-7,0.000424447,0.00016983828,0.929111,0.000054749875,0.0011515141,0.06803965],"study_design_scores_gemma":[0.0013924108,0.00016342792,0.00084741664,0.00021650101,0.000032617983,0.0000027452204,0.0008071205,0.122321725,0.85318494,0.000031473242,0.020642571,0.0003570334],"about_ca_topic_score_codex":0.000036580517,"about_ca_topic_score_gemma":0.000023605458,"teacher_disagreement_score":0.18992206,"about_ca_system_score_codex":0.000018051165,"about_ca_system_score_gemma":0.00009034962,"threshold_uncertainty_score":0.5815823},"labels":[],"label_agreement":null},{"id":"W4411705236","doi":"10.1093/bioinformatics/btaf375","title":"Benchmarking peak calling methods for CUT&amp;RUN","year":2025,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"Canadian Institutes of Health Research","keywords":"Benchmarking; Computer science; Chromatin; Chromatin immunoprecipitation; Histone; Micrococcal nuclease; Identification (biology); Bottleneck; Data mining; Benchmark (surveying); Computational biology; Biology; Nucleosome; DNA; Genetics; Gene; Gene expression","score_opus":0.015096092663729303,"score_gpt":0.319743551025407,"score_spread":0.3046474583616777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411705236","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055349182,0.00034399764,0.9351112,0.000089919056,0.00046853515,0.00030287754,0.000029809307,0.00001902748,0.008285444],"genre_scores_gemma":[0.037894048,0.00020893136,0.9590743,0.00065182353,0.00016146088,0.00003925613,0.00043936164,0.000018926425,0.0015118814],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991788,0.000018740233,0.0003617139,0.0001399253,0.00005180089,0.0002490075],"domain_scores_gemma":[0.9993572,0.00004040141,0.00011500978,0.00034496415,0.0000935714,0.000048811024],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038715877,0.00014570293,0.00015100361,0.000059069127,0.00014117743,0.000057497575,0.00022672689,0.00015687213,0.0000064162514],"category_scores_gemma":[0.00012913176,0.000142335,0.00012349851,0.00008727171,0.000035184003,0.0000041816324,0.0001431932,0.00006302824,0.000005108931],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019167192,0.00020945825,0.0011997444,0.0020380334,0.00076506654,6.66648e-7,0.0016376365,0.005035582,0.34089682,0.020262681,0.030825082,0.59693754],"study_design_scores_gemma":[0.0008554925,0.00014524898,0.0002427219,0.00006763015,0.000078818746,0.000008094782,0.0003849455,0.24455816,0.026302544,0.0017063243,0.72521305,0.0004369619],"about_ca_topic_score_codex":0.000004512475,"about_ca_topic_score_gemma":0.000020619364,"teacher_disagreement_score":0.694388,"about_ca_system_score_codex":0.000024361663,"about_ca_system_score_gemma":0.00010299209,"threshold_uncertainty_score":0.5804253},"labels":[],"label_agreement":null},{"id":"W4411803876","doi":"10.1093/bioinformatics/btaf382","title":"AutoPM3: enhancing variant interpretation via LLM-driven PM3 evidence extraction from scientific literature","year":2025,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Genome Canada","funders":"","keywords":"Interpretation (philosophy); Extraction (chemistry); Computer science; Scientific evidence; Epistemology; Artificial intelligence; Data science; Chemistry; Chromatography; Programming language; Philosophy","score_opus":0.00672845336697882,"score_gpt":0.257173390281499,"score_spread":0.2504449369145202,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411803876","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69147205,0.0028884576,0.30244341,0.00012558998,0.0016739692,0.00028539554,0.00009889631,0.00003558646,0.0009766038],"genre_scores_gemma":[0.98859227,0.00015972639,0.009619266,0.00027855946,0.00009648542,0.000011559357,0.00058542856,0.000007172814,0.00064951123],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992211,0.000023551027,0.00029943007,0.00019243248,0.00010977325,0.00015371415],"domain_scores_gemma":[0.9993205,0.000025680263,0.00012238671,0.00033463736,0.00014196898,0.00005484801],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013513547,0.00012500497,0.000098924254,0.000091983544,0.00016114632,0.0002737349,0.00018152302,0.00013248017,0.000015300302],"category_scores_gemma":[0.00015417383,0.00011354643,0.000082635044,0.00016888339,0.000045582787,0.000034350105,0.00010120358,0.00008012253,0.000030559164],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017724134,0.0001353257,0.00053149316,0.00030438544,0.00015252047,0.000013743762,0.002364265,0.0008339159,0.9512355,0.00029800428,0.005060989,0.038892627],"study_design_scores_gemma":[0.0013502523,0.0004735693,0.017696142,0.0030390501,0.0003586,0.0000812697,0.0016350215,0.38470244,0.5101325,0.0022321804,0.076993376,0.0013056118],"about_ca_topic_score_codex":0.000009958524,"about_ca_topic_score_gemma":0.000025578596,"teacher_disagreement_score":0.441103,"about_ca_system_score_codex":0.000030793122,"about_ca_system_score_gemma":0.00015180091,"threshold_uncertainty_score":0.4630289},"labels":[],"label_agreement":null},{"id":"W4412347897","doi":"10.1093/bioinformatics/btaf401","title":"shinyDSP: a Shiny application for interactive analysis and visualization of NanoString GeoMx Whole Transcriptome Atlas data","year":2025,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Physicians' Services Incorporated Foundation; Academic Medical Organization of Southwestern Ontario","keywords":"Bioconductor; MIT License; Computer science; Personalization; Normalization (sociology); Visualization; Profiling (computer programming); Open source; Transcriptome; Software; World Wide Web; Information retrieval; Data mining; Operating system; Biology; Gene; Gene