{"meta":{"query_hash":"c7cf3172b93e","filters":{"venue":"BioData Mining"},"cohort_total":48,"direct_labels_cover":0,"predictions_cover":48,"exported":48,"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/c7cf3172b93e","api":"https://metacan.xera.ac/api/v1/cohort?venue=BioData+Mining"},"results":[{"id":"W2069849680","doi":"10.1186/1756-0381-6-8","title":"Prediction of Drosophila melanogaster gene function using Support Vector Machines","year":2013,"lang":"en","type":"article","venue":"BioData Mining","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":"Public Health Ontario; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; University of Toronto; University of Washington","keywords":"Drosophila melanogaster; Gene; Genome; Biology; Computational biology; Support vector machine; Gene prediction; Genome project; Microarray analysis techniques; Melanogaster; Gene Annotation; Genetics; Annotation; Function (biology); Computer science; Artificial intelligence; Gene expression","score_opus":0.02614048323694971,"score_gpt":0.22492678509502498,"score_spread":0.19878630185807528,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2069849680","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9887379,0.00022861792,0.009700145,0.0000294747,0.00041859836,0.00014824918,0.00015877026,0.000009886924,0.00056836696],"genre_scores_gemma":[0.99305576,0.000024779287,0.005237799,0.00012671058,0.00041375554,0.0000070604024,0.0009489257,0.000014189275,0.00017101763],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99932396,0.000014229102,0.00025864178,0.00016742568,0.00007848915,0.0001572435],"domain_scores_gemma":[0.9994865,0.0000040819123,0.0001283983,0.00027753523,0.000054363536,0.000049132643],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000110946654,0.00010749537,0.00010704264,0.000036237037,0.000052599284,0.000025279149,0.00011029675,0.00012020535,0.00011233945],"category_scores_gemma":[0.000011405476,0.00009790954,0.000046157536,0.000050505354,0.000038800208,0.000014939369,0.00011119011,0.00004188047,0.000015913387],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000326911,0.000021713484,0.006812282,0.00002645971,0.00007383496,3.4919663e-7,0.00006792496,0.000058358488,0.97883993,0.000021953085,0.005761096,0.008283396],"study_design_scores_gemma":[0.005861073,0.004372421,0.21468228,0.00025846815,0.0007520072,0.00038391026,0.0011670513,0.1537419,0.51267165,0.0006328018,0.103416234,0.0020602082],"about_ca_topic_score_codex":0.000026178559,"about_ca_topic_score_gemma":0.0000030047183,"teacher_disagreement_score":0.46616828,"about_ca_system_score_codex":0.000006063194,"about_ca_system_score_gemma":0.000029685832,"threshold_uncertainty_score":0.39926353},"labels":[],"label_agreement":null},{"id":"W2101279094","doi":"10.1186/1756-0381-7-17","title":"Computational genetics analysis of grey matter density in Alzheimer’s disease","year":2014,"lang":"en","type":"article","venue":"BioData Mining","topic":"Olfactory and Sensory Function Studies","field":"Neuroscience","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 Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; U.S. National Library of Medicine; IXICO; National Cancer Institute; Servier; Eisai; Northern California Institute for Research and Education; University of California, San Diego; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; Synarc; University of Southern California; Medpace; Novartis Pharmaceuticals Corporation; Dartmouth College; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; Alzheimer's Disease Neuroimaging Initiative; National Center for Advancing Translational Sciences; Meso Scale Diagnostics; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Grey matter; Disease; Computer science; Data science; Computational biology; Biology; Medicine; Pathology","score_opus":0.19009645677759274,"score_gpt":0.3033707888264548,"score_spread":0.11327433204886206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2101279094","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.998397,0.000040427654,0.0009697186,0.00011877808,0.00010041046,0.000037174563,0.00008438841,0.000011280467,0.00024084753],"genre_scores_gemma":[0.9988786,0.0000035535422,0.00044819494,0.0005907781,0.000018197201,0.0000013583734,0.000028052786,0.0000037208547,0.00002752603],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99921405,0.00010220083,0.00018511279,0.00024252525,0.00015196737,0.000104134764],"domain_scores_gemma":[0.9994219,0.00024297625,0.000075312586,0.00018449251,0.000028026043,0.00004730205],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010539632,0.000071021546,0.00015988895,0.00018874065,0.00006855484,0.000015967134,0.00009682115,0.000017917911,0.000115528535],"category_scores_gemma":[0.00018546633,0.00006701174,0.00004862301,0.0003909331,0.000083110644,0.00007816552,0.00007326807,0.000036358426,0.000043438922],"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":[0.00003495546,0.00004264815,0.99160326,0.0000049534374,0.00006132537,0.000004023291,0.00027252152,0.0043246173,0.0022560216,0.00011044613,0.00045006713,0.00083514705],"study_design_scores_gemma":[0.00013519281,0.000011720693,0.9618882,0.0000047888575,0.00024195926,4.5020298e-7,0.00006160583,0.03460365,0.0020483523,0.00003483369,0.0008805301,0.00008869949],"about_ca_topic_score_codex":0.0000055549367,"about_ca_topic_score_gemma":0.000013162233,"teacher_disagreement_score":0.030279035,"about_ca_system_score_codex":0.0000055377523,"about_ca_system_score_gemma":0.000009899181,"threshold_uncertainty_score":0.27326593},"labels":[],"label_agreement":null},{"id":"W2102718331","doi":"10.1186/1756-0381-7-25","title":"Updating microbial genomic sequences: improving accuracy & innovation","year":2014,"lang":"en","type":"article","venue":"BioData Mining","topic":"Vibrio bacteria research studies","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":"McMaster University","keywords":"Sanger sequencing; Biology; Genome; Whole genome sequencing; Computational biology; Salmonella enterica; Biovar; Genetics; DNA sequencing; Caulobacter crescentus; Salmonella; Gene; Bacterial protein; Bacteria","score_opus":0.03551480171943568,"score_gpt":0.30131152252589205,"score_spread":0.2657967208064564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102718331","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9949825,0.000095890326,0.0038875905,0.00015664172,0.00016661288,0.000120590805,0.0000568384,0.000022820717,0.00051053776],"genre_scores_gemma":[0.97883654,0.000035012465,0.018872323,0.0002570248,0.00062955887,0.000015021012,0.001172549,0.00002119655,0.00016078708],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99883604,0.00006858689,0.00027045843,0.0004017336,0.00010075403,0.00032240723],"domain_scores_gemma":[0.9992366,0.000035747715,0.00015912682,0.00041707102,0.00011357681,0.00003786593],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005214084,0.00014287358,0.00012629226,0.00008077616,0.00019685007,0.000109557375,0.00031091913,0.00008647987,0.000023628947],"category_scores_gemma":[0.001826857,0.00013977475,0.000029408564,0.00017314222,0.000083046005,0.000017214183,0.00053513574,0.00007872747,0.000037656402],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002050296,0.000007472854,0.0021848076,0.000023748527,0.000023765182,4.1030142e-7,0.000067890665,0.0000027764127,0.9791818,0.000045593326,0.0020582736,0.016382912],"study_design_scores_gemma":[0.0010766598,0.00025489985,0.009635469,0.000073042174,0.000024240631,0.000027875994,0.0004889811,0.00027555018,0.62759584,0.000027556036,0.35984358,0.0006763188],"about_ca_topic_score_codex":0.00005514313,"about_ca_topic_score_gemma":0.000057617828,"teacher_disagreement_score":0.3577853,"about_ca_system_score_codex":0.000025193121,"about_ca_system_score_gemma":0.000088451416,"threshold_uncertainty_score":0.5699849},"labels":[],"label_agreement":null},{"id":"W2111827030","doi":"10.1186/1756-0381-7-7","title":"Semi-supervised consensus clustering for gene expression data analysis","year":2014,"lang":"en","type":"article","venue":"BioData Mining","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","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":"National Research Council Canada","funders":"National Research Council Canada","keywords":"Cluster analysis; Computer science; Data mining; Consensus clustering; Computational biology; Expression (computer science); Artificial intelligence; Biology; Correlation clustering; CURE data clustering algorithm","score_opus":0.10870116120127883,"score_gpt":0.350048260191916,"score_spread":0.24134709899063717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111827030","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":[0.009160727,0.00009615543,0.98954815,0.00029908068,0.00021241573,0.00019267082,0.00019287046,0.0001903047,0.00010763375],"genre_scores_gemma":[0.100251526,0.000008777801,0.8988735,0.000102494276,0.00016945071,0.000026265225,0.00039335602,0.000019435933,0.00015516976],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975791,0.00011049992,0.00032733305,0.0010838093,0.0003712849,0.0005279975],"domain_scores_gemma":[0.9956253,0.0006040205,0.0001127965,0.0033836307,0.00010081248,0.00017341977],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010748924,0.00018652648,0.00030423436,0.00028189865,0.00027555652,0.00028352565,0.0032198285,0.00007660229,0.000009857924],"category_scores_gemma":[0.00063049985,0.00017847959,0.00006704203,0.00076485926,0.000054739427,0.00055216544,0.0039583724,0.000107037326,0.000014821318],"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":[0.0001242456,0.00013840171,0.0022234092,0.0002391892,0.0006212818,0.000048752372,0.0015851946,0.017231265,0.23725398,0.00023383195,0.0066864477,0.733614],"study_design_scores_gemma":[0.0004974369,0.00004901356,0.00019217124,0.00003076276,0.000039380524,0.000009660277,0.000063021114,0.98215234,0.009976949,0.000034052187,0.0067231623,0.00023204969],"about_ca_topic_score_codex":0.000024657864,"about_ca_topic_score_gemma":0.000017973636,"teacher_disagreement_score":0.96492106,"about_ca_system_score_codex":0.00003882491,"about_ca_system_score_gemma":0.000049171987,"threshold_uncertainty_score":0.72781867},"labels":[],"label_agreement":null},{"id":"W2120184682","doi":"10.1186/s13040-014-0032-2","title":"Integrative genomics and transcriptomics analysis of human embryonic and induced pluripotent stem cells","year":2014,"lang":"en","type":"article","venue":"BioData Mining","topic":"Genomic variations and chromosomal abnormalities","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":"Lunenfeld-Tanenbaum Research Institute","funders":"Emil Aaltosen Säätiö; European Commission","keywords":"Embryonic stem cell; Induced pluripotent stem cell; Genomics; Transcriptome; Computational biology; Biology; Human Induced Pluripotent Stem Cells; Stem cell; Data science; Computer science; Genetics; Genome; Gene; Gene expression","score_opus":0.017187619078278094,"score_gpt":0.23010869046941393,"score_spread":0.21292107139113584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120184682","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.998571,0.00027063894,0.0007667626,0.000024903242,0.00003704521,0.00006011386,0.00014046507,0.0000036305685,0.00012544614],"genre_scores_gemma":[0.998676,0.0001135899,0.00082880305,0.000041551277,0.00003308839,0.0000037384846,0.00016272264,0.0000082846955,0.00013220061],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99935836,0.000043077136,0.00019134412,0.0002431014,0.000044059347,0.00012007445],"domain_scores_gemma":[0.9995872,0.000011678463,0.00009822621,0.00021696615,0.00003651879,0.000049424598],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014267188,0.00011342824,0.00020404485,0.00008537683,0.00007682276,0.000028264058,0.00010123063,0.0000836539,0.0000046055634],"category_scores_gemma":[0.000005928216,0.00010329277,0.00005050739,0.00008499524,0.00006208806,0.0000055496866,0.000085941356,0.000039645547,2.7529248e-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":[0.00001295563,0.000014871164,0.0046887184,0.000016579928,0.0003540641,1.9101655e-7,0.00096148695,0.000012950385,0.99158657,0.00041283458,0.00002751039,0.0019112548],"study_design_scores_gemma":[0.00079060794,0.0005902258,0.015885336,0.000023550974,0.00088069553,0.000006160422,0.008538934,0.002159905,0.9667554,0.000029107803,0.0039595393,0.00038052967],"about_ca_topic_score_codex":0.000055471588,"about_ca_topic_score_gemma":0.00014007324,"teacher_disagreement_score":0.024831176,"about_ca_system_score_codex":0.000008707048,"about_ca_system_score_gemma":0.000022981238,"threshold_uncertainty_score":0.42121568},"labels":[],"label_agreement":null},{"id":"W2136227372","doi":"10.1186/s13040-015-0056-2","title":"The role of visualization and 3-D printing in biological data mining","year":2015,"lang":"en","type":"article","venue":"BioData Mining","topic":"Data Visualization and Analytics","field":"Computer Science","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 Institute of General Medical Sciences; National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; U.S. National Library of Medicine; IXICO; Servier; Eisai; Northern California Institute for Research and Education; University of California, San Diego; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; Synarc; University of Southern California; Medpace; Novartis Pharmaceuticals Corporation; Dartmouth College; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; Alzheimer's Disease Neuroimaging Initiative; National Center for Advancing Translational Sciences; Meso Scale Diagnostics; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Visualization; Data science; Computer science; Biological network; Biological data; Data mining; Endophenotype; Data visualization; Artificial intelligence; Machine