{"meta":{"query_hash":"432751205d30","filters":{"venue":"BMC Bioinformatics"},"cohort_total":647,"direct_labels_cover":1,"predictions_cover":647,"exported":647,"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/432751205d30","api":"https://metacan.xera.ac/api/v1/cohort?venue=BMC+Bioinformatics"},"results":[{"id":"W1480287196","doi":"10.1186/1471-2105-7-356","title":"New directions in biomedical text annotation: definitions, guidelines and corpus construction","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":169,"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; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; National Science Foundation","keywords":"Annotation; Computer science; Task (project management); Information retrieval; Natural language processing; Categorization; Set (abstract data type); Biomedical text mining; Executable; Focus (optics); Artificial intelligence; Unified Medical Language System; Text corpus; Text mining","score_opus":0.03638827609910656,"score_gpt":0.27885588333730144,"score_spread":0.24246760723819488,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1480287196","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006766012,0.009523025,0.92201364,0.049178652,0.0011525361,0.0026846072,0.0014204694,0.0017181755,0.005542841],"genre_scores_gemma":[0.011935683,0.0022064364,0.97548467,0.0019562116,0.0005332645,0.0046173115,0.0018220157,0.00047744188,0.0009670536],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.789187,0.14583577,0.03294713,0.012357975,0.018236658,0.0014355531],"domain_scores_gemma":[0.51539034,0.2991873,0.027742898,0.06283832,0.08872668,0.006114454],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.21495683,0.0024292807,0.0028096174,0.023429336,0.005309296,0.01766306,0.009875565,0.0068940474,0.0035025233],"category_scores_gemma":[0.293678,0.0030351805,0.0018450463,0.017760256,0.0293193,0.03766417,0.01180518,0.012632048,0.0035989748],"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":[0.0003403772,0.00047734013,0.007899763,0.012313337,0.00012411176,0.0009237124,0.0500807,0.0038545392,0.015610263,0.3488904,0.06746679,0.4920187],"study_design_scores_gemma":[0.00016918557,0.00027294687,0.005266161,0.011287324,0.0001398065,0.0013059698,0.019652218,0.022555137,0.013032159,0.50467914,0.42114982,0.0004901489],"about_ca_topic_score_codex":0.0073177093,"about_ca_topic_score_gemma":0.009847852,"teacher_disagreement_score":0.21495683,"about_ca_system_score_codex":0.0073184646,"about_ca_system_score_gemma":0.017111884,"threshold_uncertainty_score":0.968098},"labels":[],"label_agreement":null},{"id":"W1491709863","doi":"10.1186/1471-2105-6-64","title":"MBEToolbox: a Matlab toolbox for sequence data analysis in molecular biology and evolution","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Directorate for Biological Sciences; Texas Tech University","keywords":"Computer science; Visualization; Toolbox; Graphical user interface; Graphics; Interface (matter); MATLAB; Software; Python (programming language); Computer graphics; Theoretical computer science; Data mining; Computational science; Data visualization; Programming language; Computer graphics (images)","score_opus":0.031234246627478465,"score_gpt":0.30439328537247495,"score_spread":0.2731590387449965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1491709863","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019786593,0.0013469858,0.82438725,0.00062011386,0.00037183898,0.00019506777,0.015921643,0.14629424,0.008884119],"genre_scores_gemma":[0.024992805,0.0024328688,0.8718124,0.0011757652,0.00036084905,0.002570494,0.025956824,0.054996613,0.015701365],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985862,0.00037489977,0.00019862757,0.00029533758,0.00043859577,0.000106392836],"domain_scores_gemma":[0.9962442,0.0019537522,0.0005069685,0.00029922984,0.0007794603,0.00021644666],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020394188,0.0019363038,0.0014438857,0.0020513271,0.0004773694,0.0019149466,0.002639031,0.0012527156,0.086980276],"category_scores_gemma":[0.010053384,0.00080941763,0.001019329,0.00153427,0.00066636404,0.001862625,0.002062614,0.0021341557,0.06147585],"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":[0.00075999374,0.00012477182,0.0021037753,0.004004269,0.00025968123,0.00086833007,0.0006295062,0.024764871,0.030298783,0.025579987,0.50986195,0.4007441],"study_design_scores_gemma":[0.00050278014,0.00020612599,0.0031643228,0.0011880286,0.00013413667,0.0019659854,0.00010689995,0.13062054,0.037982352,0.05016872,0.77366215,0.000298032],"about_ca_topic_score_codex":0.0011958007,"about_ca_topic_score_gemma":0.0010752579,"teacher_disagreement_score":0.086980276,"about_ca_system_score_codex":0.0005293036,"about_ca_system_score_gemma":0.0019332488,"threshold_uncertainty_score":0.290978},"labels":[],"label_agreement":null},{"id":"W1494019191","doi":"10.1186/1471-2105-8-33","title":"Considerations