expression","score_opus":0.015490822766732453,"score_gpt":0.28644973302687343,"score_spread":0.27095891026014096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412347897","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27599415,0.00017630644,0.7227382,0.000052739557,0.000076855205,0.0003461694,0.00031930907,0.000011462351,0.00028482228],"genre_scores_gemma":[0.98998344,0.00011076657,0.007089711,0.00011406679,0.00002826851,0.000019858737,0.0025193335,0.000008292804,0.00012624873],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99925756,0.000013165713,0.00035829618,0.00017782718,0.00007597139,0.00011719518],"domain_scores_gemma":[0.999318,0.000026138525,0.00013484461,0.00038346325,0.000106189276,0.000031345025],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016892349,0.00010999721,0.00018431181,0.00015766393,0.000061664454,0.000033718443,0.00023232476,0.000110075176,0.0000013031383],"category_scores_gemma":[0.00006655798,0.00010734785,0.00007148035,0.0003240772,0.00004782322,0.000027100945,0.0000731162,0.00003658699,5.5229106e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042406234,0.00020569497,0.017705811,0.0008316362,0.0013366196,1.08522e-7,0.0012798703,0.00037027948,0.93777275,0.0008566754,0.0011615211,0.038054977],"study_design_scores_gemma":[0.002247092,0.00034354208,0.008453,0.00010245668,0.0014127885,0.0000019065626,0.00091412116,0.48485497,0.44943085,0.00020206207,0.05156919,0.00046801334],"about_ca_topic_score_codex":0.000046064426,"about_ca_topic_score_gemma":0.00010449271,"teacher_disagreement_score":0.7156485,"about_ca_system_score_codex":0.000011593716,"about_ca_system_score_gemma":0.00005302791,"threshold_uncertainty_score":0.4377518},"labels":[],"label_agreement":null},{"id":"W4412454105","doi":"10.1093/bioinformatics/btaf259","title":"ADME-drug-likeness: enriching molecular foundation models via pharmacokinetics-guided multi-task learning for drug-likeness prediction","year":2025,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Ministry of Science and ICT, South Korea; Seoul National University; National Research Foundation; AIGENDRUG","keywords":"ADME; Computer science; Drug discovery; Drug development; Drug; Machine learning; Artificial intelligence; Computational biology; Pharmacology; Bioinformatics; Medicine; Biology","score_opus":0.027931166727851352,"score_gpt":0.321388499425966,"score_spread":0.29345733269811464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412454105","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011883444,0.0001349004,0.98372513,0.0003660871,0.0015485642,0.0009189354,0.000013551221,0.00041937578,0.0009900257],"genre_scores_gemma":[0.35745412,0.00003922864,0.641097,0.0006016332,0.000080662925,0.00016465841,0.00017216128,0.00002767736,0.00036283614],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974129,0.0002187463,0.0009641183,0.00040744504,0.0005405561,0.0004562117],"domain_scores_gemma":[0.9979662,0.0005542216,0.00040152366,0.00049324834,0.0004695282,0.000115296694],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001290081,0.00033453503,0.00032423224,0.0004874576,0.00043910232,0.00049139303,0.0008939736,0.000094807394,0.0000029200685],"category_scores_gemma":[0.0002472034,0.00035560163,0.00018234951,0.0008876452,0.000052234034,0.0022593043,0.00045334242,0.00027296355,0.000021191541],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015697366,0.00007414851,0.000072793344,0.0003116701,0.00006838673,0.0000012951292,0.0019709961,0.8675829,0.0010708291,0.013165047,0.00046158629,0.11520461],"study_design_scores_gemma":[0.0013074802,0.00002475638,0.0001790375,0.0001097124,0.000058578305,0.0000067024835,0.00014636603,0.9784853,0.004045652,0.01091202,0.0044040177,0.00032036664],"about_ca_topic_score_codex":0.000027870214,"about_ca_topic_score_gemma":0.0000035186913,"teacher_disagreement_score":0.34557068,"about_ca_system_score_codex":0.00023689962,"about_ca_system_score_gemma":0.00033666912,"threshold_uncertainty_score":0.9998896},"labels":[],"label_agreement":null},{"id":"W4412454224","doi":"10.1093/bioinformatics/btaf238","title":"MixingDTA: improved drug–target affinity prediction by extending mixup with guilt-by-association","year":2025,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Institute for Information and Communications Technology Promotion; Seoul National University; National Research Foundation; Ministry of Science and ICT, South Korea; Neurosciences Research Foundation; AIGENDRUG","keywords":"Computer science; Drug target; Binary classification; Generalizability theory; Benchmark (surveying); Machine learning; Artificial intelligence; Drug discovery; Task (project management); Chemical space; Regression; Data mining; Support vector machine; Bioinformatics; Mathematics; Statistics; Medicine","score_opus":0.005990640469809734,"score_gpt":0.24150881920899692,"score_spread":0.23551817873918718,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412454224","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014772992,0.00011898162,0.9775765,0.0015114433,0.0007448026,0.0003193265,0.00009330481,0.00029903138,0.004563604],"genre_scores_gemma":[0.064177014,0.00003778066,0.93193156,0.0010645627,0.0000729649,0.00005479334,0.00019967876,0.000017764492,0.0024439145],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983417,0.0001052671,0.00051551353,0.00023083793,0.00046813692,0.00033853893],"domain_scores_gemma":[0.99834555,0.00044792207,0.0003601861,0.0005752389,0.00019133276,0.00007978442],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009769165,0.00019754455,0.00021097052,0.00016641627,0.00024298503,0.00036155662,0.00086625427,0.000092747,0.0000053627823],"category_scores_gemma":[0.0004425455,0.00018002502,0.000063298874,0.000734636,0.000027452035,0.0014771232,0.00039618413,0.00019664587,0.000019566414],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006076266,0.0004958085,0.011991193,0.0005007246,0.00041671927,0.0000024567055,0.004443219,0.01107519,0.0023931786,0.021298965,0.8913981,0.055923697],"study_design_scores_gemma":[0.0007266459,0.00007645554,0.0018053404,0.000066600645,0.000022953594,0.0000027860963,0.00014000348,0.9670732,0.004701049,0.0037999516,0.021340644,0.00024439456],"about_ca_topic_score_codex":0.00002549386,"about_ca_topic_score_gemma":0.0000036091415,"teacher_disagreement_score":0.955998,"about_ca_system_score_codex":0.0004673513,"about_ca_system_score_gemma":0.00022840273,"threshold_uncertainty_score":0.73412067},"labels":[],"label_agreement":null},{"id":"W4412492686","doi":"10.1093/bioinformatics/btaf407","title":"<tt>AdDeam</tt> : a fast and scalable tool for estimating and clustering reference-level damage profiles","year":2025,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Forensic and Genetic Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Novo Nordisk","keywords":"Cluster analysis; Computer science; Scalability; Software; Data mining; Artificial intelligence; Database; Programming