learning; Bioinformatics; Biology; Neuroscience","score_opus":0.1481506632125918,"score_gpt":0.3576323327334887,"score_spread":0.20948166952089692,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136227372","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66082215,0.0032795097,0.3322251,0.0004706022,0.00036382294,0.0002570251,0.000100724086,0.00016690222,0.00231413],"genre_scores_gemma":[0.97095925,0.00012575566,0.028594237,0.00007345355,0.000032787306,0.0000013270541,0.00019010752,0.0000044238377,0.00001864554],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991651,0.00007305424,0.00023737407,0.00026034244,0.0001337954,0.00013031787],"domain_scores_gemma":[0.9990768,0.00013280028,0.000114738265,0.0005856568,0.00004200575,0.000048024925],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010654032,0.000060306236,0.00008951568,0.00006060499,0.000062419516,0.00015687205,0.0009800876,0.000032150616,9.549539e-7],"category_scores_gemma":[0.0008314543,0.00004291663,0.000005482324,0.00033849222,0.00005735435,0.0005165736,0.0014805039,0.000030220343,0.0000022913896],"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":[0.000012924076,0.000099795456,0.3952276,0.0000179798,0.000022803695,0.0000067269143,0.005399566,0.000013717566,0.0012090281,0.16742767,0.0020057834,0.42855638],"study_design_scores_gemma":[0.0002800441,0.00004452606,0.0037744404,0.000050314786,0.0000033753845,0.000005890909,0.00362853,0.9367109,0.00064960314,0.00026643474,0.054459315,0.00012663567],"about_ca_topic_score_codex":0.0000152099055,"about_ca_topic_score_gemma":0.000017026034,"teacher_disagreement_score":0.9366972,"about_ca_system_score_codex":0.000006276935,"about_ca_system_score_gemma":0.000046746263,"threshold_uncertainty_score":0.18453422},"labels":[],"label_agreement":null},{"id":"W2155858762","doi":"10.1186/1756-0381-4-22","title":"Detection of putative new mutacins by bioinformatic analysis using available web tools","year":2011,"lang":"en","type":"article","venue":"BioData Mining","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":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bacteriocin; Computational biology; Context (archaeology); Identification (biology); Genome; Biology; Drug discovery; Whole genome sequencing; Computer science; Genetics; Gene; Bioinformatics; Bacteria","score_opus":0.06311613741850325,"score_gpt":0.2527864325412549,"score_spread":0.18967029512275163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155858762","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99073744,0.0010333546,0.0067123976,0.000002858626,0.0000626828,0.00008053322,0.00026979067,0.000002909309,0.0010980127],"genre_scores_gemma":[0.9875294,0.00012903872,0.011943589,0.000028262233,0.000032787895,0.0000025524246,0.00014789293,0.00000851129,0.0001779969],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999316,0.000019218392,0.00024181773,0.00019796765,0.00006527873,0.00015976466],"domain_scores_gemma":[0.99946713,0.000009636507,0.00016258522,0.00026110688,0.000047422458,0.00005213575],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011219183,0.000114672745,0.00017848115,0.00008313139,0.000063224594,0.000015897014,0.0001342907,0.0000692193,0.000035549485],"category_scores_gemma":[0.00004953511,0.000110041656,0.000082826664,0.00023252226,0.00004806929,0.0000041295148,0.00012152587,0.00002628893,0.000007485236],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023700859,0.000015531252,0.0037617458,0.000009567765,0.00048395438,2.832639e-7,0.000556665,0.000017975566,0.9912604,0.0000014937152,0.00035080823,0.0035178855],"study_design_scores_gemma":[0.00031098173,0.00021195938,0.0023260876,0.0000064580504,0.00038067796,0.0000035525766,0.0010092106,0.002018586,0.98893195,0.0000061434,0.0045974497,0.00019694315],"about_ca_topic_score_codex":0.00018955335,"about_ca_topic_score_gemma":0.00003725627,"teacher_disagreement_score":0.005231192,"about_ca_system_score_codex":0.000008352761,"about_ca_system_score_gemma":0.000060403752,"threshold_uncertainty_score":0.44873685},"labels":[],"label_agreement":null},{"id":"W2161488150","doi":"10.1186/1756-0381-5-8","title":"A comparison and evaluation of five biclustering algorithms by quantifying goodness of biclusters for gene expression data","year":2012,"lang":"en","type":"article","venue":"BioData Mining","topic":"Gene expression and cancer classification","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":"York University","keywords":"Biclustering; Ranking (information retrieval); Computer science; Data mining; Gene ontology; Correlation; Algorithm; Expression (computer science); Cluster analysis; Artificial intelligence; Pattern recognition (psychology); Mathematics; Gene; Gene expression; Biology; Correlation clustering","score_opus":0.26423594520003696,"score_gpt":0.4307928668063278,"score_spread":0.16655692160629082,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161488150","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96432525,0.004466833,0.030310767,0.0000224571,0.0001949673,0.00025757463,0.0003959804,0.000004119159,0.00002202492],"genre_scores_gemma":[0.98160875,0.00008516629,0.016050547,0.000013081649,0.00008735937,0.000028830747,0.002096337,0.000012285954,0.00001763394],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99903333,0.00007178386,0.00027782074,0.00028733307,0.00018480043,0.0001449146],"domain_scores_gemma":[0.99902517,0.000023217668,0.00026884663,0.00052447605,0.000104370665,0.000053937525],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00083642197,0.00009516445,0.00015031389,0.000046995294,0.000053332427,0.000010917454,0.00023247497,0.0000863854,0.000004157487],"category_scores_gemma":[0.00012328499,0.00008934622,0.000020602376,0.00006443893,0.00004478934,0.00002682007,0.00031910438,0.000024137827,1.6611052e-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":[0.00006154382,0.000049122504,0.008278358,0.00006325463,0.000018620913,6.815372e-9,0.00031717293,0.00002155566,0.9716069,0.0000010156267,0.0031064611,0.016475998],"study_design_scores_gemma":[0.0008091119,0.00006487116,0.002056366,0.0000773194,0.00005968614,0.0000014127116,0.0019903514,0.021546438,0.9695394,7.799332e-7,0.0037397367,0.00011454889],"about_ca_topic_score_codex":0.000012811014,"about_ca_topic_score_gemma":0.0000023895127,"teacher_disagreement_score":0.021524882,"about_ca_system_score_codex":0.000008202066,"about_ca_system_score_gemma":0.000037242524,"threshold_uncertainty_score":0.36434332},"labels":[],"label_agreement":null},{"id":"W2165336562","doi":"10.1186/1756-0381-5-14","title":"Peer2ref: a peer-reviewer finding web tool that uses author disambiguation","year":2012,"lang":"en","type":"article","venue":"BioData Mining","topic":"Biomedical Text Mining and Ontologies","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":"Ottawa Hospital","funders":"","keywords":"Computer science; MEDLINE; Information retrieval; Web of science; World Wide Web; Selection (genetic algorithm); Data science; Artificial intelligence","score_opus":0.11928096650161898,"score_gpt":0.35438555593076476,"score_spread":0.23510458942914578,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2165336562","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98950434,0.005100616,0.0017662668,0.0011802912,0.0013302644,0.00014763874,0.00013065766,0.00007072637,0.00076922285],"genre_scores_gemma":[0.9821376,0.00015399998,0.01211789,0.0003785236,0.00089495967,0.00003063656,0.00074405613,0.000023479843,0.0035188145],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985997,0.00008202893,0.0002324081,0.00033590553,0.0002934553,0.00045651398],"domain_scores_gemma":[0.99917686,0.00004870466,0.00011679211,0.0004454548,0.00008527291,0.00012693244],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008672047,0.00019303523,0.00019282624,0.000053929085,0.0001446062,0.000058737987,0.0002794079,0.00023792886,0.0001037746],"category_scores_gemma":[0.002132459,0.00016061682,0.000087618195,0.00011552478,0.0001143357,0.000018184064,0.00024352688,0.000099886456,0.00007114138],"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":[0.00007813299,0.00020870924,0.16185717,0.00012740852,0.0001551075,0.000005408124,0.0010831968,8.838655e-7,0.14617202,0.00012716594,0.4069409,0.2832439],"study_design_scores_gemma":[0.00031837594,0.000103442,0.016629763,0.0000706685,0.000046050383,0.000018660932,0.0007237142,0.00005116597,0.017708384,0.0000042583492,0.964009,0.00031654254],"about_ca_topic_score_codex":0.000008701321,"about_ca_topic_score_gemma":0.000008877893,"teacher_disagreement_score":0.55706805,"about_ca_system_score_codex":0.000016597882,"about_ca_system_score_gemma":0.00005235821,"threshold_uncertainty_score":0.65497637},"labels":[],"label_agreement":null},{"id":"W2171815584","doi":"10.1186/1756-0381-7-22","title":"Applications of the MapReduce programming framework to clinical big data analysis: current landscape and future trends","year":2014,"lang":"en","type":"review","venue":"BioData Mining","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":147,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Calgary Laboratory Services; University of Calgary","funders":"","keywords":"Computer science; Big data; Scalability; Programming paradigm; Data-intensive computing; Distributed computing; Data processing; Node (physics); Distributed File System; Grid computing; Grid; Database; Data mining; Operating system; Programming language","score_opus":0.5193724130788084,"score_gpt":0.6095661319612116,"score_spread":0.09019371888240313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171815584","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":[0.000018338575,0.98756754,0.004133681,0.00074314047,0.003201017,0.0019603532,0.0022286815,0.00006137962,0.00008585974],"genre_scores_gemma":[0.00007047948,0.980335,0.0073614377,0.0001415855,0.00876006,0.00082986674,0.0023534128,0.00005435283,0.00009382927],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9936592,0.0016312766,0.0025534867,0.0012125572,0.00036604702,0.0005774499],"domain_scores_gemma":[0.99085635,0.002586156,0.0016158135,0.0044381097,0.00017990271,0.0003236547],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003090408,0.0003914495,0.001985457,0.00046666726,0.00072144927,0.000036353544,0.0024423471,0.00085680536,0.000088081884],"category_scores_gemma":[0.0011630998,0.00025495907,0.00033952316,0.0031610602,0.00014667163,0.000070517315,0.0024422428,0.001921242,0.00008166684],"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":[0.0000036035487,0.000037487043,0.012373598,0.006829333,0.00021227589,1.9036837e-7,0.00051273336,6.334742e-8,2.8235516e-9,0.00020375005,0.0039520985,0.97587484],"study_design_scores_gemma":[0.000021921853,0.000025269375,0.0002790058,0.009436141,0.002326132,7.593265e-7,0.0015976354,0.00005883389,1.6051013e-8,0.000014784382,0.9860072,0.0002322844],"about_ca_topic_score_codex":0.00009804327,"about_ca_topic_score_gemma":0.0006583137,"teacher_disagreement_score":0.9820551,"about_ca_system_score_codex":0.000050366183,"about_ca_system_score_gemma":0.000713143,"threshold_uncertainty_score":0.9999903},"labels":[],"label_agreement":null},{"id":"W2202714662","doi":"10.1186/s13040-015-0077-x","title":"Characterizing gene-gene interactions in a statistical epistasis network of twelve candidate genes for obesity","year":2015,"lang":"en","type":"article","venue":"BioData Mining","topic":"Genetic Associations and Epidemiology","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":"Memorial University of Newfoundland","funders":"U.S. National Library of Medicine; National Institute of General Medical Sciences; National Institutes of Health","keywords":"Epistasis; SNP; Missing heritability problem; Single-nucleotide polymorphism; Genetics; Gene; Genome-wide association study; Biology; Candidate gene; Pairwise comparison; Computational biology; Statistics; Genotype; Mathematics","score_opus":0.059058872348792146,"score_gpt":0.32741833500269707,"score_spread":0.2683594626539049,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2202714662","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9683664,0.0004976006,0.02951682,0.00019148014,0.00026014072,0.00016953923,0.00090817054,0.0000054692305,0.00008437403],"genre_scores_gemma":[0.9239696,0.00011127246,0.07297545,0.00013710176,0.00029371574,0.000045085708,0.0023848508,0.000013654665,0.00006921602],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988764,0.00010275547,0.00036910974,0.00029617856,0.000059010817,0.00029656358],"domain_scores_gemma":[0.99927825,0.000084719104,0.00018026843,0.00026162874,0.000103790895,0.00009131681],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059520046,0.00011663089,0.000241204,0.00003506705,0.000057747442,0.000011117635,0.00014638156,0.000088188375,0.000008474427],"category_scores_gemma":[0.0005252609,0.00012006146,0.000048484806,0.000086234984,0.000050574872,0.0000057648585,0.00012887995,0.000048573842,0.0000026819287],"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":[0.00029736166,0.00017251285,0.6614468,0.000038119724,0.0002019444,0.000005777489,0.0003680948,0.00051928783,0.3078722,0.00017028901,0.014719871,0.014187727],"study_design_scores_gemma":[0.0033410096,0.0009404897,0.7237233,0.0000917791,0.00019542314,0.0000621027,0.0014541008,0.005521557,0.11951453,0.0006267246,0.14351878,0.0010102289],"about_ca_topic_score_codex":0.0002157753,"about_ca_topic_score_gemma":0.00048664695,"teacher_disagreement_score":0.18835767,"about_ca_system_score_codex":0.000034563967,"about_ca_system_score_gemma":0.00013147548,"threshold_uncertainty_score":0.48959643},"labels":[],"label_agreement":null},{"id":"W2222833576","doi":"10.1186/s13040-015-0062-4","title":"Functional dyadicity and heterophilicity of gene-gene interactions in statistical epistasis networks","year":2015,"lang":"en","type":"article","venue":"BioData Mining","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":"Memorial University of Newfoundland","funders":"National Institute of Allergy and Infectious Diseases; U.S. National Library of Medicine; National Institute of General Medical Sciences; National Cancer Institute; National Institutes of Health","keywords":"Epistasis; Context (archaeology); Computational biology; Biology; Genetic association; Gene; Gene interaction; Gene ontology; Genetics; Computer science; Genotype; Single-nucleotide polymorphism; Gene expression","score_opus":0.04534004385984268,"score_gpt":0.2740099323237019,"score_spread":0.22866988846385922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2222833576","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8859716,0.0005469391,0.11257617,0.000062003266,0.00022182759,0.00008350639,0.00024830562,0.0000045474194,0.00028511937],"genre_scores_gemma":[0.9878322,0.000057887104,0.010984727,0.000118656135,0.00015983752,0.0000055417668,0.0007998287,0.00000767144,0.000033678625],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99927163,0.000033974746,0.0002709529,0.00018763171,0.000074512194,0.00016129472],"domain_scores_gemma":[0.99954104,0.000025203079,0.00008391117,0.00020114715,0.000044704277,0.00010396485],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025143282,0.00009828845,0.00013417091,0.000040884075,0.00003350321,0.00001721909,0.00008495055,0.00007370537,0.000010488771],"category_scores_gemma":[0.00006658953,0.00009698726,0.000022146925,0.000062645195,0.00009915008,0.000008205081,0.00012896703,0.00008352226,0.0000016994188],"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":[0.0033010645,0.0010848962,0.3741522,0.0002466036,0.00090381847,0.00006484165,0.002095484,0.020203339,0.25974306,0.0026752816,0.12617947,0.20934992],"study_design_scores_gemma":[0.01306244,0.002928176,0.45500582,0.00030842205,0.00032894482,0.00087903265,0.0037995547,0.33562508,0.10141459,0.0016617315,0.08171199,0.0032742047],"about_ca_topic_score_codex":0.00007665505,"about_ca_topic_score_gemma":0.00015202495,"teacher_disagreement_score":0.31542176,"about_ca_system_score_codex":0.000015579837,"about_ca_system_score_gemma":0.000044692457,"threshold_uncertainty_score":0.39550257},"labels":[],"label_agreement":null},{"id":"W2232773008","doi":"10.1186/s13040-015-0078-9","title":"Iteratively