in the identification of functional RNA structural elements in genomic alignments","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":69,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Pairwise comparison; Nucleic acid secondary structure; Shuffling; Computational biology; Biology; Computer science; Identification (biology); Genome; Genetics; Data mining; RNA; Artificial intelligence; Gene","score_opus":0.022282450520768902,"score_gpt":0.2611371528625071,"score_spread":0.2388547023417382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1494019191","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34620348,0.005136712,0.63805485,0.0018238957,0.00012576768,0.00025605407,0.00070314994,0.003236802,0.004459332],"genre_scores_gemma":[0.57324594,0.00053340313,0.42398775,0.00043286735,0.000074917516,0.00012564355,0.0006839482,0.00042395768,0.00049156597],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.97233576,0.016885873,0.0021476839,0.00344359,0.0047640107,0.00042309804],"domain_scores_gemma":[0.8561561,0.12146334,0.0054072267,0.009945923,0.006313416,0.000713935],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04171945,0.0010222475,0.0010479126,0.001902158,0.0010028544,0.0036805,0.0022221643,0.0016175776,0.0007409369],"category_scores_gemma":[0.12968723,0.00062047376,0.00085811655,0.0018997706,0.0021191763,0.0029944896,0.0022291162,0.0017327721,0.00084997795],"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":[0.0034064022,0.00035167555,0.15635464,0.0024933678,0.0011014839,0.0010420643,0.0034987116,0.10099968,0.11761724,0.024064636,0.005441572,0.5836286],"study_design_scores_gemma":[0.00035586275,0.0028406293,0.083830856,0.0009952341,0.000622946,0.0073132734,0.0015228599,0.56842023,0.23212469,0.08075215,0.020935522,0.00028573468],"about_ca_topic_score_codex":0.0010864307,"about_ca_topic_score_gemma":0.0017485531,"teacher_disagreement_score":0.04171945,"about_ca_system_score_codex":0.0007951413,"about_ca_system_score_gemma":0.0010399583,"threshold_uncertainty_score":0.22063619},"labels":[],"label_agreement":null},{"id":"W1496257230","doi":"10.1186/s12859-015-0586-0","title":"ProtDCal: A program to compute general-purpose-numerical descriptors for sequences and 3D-structures of proteins","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":80,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; Universidad de San Buenaventura","keywords":"Computer science; Data mining; Sequence (biology); Java; Feature (linguistics); Sequence alignment; Software; Key (lock); Protein function prediction; Artificial intelligence; Theoretical computer science; Machine learning; Programming language; Protein function; Peptide sequence","score_opus":0.03172182749760137,"score_gpt":0.30741463866839125,"score_spread":0.27569281117078986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1496257230","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032128558,0.0005221481,0.602225,0.00034237726,0.00017078756,0.0005495641,0.028177612,0.32562852,0.010255364],"genre_scores_gemma":[0.15520562,0.0009853867,0.71407336,0.00050108274,0.00007174152,0.003373537,0.07688837,0.039019417,0.009881601],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995553,0.000057265115,0.000040258932,0.000117337455,0.00018467222,0.000045167006],"domain_scores_gemma":[0.99899894,0.0005514036,0.000098855846,0.00011613879,0.00015541563,0.000079274134],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00092129403,0.0019739603,0.0011808043,0.001577127,0.0006821202,0.0016117432,0.003393234,0.00081223226,0.01924598],"category_scores_gemma":[0.002821401,0.0008704077,0.0014801438,0.0013148616,0.0007749814,0.001300351,0.0018115704,0.0019136027,0.0070154457],"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":[0.002949845,0.00072144775,0.014115117,0.0050075296,0.0008516621,0.0022817135,0.0011833892,0.1249902,0.060446214,0.03737951,0.40203384,0.3480395],"study_design_scores_gemma":[0.0008164975,0.00023264716,0.0035207744,0.00016954861,0.00012504318,0.0009654064,0.00016649424,0.7871431,0.043178733,0.015794456,0.14771299,0.0001742181],"about_ca_topic_score_codex":0.0039872057,"about_ca_topic_score_gemma":0.0046265814,"teacher_disagreement_score":0.01924598,"about_ca_system_score_codex":0.0009782778,"about_ca_system_score_gemma":0.0020750694,"threshold_uncertainty_score":0.06438422},"labels":[],"label_agreement":null},{"id":"W1497984091","doi":"10.1186/1471-2105-7-441","title":"Exhaustive