language","score_opus":0.028539724186112926,"score_gpt":0.29874605660229886,"score_spread":0.2702063324161859,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412492686","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.63104486,0.0003992685,0.35665008,0.00028812658,0.00016724045,0.0009941309,0.00018111704,0.000026451276,0.010248715],"genre_scores_gemma":[0.3086541,0.0002719002,0.6848053,0.00035247524,0.0001163961,0.00010881781,0.00026214225,0.000020832971,0.0054080863],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999239,0.0000114319,0.0002541199,0.00015652688,0.00008943251,0.00024944026],"domain_scores_gemma":[0.9995566,0.000030421716,0.000056859943,0.00021085479,0.00008992392,0.000055325712],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023191677,0.00012764861,0.00013685784,0.00005828359,0.00015995589,0.00009803677,0.00010616019,0.00011816177,0.0000042197294],"category_scores_gemma":[0.000185113,0.00011028155,0.00002475604,0.00006860285,0.00012646009,0.000010340919,0.00028444052,0.00006672081,0.0000022966326],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003220343,0.00007394383,0.0062407698,0.0042021866,0.00023702072,0.000001970331,0.0011757605,0.000489639,0.050812084,0.0016227987,0.029560927,0.90526086],"study_design_scores_gemma":[0.0025139805,0.0007335431,0.0072685657,0.00037882905,0.000060747218,0.000029911527,0.0017206419,0.89929765,0.054349095,0.00066570635,0.032361247,0.0006200992],"about_ca_topic_score_codex":0.000011891054,"about_ca_topic_score_gemma":0.000018890589,"teacher_disagreement_score":0.9046408,"about_ca_system_score_codex":0.0000074385935,"about_ca_system_score_gemma":0.0000876608,"threshold_uncertainty_score":0.4497151},"labels":[],"label_agreement":null},{"id":"W4413396779","doi":"10.1093/bioinformatics/btaf460","title":"PDP-Miner: an AI/ML tool to detect prophage tail proteins with depolymerase domains across thousands of bacterial genomes","year":2025,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Prophage; Genome; Bacteriophage; Bacterial genome size; Source code; Computational biology; Computer science; Biology; Software; Gene; Genetics; Programming language; Escherichia coli","score_opus":0.00454705534616463,"score_gpt":0.2597397804878549,"score_spread":0.2551927251416903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413396779","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93185997,0.00010311653,0.0646424,0.00008107727,0.00015822583,0.0010629846,0.00017439814,0.00006242612,0.001855427],"genre_scores_gemma":[0.83023316,0.000045731398,0.16702443,0.0009974455,0.00019406619,0.0001276074,0.00043974418,0.000049106297,0.00088873756],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99818873,0.000046357713,0.0007591648,0.0002239009,0.00028654945,0.00049527566],"domain_scores_gemma":[0.9984945,0.000014861605,0.00030425758,0.0008646052,0.0001731546,0.00014861983],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003462696,0.00034249388,0.0003531526,0.00012089617,0.0001868465,0.00012880903,0.0004931689,0.00023495813,0.00002280038],"category_scores_gemma":[0.00015980031,0.0002698565,0.00009755426,0.0003243437,0.00014938125,0.000041676172,0.0003183056,0.00018298127,0.00001428889],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003400485,0.00045355665,0.009106941,0.0035123373,0.0005887993,0.000018468972,0.007914715,0.0026164167,0.79746145,0.0005328058,0.0040853573,0.17030866],"study_design_scores_gemma":[0.003997643,0.004278224,0.0026832127,0.00023434458,0.00011407132,0.00007271528,0.0011451432,0.0086757485,0.9077847,0.00003159653,0.06985818,0.0011244472],"about_ca_topic_score_codex":0.000020230222,"about_ca_topic_score_gemma":0.000100349,"teacher_disagreement_score":0.16918422,"about_ca_system_score_codex":0.000029896817,"about_ca_system_score_gemma":0.00029087407,"threshold_uncertainty_score":0.9999754},"labels":[],"label_agreement":null},{"id":"W4413445904","doi":"10.1093/bioinformatics/btaf465","title":"Privacy-preserving federated unsupervised domain adaptation with application to age prediction from DNA methylation data","year":2025,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Privy Council Office","funders":"Bundesministerium für Bildung und Forschung","keywords":"Computer science; Adaptation (eye); DNA methylation; Domain (mathematical analysis); Data mining; Computational biology; Biology; Genetics; Gene; Mathematics","score_opus":0.03585036117643044,"score_gpt":0.27262643966513717,"score_spread":0.23677607848870674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413445904","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015307255,0.00003894558,0.97261405,0.008221905,0.00019807101,0.0009002969,0.00023044848,0.0012473757,0.0012416644],"genre_scores_gemma":[0.110173576,0.000020099855,0.88726395,0.00039337415,0.000030212175,0.00007964043,0.002005215,0.0000125199385,0.000021412747],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979572,0.000070431604,0.0006216509,0.0005379129,0.00049771677,0.0003150833],"domain_scores_gemma":[0.9889541,0.00020531098,0.00023717273,0.010353466,0.00016957628,0.00008035745],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0006250882,0.00023364676,0.00022587074,0.00034998215,0.00029524098,0.00059722614,0.018494982,0.0001791176,0.0000044319886],"category_scores_gemma":[0.004181218,0.00021289157,0.000021926355,0.0015948929,0.00004665255,0.0031353869,0.0391736,0.00021252477,0.00005213038],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002537457,0.00035608272,0.003724142,0.000567486,0.0005148738,0.000016494334,0.006876181,0.0044492413,0.019064281,0.011984282,0.25401342,0.6981798],"study_design_scores_gemma":[0.000498842,0.000052848056,0.004812237,0.00012867847,0.000020312127,0.0000012693941,0.00037267,0.95030767,0.0025406713,0.035291813,0.005762206,0.0002107881],"about_ca_topic_score_codex":0.000182637,"about_ca_topic_score_gemma":0.00012852057,"teacher_disagreement_score":0.9458584,"about_ca_system_score_codex":0.00017896593,"about_ca_system_score_gemma":0.0001668681,"threshold_uncertainty_score":0.98681545},"labels":[],"label_agreement":null},{"id":"W4413491758","doi":"10.1093/bioinformatics/btaf458","title":"An interpretable alphabet for local protein structure search based on amino acid neighborhoods","year":2025,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Aeronautics and Space Institute; Wellcome Trust","keywords":"Alphabet; Computer science; Amino acid; Computational biology; Artificial