refining breast cancer intrinsic subtypes in the METABRIC dataset","year":2016,"lang":"en","type":"article","venue":"BioData Mining","topic":"AI in cancer detection","field":"Computer Science","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":"BC Cancer Agency; Australian Research Council; Cancer Research UK","keywords":"Discriminative model; Computer science; Machine learning; Artificial intelligence; Set (abstract data type); Breast cancer; Class (philosophy); Data mining; Pattern recognition (psychology); Cancer; Medicine","score_opus":0.04386414633269161,"score_gpt":0.2884951767383135,"score_spread":0.24463103040562187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2232773008","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5046088,0.005460222,0.3870594,0.073456556,0.0064642713,0.0010018814,0.018871747,0.00081595406,0.0022611383],"genre_scores_gemma":[0.9847666,0.00012620247,0.013276621,0.0012472902,0.0002996771,0.00008172485,0.000093137736,0.000013123909,0.000095642354],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986773,0.00015001814,0.00021212701,0.00044976553,0.00023999752,0.00027074976],"domain_scores_gemma":[0.9988001,0.00025158655,0.00011550536,0.00076667353,0.000031352407,0.00003480083],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006578565,0.0001289336,0.0001283753,0.00013486069,0.00011530317,0.00018506176,0.0012282039,0.000040397674,0.000051162984],"category_scores_gemma":[0.00006078825,0.00007262917,0.000020174148,0.0006225513,0.00005333847,0.0013027688,0.0003569616,0.000097631186,0.00007410496],"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":[0.000023885128,0.000023275617,0.011796654,0.000008783866,0.000022829508,0.000026721425,0.0013581882,0.0000025340507,0.002261038,0.0015491381,0.019813754,0.9631132],"study_design_scores_gemma":[0.002147567,0.0002068578,0.39357874,0.0006967668,0.000052030184,0.0004697305,0.00059287465,0.002609158,0.0070255576,0.0003932452,0.5910686,0.0011588426],"about_ca_topic_score_codex":0.0003516575,"about_ca_topic_score_gemma":0.00039944996,"teacher_disagreement_score":0.96195436,"about_ca_system_score_codex":0.00009965905,"about_ca_system_score_gemma":0.000084498504,"threshold_uncertainty_score":0.29617316},"labels":[],"label_agreement":null},{"id":"W2273538503","doi":"10.1186/s13040-016-0082-8","title":"Network-based analysis of genetic variants associated with hippocampal volume in Alzheimer’s disease: a study of ADNI cohorts","year":2016,"lang":"en","type":"article","venue":"BioData Mining","topic":"Genetic Associations and Epidemiology","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":"National Institute of General Medical Sciences; 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; Genentech; U.S. National Library of Medicine; IXICO; Servier; Eisai; Pfizer; Biogen; BioClinica; Medpace; F. Hoffmann-La Roche; Synarc; University of Southern California; Novartis Pharmaceuticals Corporation; Dartmouth College; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; Alzheimer's Disease Neuroimaging Initiative; National Center for Advancing Translational Sciences; Meso Scale Diagnostics; Gordon and Betty Moore Foundation; Foundation for the National Institutes of Health; Alzheimer's Association; National Science Foundation","keywords":"Hippocampal formation; Disease; Volume (thermodynamics); Genetic variants; Alzheimer's disease; Neuroscience; Computer science; Medicine; Data science; Computational biology; Biology; Internal medicine; Genetics; Genotype; Gene","score_opus":0.028979905395350163,"score_gpt":0.2713402144407311,"score_spread":0.24236030904538092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2273538503","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9970605,0.00048576292,0.0018606718,0.000059173977,0.000038801707,0.00023136733,0.00023816951,0.0000049196706,0.00002063636],"genre_scores_gemma":[0.99813443,0.000018240482,0.0013570499,0.00004800843,0.000031465963,0.000030149673,0.0003389554,0.000014031342,0.000027644464],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99833775,0.0003030643,0.0005033942,0.00040857994,0.0001523856,0.00029482917],"domain_scores_gemma":[0.9987598,0.00010209969,0.00042420675,0.00052149803,0.00011224196,0.00008015046],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005515988,0.00014950328,0.00046338054,0.00014509549,0.000034816392,0.0000043869377,0.00021363255,0.00011509163,0.00003841625],"category_scores_gemma":[0.00040901056,0.00011185621,0.0000736482,0.0005533658,0.00007982076,0.0000033829035,0.00009039056,0.000032919466,7.6366916e-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":[0.00012122423,0.00030937523,0.99126536,0.0000022071958,0.001282145,0.000005206212,0.000050156945,0.00372702,0.0013384621,8.8133385e-7,0.0004011757,0.0014967615],"study_design_scores_gemma":[0.0011451448,0.0005354465,0.9946813,0.000038399205,0.0012319365,2.0867733e-7,0.000082900755,0.0020225798,0.00006045047,0.000005670055,0.000048387723,0.00014756093],"about_ca_topic_score_codex":0.00012400938,"about_ca_topic_score_gemma":0.0009912568,"teacher_disagreement_score":0.0034159299,"about_ca_system_score_codex":0.00001632068,"about_ca_system_score_gemma":0.00013366337,"threshold_uncertainty_score":0.45613638},"labels":[],"label_agreement":null},{"id":"W2368906419","doi":"10.1186/s13040-016-0098-0","title":"Machine learning algorithms for mode-of-action classification in toxicity assessment","year":2016,"lang":"en","type":"article","venue":"BioData Mining","topic":"Gene expression and cancer classification","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":"MacEwan University; University of Calgary; Alberta Health; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Computer science; Action (physics); Mode (computer interface); Machine learning; Artificial intelligence; Mode of action; Algorithm; Chemistry; Human–computer interaction","score_opus":0.08482953243657332,"score_gpt":0.3714903720574589,"score_spread":0.28666083962088557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2368906419","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7219605,0.00017368885,0.27639496,0.0004426615,0.00021350055,0.00024697537,0.00010387858,0.00001531479,0.00044851608],"genre_scores_gemma":[0.9904549,0.00023054577,0.008397649,0.000024438348,0.0000861273,0.000071020026,0.00033137543,0.000010820465,0.00039312954],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99927795,0.000046591944,0.00020155107,0.00027494296,0.00008135638,0.00011759396],"domain_scores_gemma":[0.99953794,0.000019075102,0.00014157128,0.00022051322,0.00005059589,0.000030302972],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019392688,0.00007786582,0.00008630115,0.00006224531,0.000043114855,0.000008671505,0.00011004916,0.0000879584,0.000012846824],"category_scores_gemma":[0.000086039225,0.000060960676,0.000033992947,0.00007134599,0.000025150235,0.000009848298,0.000041023082,0.000033113047,0.0000010227828],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004520913,0.000030948566,0.009402194,0.000010274243,0.0000059028002,4.998762e-8,0.0000180644,0.000010611825,0.87752885,0.000084572166,0.0002919388,0.1125714],"study_design_scores_gemma":[0.0010689815,0.00023041363,0.024011921,0.000057697056,0.000008593912,0.0000014244171,0.00026540988,0.010553146,0.8944213,0.00003987935,0.069172874,0.00016839556],"about_ca_topic_score_codex":0.00000997814,"about_ca_topic_score_gemma":0.000018476947,"teacher_disagreement_score":0.2684944,"about_ca_system_score_codex":0.000031885993,"about_ca_system_score_gemma":0.000055735854,"threshold_uncertainty_score":0.24859042},"labels":[],"label_agreement":null},{"id":"W2528021625","doi":"10.1186/s13040-017-0129-5","title":"Variant Set Enrichment: an R package to identify disease-associated functional genomic regions","year":2017,"lang":"en","type":"article","venue":"BioData Mining","topic":"Genomics and Rare Diseases","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 Health Network; Ontario Institute for Cancer Research; University of Toronto; Princess Margaret Cancer Centre","funders":"U.S. National Library of Medicine; National Institute of Environmental Health Sciences; Canadian Cancer Society Research Institute; Canadian Institutes of Health Research; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; National Cancer Institute; National Institutes of Health; Prostate Cancer Canada; Natural Sciences and Engineering Research Council of Canada; Princess Margaret Cancer Foundation","keywords":"Computational biology; Disease; Set (abstract data type); Genome; R package; Human genome; Computer science; Biology; Genetics; Gene; Medicine","score_opus":0.05028613776478923,"score_gpt":0.31212661942188835,"score_spread":0.2618404816570991,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2528021625","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9961224,0.000262652,0.00065330724,0.000359256,0.0004150873,0.00015107972,0.0016942541,0.000017277518,0.000324675],"genre_scores_gemma":[0.9934433,0.00005694859,0.000329553,0.0004419348,0.00035186892,0.000024138537,0.0046342006,0.000025669127,0.00069235865],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99888664,0.00003978664,0.00016519964,0.0005094143,0.00011787985,0.00028110025],"domain_scores_gemma":[0.9983409,0.000007023969,0.00013448136,0.0011035176,0.0000593586,0.00035471382],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016357806,0.00015807149,0.00011426646,0.00004403819,0.0006131394,0.00025805403,0.00051212293,0.000082530896,0.000052030293],"category_scores_gemma":[0.0002443164,0.00015997779,0.000082007,0.00002958017,0.000053965607,0.000015934284,0.0004401143,0.000043268294,0.000060358187],"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":[0.0005127924,0.000557189,0.09996618,0.000033153578,0.0004852827,0.00039036223,0.00030808573,0.000075614436,0.78363,0.00075923814,0.11041342,0.0028686782],"study_design_scores_gemma":[0.0006449974,0.00014440202,0.95519733,0.000026336484,0.000096202966,0.000016898046,0.00018567703,0.000073551884,0.0013844878,0.00011646471,0.041696727,0.00041691752],"about_ca_topic_score_codex":0.00004115216,"about_ca_topic_score_gemma":0.00007308572,"teacher_disagreement_score":0.85523117,"about_ca_system_score_codex":0.00002456577,"about_ca_system_score_gemma":0.00013233876,"threshold_uncertainty_score":0.6523705},"labels":[],"label_agreement":null},{"id":"W2587099845","doi":"10.1186/s13040-017-0123-y","title":"Semantics-based plausible reasoning to extend the knowledge coverage of medical knowledge bases for improved clinical decision support","year":2017,"lang":"en","type":"article","venue":"BioData Mining","topic":"Biomedical Text Mining and Ontologies","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":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Model-based reasoning; Semantics (computer science); Semantic Web; Data science; Artificial intelligence; Information retrieval; Knowledge representation and reasoning","score_opus":0.076125745526062,"score_gpt":0.4277109479327042,"score_spread":0.3515852024066422,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2587099845","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8281624,0.001747478,0.16089898,0.0038353945,0.0021578032,0.0008225049,0.00066238776,0.000061339815,0.0016517526],"genre_scores_gemma":[0.95138985,0.00022014018,0.045951534,0.00064103416,0.0008734776,0.00005659929,0.00027010991,0.000038694892,0.000558543],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99810565,0.000093682764,0.00058929,0.0005933867,0.00022489623,0.0003931258],"domain_scores_gemma":[0.99746454,0.00069092185,0.00029335835,0.001130287,0.0001623192,0.0002585555],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002621737,0.00021415803,0.00038519118,0.000054215085,0.0004391892,0.0000974355,0.0014499075,0.00043261348,0.00006001593],"category_scores_gemma":[0.011651023,0.00014988297,0.00019377525,0.000066522996,0.00048308252,0.000008058413,0.0008788945,0.00015807674,0.000013698179],"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":[0.000834221,0.00042496307,0.012752078,0.00011221079,0.00012975953,0.00000771902,0.00015144344,0.0000017736417,0.012469454,0.00014567618,0.09258411,0.8803866],"study_design_scores_gemma":[0.0031854731,0.0019870005,0.015712813,0.0005119773,0.000099454905,0.000017472208,0.00024927306,0.007726649,0.023242526,0.000030433412,0.94680065,0.00043627768],"about_ca_topic_score_codex":0.00002308773,"about_ca_topic_score_gemma":0.0002851382,"teacher_disagreement_score":0.8799503,"about_ca_system_score_codex":0.000010330932,"about_ca_system_score_gemma":0.00058704265,"threshold_uncertainty_score":0.99667424},"labels":[],"label_agreement":null},{"id":"W2610597045","doi":"10.1186/s13040-017-0136-6","title":"Study of Meta-analysis strategies for network inference using information-theoretic approaches","year":2017,"lang":"en","type":"article","venue":"BioData Mining","topic":"Gene Regulatory Network 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":"Princess Margaret Cancer Centre; University of Toronto; Ontario Institute for Cancer Research","funders":"Université de Liège; Fonds De La Recherche Scientifique - FNRS","keywords":"Pairwise comparison; Computer science; Data mining; Inference; Set (abstract data type); Reverse engineering; Machine learning; Artificial