assignment of compositional bias reveals universally prevalent biased regions: analysis of functional associations in human and Drosophila","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":62,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"McGill University","keywords":"Biology; Drosophila melanogaster; Melanogaster; Genetics; Proteome; Transcription factor; Computational biology; Gene; Evolutionary biology; Homeobox","score_opus":0.02236267727418445,"score_gpt":0.23964584734983221,"score_spread":0.21728317007564776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1497984091","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9980204,0.00026187647,0.0009897428,0.000007760897,7.962763e-7,0.0000061060277,0.000544304,0.000015494072,0.00015346652],"genre_scores_gemma":[0.99397933,0.00012209304,0.0043294537,0.0000178365,0.0000027841893,0.0000120172135,0.0013938259,0.000015295236,0.00012745611],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99986935,0.000016391083,0.000013542885,0.000056636207,0.000024887713,0.000019162293],"domain_scores_gemma":[0.9995372,0.0001318101,0.00016102867,0.000035236404,0.000066145425,0.00006858216],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002882619,0.00016913911,0.00019965105,0.0010294969,0.00027814152,0.00023186012,0.00016010844,0.00019622249,0.000629563],"category_scores_gemma":[0.00073763134,0.000103595274,0.00023010837,0.00062262855,0.00020273532,0.00013343184,0.0002941862,0.00015300699,0.0002294321],"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":[0.0008300136,0.000056028162,0.4411389,0.0004197344,0.0002523892,0.00066246215,0.00054936437,0.0016234706,0.5268829,0.00034949242,0.0004453235,0.026789948],"study_design_scores_gemma":[0.000015385333,0.0001367494,0.9489942,0.000022712866,0.00013143374,0.0018329098,0.0002899544,0.00772373,0.038938675,0.00029426024,0.001602763,0.000017160422],"about_ca_topic_score_codex":0.0015480622,"about_ca_topic_score_gemma":0.0024411518,"teacher_disagreement_score":0.0015480622,"about_ca_system_score_codex":0.00019807558,"about_ca_system_score_gemma":0.00019479326,"threshold_uncertainty_score":0.003078103},"labels":[],"label_agreement":null},{"id":"W1504124766","doi":"10.1186/1471-2105-14-s3-s14","title":"Protein Function Prediction using Text-based Features extracted from the Biomedical Literature: The CAFA Challenge","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Protein function prediction; Classifier (UML); Function (biology); DNA microarray; Gene ontology; Artificial intelligence; Data mining; Precision and recall; Protein function; Computational biology; Machine learning; Gene; Biology; Genetics","score_opus":0.019870383805722213,"score_gpt":0.2384098960389598,"score_spread":0.2185395122332376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1504124766","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49922782,0.017672509,0.16437976,0.014472689,0.0017100923,0.0020901863,0.16855825,0.122143544,0.009745201],"genre_scores_gemma":[0.39422622,0.003310341,0.41921648,0.0016432336,0.0007866656,0.001062259,0.17362821,0.0011508404,0.0049758903],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99663574,0.00050879794,0.0005389025,0.0011319093,0.0010169472,0.0001676286],"domain_scores_gemma":[0.9792244,0.013567581,0.0016710985,0.0014658584,0.003182848,0.00088822324],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004754442,0.0020868082,0.0017628352,0.008255143,0.0013130577,0.002401283,0.0023713862,0.003556804,0.004086746],"category_scores_gemma":[0.020632023,0.000399575,0.0015064685,0.0044734674,0.00059879746,0.0052828896,0.0020595284,0.0018456524,0.0037159754],"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":[0.0014956556,0.0013506749,0.027994106,0.007044558,0.00044404727,0.0031614841,0.0011143538,0.008975372,0.07211426,0.0016123877,0.1865379,0.68815523],"study_design_scores_gemma":[0.0006993729,0.0017857845,0.11133221,0.0013967643,0.00077308615,0.011950273,0.0031755378,0.5381447,0.13508604,0.011185955,0.18387677,0.00059355184],"about_ca_topic_score_codex":0.006204196,"about_ca_topic_score_gemma":0.0068660146,"teacher_disagreement_score":0.008255143,"about_ca_system_score_codex":0.0016503761,"about_ca_system_score_gemma":0.0024287929,"threshold_uncertainty_score":0.02514416},"labels":[],"label_agreement":null},{"id":"W1505843021","doi":"10.1186/1471-2105-16-s5-s7","title":"Isomorphism