intelligence; Biology; Genetics","score_opus":0.004914227286936982,"score_gpt":0.25773394991352166,"score_spread":0.2528197226265847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413491758","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.089288786,0.000062027866,0.90594673,0.00012621697,0.00017768446,0.0010140323,0.00034360745,0.000036527406,0.003004372],"genre_scores_gemma":[0.9537225,0.0000025392849,0.043750685,0.0013784245,0.00008211966,0.000055186425,0.00072615274,0.000018143846,0.000264286],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989861,0.000028671953,0.00028857286,0.00021450882,0.000150712,0.0003313893],"domain_scores_gemma":[0.99912405,0.000011288317,0.000069068374,0.0005897295,0.000115355324,0.00009052468],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013971807,0.0002165663,0.00017807292,0.00009402981,0.00011759156,0.00006963576,0.00035800366,0.00028380138,0.000014840015],"category_scores_gemma":[0.000056408146,0.0001843757,0.000090171525,0.00012899775,0.000089664776,0.0000138951655,0.00007405635,0.0001411129,0.0000034170653],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020543167,0.0002699172,0.0011606796,0.0015660302,0.00026322005,0.0000030066883,0.00033017763,0.018748678,0.74059874,0.011447539,0.008146205,0.21541147],"study_design_scores_gemma":[0.0010142527,0.00087953097,0.00014697784,0.00006349325,0.00002201966,0.0000019872139,0.00011910993,0.4995902,0.48809618,0.00069053605,0.009108767,0.00026697223],"about_ca_topic_score_codex":0.0000054972948,"about_ca_topic_score_gemma":0.000014681278,"teacher_disagreement_score":0.8644337,"about_ca_system_score_codex":0.000035561065,"about_ca_system_score_gemma":0.00023148052,"threshold_uncertainty_score":0.7518623},"labels":[],"label_agreement":null},{"id":"W4413814807","doi":"10.1093/bioinformatics/btaf474","title":"Autocycler: long-read consensus assembly for bacterial genomes","year":2025,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Health and Medical Research Council; Institute of Infection and Immunity; Centers for Disease Control and Prevention; State Government of Victoria","keywords":"Computer science; Contig; Bacterial genome size; Sequence assembly; Nanopore sequencing; Scalability; De Bruijn graph; Genome; Automation; De Bruijn sequence; Software; Data mining; Levenshtein distance; Graph; Computational biology; Artificial intelligence; Theoretical computer science; Programming language; Biology; Database; Genetics; Engineering; Gene","score_opus":0.013589816077252527,"score_gpt":0.25762647453241855,"score_spread":0.24403665845516603,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413814807","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9733276,0.0018469692,0.009106705,0.00040835398,0.0012175614,0.00079277565,0.00023279135,0.00001679092,0.013050487],"genre_scores_gemma":[0.94967234,0.0008425861,0.042166445,0.001144514,0.0005458659,0.00014112549,0.00034353192,0.00003417486,0.005109385],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992352,0.0000103619295,0.00031072233,0.00014016885,0.000056633144,0.00024690307],"domain_scores_gemma":[0.99944854,0.000031274365,0.00009172053,0.00028035752,0.00010355664,0.000044535103],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012336597,0.00015428264,0.00016920989,0.000046037276,0.00012846787,0.000043201253,0.00016502105,0.00012337149,0.0000068622417],"category_scores_gemma":[0.00007289447,0.00014321184,0.0001076583,0.000053984844,0.00006641611,6.6951054e-7,0.00012837016,0.000032621985,0.000009571481],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010113092,0.0002963923,0.013627875,0.0013698267,0.0019508264,0.0000033562842,0.0008817979,0.00046618877,0.61130863,0.006861892,0.15422493,0.20799693],"study_design_scores_gemma":[0.002289756,0.0004206707,0.009501228,0.00003675661,0.00011610631,0.000010641294,0.00030914813,0.0025758853,0.06984905,0.00045154552,0.9139311,0.00050814473],"about_ca_topic_score_codex":0.0000037298976,"about_ca_topic_score_gemma":0.000019568719,"teacher_disagreement_score":0.75970614,"about_ca_system_score_codex":0.000013751879,"about_ca_system_score_gemma":0.00012991823,"threshold_uncertainty_score":0.58400095},"labels":[],"label_agreement":null},{"id":"W4414084902","doi":"10.1093/bioinformatics/btaf497","title":"PEtab.jl: advancing the efficiency and utility of dynamic modelling","year":2025,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Medical Research Council; Stiftelsen för Strategisk Forskning; Deutsche Forschungsgemeinschaft; Wellcome Trust; Francis Crick Institute; Vetenskapsrådet; Cancer Research UK","keywords":"R package; Software package; Software; Dynamic programming","score_opus":0.005400617714703178,"score_gpt":0.22796683724358083,"score_spread":0.22256621952887765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414084902","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6639266,0.0017052792,0.33246124,0.000058501642,0.000050553204,0.00010325495,0.000004593765,0.0000061779397,0.0016838019],"genre_scores_gemma":[0.99335593,0.00030380714,0.0060533173,0.000064971464,0.000009777008,0.0000023745176,0.000013108091,0.0000037673192,0.00019294156],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99940467,0.000018704355,0.00026489302,0.00009096504,0.00008105843,0.000139717],"domain_scores_gemma":[0.9994746,0.000015805634,0.00009321483,0.0003348421,0.000056983372,0.000024543915],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027498847,0.000084947016,0.00011619074,0.000037044356,0.000085975225,0.0000116136225,0.0001391276,0.000058521586,0.0000027415863],"category_scores_gemma":[0.000029935205,0.00006184894,0.00006383312,0.00014670996,0.00009538539,0.0000035324376,0.000116634765,0.000044943834,8.052847e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034977836,0.0004882873,0.040976107,0.0033427954,0.0018820304,0.0000021612207,0.0040048263,0.55438566,0.1016679,0.0035460435,0.00875409,0.28060034],"study_design_scores_gemma":[0.00012494347,0.000020906522,0.00073283835,0.000017696271,0.000052393272,0.0000017056808,0.00031138683,0.9905298,0.005646283,0.00011838593,0.0023740656,0.00006961997],"about_ca_topic_score_codex":0.0000042317924,"about_ca_topic_score_gemma":0.00001263652,"teacher_disagreement_score":0.43614414,"about_ca_system_score_codex":0.0000053984336,"about_ca_system_score_gemma":0.000055213215,"threshold_uncertainty_score":0.25221267},"labels":[],"label_agreement":null},{"id":"W4414380127","doi":"10.1093/bioinformatics/btaf501","title":"ChemBounce: a computational framework for scaffold hopping in drug