intelligence","score_opus":0.21284763766452527,"score_gpt":0.3422631988385581,"score_spread":0.12941556117403283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2610597045","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95629406,0.0005366302,0.04253909,0.00001626934,0.000039098748,0.00028536873,0.00006582367,0.0000058900487,0.00021778408],"genre_scores_gemma":[0.9896316,0.000008498205,0.009926555,0.000015495361,0.00008976804,0.000038129456,0.00025903908,0.000008985703,0.000021913505],"study_design_codex":"simulation_or_modeling","study_design_gemma":"meta_analysis","domain_scores_codex":[0.9989002,0.00006826757,0.00039479884,0.0002753216,0.00014650777,0.0002149025],"domain_scores_gemma":[0.99795383,0.000030920633,0.0005800706,0.0012683623,0.000121212186,0.00004559193],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056296866,0.00017008561,0.00051986286,0.00008841585,0.000340019,0.0001996672,0.0005709426,0.00008969317,0.000015374473],"category_scores_gemma":[0.000115070936,0.00014573953,0.0004133616,0.00015678868,0.00011655289,0.000044075357,0.00028277698,0.00003262347,6.489064e-7],"study_design_candidate":"meta_analysis","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001979097,0.0003402522,0.104759015,0.00014887434,0.28348234,0.000001878172,0.0022562162,0.6001625,0.0028390302,0.0027611929,0.00085784914,0.0021929147],"study_design_scores_gemma":[0.0033634573,0.0018685057,0.031245654,0.000023080524,0.7075258,0.000008455584,0.043986678,0.19258279,0.01084753,0.0012539403,0.0048993467,0.0023947875],"about_ca_topic_score_codex":0.0000546036,"about_ca_topic_score_gemma":0.00017054382,"teacher_disagreement_score":0.42404342,"about_ca_system_score_codex":0.00000515617,"about_ca_system_score_gemma":0.00008053051,"threshold_uncertainty_score":0.5943085},"labels":[],"label_agreement":null},{"id":"W2736939530","doi":"10.1186/s13040-017-0145-5","title":"Discovery and replication of SNP-SNP interactions for quantitative lipid traits in over 60,000 individuals","year":2017,"lang":"en","type":"article","venue":"BioData Mining","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":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"U.S. National Library of Medicine; National Center for Advancing Translational Sciences; National Human Genome Research Institute; National Heart, Lung, and Blood Institute; National Eye Institute; National Institute on Aging; Medical Research Council; British Heart Foundation; European Hematology Association; National Institute of General Medical Sciences; National Institute for Health and Care Research; Broad Institute; Harvard University; National Institutes of Health; U.S. Department of Health and Human Services","keywords":"Replication (statistics); SNP; Single-nucleotide polymorphism; Computational biology; Biology; Pairwise comparison; Genetics; Bioinformatics; Gene; Computer science; Artificial intelligence; Genotype","score_opus":0.09098401409320957,"score_gpt":0.3887127870929476,"score_spread":0.29772877299973804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2736939530","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9961272,0.0001708653,0.002286015,0.00039538025,0.00008598913,0.00015822338,0.00053225784,0.000002032125,0.00024202345],"genre_scores_gemma":[0.9882939,0.00011789541,0.010803491,0.00006614529,0.00007230226,0.000042357762,0.0003713094,0.000007515524,0.00022511989],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99925154,0.00004160552,0.00023644516,0.00030863174,0.000034637633,0.00012714932],"domain_scores_gemma":[0.9991397,0.00009363434,0.0002969953,0.00040853705,0.00003888293,0.000022196475],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043050948,0.00007577794,0.00014871031,0.000043394957,0.00011323697,0.000032853037,0.0001578385,0.00008599434,0.0000035104515],"category_scores_gemma":[0.0015288382,0.000074285614,0.000034358978,0.000022704631,0.000077186814,0.000021156233,0.000118673335,0.00003602601,4.793459e-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":[0.00008410083,0.00009573015,0.64490837,0.000036598187,0.00011741389,3.0729504e-7,0.00061452744,0.000016021579,0.32982466,0.0008022752,0.006484946,0.017015027],"study_design_scores_gemma":[0.0004681236,0.00015259552,0.98119706,0.000029143574,0.000019140662,0.0000017047225,0.0003960382,0.00022441144,0.0068181157,0.00011156625,0.0104804365,0.00010164785],"about_ca_topic_score_codex":0.00008279683,"about_ca_topic_score_gemma":0.0002666748,"teacher_disagreement_score":0.3362887,"about_ca_system_score_codex":0.0000075365037,"about_ca_system_score_gemma":0.000029467168,"threshold_uncertainty_score":0.30292794},"labels":[],"label_agreement":null},{"id":"W2771169143","doi":"10.1186/s13040-017-0155-3","title":"Ten quick tips for machine learning in computational biology","year":2017,"lang":"en","type":"review","venue":"BioData Mining","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":915,"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":"Natural Sciences and Engineering Research Council of Canada; University of California, Irvine; University of Toronto","keywords":"Computer science; Informatics; Context (archaeology); Data science; Artificial intelligence; Machine learning; Biology; Engineering","score_opus":0.14248121591791127,"score_gpt":0.4167059229229167,"score_spread":0.27422470700500545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2771169143","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":[0.00003616129,0.9951862,0.0022858407,0.000083915496,0.0002779021,0.0006352193,0.0010351996,0.000013239517,0.0004463413],"genre_scores_gemma":[0.000108552114,0.96719426,0.009108716,0.000053454947,0.0004734231,0.00009475398,0.021914186,0.000042189404,0.0010104681],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979508,0.00012212615,0.0006868754,0.00054057146,0.00017227467,0.0005273508],"domain_scores_gemma":[0.9986847,0.00015583665,0.00040413273,0.0005169205,0.000090627946,0.00014775747],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00091793557,0.00033756444,0.00082375243,0.00022841516,0.00018862533,0.00009141845,0.00088883995,0.0006316953,0.000018823303],"category_scores_gemma":[0.0015356421,0.00027608848,0.00025020333,0.00007949196,0.00024468655,0.0000057691127,0.0006040239,0.0003094054,0.000039853843],"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":[0.000016834145,0.000029871551,0.00017705176,0.0025324295,0.00009047185,0.0000024075061,0.00001914958,0.0000018251125,0.000016740732,0.000019203884,0.0023943018,0.9946997],"study_design_scores_gemma":[0.0004362948,0.00031218765,0.000016161177,0.0009650246,0.000053074273,0.000021342297,0.000023331235,0.0006337372,0.000008047216,0.000025598018,0.9971819,0.00032333063],"about_ca_topic_score_codex":0.000026802987,"about_ca_topic_score_gemma":0.00005673579,"teacher_disagreement_score":0.9947876,"about_ca_system_score_codex":0.000033019427,"about_ca_system_score_gemma":0.00054721604,"threshold_uncertainty_score":0.9999691},"labels":[],"label_agreement":null},{"id":"W3040486170","doi":"10.1186/s13040-020-00218-7","title":"An epistatic interaction between pre-natal smoke exposure and socioeconomic status has a significant impact on bronchodilator drug response in African American youth with asthma","year":2020,"lang":"en","type":"article","venue":"BioData Mining","topic":"Health, Environment, Cognitive Aging","field":"Environmental Science","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":"Queen's University","funders":"National Institute of General Medical Sciences; University of California, San Francisco; National Institutes of Health; National Institute of Environmental Health Sciences; San Francisco State University; National Institute on Minority Health and Health Disparities; Tobacco-Related Disease Research Program; National Heart, Lung, and Blood Institute; Gordon and Betty Moore Foundation; American Asthma Foundation; Alfred P. Sloan Foundation; Robert Wood Johnson Foundation","keywords":"Bronchodilator; Socioeconomic status; Asthma; Smoke; Drug; Drug response; Environmental health; African american; Medicine; Demography; Pharmacology; Internal medicine; Geography; Sociology","score_opus":0.036390835657297366,"score_gpt":0.29049632596453406,"score_spread":0.2541054903072367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3040486170","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99767464,0.000009608879,0.00028458255,0.0007560444,0.000016085958,0.0004293921,0.0007279355,0.00004213778,0.000059543192],"genre_scores_gemma":[0.9978936,0.000010352395,0.0013933207,0.00041536154,0.000042634274,0.000021930447,0.00017672607,0.00004177235,0.0000043410523],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9973215,0.0005786532,0.0003630316,0.00092950964,0.0002461546,0.00056117267],"domain_scores_gemma":[0.9983772,0.0004312582,0.00028250818,0.0003710945,0.0000030543333,0.00053489284],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00078607636,0.0002895143,0.00033717797,0.00009110519,0.0001642275,0.00012982798,0.00021957538,0.000042352716,0.00020409291],"category_scores_gemma":[0.00012894909,0.00025816346,0.000030426787,0.00019328103,0.0004859431,0.0006823701,0.00013988907,0.00033685425,0.00006778034],"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":[0.0020547449,0.00006439527,0.92642903,0.000010750739,0.00002353243,0.00003023976,0.039652992,0.00042414904,0.0021496457,2.7155912e-7,0.000035161545,0.029125076],"study_design_scores_gemma":[0.0007489773,0.002134806,0.967228,0.00004124727,0.000018756105,0.0000025831357,0.027199186,0.001575907,0.00047009636,0.000001537812,0.00025776413,0.0003211225],"about_ca_topic_score_codex":0.0040492937,"about_ca_topic_score_gemma":0.00023721867,"teacher_disagreement_score":0.040798973,"about_ca_system_score_codex":0.00072684087,"about_ca_system_score_gemma":0.00008398498,"threshold_uncertainty_score":0.99998707},"labels":[],"label_agreement":null},{"id":"W3101574558","doi":"10.1186/s13040-016-0108-2","title":"ProtNN: fast and accurate protein 3D-structure classification in structural and topological space","year":2016,"lang":"en","type":"article","venue":"BioData Mining","topic":"Machine Learning in Bioinformatics","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","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Space (punctuation); Topology (electrical circuits); Topological space; Data mining; Pattern recognition (psychology); Artificial intelligence; Mathematics; Pure mathematics; Combinatorics","score_opus":0.016169668764608368,"score_gpt":0.2731470377325991,"score_spread":0.2569773689679907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3101574558","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.997902,0.00010719903,0.00076090643,0.0006712601,0.00003083632,0.00025656118,0.000054331853,0.000011329722,0.00020562245],"genre_scores_gemma":[0.9849529,0.000030133197,0.014622772,0.000054070868,0.00006699149,0.000013360796,0.00007895111,0.00000791714,0.0001728997],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.999288,0.000048034064,0.00016719925,0.0002581444,0.00006680194,0.00017181435],"domain_scores_gemma":[0.9996044,0.000013318274,0.00009546259,0.0002171801,0.000019487932,0.000050145773],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011721412,0.00012454008,0.00010000819,0.000034779292,0.000057046847,0.00004156224,0.00011247415,0.00014862671,0.000019370731],"category_scores_gemma":[0.0002719962,0.000080265396,0.000009272518,0.00004583746,0.00013443305,0.000016310072,0.0001857671,0.00007860058,0.0000014081947],"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":[0.00008421532,0.000005244339,0.10438586,0.00005200848,0.000011518793,0.0000023053994,0.00021659363,0.0000015864144,0.841424,0.0008054814,0.00011131247,0.05289991],"study_design_scores_gemma":[0.00375592,0.0010150385,0.8217405,0.00033109172,0.000027134161,0.00028225893,0.0013114985,0.0098505085,0.13228053,0.00044660983,0.027705051,0.0012538685],"about_ca_topic_score_codex":0.000008002297,"about_ca_topic_score_gemma":0.000032652013,"teacher_disagreement_score":0.71735466,"about_ca_system_score_codex":0.000008499168,"about_ca_system_score_gemma":0.000020204054,"threshold_uncertainty_score":0.3273128},"labels":[],"label_agreement":null},{"id":"W3126232929","doi":"10.1186/s13040-021-00244-z","title":"The Matthews correlation coefficient (MCC) is more reliable than balanced accuracy, bookmaker informedness, and markedness in two-class confusion matrix evaluation","year":2021,"lang":"en","type":"article","venue":"BioData Mining","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":893,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Krembil Foundation","funders":"Deutsche Forschungsgemeinschaft","keywords":"Confusion matrix; Correlation; False positive paradox; Computer science; Confusion; False positives and false negatives; Classifier (UML); Statistics; Artificial intelligence; Metric (unit); Correlation coefficient; Machine learning; Data mining; Mathematics; Psychology; Operations management","score_opus":0.029274177312831263,"score_gpt":0.33077275706615017,"score_spread":0.3014985797533189,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3126232929","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.51271933,0.002180492,0.45863113,0.015171728,0.0027170554,0.0030339055,0.00031826587,0.0008298899,0.0043982207],"genre_scores_gemma":[0.94204485,0.0007553545,0.053163197,0.0013559419,0.00007308814,0.00028088348,0.00098885,0.000034501772,0.0013033159],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977421,0.00014925408,0.0005368413,0.0005956199,0.00062704476,0.00034913066],"domain_scores_gemma":[0.9976253,0.00036339695,0.0003491719,0.0012760708,0.00031780123,0.00006828783],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017624275,0.00019703536,0.00020025224,0.00012602513,0.0003517381,0.00058337074,0.00073990796,0.000095512616,0.000032477732],"category_scores_gemma":[0.0006715515,0.00014895406,0.000029995717,0.00069287274,0.00010559551,0.0012346709,0.000704595,0.00018300196,0.000028347724],"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":[0.00028766316,0.00036271213,0.10411163,0.0002320732,0.00007303976,0.000055861878,0.01516407,0.00079749955,0.024644421,0.035760794,0.09862348,0.7198868],"study_design_scores_gemma":[0.001067561,0.000031574982,0.050699215,0.00022630463,0.000016119164,0.000038756523,0.0012500271,0.88833654,0.007416944,0.00038092022,0.05020287,0.00033317623],"about_ca_topic_score_codex":0.000071341456,"about_ca_topic_score_gemma":0.00011562997,"teacher_disagreement_score":0.887539,"about_ca_system_score_codex":0.00016230629,"about_ca_system_score_gemma":0.00034145432,"threshold_uncertainty_score":0.607417},"labels":[],"label_agreement":null},{"id":"W3128825412","doi":"10.1186/s13040-021-00235-0","title":"Data analytics and clinical feature ranking of medical records of patients with sepsis","year":2021,"lang":"en","type":"article","venue":"BioData Mining","topic":"Sepsis Diagnosis and Treatment","field":"Medicine","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":"Krembil Foundation","funders":"University of Toronto","keywords":"Sepsis; Medical record; Septic shock; Medicine; Context (archaeology); Ranking (information retrieval); Electronic medical record; Machine learning; Binary classification; Computer science; Logistic regression; SOFA score; Artificial intelligence; Intensive care medicine; Data mining; Emergency medicine; Internal medicine; Support vector