discovery","year":2025,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Research Foundation of Korea; Korea Research Institute of Chemical Technology","keywords":"Drug discovery; Source code; Scaffold; Code (set theory); Software","score_opus":0.019675415154723378,"score_gpt":0.3165883645346435,"score_spread":0.29691294937992013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414380127","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010926499,0.00008306817,0.9840589,0.0013306204,0.00061708566,0.00041044128,0.00001697887,0.00009596938,0.0024604113],"genre_scores_gemma":[0.10745097,0.0000041122544,0.89085317,0.0013795288,0.000038796014,0.000056202047,0.00002298369,0.000006070167,0.0001881651],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985819,0.000041759293,0.0005533745,0.0002155011,0.0003119747,0.0002955293],"domain_scores_gemma":[0.9977451,0.0016206938,0.0001463096,0.00033252343,0.000111044435,0.000044332446],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006986447,0.0001625646,0.00022379751,0.0003361927,0.00012266522,0.00046423325,0.0007375297,0.000071055365,0.0000015657085],"category_scores_gemma":[0.0003744067,0.00016376282,0.00010435626,0.0009296482,0.000048056598,0.0015438487,0.00032586127,0.00014166323,0.000012205026],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000929018,0.000046380042,0.00023618339,0.0001516434,0.000016791453,7.7089004e-7,0.0009838393,0.12037498,0.000002684274,0.8568785,0.0013221393,0.019976772],"study_design_scores_gemma":[0.00030377528,0.000010364956,0.0018299351,0.0001627283,0.000003216974,0.0000015536033,0.00010457248,0.672196,0.00008205931,0.32384762,0.0013275115,0.00013069526],"about_ca_topic_score_codex":0.000008906056,"about_ca_topic_score_gemma":0.000005289464,"teacher_disagreement_score":0.551821,"about_ca_system_score_codex":0.00016739115,"about_ca_system_score_gemma":0.00045757933,"threshold_uncertainty_score":0.6678054},"labels":[],"label_agreement":null},{"id":"W4414422676","doi":"10.1093/bioinformatics/btaf530","title":"DiSTect: a Bayesian model for disease-associated gene discovery and prediction in spatial transcriptomics","year":2025,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Source code; Bayesian probability; Code (set theory); Software; Bayesian network; Transcriptome","score_opus":0.009850950237346955,"score_gpt":0.219404878304263,"score_spread":0.20955392806691606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414422676","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37630418,0.00017771145,0.6221785,0.000090826645,0.00016773485,0.00037387921,0.00050721946,0.000015915153,0.00018407553],"genre_scores_gemma":[0.9949307,0.00016599633,0.0032347855,0.00028851832,0.000040590556,0.000049410144,0.00068339426,0.000015300782,0.0005913263],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991599,0.0000129021955,0.00035447936,0.00017219123,0.000078531775,0.00022200434],"domain_scores_gemma":[0.9996463,0.000011473312,0.00006003535,0.00017459995,0.000039693692,0.0000678895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001240073,0.00015685108,0.00015830908,0.00007617684,0.000082701554,0.0000620051,0.00010431008,0.00015511195,5.7564085e-7],"category_scores_gemma":[0.000056253826,0.0001564891,0.00008581793,0.000082678656,0.00005686435,0.000020767515,0.000027886774,0.00006865167,2.621493e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009818493,0.002986889,0.29341087,0.005115787,0.00092817994,0.000009932935,0.0062224567,0.044260494,0.52120906,0.004604608,0.007909776,0.10352344],"study_design_scores_gemma":[0.0019497647,0.00010452804,0.0065569147,0.000058081234,0.000062989,7.488568e-7,0.00005701842,0.98430026,0.005753061,0.0005088102,0.00045504834,0.00019279523],"about_ca_topic_score_codex":0.000022710325,"about_ca_topic_score_gemma":0.00026115857,"teacher_disagreement_score":0.94003975,"about_ca_system_score_codex":0.000038202088,"about_ca_system_score_gemma":0.00013731116,"threshold_uncertainty_score":0.638144},"labels":[],"label_agreement":null},{"id":"W4414458008","doi":"10.1093/bioinformatics/btaf531","title":"SPAED: harnessing AlphaFold output for accurate segmentation of phage endolysin domains","year":2025,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Vlaamse regering; Universiteit Gent; Alliance de recherche numérique du Canada; European Society of Clinical Microbiology and Infectious Diseases; Mitacs; Fonds de Recherche du Québec - Santé; Fonds Wetenschappelijk Onderzoek","keywords":"Lysin; Segmentation; Bacteriophage; Software; Pattern recognition (psychology)","score_opus":0.012178475071931668,"score_gpt":0.2942372479139277,"score_spread":0.28205877284199604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414458008","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19707598,0.0002405769,0.7869764,0.00020318445,0.0005391098,0.0009418999,0.00013626358,0.000051881558,0.013834719],"genre_scores_gemma":[0.7434788,0.000108540036,0.25115547,0.0008945844,0.00012668292,0.00006457092,0.00094460143,0.000029501742,0.0031972546],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998763,0.000026335998,0.0006791012,0.00012131074,0.00015596786,0.00025428584],"domain_scores_gemma":[0.9989631,0.000054314813,0.000417838,0.0003728671,0.000144582,0.000047261856],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003582448,0.00019104026,0.00022501641,0.00013578417,0.000123436,0.0000572559,0.00025678775,0.00015363262,0.000008049338],"category_scores_gemma":[0.0003003656,0.00017853359,0.00013814196,0.0001691216,0.0000776851,0.000026348685,0.00012886706,0.000084774154,0.000008031569],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010727489,0.0005862501,0.010890628,0.008863434,0.001439639,0.0000024581218,0.005618055,0.012319235,0.54090834,0.012474406,0.08449164,0.32133314],"study_design_scores_gemma":[0.0047098724,0.000509448,0.0015959896,0.00024628796,0.00022564677,0.000013966046,0.0019221489,0.170625,0.70488065,0.00038235288,0.11423173,0.0006569094],"about_ca_topic_score_codex":0.0000049181467,"about_ca_topic_score_gemma":0.0000047740086,"teacher_disagreement_score":0.5464028,"about_ca_system_score_codex":0.00002548291,"about_ca_system_score_gemma":0.00012474596,"threshold_uncertainty_score":0.7280389},"labels":[],"label_agreement":null},{"id":"W4414474889","doi":"10.1093/bioinformatics/btag366","title":"LCR-modules: a collection of workflows for cancer genome analysis","year":2025,"lang":"en","type":"preprint","venue":"Bioinformatics","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; Spinal Cord Injury BC; Canada's Michael Smith Genome Sciences Centre; Simon Fraser University","funders":"Michael Smith Health Research BC","keywords":"Workflow; Genomics; Exome sequencing; Suite; Genome; Scalability; Flexibility (engineering); Exome; Pipeline (software)","score_opus":0.02317833863942167,"score_gpt":0.3131928350839846,"score_spread":0.29001449644456295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414474889","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12867567,0.0058846017,0.8311197,0.00082877977,0.0030065128,0.0061067194,0.011579342,0.00010221179,0.012696471],"genre_scores_gemma":[0.4090346,0.047825627,0.4766471,0.0018070828,0.0024254876,0.002611711,0.026319494,0.0001573193,0.033171564],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99752396,0.00003671522,0.0011670233,0.00032123493,0.00047205648,0.00047901756],"domain_scores_gemma":[0.99762326,0.000051098148,0.0005838569,0.0008564278,0.000705501,0.00017983427],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005820289,0.0003627481,0.0006966458,0.0006101915,0.000115710754,0.000066851004,0.0006978226,0.00081917446,0.000040476436],"category_scores_gemma":[0.00034332633,0.00033043217,0.0006999392,0.00063135696,0.0002125828,0.0000055616997,0.0008563412,0.00026375506,0.000004326839],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0046142433,0.0028517472,0.018815648,0.08267353,0.06559594,0.0000047324475,0.0153180435,0.12670279,0.046000876,0.0008334593,0.17865095,0.45793805],"study_design_scores_gemma":[0.003966101,0.001634166,0.008025661,0.00087506784,0.0053882245,0.0000035800667,0.0018848905,0.5423183,0.055409163,0.001026584,0.37695923,0.00250902],"about_ca_topic_score_codex":0.00009629392,"about_ca_topic_score_gemma":0.0002996629,"teacher_disagreement_score":0.45542902,"about_ca_system_score_codex":0.00009175182,"about_ca_system_score_gemma":0.00085439463,"threshold_uncertainty_score":0.99991477},"labels":[],"label_agreement":null},{"id":"W4414874493","doi":"10.1093/bioinformatics/btaf555","title":"Doblin: inferring dominant clonal lineages from high-resolution DNA barcoding time series","year":2025,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Evolution and Genetic Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Canadian Institutes of Health Research; Université de Montréal; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"DNA barcoding; Series (stratigraphy); DNA; DNA sequencing; Time series","score_opus":0.005501050349470936,"score_gpt":0.22789125407750205,"score_spread":0.22239020372803112,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414874493","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77460104,0.0008120421,0.21424253,0.0008786971,0.00082430424,0.0003453661,0.00025599208,0.000079680685,0.007960327],"genre_scores_gemma":[0.9171376,0.0006788562,0.071708284,0.0010075019,0.00039551567,0.000020720809,0.0016909697,0.000024646892,0.007335879],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99908465,0.000023223563,0.00038000502,0.00015333043,0.0001266456,0.00023216348],"domain_scores_gemma":[0.9994359,0.000016942955,0.00010338876,0.00030120098,0.00008162007,0.000060922586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014601386,0.00016265333,0.0001553746,0.00007650445,0.00014417189,0.000056829635,0.00018516545,0.00018100107,0.000037873746],"category_scores_gemma":[0.00010535459,0.00015501978,0.00007727199,0.00011583933,0.00008390139,0.000014792888,0.00021116984,0.000087699744,0.000076281234],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007740629,0.00033348537,0.011676384,0.00050914235,0.0007598498,0.000009227371,0.00086278823,0.018925307,0.8598319,0.013772798,0.063817665,0.02872739],"study_design_scores_gemma":[0.0037709447,0.0005086591,0.038041905,0.00033367152,0.00019107551,0.000024994235,0.0007618913,0.42585477,0.30607066,0.0020965845,0.22099902,0.0013458333],"about_ca_topic_score_codex":0.000024428438,"about_ca_topic_score_gemma":0.000037969785,"teacher_disagreement_score":0.55376124,"about_ca_system_score_codex":0.000029057139,"about_ca_system_score_gemma":0.00011023496,"threshold_uncertainty_score":0.6321523},"labels":[],"label_agreement":null},{"id":"W4415283170","doi":"10.1093/bioinformatics/btaf578","title":"Sparse polygenic risk score inference with the spike-and-slab LASSO","year":2025,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill Genome Centre; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Inference; Lasso (programming language); R package; Polygenic risk score; Covariate; Elastic net regularization; Software","score_opus":0.011044334332258661,"score_gpt":0.2495141751595947,"score_spread":0.23846984082733605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415283170","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9726621,0.00063367677,0.020801215,0.001029723,0.00008883476,0.00020045097,0.000028558701,0.000013569203,0.0045419075],"genre_scores_gemma":[0.9910755,0.00083422253,0.005760619,0.0010861633,0.000041828745,0.000017626886,0.000039567167,0.0000060288075,0.0011384198],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9993537,0.00004720373,0.00021302007,0.00011357286,0.00006600532,0.00020649315],"domain_scores_gemma":[0.9993649,0.00005910887,0.00014932668,0.00032142998,0.00006616708,0.000039066064],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028662424,0.00011880969,0.00012813632,0.000032049295,0.00017335959,0.000027523893,0.00016553252,0.00012121214,0.00000616863],"category_scores_gemma":[0.00024640237,0.00007278416,0.000038857048,0.00011525187,0.0001263403,0.0000036561862,0.00013274056,0.00010636681,0.000014935596],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000086522894,0.000056774916,0.9081201,0.000081561964,0.0004025308,8.091424e-7,0.00058748387,0.0007157983,0.0013979294,0.0026476434,0.041378163,0.04452466],"study_design_scores_gemma":[0.0014031945,0.0005340308,0.83791506,0.00005144533,0.00022206723,0.000017829665,0.0014062541,0.009772877,0.0020960756,0.00073965196,0.14537172,0.0004697737],"about_ca_topic_score_codex":0.00003673193,"about_ca_topic_score_gemma":0.00016221959,"teacher_disagreement_score":0.10399355,"about_ca_system_score_codex":0.0000099871495,"about_ca_system_score_gemma":0.00011144944,"threshold_uncertainty_score":0.2968052},"labels":[],"label_agreement":null},{"id":"W4415295489","doi":"10.1093/bioinformatics/btag362","title":"Movi 