machine","score_opus":0.21828630754067863,"score_gpt":0.41707643113932913,"score_spread":0.1987901235986505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3128825412","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99678344,0.00094485225,0.00004079502,0.0013306384,0.00009577035,0.00009496078,0.00056321686,0.000006908987,0.00013940058],"genre_scores_gemma":[0.98053676,0.0010368775,0.015528469,0.00031230642,0.000078046614,0.0000015195255,0.0024599156,0.000013627043,0.00003245137],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.998611,0.00004841631,0.00035849022,0.00034299382,0.0005242733,0.000114823306],"domain_scores_gemma":[0.9984432,0.00035295088,0.00016535609,0.00076961855,0.00013861596,0.00013024331],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042067334,0.00009859974,0.00043856335,0.00004677206,0.000022136732,0.000009260788,0.00016041606,0.00012661166,0.00016361632],"category_scores_gemma":[0.0009935577,0.00006868263,0.00004090194,0.00019372422,0.00010767622,0.00006861632,0.00032559404,0.00011768851,7.4870974e-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":[0.000094881514,0.0006131957,0.95650566,0.00007678131,0.00042913712,0.000048616497,0.000047877635,3.7930178e-8,0.0000027528483,0.000009242114,0.00601961,0.036152188],"study_design_scores_gemma":[0.0035948674,0.00047588823,0.98712975,0.00080448744,0.0007790867,0.000010247473,0.00029963246,0.0003507899,0.00019799006,0.000001297284,0.0062795863,0.000076366],"about_ca_topic_score_codex":0.000027096117,"about_ca_topic_score_gemma":0.00009029516,"teacher_disagreement_score":0.03607582,"about_ca_system_score_codex":0.0000101645055,"about_ca_system_score_gemma":0.00018627028,"threshold_uncertainty_score":0.28007963},"labels":[],"label_agreement":null},{"id":"W3136786679","doi":"10.1186/s13040-021-00251-0","title":"Indels in SARS-CoV-2 occur at template-switching hotspots","year":2021,"lang":"en","type":"article","venue":"BioData Mining","topic":"SARS-CoV-2 and COVID-19 Research","field":"Medicine","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":"McMaster University","funders":"National Science Foundation of Sri Lanka; Stanford Bio-X; National Science Foundation","keywords":"Indel; Genetics; Biology; RNA; Computational biology; Homologous recombination; RNA polymerase; Recombination; Evolutionary biology; Gene; Single-nucleotide polymorphism; Genotype","score_opus":0.12193423570309297,"score_gpt":0.3875826429091648,"score_spread":0.2656484072060718,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3136786679","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99341565,0.00096898666,0.00009761504,0.00046270114,0.00020785193,0.00021062161,0.000036575562,0.00008058277,0.004519425],"genre_scores_gemma":[0.9728529,0.00001224397,0.0012741954,0.025455244,0.00019468226,0.000023099707,0.000052349762,0.000042731357,0.00009254414],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.997633,0.000088544395,0.00043688362,0.0006724215,0.00053104624,0.00063815276],"domain_scores_gemma":[0.99876755,0.00021474181,0.000080561615,0.0007849624,0.00010111386,0.000051087467],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058814714,0.00023366664,0.00042813655,0.000335921,0.00012990569,0.00008756403,0.00027981814,0.0002032894,0.000037339356],"category_scores_gemma":[0.00066071167,0.0002251014,0.00009417207,0.00080380717,0.0000542124,0.000254126,0.0005544227,0.0004251776,0.00032586444],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001995583,0.00011043586,0.27494162,0.00011343983,0.000047643403,0.0021572656,0.00089887716,1.5423225e-7,0.7078355,0.000022909262,0.0030578985,0.01061468],"study_design_scores_gemma":[0.0028629596,0.00012128136,0.04115409,0.00056082197,0.00004013232,0.00040420462,0.00095858186,0.00073034206,0.785057,0.0000347399,0.16768928,0.00038658566],"about_ca_topic_score_codex":0.00033961036,"about_ca_topic_score_gemma":0.000555017,"teacher_disagreement_score":0.23378754,"about_ca_system_score_codex":0.00023961294,"about_ca_system_score_gemma":0.00048195716,"threshold_uncertainty_score":0.91793686},"labels":[],"label_agreement":null},{"id":"W3141242658","doi":"10.1186/s13040-021-00249-8","title":"Prescreening and treatment of aortic dissection through an analysis of infinite-dimension data","year":2021,"lang":"en","type":"article","venue":"BioData Mining","topic":"Aortic Disease and Treatment Approaches","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 Prince Edward Island; University of Waterloo","funders":"Shanghai Jiao Tong University; Shanghai Municipal Health Bureau; National Natural Science Foundation of China; School of Medicine, Shanghai Jiao Tong University; Comanche Nation","keywords":"Aortic dissection; Medicine; Cardiology; Blood pressure; Internal medicine; Mortality rate; Disease; Incidence (geometry); Medical diagnosis; Psychological intervention; Dissection (medical); Intensive care medicine; Emergency medicine; Surgery; Radiology; Aorta","score_opus":0.15880538879975056,"score_gpt":0.3612328588707938,"score_spread":0.20242747007104325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3141242658","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9978841,0.0011506412,0.00031208512,0.00004182628,0.000014394903,0.00010243098,0.00023234276,0.000015484346,0.00024670485],"genre_scores_gemma":[0.98365474,0.00028979432,0.010372838,0.000010236946,0.000021185384,0.0000042325587,0.0055925245,0.000007970896,0.000046492005],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99912447,0.00003295682,0.00026218046,0.00033831078,0.00014189193,0.00010020386],"domain_scores_gemma":[0.9988964,0.00006690596,0.00011760384,0.00080520345,0.000045044282,0.00006882924],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005965737,0.000103779974,0.00036780981,0.00009641574,0.00003635504,0.000009590522,0.000048426562,0.00003978886,0.000052950825],"category_scores_gemma":[0.00006328208,0.000082021106,0.00005391537,0.00038922552,0.000052980213,0.00028513616,0.00008869472,0.000016809108,4.2180045e-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":[0.00027002647,0.0012329145,0.93220395,0.00006961172,0.0036186967,0.00006822185,0.0018754808,0.00001202601,0.008309008,0.00007726751,0.000016330256,0.052246474],"study_design_scores_gemma":[0.0024612404,0.0013057649,0.88437635,0.00018700091,0.024152642,0.00002438146,0.007248265,0.047797505,0.031921815,0.000010188604,0.00032184512,0.00019300096],"about_ca_topic_score_codex":0.00024288846,"about_ca_topic_score_gemma":0.00007747343,"teacher_disagreement_score":0.052053474,"about_ca_system_score_codex":0.000014838772,"about_ca_system_score_gemma":0.000057008736,"threshold_uncertainty_score":0.33447236},"labels":[],"label_agreement":null},{"id":"W3215710945","doi":"10.1186/s13040-021-00281-8","title":"Development of glaucoma predictive model and risk factors assessment based on supervised models","year":2021,"lang":"en","type":"article","venue":"BioData Mining","topic":"Retinal Imaging and Analysis","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":"University of Toronto","funders":"","keywords":"Computer science; Glaucoma; Machine learning; Artificial intelligence; Data science; Risk analysis (engineering); Medicine; Ophthalmology","score_opus":0.055093053541754644,"score_gpt":0.3059507429795755,"score_spread":0.25085768943782083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3215710945","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.943854,0.00007228615,0.054800212,0.00009467551,0.000016134736,0.00006182921,0.00009760877,0.000023147304,0.0009801554],"genre_scores_gemma":[0.8287465,0.000034582576,0.17078996,0.00005406063,0.000010212056,0.000004406925,0.00027789708,0.000010408171,0.000071988805],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989323,0.000041029027,0.00027964037,0.00030864883,0.00029297874,0.00014540472],"domain_scores_gemma":[0.9993305,0.000077026176,0.000094255745,0.00029108673,0.00010148248,0.00010563452],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022416428,0.00013076873,0.0002851545,0.00010583807,0.00008384713,0.000020259273,0.000057092308,0.000042165164,0.000020047486],"category_scores_gemma":[0.00007944686,0.00010667675,0.000055784996,0.00015314134,0.000037624544,0.00008061558,0.00006185797,0.00010939464,6.245388e-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":[0.00016912122,0.00048031184,0.956747,0.00018521861,0.0005263974,0.000045246914,0.0033765335,0.0038478638,0.01712128,0.000046756384,0.00023087834,0.017223403],"study_design_scores_gemma":[0.0006819917,0.000063849344,0.069005415,0.00022076328,0.00024399784,0.0000018697508,0.0016425302,0.9195775,0.008401199,0.00001028882,0.00005201012,0.00009859442],"about_ca_topic_score_codex":0.000025348889,"about_ca_topic_score_gemma":0.0000042032984,"teacher_disagreement_score":0.91572964,"about_ca_system_score_codex":0.000046139663,"about_ca_system_score_gemma":0.00032883527,"threshold_uncertainty_score":0.43501517},"labels":[],"label_agreement":null},{"id":"W4234031396","doi":"10.1186/preaccept-8590947901180703","title":"Integrative genomics and transcriptomics analysis of human embryonic and induced pluripotent stem cells","year":2014,"lang":"en","type":"article","venue":"BioData Mining","topic":"Genomic variations and chromosomal abnormalities","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":"Lunenfeld-Tanenbaum Research Institute","funders":"Emil Aaltosen Säätiö; European Commission","keywords":"Biology; Induced pluripotent stem cell; Genetics; Single-nucleotide polymorphism; Gene; SNP array; Copy-number variation; Genomics; DNA microarray; Transcriptome; Embryonic stem cell; Human genome; Functional genomics; Phenotype; Exon; Genome; Computational biology; Gene expression; Genotype","score_opus":0.017187619078278094,"score_gpt":0.23010869046941393,"score_spread":0.21292107139113584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4234031396","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.998571,0.00027063894,0.0007667626,0.000024903242,0.00003704521,0.00006011386,0.00014046507,0.0000036305685,0.00012544614],"genre_scores_gemma":[0.998676,0.0001135899,0.00082880305,0.000041551277,0.00003308839,0.0000037384846,0.00016272264,0.0000082846955,0.00013220061],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99935836,0.000043077136,0.00019134412,0.0002431014,0.000044059347,0.00012007445],"domain_scores_gemma":[0.9995872,0.000011678463,0.00009822621,0.00021696615,0.00003651879,0.000049424598],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014267188,0.00011342824,0.00020404485,0.00008537683,0.00007682276,0.000028264058,0.00010123063,0.0000836539,0.0000046055634],"category_scores_gemma":[0.000005928216,0.00010329277,0.00005050739,0.00008499524,0.00006208806,0.0000055496866,0.000085941356,0.000039645547,2.7529248e-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":[0.00001295563,0.000014871164,0.0046887184,0.000016579928,0.0003540641,1.9101655e-7,0.00096148695,0.000012950385,0.99158657,0.00041283458,0.00002751039,0.0019112548],"study_design_scores_gemma":[0.00079060794,0.0005902258,0.015885336,0.000023550974,0.00088069553,0.000006160422,0.008538934,0.002159905,0.9667554,0.000029107803,0.0039595393,0.00038052967],"about_ca_topic_score_codex":0.000055471588,"about_ca_topic_score_gemma":0.00014007324,"teacher_disagreement_score":0.024831176,"about_ca_system_score_codex":0.000008707048,"about_ca_system_score_gemma":0.000022981238,"threshold_uncertainty_score":0.42121568},"labels":[],"label_agreement":null},{"id":"W4307995431","doi":"10.1186/s13040-022-00312-y","title":"Towards a potential pan-cancer prognostic signature for gene expression based on probesets and ensemble machine learning","year":2022,"lang":"en","type":"article","venue":"BioData Mining","topic":"Bioinformatics and Genomic Networks","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":"Krembil Foundation; University of Toronto","funders":"","keywords":"Signature (topology); Gene signature; Cancer; Gene; Computational biology; Random forest; Relevance (law); Microarray analysis techniques; Biology; Microarray; Bioinformatics; Computer science; Gene expression; Machine learning; Genetics; Mathematics","score_opus":0.012604550967461287,"score_gpt":0.24221652434108,"score_spread":0.2296119733736187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307995431","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.920066,0.007589141,0.06793922,0.00060334546,0.0005937294,0.0013170149,0.0015206404,0.000045530494,0.00032540492],"genre_scores_gemma":[0.9849222,0.00006871464,0.011499012,0.0003414821,0.00019506544,0.00021749573,0.0024371939,0.000025207255,0.00029364572],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991194,0.000043350024,0.00015858312,0.0003158731,0.00012775502,0.00023503376],"domain_scores_gemma":[0.9995983,0.000016917445,0.00010496934,0.00019704015,0.000026366517,0.000056393477],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024614524,0.00014439085,0.00011841725,0.000039392005,0.000330226,0.000042295593,0.00014894524,0.00009261132,0.000038505434],"category_scores_gemma":[0.000039822462,0.00013163796,0.000048498976,0.000052379666,0.000025287105,0.0000046922155,0.00028595902,0.00016089661,6.3051186e-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":[0.00072880404,0.00010697795,0.0011844737,0.000110312394,0.000053860607,0.0000069543185,0.00017552658,0.010006645,0.8711521,0.00001206475,0.008621194,0.10784111],"study_design_scores_gemma":[0.005490372,0.003908546,0.00101478,0.00018551864,0.00015922764,0.00007171091,0.000626083,0.4449203,0.3490658,0.000089116256,0.19321436,0.0012541784],"about_ca_topic_score_codex":0.0000070294677,"about_ca_topic_score_gemma":0.000004112618,"teacher_disagreement_score":0.52208626,"about_ca_system_score_codex":0.000013011496,"about_ca_system_score_gemma":0.000073555835,"threshold_uncertainty_score":0.5368041},"labels":[],"label_agreement":null},{"id":"W4321214126","doi":"10.1186/s13040-023-00322-4","title":"The Matthews correlation coefficient (MCC) should replace the ROC AUC as the standard metric for assessing binary classification","year":2023,"lang":"en","type":"article","venue":"BioData Mining","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":513,"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":"Receiver operating characteristic; Matthews correlation coefficient; Binary classification; Statistics; Confusion matrix; False positive rate; Artificial intelligence; Correlation; Mathematics; Binary number; Sensitivity (control systems); Metric (unit); Classifier (UML); Computer science; Pattern recognition (psychology); Machine learning; Support vector