2: Fast and Space-Efficient Queries on Pangenomes","year":2025,"lang":"en","type":"preprint","venue":"Bioinformatics","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Memory footprint; Search engine indexing; Space (punctuation); Footprint; Compression (physics); Variety (cybernetics)","score_opus":0.015049534014978837,"score_gpt":0.24618535397210797,"score_spread":0.23113581995712915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415295489","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0064841015,0.0013539781,0.9728259,0.001359704,0.0022459463,0.00080701004,0.000104463696,0.00055083464,0.014268055],"genre_scores_gemma":[0.0836134,0.002449799,0.9079783,0.00281299,0.00028271633,0.00013187373,0.00007175787,0.00003725769,0.0026219052],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99855393,0.000025653713,0.00041957555,0.0003334696,0.0003160144,0.00035138073],"domain_scores_gemma":[0.99836624,0.00014006397,0.00027900736,0.0010275809,0.00007327678,0.00011381804],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00012842256,0.00034992213,0.00034352383,0.0002594332,0.00014435856,0.000311779,0.0008929994,0.00021626518,0.0000021067417],"category_scores_gemma":[0.00004159329,0.00030258193,0.00009568595,0.00028157784,0.00011273795,0.00017398025,0.0024892334,0.00050764333,0.00002099645],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023059723,0.00009557641,0.00017931449,0.0012053837,0.000107150896,0.000023407592,0.0077897483,0.22672139,0.000003995022,0.25621942,0.004737094,0.50289446],"study_design_scores_gemma":[0.00018377384,0.000079759244,0.00051395525,0.0003938199,0.0000148469435,0.000009340167,0.0001681013,0.98088855,0.00013171336,0.0051927753,0.011932439,0.00049090094],"about_ca_topic_score_codex":0.0000051674683,"about_ca_topic_score_gemma":0.0000038633502,"teacher_disagreement_score":0.7541672,"about_ca_system_score_codex":0.00006333183,"about_ca_system_score_gemma":0.00010440911,"threshold_uncertainty_score":0.9999426},"labels":[],"label_agreement":null},{"id":"W4415405753","doi":"10.1093/bioinformatics/btaf574","title":"aPhyloGeo: a Python application for correlating genetic and climatic conditions","year":2025,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic diversity and population structure","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Python (programming language); Scripting language; Software; R package; Software package","score_opus":0.0074076524019816995,"score_gpt":0.24863392399308845,"score_spread":0.24122627159110674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415405753","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76259726,0.0002580685,0.23355907,0.000143467,0.00016887205,0.00066512194,0.00011557664,0.000021486601,0.0024710777],"genre_scores_gemma":[0.958345,0.000037087684,0.04035064,0.0004929102,0.00003756743,0.00003731901,0.00034252336,0.000005331284,0.0003516477],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99954987,0.000008361087,0.00019102637,0.00009612142,0.000046748326,0.00010786348],"domain_scores_gemma":[0.9996533,0.000017815828,0.00008188261,0.00015611277,0.000058670565,0.000032255975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000059165897,0.00007969278,0.00007770221,0.00004741161,0.00015928855,0.000023604356,0.00006879945,0.000103556835,0.0000037525595],"category_scores_gemma":[0.000050822666,0.00008155129,0.000037545768,0.000070606744,0.000044860975,0.0000028080801,0.000052930434,0.0000317919,0.0000046369346],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037411918,0.00025076736,0.36821976,0.004642866,0.00084336166,0.0000011812328,0.0038598056,0.014452141,0.13355768,0.052376654,0.055861484,0.36556017],"study_design_scores_gemma":[0.00549813,0.00062471506,0.38092855,0.00018447037,0.00051713566,0.00005634801,0.0034767261,0.31564197,0.016515387,0.017948143,0.25736412,0.0012443053],"about_ca_topic_score_codex":0.0000026072432,"about_ca_topic_score_gemma":0.000005674552,"teacher_disagreement_score":0.36431587,"about_ca_system_score_codex":0.000005340249,"about_ca_system_score_gemma":0.000030601037,"threshold_uncertainty_score":0.33255652},"labels":[],"label_agreement":null},{"id":"W4415683348","doi":"10.1093/bioinformatics/btaf582","title":"Endowing protein language models with structural knowledge","year":2025,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Instituto de Ciencias del Mar y Limnología, Universidad Nacional Autónoma de México; Institute for Catastrophic Loss Reduction","keywords":"Code (set theory); Software; Source code; Knowledge representation and reasoning; Natural language; Language model","score_opus":0.01077066642079481,"score_gpt":0.26765891738078107,"score_spread":0.25688825095998624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415683348","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86852473,0.0018367148,0.07787958,0.0002558692,0.00017383357,0.0004051248,0.00002266407,0.000105151914,0.050796334],"genre_scores_gemma":[0.94915456,0.000009674503,0.047744855,0.00024320743,0.000053948694,0.000021132872,0.000052913743,0.0000072293997,0.0027124716],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994758,0.000012747063,0.00015927,0.00009889079,0.00007039826,0.00018293102],"domain_scores_gemma":[0.9996433,0.000007684356,0.00004060408,0.00021878559,0.000036417296,0.00005319645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000755503,0.0001098221,0.000104912004,0.000043301367,0.000069511145,0.000025988129,0.00015942496,0.00011368781,0.0000045422225],"category_scores_gemma":[0.00007197369,0.000076193704,0.00003540226,0.00010131889,0.000096769305,0.000005146902,0.00009509173,0.00007435366,0.000006919238],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000464587,0.00014236031,0.0016726654,0.0013579504,0.00058713945,0.000018870986,0.007678702,0.00047710745,0.108888894,0.014103566,0.024688747,0.8399194],"study_design_scores_gemma":[0.007535197,0.002058163,0.0019493487,0.0011428915,0.00018324396,0.000115816154,0.01736194,0.13553849,0.5677266,0.0026471636,0.26164517,0.0020960036],"about_ca_topic_score_codex":0.000006151778,"about_ca_topic_score_gemma":0.000014034029,"teacher_disagreement_score":0.8378234,"about_ca_system_score_codex":0.000009736745,"about_ca_system_score_gemma":0.00012353499,"threshold_uncertainty_score":0.3107089},"labels":[],"label_agreement":null},{"id":"W4416888770","doi":"10.1093/bioinformatics/btaf647","title":"PICNIC