machine; Arithmetic","score_opus":0.10998735913183141,"score_gpt":0.36279671487678333,"score_spread":0.2528093557449519,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321214126","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":[0.0039828117,0.00022323284,0.9644635,0.027894419,0.0008631662,0.0010407153,0.00010581817,0.00080318394,0.0006231703],"genre_scores_gemma":[0.9387665,0.00034134425,0.054829586,0.0015479717,0.00028157138,0.0009967815,0.0007729403,0.00006939482,0.0023939372],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975507,0.0002870343,0.00049098453,0.00060057244,0.0006539651,0.00041670157],"domain_scores_gemma":[0.9942104,0.0027754407,0.00047846045,0.0022677372,0.0002188182,0.00004914254],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.004527626,0.00018973264,0.00015001085,0.00020212469,0.0020259724,0.0014435645,0.0025468036,0.00010238495,0.0000044579733],"category_scores_gemma":[0.0017641303,0.000101471494,0.00007332858,0.0023705594,0.00018220485,0.0008307789,0.0005902674,0.00023587517,0.00008865461],"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":[0.00009181811,0.000065025815,0.0016170777,0.000038780618,0.00006402737,0.0000042681704,0.002719463,0.00059087115,0.009261704,0.15718496,0.44647434,0.38188767],"study_design_scores_gemma":[0.00024582812,0.00010288902,0.013934743,0.00005681081,0.00002881783,0.000014721703,0.0023239823,0.60296786,0.003380282,0.0010246678,0.37566796,0.00025146888],"about_ca_topic_score_codex":0.000011519151,"about_ca_topic_score_gemma":0.0000058206306,"teacher_disagreement_score":0.93478364,"about_ca_system_score_codex":0.00016728048,"about_ca_system_score_gemma":0.00022916222,"threshold_uncertainty_score":0.999593},"labels":[],"label_agreement":null},{"id":"W4321598956","doi":"10.1186/s13040-023-00326-0","title":"Ten simple rules for providing bioinformatics support within a hospital","year":2023,"lang":"en","type":"article","venue":"BioData Mining","topic":"Genetics, Bioinformatics, and Biomedical Research","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":"Simple (philosophy); Computer science; Data science; Data mining; Bioinformatics; Biology","score_opus":0.037680212675283105,"score_gpt":0.3102693955737785,"score_spread":0.2725891828984954,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321598956","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98552394,0.000100009005,0.008086264,0.00094744464,0.0007729179,0.0011567174,0.0017537649,0.00015271302,0.0015062047],"genre_scores_gemma":[0.8393696,0.0006625907,0.12382508,0.0010367014,0.0015635575,0.00031830417,0.02858669,0.00013042825,0.0045070667],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982327,0.000016750813,0.0004982576,0.00029691053,0.0003303783,0.0006249817],"domain_scores_gemma":[0.9989906,0.00005151645,0.00014899076,0.00046333743,0.00012835367,0.0002172144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008073096,0.00019902171,0.00019084371,0.00014919249,0.00020103605,0.00012786151,0.00050285546,0.00020459638,0.000019156714],"category_scores_gemma":[0.0010976584,0.00017065728,0.00010593904,0.00020456745,0.00016373393,0.000019535955,0.00049963896,0.00008416125,0.00015604505],"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":[0.00025092068,0.000210528,0.010501208,0.0013180646,0.00037460562,0.00002014887,0.0041931383,0.000027443084,0.089948535,0.00022480398,0.72947943,0.16345115],"study_design_scores_gemma":[0.0028933764,0.004059665,0.0028636416,0.00011747866,0.00008092825,0.00002840915,0.013724507,0.0395967,0.14919148,0.00031310474,0.78575826,0.0013724683],"about_ca_topic_score_codex":0.000007629602,"about_ca_topic_score_gemma":0.0000112899115,"teacher_disagreement_score":0.16207868,"about_ca_system_score_codex":0.000016007565,"about_ca_system_score_gemma":0.00024049381,"threshold_uncertainty_score":0.69592017},"labels":[],"label_agreement":null},{"id":"W4323050290","doi":"10.1186/s13040-023-00325-1","title":"Signature literature review reveals AHCY, DPYSL3, and NME1 as the most recurrent prognostic genes for neuroblastoma","year":2023,"lang":"en","type":"article","venue":"BioData Mining","topic":"Neuroblastoma Research and Treatments","field":"Medicine","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":"","keywords":"Neuroblastoma; Gene; Bioinformatics; Oncology; Biology; Computational biology; Medicine; Internal medicine; Genetics","score_opus":0.04151356111928294,"score_gpt":0.3423840202260795,"score_spread":0.30087045910679655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323050290","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70836586,0.25688183,0.000010845639,0.026036328,0.000502131,0.0062678736,0.0011769106,0.00037576343,0.00038245032],"genre_scores_gemma":[0.5168814,0.43197948,0.004380993,0.019670261,0.0019958736,0.0029854614,0.007927476,0.0004002336,0.013778799],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99836195,0.000099913756,0.00025182497,0.00050190627,0.00033205867,0.00045236413],"domain_scores_gemma":[0.9985467,0.0005147771,0.00008711711,0.0005012208,0.0001318591,0.00021828014],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003429684,0.00023348072,0.0003156793,0.000119981996,0.00021703861,0.000103062135,0.00019295776,0.00008195115,0.00001981944],"category_scores_gemma":[0.0014665398,0.00014119272,0.00008128423,0.0007749032,0.000076669734,0.00012162476,0.00020915366,0.00025857097,0.000069656424],"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":[0.0009829717,0.0003263713,0.0061929394,0.012225183,0.00043643895,0.002645029,0.0006539954,3.9245722e-7,0.02304524,0.0001513466,0.49584508,0.457495],"study_design_scores_gemma":[0.0057875486,0.009276769,0.05279427,0.057241272,0.0014007384,0.0033787873,0.0003752952,0.00088514044,0.00697872,0.00028896367,0.86054015,0.0010523612],"about_ca_topic_score_codex":0.0000014200962,"about_ca_topic_score_gemma":0.0000030487772,"teacher_disagreement_score":0.45644265,"about_ca_system_score_codex":0.000017504366,"about_ca_system_score_gemma":0.00008464901,"threshold_uncertainty_score":0.5757672},"labels":[],"label_agreement":null},{"id":"W4387402455","doi":"10.1186/s13040-023-00343-z","title":"Quantum analysis of squiggle data","year":2023,"lang":"en","type":"article","venue":"BioData Mining","topic":"Quantum Computing Algorithms and Architecture","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":"University of Lethbridge","funders":"Alberta Innovates; Ministero dello Sviluppo Economico; Government of Alberta; Genome Canada","keywords":"Nanopore sequencing; Computer science; Curse of dimensionality; Algorithm; Quantum; IBM; Quantum computer; Current (fluid); Computer engineering; DNA sequencing; Theoretical computer science; Artificial intelligence; DNA; Electrical engineering; Physics","score_opus":0.07099168818858985,"score_gpt":0.30829258730085923,"score_spread":0.23730089911226937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387402455","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6940934,0.0002204629,0.302715,0.00096800737,0.0006345537,0.000078130324,0.00044386977,0.0005924657,0.00025407498],"genre_scores_gemma":[0.9139639,0.000019286803,0.08502722,0.00009755926,0.00009317348,0.0000015484865,0.0007131909,0.000010115543,0.00007398795],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998628,0.00004641853,0.00025302914,0.0005426208,0.0002624542,0.00026745666],"domain_scores_gemma":[0.9974073,0.0002142316,0.00011806945,0.0021683562,0.000030797197,0.00006120925],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064037245,0.00010351875,0.0002444406,0.00054261286,0.000098413315,0.00008943352,0.0027237367,0.00003654877,0.000010651644],"category_scores_gemma":[0.00012395754,0.0000909655,0.00006427458,0.004041322,0.000039714316,0.0002642546,0.0024810238,0.00007228331,0.000035741934],"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":[0.0000141282335,0.0002160708,0.020655198,0.0001196199,0.0026735724,0.00030415168,0.007163027,0.02546749,0.005324243,0.02318767,0.07048795,0.8443869],"study_design_scores_gemma":[0.0000707908,0.000024800594,0.011129582,0.000015686279,0.000068576905,0.0000026687148,0.00006127136,0.9829391,0.000120581804,0.00009683856,0.005357162,0.00011292122],"about_ca_topic_score_codex":0.000056576846,"about_ca_topic_score_gemma":0.000010140739,"teacher_disagreement_score":0.9574716,"about_ca_system_score_codex":0.0000048914917,"about_ca_system_score_gemma":0.000043757194,"threshold_uncertainty_score":0.5061426},"labels":[],"label_agreement":null},{"id":"W4387813874","doi":"10.1186/s13040-023-00344-y","title":"Prescription pattern analysis of Type 2 Diabetes Mellitus: a cross-sectional study in Isfahan, Iran","year":2023,"lang":"en","type":"article","venue":"BioData Mining","topic":"Machine Learning in Healthcare","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); University of Toronto","funders":"","keywords":"Medical prescription; Medicine; Diabetes mellitus; Polypharmacy; Type 2 Diabetes Mellitus; Cross-sectional study; Type 2 diabetes; Internal medicine; Pharmacology; Endocrinology","score_opus":0.08700440662326508,"score_gpt":0.3629943011081319,"score_spread":0.2759898944848668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387813874","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99694175,0.00013243422,0.0020727622,0.000071202056,0.00042421592,0.00016210462,0.00003021253,0.00013566582,0.000029682877],"genre_scores_gemma":[0.9989523,0.000011383063,0.0007592026,0.00004241146,0.00004413608,0.000016626816,0.0001166376,0.000007685678,0.00004957637],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99815655,0.00022617576,0.0004600256,0.0004982633,0.000383531,0.0002754561],"domain_scores_gemma":[0.998839,0.00021429297,0.00014246529,0.0006643168,0.00008837839,0.000051509913],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012661928,0.000108877466,0.00024570717,0.0008716397,0.0000807414,0.00011302154,0.00071837084,0.00006107183,0.00003804608],"category_scores_gemma":[0.0002820478,0.00010985436,0.00005498872,0.0037097407,0.000026956732,0.00034895918,0.00041405,0.0001645773,0.00003645115],"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":[0.0000036060496,0.000039177972,0.9853138,0.000028483691,0.00008339314,0.000006077672,0.0022350322,0.0016220853,0.00008293132,0.00002082291,0.000046824123,0.010517787],"study_design_scores_gemma":[0.00012465862,0.00009752198,0.7443079,0.000013880953,0.000016624572,1.6748537e-7,0.00013488637,0.25514227,0.000017678196,0.000009021073,0.000060881943,0.00007451253],"about_ca_topic_score_codex":0.0010329323,"about_ca_topic_score_gemma":0.0006411014,"teacher_disagreement_score":0.2535202,"about_ca_system_score_codex":0.000040414292,"about_ca_system_score_gemma":0.00003965739,"threshold_uncertainty_score":0.44797307},"labels":[],"label_agreement":null},{"id":"W4390605262","doi":"10.1186/s13040-023-00352-y","title":"Machine learning approaches to identify systemic lupus erythematosus in anti-nuclear antibody-positive patients using genomic data and electronic health records","year":2024,"lang":"en","type":"article","venue":"BioData Mining","topic":"Systemic Lupus Erythematosus Research","field":"Medicine","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 British Columbia","funders":"Academia Sinica; Taichung Veterans General Hospital; National Science and Technology Council","keywords":"Logistic regression; Single-nucleotide polymorphism; Medicine; Random forest; Titer; Gradient boosting; Artificial intelligence; Medical record; Machine learning; Systemic lupus erythematosus; Internal medicine; Cohort; Support vector machine; Oncology; Immunology; Antibody; Computer science; Disease; Biology; Genetics; Genotype","score_opus":0.11259950949713039,"score_gpt":0.36030285822970487,"score_spread":0.2477033487325745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390605262","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9819611,0.01484204,0.0005322692,0.00027183385,0.00042441426,0.0013468696,0.00031845146,0.00015312273,0.00014994896],"genre_scores_gemma":[0.9951003,0.0010420872,0.0018597873,0.000072137285,0.00016265469,0.0000130523,0.0014281669,0.00014017476,0.00018159547],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959561,0.00036271368,0.00081817585,0.0013088201,0.00053941034,0.001014754],"domain_scores_gemma":[0.998225,0.00021472063,0.00016940452,0.0010220197,0.00004895051,0.00031994627],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0022582875,0.0003620259,0.0008233445,0.00084978365,0.00021452786,0.00028513154,0.00053430576,0.00014751358,0.000020947553],"category_scores_gemma":[0.00032830244,0.0003353977,0.00005450282,0.00084425765,0.000076415345,0.00045040017,0.0012904576,0.0006598197,0.000076988836],"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":[0.00022219465,0.00012593532,0.9690961,0.0045614513,0.00026369706,0.00022679765,0.0077206693,0.000022171394,0.008346267,0.00015938371,0.00044352948,0.008811775],"study_design_scores_gemma":[0.011449896,0.0030645407,0.05727405,0.062195525,0.00059812225,0.11542723,0.034625996,0.69649804,0.00028005638,0.000040526324,0.015826756,0.0027192438],"about_ca_topic_score_codex":0.00076651014,"about_ca_topic_score_gemma":0.00007932384,"teacher_disagreement_score":0.9118221,"about_ca_system_score_codex":0.0008521454,"about_ca_system_score_gemma":0.0005314467,"threshold_uncertainty_score":0.9999098},"labels":[],"label_agreement":null},{"id":"W4391353343","doi":"10.1186/s13040-024-00355-3","title":"Revealing third-order interactions through the integration of machine learning and entropy methods in genomic studies","year":2024,"lang":"en","type":"article","venue":"BioData Mining","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"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; Canadian Institutes of Health Research; Genentech; IXICO; H. Lundbeck A/S; Servier; National Institutes of Health; Türkiye Bilimsel ve Teknolojik Araştırma Kurumu; Eisai; Pfizer; Novartis Pharmaceuticals Corporation; U.S. Department of Defense; Meso Scale Diagnostics; Northern California Institute for Research and Education; F. Hoffmann-La Roche; University of Southern California; BioClinica; Bristol-Myers Squibb; Eli Lilly and Company; Biogen","keywords":"Genome-wide association study; Computer science; Epistasis; Single-nucleotide polymorphism; Genetic association; SNP; Computational biology; Artificial intelligence; Data mining; Machine learning; Biology; Genetics; Genotype; Gene","score_opus":0.07409299352930675,"score_gpt":0.42225888025484476,"score_spread":0.348165886725538,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391353343","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9009496,0.04242424,0.05414287,0.0015885957,0.00036757535,0.00013243375,0.000027872678,0.000013113232,0.00035370147],"genre_scores_gemma":[0.86305386,0.0052979128,0.13078435,0.000104348546,0.0001098732,0.000017558785,0.0001298941,0.000010981176,0.0004912069],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991493,0.00025788686,0.00024902017,0.0002050298,0.000029177298,0.00010953981],"domain_scores_gemma":[0.9995219,0.00023565075,0.00007670773,0.00011716312,0.000038340535,0.000010231046],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072135596,0.000080152065,0.00013656972,0.0000389613,0.000075069824,0.000016562597,0.00007056826,0.000054046963,0.000006285318],"category_scores_gemma":[0.00091585226,0.000056278506,0.000029687439,0.000110238594,0.00006314071,0.0000062403788,0.00013684205,0.00012273414,0.0000010762899],"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":[0.000022834265,0.000018048791,0.022808436,0.000056690977,0.00026740655,0.0000014142908,0.004679339,0.0003074691,0.91879576,0.00068182324,0.0016394277,0.050721318],"study_design_scores_gemma":[0.0012643185,0.0008207104,0.04622378,0.0008396295,0.00042832893,0.00013045814,0.064488396,0.08568937,0.08552946,0.0024964788,0.7110993,0.0009897436],"about_ca_topic_score_codex":0.00010339185,"about_ca_topic_score_gemma":0.00016558717,"teacher_disagreement_score":0.8332663,"about_ca_system_score_codex":0.000015262403,"about_ca_system_score_gemma":0.000024310684,"threshold_uncertainty_score":0.22949709},"labels":[],"label_agreement":null},{"id":"W4402164248","doi":"10.1186/s13040-024-00380-2","title":"Seven quick tips for gene-focused computational pangenomic analysis","year":2024,"lang":"en","type":"article","venue":"BioData Mining","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":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Università degli Studi di Parma; Università degli Studi di Trento","keywords":"Computer science; Data science; Computational biology; Data mining; Biology","score_opus":0.021258712347645495,"score_gpt":0.29616306982242957,"score_spread":0.2749043574747841,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402164248","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.58705235,0.003467466,0.40783876,0.00019863312,0.00006102086,0.00026130458,0.0004227065,0.000109619075,0.0005881376],"genre_scores_gemma":[0.9196725,0.00006917906,0.07221414,0.00018530812,0.00027384778,0.00004604709,0.0064319596,0.000028953022,0.0010780501],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990202,0.000026607031,0.00021095718,0.00047100545,0.00009223869,0.00017895199],"domain_scores_gemma":[0.99945235,0.0000362556,0.000047358157,0.00035766725,0.000057863628,0.000048484013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002518511,0.00012868845,0.00016337431,0.00018677254,0.00006427177,0.00010630801,0.00021720983,0.00009109627,0.000046381905],"category_scores_gemma":[0.00004206524,0.00012887584,0.00023159027,0.00030560076,0.00003679538,0.0000075349335,0.000118508455,0.000038036473,0.000021011125],"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":[0.000072454175,0.00006893632,0.0036406016,0.00008349125,0.0043296167,0.00001974656,0.00027293985,0.00067291723,0.7957428,0.0000822881,0.14802143,0.04699275],"study_design_scores_gemma":[0.00052462815,0.0002631042,0.0016888895,0.00003107525,0.0025307662,0.000024707437,0.00018913101,0.07275642,0.40044454,0.00019640979,0.5205456,0.00080474967],"about_ca_topic_score_codex":0.000023531991,"about_ca_topic_score_gemma":0.000047890477,"teacher_disagreement_score":0.3952983,"about_ca_system_score_codex":0.000020466396,"about_ca_system_score_gemma":0.00006856717,"threshold_uncertainty_score":0.5255404},"labels":[],"label_agreement":null},{"id":"W4404300486","doi":"10.1186/s13040-024-00400-1","title":"Deciphering the tissue-specific functional effect of Alzheimer risk SNPs with deep genome annotation","year":2024,"lang":"en","type":"article","venue":"BioData Mining","topic":"Bioinformatics and Genomic Networks","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 Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; University of Southern California; Biogen; BioClinica; Meso Scale Diagnostics; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Pfizer; Eli Lilly and Company; Bristol-Myers Squibb; National Institute on Aging; Alzheimer's Association; Canadian Institutes of Health Research; National Science Foundation","keywords":"Annotation; Genome-wide association study; Single-nucleotide polymorphism; Genome; Computer science; Computational biology; Biology; Data science; Artificial intelligence; Genetics; Gene; Genotype","score_opus":0.013763408373050517,"score_gpt":0.23232748207770818,"score_spread":0.21856407370465766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404300486","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90613157,0.022621103,0.06961823,0.000044748565,0.0003803974,0.00025217838,0.000095091564,0.000020526168,0.000836163],"genre_scores_gemma":[0.99617213,0.00029749106,0.0026075551,0.000026000287,0.00034504852,0.000015985406,0.00046321817,0.000018338158,0.000054257453],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99933046,0.000035491426,0.00018318003,0.00020029253,0.0001028538,0.00014770607],"domain_scores_gemma":[0.99954003,0.00004108788,0.000075028634,0.00028648478,0.000026121985,0.000031255877],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034480047,0.00012101505,0.000100117,0.000027138778,0.00009272188,0.0000575659,0.00012735093,0.000074224154,0.000035768444],"category_scores_gemma":[0.000011012393,0.00007558276,0.00004030297,0.000104986124,0.00007011521,0.000008658042,0.00008100861,0.00008403696,0.000017169727],"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":[0.0005656263,0.00003240381,0.002445598,0.00016995652,0.0013063542,0.00001284014,0.0014747565,0.005365742,0.3795955,0.0002747452,0.0071814116,0.6015751],"study_design_scores_gemma":[0.0017087122,0.0025304395,0.020095484,0.0002301253,0.0006804609,0.00016101579,0.0010368079,0.020578466,0.1990355,0.000052541134,0.7529113,0.0009791122],"about_ca_topic_score_codex":0.0000054973902,"about_ca_topic_score_gemma":0.000009329157,"teacher_disagreement_score":0.7457299,"about_ca_system_score_codex":0.0000059068475,"about_ca_system_score_gemma":0.00002359993,"threshold_uncertainty_score":0.30821756},"labels":[],"label_agreement":null},{"id":"W4405855303","doi":"10.1186/s13040-024-00413-w","title":"Distinct network patterns emerge from Cartesian and XOR epistasis models: a comparative network science analysis","year":2024,"lang":"en","type":"article","venue":"BioData Mining","topic":"Bioinformatics and Genomic Networks","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":"Queen's University","funders":"U.S. National Library of Medicine; National Institutes of Health; Alliance de recherche numérique du Canada","keywords":"Epistasis; Biology; Computational biology; Genetics; Gene","score_opus":0.03330849453372306,"score_gpt":0.27841169382494874,"score_spread":0.24510319929122568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405855303","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8635348,0.012404642,0.120509624,0.0001449783,0.00055727066,0.00019717115,0.0010303352,0.000044845106,0.0015763007],"genre_scores_gemma":[0.9911313,0.00023527218,0.006375012,0.0001332537,0.00073917763,0.000012824358,0.001290785,0.000014014408,0.000068384485],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99844605,0.000035680623,0.0003177699,0.00058074,0.00015476726,0.00046501117],"domain_scores_gemma":[0.99919665,0.00003893711,0.00008334286,0.0004802507,0.000041414667,0.00015939485],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042740672,0.00021350484,0.00027462823,0.00007165325,0.0002873649,0.00026715145,0.00032646864,0.00010313901,0.000031714473],"category_scores_gemma":[0.000010068675,0.00019233872,0.000098602315,0.00064345,0.00021027765,0.000027486132,0.00040411158,0.00010611294,0.0000058439273],"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":[0.0006680359,0.00028145386,0.30458823,0.00049651234,0.01690841,0.00018807512,0.01623034,0.10590084,0.01688659,0.010202926,0.23321071,0.29443786],"study_design_scores_gemma":[0.0003487282,0.00017652698,0.020891963,0.00018730441,0.00096538285,0.000010437686,0.000998963,0.93996197,0.00047109573,0.00096528814,0.034156933,0.0008653871],"about_ca_topic_score_codex":0.00015717348,"about_ca_topic_score_gemma":0.00065362826,"teacher_disagreement_score":0.83406115,"about_ca_system_score_codex":0.00001816702,"about_ca_system_score_gemma":0.00008344557,"threshold_uncertainty_score":0.78433454},"labels":[],"label_agreement":null},{"id":"W4406160197","doi":"10.1186/s13040-024-00412-x","title":"The Venus score for the assessment of the quality and trustworthiness of biomedical datasets","year":2025,"lang":"en","type":"article","venue":"BioData Mining","topic":"Artificial Intelligence in Healthcare and Education","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 Toronto","funders":"HORIZON EUROPE European Research Council; Ministero dell'Università e della Ricerca; HORIZON EUROPE Framework Programme; Dipartimenti di Eccellenza; European Commission; Alexander von Humboldt-Stiftung","keywords":"Computer science; Quality (philosophy); Informatics; Usability; Data science; Data quality; Data mining; Artificial intelligence","score_opus":0.33500278629655134,"score_gpt":0.5494247029763654,"score_spread":0.21442191667981403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406160197","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9646404,0.0015118766,0.0018972261,0.029480742,0.0011847127,0.00068438926,0.0005241935,0.000006000145,0.00007047819],"genre_scores_gemma":[0.99882615,0.00012640202,0.00044295547,0.00030798014,0.00009192425,0.000028567321,0.00013904959,0.000002623609,0.000034367382],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9992637,0.000053830063,0.0003370503,0.00010598123,0.00014354601,0.000095907366],"domain_scores_gemma":[0.9979889,0.0013133634,0.00013753436,0.0004579192,0.00007850109,0.000023813223],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011916844,0.000046111094,0.00011476353,0.000020105652,0.00022032205,0.000010326414,0.000181477,0.000040114926,0.000004436397],"category_scores_gemma":[0.0011153584,0.000020729862,0.00002908295,0.00017563609,0.0002993085,0.00002573567,0.000086456916,0.00007845483,1.3261112e-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":[0.00014588016,0.00012755347,0.28347188,0.00063225115,0.00010354943,3.415571e-7,0.0012903148,0.0000011746697,0.0014004585,0.0055571096,0.02157002,0.68569946],"study_design_scores_gemma":[0.00019997566,0.00017299231,0.86630136,0.0007483834,0.00023262922,0.0000051079783,0.011003652,0.003057357,0.0070290407,0.00086825836,0.110299595,0.000081629114],"about_ca_topic_score_codex":0.00039319773,"about_ca_topic_score_gemma":0.000097723765,"teacher_disagreement_score":0.68561786,"about_ca_system_score_codex":0.00001573843,"about_ca_system_score_gemma":0.00032546787,"threshold_uncertainty_score":0.16945614},"labels":[],"label_agreement":null},{"id":"W4408930421","doi":"10.1186/s13040-025-00441-0","title":"Multivariate longitudinal clustering reveals neuropsychological factors as dementia predictors in an Alzheimer’s disease progression study","year":2025,"lang":"en","type":"article","venue":"BioData Mining","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","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":"Multivariate statistics; Dementia; Neuropsychology; Multivariate analysis; Cluster analysis; Disease; Longitudinal study; Psychology; Alzheimer's disease; Longitudinal data; Medicine; Computer science; Cognition; Psychiatry; Artificial intelligence; Internal medicine; Data mining; Machine learning; Pathology","score_opus":0.10375330141926643,"score_gpt":0.43651103475654657,"score_spread":0.33275773333728015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408930421","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9968883,0.0003123315,0.0001654687,0.00016907262,0.0002219397,0.0015303481,0.000025074336,0.000093803596,0.00059368246],"genre_scores_gemma":[0.99895585,0.00001208129,0.00036128212,0.00013795368,0.000054916945,0.00011846005,0.0002031622,0.000018227534,0.00013804423],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.997521,0.00031389238,0.0004313784,0.00076502434,0.00047720392,0.00049149233],"domain_scores_gemma":[0.998946,0.000083139945,0.00007929326,0.00047668428,0.00008318915,0.0003316531],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006002265,0.00024241803,0.00030068035,0.00036117889,0.00015101429,0.000110538735,0.0002625486,0.000065453496,0.00024764886],"category_scores_gemma":[0.00034660436,0.00018781544,0.000059109858,0.00045865544,0.00008074514,0.00030012545,0.00043803855,0.00025439332,0.000016966973],"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":[0.0012937246,0.0021066144,0.9830848,0.000040158462,0.00018254068,0.0005931605,0.0003736189,9.258553e-7,0.0014928514,0.0000035052221,0.000119416705,0.0107087055],"study_design_scores_gemma":[0.0027891693,0.001520507,0.99265504,0.0003777974,0.000379005,0.0000034288526,0.0013873943,0.0004637667,0.00014594388,0.000007986671,0.00011546373,0.00015448607],"about_ca_topic_score_codex":0.000063902524,"about_ca_topic_score_gemma":0.000025913572,"teacher_disagreement_score":0.01055422,"about_ca_system_score_codex":0.000036213303,"about_ca_system_score_gemma":0.000100791025,"threshold_uncertainty_score":0.76588917},"labels":[],"label_agreement":null},{"id":"W4410024327","doi":"10.1186/s13040-025-00444-x","title":"Learning the therapeutic targets of acute myeloid leukemia through multiscale human interactome network and community analysis","year":2025,"lang":"en","type":"article","venue":"BioData Mining","topic":"Computational Drug Discovery Methods","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":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Interactome; Myeloid leukemia; Computer science; Computational biology; Data science; Medicine; Biology; Cancer research; Gene; Genetics","score_opus":0.040764673387921384,"score_gpt":0.3493131891731776,"score_spread":0.3085485157852562,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410024327","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":[0.4945467,0.00047753306,0.50379753,0.00026121497,0.00013816835,0.00009036156,0.000010501895,0.00005064473,0.0006273564],"genre_scores_gemma":[0.9351062,0.000030988198,0.06438945,0.00026984862,0.000024566601,0.0000067743667,0.000053846245,0.0000052389223,0.00011306736],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978455,0.0011688353,0.00032090978,0.00027171106,0.00017673416,0.00021634322],"domain_scores_gemma":[0.9971945,0.0018231908,0.00018831308,0.0007037774,0.00006363141,0.000026543798],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013901232,0.00014407969,0.00028486855,0.00012976895,0.0007409565,0.00018234891,0.0011680922,0.00004591787,0.000008859772],"category_scores_gemma":[0.00008837935,0.0001125832,0.00009672047,0.0013225839,0.00015109175,0.00050286466,0.0013649733,0.0004469547,0.0000014570819],"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":[0.00012385982,0.0003690728,0.24166352,0.00020614981,0.012753429,0.00002340656,0.08488394,0.22968706,0.010278369,0.07653844,0.0022038445,0.3412689],"study_design_scores_gemma":[0.0005039837,0.00013857613,0.3340557,0.00012096728,0.00066880987,0.0000061734463,0.0017620365,0.6508644,0.0010004619,0.0068262964,0.0037327206,0.00031984245],"about_ca_topic_score_codex":0.00027534465,"about_ca_topic_score_gemma":0.000066730085,"teacher_disagreement_score":0.4405595,"about_ca_system_score_codex":0.0000527354,"about_ca_system_score_gemma":0.00006747779,"threshold_uncertainty_score":0.56989133},"labels":[],"label_agreement":null},{"id":"W4410588018","doi":"10.1186/s13040-025-00451-y","title":"Correction: Learning the therapeutic targets of acute myeloid leukemia through multiscale human interactome network and community analysis","year":2025,"lang":"en","type":"erratum","venue":"BioData Mining","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Interactome; Myeloid leukemia; Computer science; Computational biology; Artificial intelligence; Data science; Medicine; Biology; Cancer research; Gene","score_opus":0.03957594418586434,"score_gpt":0.33867440917041225,"score_spread":0.2990984649845479,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410588018","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":[0.0053656665,0.0060849194,0.94496036,0.00048498684,0.027072515,0.00048940605,0.00017239377,0.00027846935,0.015091315],"genre_scores_gemma":[0.491446,0.0036508483,0.28324062,0.00283348,0.00445588,0.0002177499,0.013305182,0.00022374619,0.20062654],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956197,0.0023565006,0.0006314234,0.000602728,0.00042479706,0.0003648396],"domain_scores_gemma":[0.99480295,0.0029454904,0.0006866435,0.0013451078,0.00016837513,0.00005141281],"candidate_categories":["metaepi_narrow","sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0018051257,0.00039312194,0.0007679686,0.000290058,0.0013019214,0.0003994897,0.0022472248,0.00025499906,0.000027329725],"category_scores_gemma":[0.00021250475,0.00032457645,0.0002635915,0.0019650667,0.0002370071,0.0006024941,0.0025259764,0.0024253658,0.0000026422485],"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":[0.00007145512,0.00020828865,0.0063002426,0.0003580178,0.013733333,0.000030216572,0.028926175,0.06431847,0.00012471886,0.002681537,0.76664823,0.11659931],"study_design_scores_gemma":[0.000409087,0.0002355899,0.039349705,0.00075813965,0.0022427936,0.000027687067,0.0013191971,0.76179904,0.00006352577,0.0013286108,0.1916581,0.0008085549],"about_ca_topic_score_codex":0.0006931936,"about_ca_topic_score_gemma":0.00025942977,"teacher_disagreement_score":0.69748056,"about_ca_system_score_codex":0.00016898889,"about_ca_system_score_gemma":0.00033715751,"threshold_uncertainty_score":0.9999983},"labels":[],"label_agreement":null},{"id":"W4411237205","doi":"10.1186/s13040-025-00455-8","title":"DBSCAN and DBCV application to open medical records heterogeneous data for identifying clinically significant clusters of patients with neuroblastoma","year":2025,"lang":"en","type":"article","venue":"BioData Mining","topic":"Neuroblastoma Research and Treatments","field":"Medicine","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":"Computer science; Data mining; Neuroblastoma; Medical record; DBSCAN; Data science; Information retrieval; Cluster analysis; Medicine; Internal medicine; Artificial intelligence; Fuzzy clustering","score_opus":0.07202205426547378,"score_gpt":0.3988111328466636,"score_spread":0.3267890785811898,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411237205","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98650616,0.000017171942,0.009224559,0.0010446332,0.00008145997,0.002253257,0.00072676426,0.000025122396,0.0001208927],"genre_scores_gemma":[0.98471826,0.000021212172,0.013133039,0.0007197188,0.000028762945,0.00013600236,0.0011056556,0.000024597048,0.00011277156],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99816865,0.000055286586,0.00044577106,0.000685449,0.00037901403,0.0002658425],"domain_scores_gemma":[0.998108,0.00033424434,0.00012843938,0.0009904358,0.00012707645,0.00031175197],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004472953,0.00014307545,0.00033260405,0.00014865899,0.00008898181,0.00006621576,0.000727019,0.00006168787,0.000014311179],"category_scores_gemma":[0.00084067875,0.00011296784,0.000024087632,0.00024722336,0.000093516785,0.00016414997,0.0013720434,0.000094986164,0.0000037490304],"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":[0.01759553,0.0018721572,0.43654686,0.0010354181,0.0008177769,0.00012208208,0.00019116836,0.0000061504356,0.003527207,0.00003521592,0.012492846,0.5257576],"study_design_scores_gemma":[0.051865675,0.024500046,0.8368514,0.004859412,0.0014213308,0.00007748537,0.0006570901,0.02433633,0.012310519,0.00007309316,0.041825645,0.0012219729],"about_ca_topic_score_codex":0.000078467536,"about_ca_topic_score_gemma":0.0000983542,"teacher_disagreement_score":0.5245356,"about_ca_system_score_codex":0.000027369057,"about_ca_system_score_gemma":0.00025337422,"threshold_uncertainty_score":0.4606695},"labels":[],"label_agreement":null},{"id":"W4413362561","doi":"10.1186/s13040-025-00465-6","title":"A simple guide to the use of Student’s t-test, Mann-Whitney U test, Chi-squared test, and Kruskal-Wallis test in biostatistics","year":2025,"lang":"en","type":"article","venue":"BioData Mining","topic":"Genetics, Bioinformatics, and Biomedical Research","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 Toronto","funders":"Ministero dell'Università e della Ricerca; Dipartimenti di Eccellenza","keywords":"Test (biology); Biostatistics; Null hypothesis; Univariate; Kruskal–Wallis one-way analysis of variance; Mann–Whitney U test; Statistical hypothesis testing; Computer science; Chi-square test; Statistics; Simple (philosophy); Machine learning; Artificial intelligence; Data mining; Mathematics; Multivariate statistics; Medicine","score_opus":0.04371332968964679,"score_gpt":0.34307389137528277,"score_spread":0.29936056168563596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413362561","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97526205,0.0015949876,0.0064227465,0.0038258345,0.0003350625,0.0019488193,0.008629618,0.000046877496,0.001934022],"genre_scores_gemma":[0.96321833,0.0015243485,0.028077211,0.002248092,0.00021195394,0.00006460139,0.0012587674,0.000040473104,0.0033561918],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979381,0.00004790775,0.00069717306,0.00044592592,0.0003637924,0.0005070939],"domain_scores_gemma":[0.99770427,0.0009969148,0.00013282408,0.0007781153,0.0001921835,0.00019567806],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0005626553,0.00024907227,0.00028241624,0.00020109673,0.00012142272,0.00014916489,0.0006753318,0.00018502481,0.000019025305],"category_scores_gemma":[0.009590433,0.00019412622,0.000049874412,0.00045130096,0.00028825054,0.00001373884,0.0010477297,0.00015285308,0.000010712806],"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":[0.00005201416,0.00059388403,0.65006244,0.00026124137,0.00007554805,0.000018995861,0.0005517808,0.000016890097,0.09366671,0.0000286952,0.22222383,0.032447934],"study_design_scores_gemma":[0.001864187,0.0019403966,0.35537887,0.00031757762,0.00007811316,0.000014030918,0.0018650527,0.004300404,0.033553418,0.00004009902,0.60004,0.0006078715],"about_ca_topic_score_codex":0.00021683428,"about_ca_topic_score_gemma":0.0008144376,"teacher_disagreement_score":0.37781614,"about_ca_system_score_codex":0.000028155377,"about_ca_system_score_gemma":0.00023530076,"threshold_uncertainty_score":0.99875224},"labels":[],"label_agreement":null},{"id":"W4414531239","doi":"10.1186/s13040-025-00480-7","title":"Temporal phenotyping and prognostic stratification of patients with sepsis through longitudinal clustering","year":2025,"lang":"en","type":"article","venue":"BioData Mining","topic":"Time Series Analysis and Forecasting","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":"University of Toronto","funders":"","keywords":"Cluster analysis; Multivariate statistics; Sepsis; Covariate; Silhouette; Disease; Biobank; Multivariate analysis; Metric (unit)","score_opus":0.0254430725212012,"score_gpt":0.24562285390312613,"score_spread":0.22017978138192493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414531239","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":[0.46226865,0.000107106636,0.53696257,0.00008567137,0.00004485946,0.00009655605,0.000008123844,0.000028939603,0.00039753877],"genre_scores_gemma":[0.88995576,0.000002270076,0.109966695,0.000013651709,0.000008199784,0.0000034534307,0.000029368417,0.000002942909,0.000017667899],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9992345,0.000016846336,0.00021742802,0.00028600506,0.00011518976,0.00013002608],"domain_scores_gemma":[0.9994291,0.00004920639,0.00014653674,0.00027988144,0.000075346106,0.000019897992],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000110065324,0.000088227695,0.00013861198,0.000063470914,0.00012538768,0.00013792513,0.00023672334,0.00002404271,0.0000038870335],"category_scores_gemma":[0.000040450144,0.00007306303,0.000016927777,0.0003830269,0.00004589854,0.0006688213,0.00022736304,0.000038718776,4.827842e-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":[0.000016312493,0.00004286765,0.9275342,0.00008854676,0.00005975863,7.901327e-7,0.00073611585,0.00007366961,0.00007035709,0.0028873917,0.000042837877,0.068447135],"study_design_scores_gemma":[0.0006124824,0.00020019722,0.79511106,0.0005204712,0.00009119558,0.0000012725116,0.00074147293,0.20145622,0.00037007654,0.00020496808,0.00040695112,0.00028360108],"about_ca_topic_score_codex":0.00004689225,"about_ca_topic_score_gemma":0.000041057363,"teacher_disagreement_score":0.4276871,"about_ca_system_score_codex":0.00001040109,"about_ca_system_score_gemma":0.000029050854,"threshold_uncertainty_score":0.2979424},"labels":[],"label_agreement":null},{"id":"W4414606898","doi":"10.1186/s13040-025-00482-5","title":"Proteome mining of Yersinia Enterocolitica for drug targets and computational inhibitor identification with ADMET, anti-inflammation potential and formulation characteristics","year":2025,"lang":"en","type":"article","venue":"BioData Mining","topic":"Pharmacological Effects of Natural Compounds","field":"Pharmacology, Toxicology and Pharmaceutics","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":"Alpha Technologies (Canada)","funders":"King Khalid University; National Research Foundation of Korea","keywords":"Yersinia enterocolitica; Proteome; Drug; Yersinia; Proteomics; Drug repositioning; Identification (biology); Drug discovery","score_opus":0.04233579431491202,"score_gpt":0.38111179151165103,"score_spread":0.338775997196739,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414606898","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99092203,0.00017556541,0.006293623,0.00074416917,0.00035169694,0.0011836627,0.00024876546,0.000042786338,0.00003772077],"genre_scores_gemma":[0.9910108,0.000015481519,0.00794734,0.00018258131,0.00012549467,0.00009620801,0.0005429766,0.000009831046,0.00006931811],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9987708,0.00014214261,0.00042396618,0.00031382396,0.00012458797,0.00022470634],"domain_scores_gemma":[0.99884236,0.00049718254,0.00029146188,0.00008441718,0.0001999832,0.00008457497],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059478055,0.00016641902,0.00025639942,0.00018263943,0.00026793542,0.000055655997,0.00011467217,0.000144289,0.000015608188],"category_scores_gemma":[0.00018362752,0.00015227862,0.000029683462,0.00014439714,0.00015475492,0.00035485672,0.00010065919,0.00017235521,9.738592e-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":[0.0028650532,0.00024076707,0.022975234,0.0013081963,0.00040409385,0.0000115615085,0.00093924516,0.00036892793,0.9171022,0.001472645,0.0018909653,0.05042109],"study_design_scores_gemma":[0.010078012,0.0007388022,0.40775916,0.00041379555,0.0009450874,0.000041508538,0.000520467,0.30775994,0.26230976,0.0010261697,0.0076934276,0.0007138317],"about_ca_topic_score_codex":0.0000023431794,"about_ca_topic_score_gemma":0.0000015060873,"teacher_disagreement_score":0.6547924,"about_ca_system_score_codex":0.00003835124,"about_ca_system_score_gemma":0.00005486838,"threshold_uncertainty_score":0.6209742},"labels":[],"label_agreement":null},{"id":"W4416785648","doi":"10.1186/s13040-025-00499-w","title":"Bioinformatics analysis of Rickettsia typhi autoimmune associations and screening of Streptomyces-derived inhibitors","year":2025,"lang":"en","type":"article","venue":"BioData Mining","topic":"vaccines and immunoinformatics approaches","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":"Alpha Technologies (Canada)","funders":"National Research Foundation of Korea; King Khalid University; National Research Foundation","keywords":"Rickettsia typhi; Salmonella typhi; Rickettsia","score_opus":0.018265540243988583,"score_gpt":0.2611037845670206,"score_spread":0.24283824432303203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416785648","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9928825,0.0010036096,0.0048760083,0.00004696097,0.00004240321,0.000090294976,0.00020978453,0.000007027923,0.00084141595],"genre_scores_gemma":[0.9808549,0.00017207113,0.017838467,0.00003070809,0.000009804475,0.000003389458,0.0010186546,0.0000051735433,0.00006682902],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9991137,0.000018819926,0.00053440913,0.00011742005,0.00008831999,0.00012736852],"domain_scores_gemma":[0.9991636,0.0000306662,0.00036035996,0.00033339582,0.00009067101,0.000021261343],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025246738,0.00010996497,0.00028486532,0.0002647724,0.00006830418,0.000022104496,0.00016578544,0.00010259881,0.0000056187123],"category_scores_gemma":[0.00016774016,0.00010391174,0.00010334289,0.0005796937,0.000054679193,0.00001638507,0.0002483651,0.0000441757,2.3084269e-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":[0.00010963118,0.00018590887,0.39824912,0.0004315033,0.008894607,4.103027e-7,0.0028368416,0.00070573617,0.49419573,0.0005587633,0.0026393759,0.09119237],"study_design_scores_gemma":[0.0017380491,0.00028472175,0.6705923,0.00022064336,0.0024160673,0.0000019534248,0.009246805,0.07121705,0.2383644,0.00001492036,0.0053670597,0.00053599774],"about_ca_topic_score_codex":0.000040707215,"about_ca_topic_score_gemma":0.000008572688,"teacher_disagreement_score":0.27234322,"about_ca_system_score_codex":0.000005827248,"about_ca_system_score_gemma":0.00004915645,"threshold_uncertainty_score":0.4237398},"labels":[],"label_agreement":null}]}