web server for predicting proteins involved in biomolecular condensates","year":2025,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Innovation Cluster (Canada)","funders":"H2020 European Research Council; NOMIS Stiftung; Max-Planck-Gesellschaft","keywords":"Picnic; Web server; Software; Clickstream; Server; The Internet","score_opus":0.008964446904368453,"score_gpt":0.26154384707350364,"score_spread":0.2525794001691352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416888770","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9558691,0.00033326255,0.03499274,0.00043896007,0.00034673238,0.001828418,0.00006671776,0.00009176402,0.0060323016],"genre_scores_gemma":[0.9515028,0.000044098466,0.04577348,0.0011266393,0.00007344478,0.00016764083,0.00039709377,0.00002736181,0.0008874253],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985893,0.000032703545,0.00066878047,0.00017429235,0.00015123883,0.0003837054],"domain_scores_gemma":[0.9991309,0.000031034073,0.00020184819,0.00046435956,0.00011163442,0.00006024723],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004844511,0.00022794135,0.00022306963,0.00019258259,0.00010362918,0.00006961711,0.0003334228,0.00025375778,0.000008027497],"category_scores_gemma":[0.0005986646,0.00021826001,0.000116061456,0.0002735308,0.00007579953,0.000018074566,0.00020925797,0.000160462,0.000013970246],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010257174,0.0007822521,0.35218087,0.010929072,0.0011207836,0.000010969993,0.0036522362,0.0054210536,0.5473537,0.011916121,0.039130278,0.026476942],"study_design_scores_gemma":[0.0071827834,0.00089355884,0.0059902836,0.0006226445,0.000106021405,0.000014966624,0.0018012547,0.6838063,0.17423072,0.0009078525,0.12326452,0.0011791056],"about_ca_topic_score_codex":0.000010997557,"about_ca_topic_score_gemma":0.00009025547,"teacher_disagreement_score":0.6783852,"about_ca_system_score_codex":0.000041154624,"about_ca_system_score_gemma":0.0002365388,"threshold_uncertainty_score":0.8900385},"labels":[],"label_agreement":null},{"id":"W4417091474","doi":"10.1093/bioinformatics/btaf652","title":"Columba: fast approximate pattern matching with optimized search schemes","year":2025,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Vlaamse regering; Fonds Wetenschappelijk Onderzoek","keywords":"Source code; Scripting language; Code (set theory); Pattern matching; Matching (statistics); Software; Pattern recognition (psychology)","score_opus":0.013772872712575615,"score_gpt":0.2763447204906703,"score_spread":0.2625718477780947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417091474","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00096710894,0.00006972032,0.98852205,0.00025189208,0.00005729764,0.00031285625,0.00000388663,0.00048754248,0.00932764],"genre_scores_gemma":[0.024852466,0.000089396795,0.97335225,0.0010774215,0.000013152318,0.000023277678,0.0000060398474,0.000008915259,0.00057707547],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99891156,0.000019228846,0.0003106269,0.00016153985,0.0002760227,0.00032103338],"domain_scores_gemma":[0.9991215,0.000059264483,0.000091247086,0.000539357,0.0001268684,0.00006177585],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024516208,0.00015557485,0.0002063835,0.00014921524,0.0001684031,0.00035682693,0.000730394,0.000056775698,0.000005079428],"category_scores_gemma":[0.00001817532,0.00012410367,0.000044305856,0.00055473257,0.00006315912,0.0011811034,0.00042939006,0.00018825472,0.000024136563],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003188338,0.00007829222,0.0003652256,0.0004897957,0.00006893896,0.000017193861,0.0017439359,0.0002975222,0.0002258465,0.014590132,0.0017320343,0.9803592],"study_design_scores_gemma":[0.0019876105,0.0002786921,0.00028864827,0.00074739,0.000025192488,0.000036880465,0.0009633854,0.89689964,0.08311851,0.0044605588,0.010446649,0.0007468654],"about_ca_topic_score_codex":0.000009093069,"about_ca_topic_score_gemma":0.0000011157808,"teacher_disagreement_score":0.97961235,"about_ca_system_score_codex":0.000048447622,"about_ca_system_score_gemma":0.00010385726,"threshold_uncertainty_score":0.5060801},"labels":[],"label_agreement":null},{"id":"W7116865545","doi":"10.1093/bioinformatics/btaf669","title":"RISK: a next-generation tool for biological network annotation and visualization","year":2025,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Canadian Institutes of Health Research; Canada Research Chairs","keywords":"Python (programming language); Visualization; Documentation; MIT License; Annotation; Software; Open source; License","score_opus":0.021530494849600415,"score_gpt":0.2663043655355657,"score_spread":0.2447738706859653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7116865545","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23448665,0.00055062067,0.7631782,0.000074645846,0.00034263753,0.00060518284,0.000040473806,0.000024067105,0.0006974759],"genre_scores_gemma":[0.90501714,0.0017056961,0.08772744,0.0018695425,0.00080531667,0.0001228688,0.0022820483,0.000018436864,0.00045150155],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992052,0.000023949333,0.00038950075,0.00012513323,0.00005385647,0.00020239897],"domain_scores_gemma":[0.99950236,0.00002752011,0.00016936612,0.0001694228,0.00009723602,0.000034084238],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036372882,0.00013188909,0.00012352734,0.0000414916,0.00021762298,0.00010340776,0.00008083946,0.0002085261,0.0000025564168],"category_scores_gemma":[0.00012646243,0.000115376286,0.000053102332,0.00011403344,0.000048134738,0.0000174941,0.00006954186,0.000049782087,0.0000028402349],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006084117,0.00017274641,0.022054192,0.00063016545,0.0005370626,3.7560645e-7,0.0011770593,0.01389076,0.033776414,0.090936705,0.2560177,0.5801984],"study_design_scores_gemma":[0.0013575965,0.000439361,0.0033673937,0.0000379614,0.00006672081,0.0000047573867,0.000198688,0.87550676,0.0027992975,0.0029546395,0.11286983,0.00039701007],"about_ca_topic_score_codex":0.0000016618411,"about_ca_topic_score_gemma":0.000007628321,"teacher_disagreement_score":0.861616,"about_ca_system_score_codex":0.000011757432,"about_ca_system_score_gemma":0.000046521254,"threshold_uncertainty_score":0.47049084},"labels":[],"label_agreement":null}]}