and similarity for 2-generation pedigrees","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"China Postdoctoral Science Foundation; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; National Science Foundation","keywords":"Pedigree chart; Isomorphism (crystallography); Combinatorics; Partition (number theory); Integer (computer science); Mathematics; Computer science; Property (philosophy); Time complexity; Theoretical computer science; Biology; Genetics","score_opus":0.09091666958478403,"score_gpt":0.2843398320754851,"score_spread":0.19342316249070104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1505843021","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24791752,0.00099619,0.7432004,0.0023491073,0.000060454662,0.00013235451,0.0011360656,0.00041592584,0.0037919537],"genre_scores_gemma":[0.74324065,0.0006227567,0.24982238,0.00046656808,0.00022360576,0.00018433435,0.0029750112,0.00013242304,0.00233229],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99475163,0.0024332465,0.0002357539,0.0015346163,0.0006822234,0.00036259904],"domain_scores_gemma":[0.960825,0.032344542,0.002155832,0.0031426798,0.0008333581,0.00069844886],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005660244,0.00060686964,0.0018217431,0.002253234,0.001191772,0.0021101928,0.0027081512,0.002164947,0.0035931075],"category_scores_gemma":[0.03599507,0.00062050985,0.0014062109,0.0032166494,0.002539376,0.0074874205,0.002693808,0.0024926055,0.00041167458],"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":[0.0006184895,0.00061735255,0.021466099,0.00066970976,0.00032686457,0.001394412,0.0017080286,0.30937555,0.0030688492,0.45099768,0.009294573,0.20046237],"study_design_scores_gemma":[0.000055393826,0.000093963354,0.0022928715,0.000030329988,0.000039219987,0.0005636403,0.00018926944,0.28255987,0.0010069597,0.7103043,0.0028341564,0.000029961198],"about_ca_topic_score_codex":0.0015818661,"about_ca_topic_score_gemma":0.0013683927,"teacher_disagreement_score":0.005660244,"about_ca_system_score_codex":0.0016091105,"about_ca_system_score_gemma":0.0010765223,"threshold_uncertainty_score":0.029934645},"labels":[],"label_agreement":null},{"id":"W1510029899","doi":"10.1186/1471-2105-5-45","title":"A hybrid clustering approach to recognition of protein families in 114 microbial genomes","year":2004,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Advanced Research","funders":"Medical Research Council; University of Queensland","keywords":"Cluster analysis; Markov chain; Data mining; Single-linkage clustering; Complete-linkage clustering; Computer science; Hierarchical clustering; Computational biology; Correlation clustering; Biology; Artificial intelligence; CURE data clustering algorithm; Machine learning","score_opus":0.015093997896921526,"score_gpt":0.21160764773952587,"score_spread":0.19651364984260433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1510029899","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35828954,0.0006698982,0.6310032,0.00014925796,0.000026580045,0.00036808173,0.0024688388,0.0038108996,0.003213745],"genre_scores_gemma":[0.28786162,0.00013887243,0.70734704,0.00003282596,0.000007188626,0.00030885066,0.0034010482,0.00018476344,0.0007178165],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990258,0.00022743041,0.000087750246,0.00024589285,0.0003507052,0.00006235642],"domain_scores_gemma":[0.9991208,0.00024381895,0.00006226215,0.0001425914,0.00038611935,0.000044407134],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00083454815,0.00047246044,0.0004836881,0.0029834146,0.0008551042,0.00092264515,0.0010247432,0.0005957056,0.0015844316],"category_scores_gemma":[0.002711721,0.00030572063,0.0008896404,0.0027881558,0.00026992324,0.0005045213,0.0008851151,0.00041184455,0.0005533271],"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":[0.0013284426,0.00031439122,0.021697806,0.0008560107,0.00070904824,0.00032467223,0.0012898056,0.1619747,0.14944637,0.011410461,0.004588955,0.64605933],"study_design_scores_gemma":[0.00010291026,0.00019895467,0.016122509,0.000046673584,0.00020166016,0.0005831539,0.0005073443,0.91253483,0.047449596,0.012218455,0.009947056,0.0000867706],"about_ca_topic_score_codex":0.006270755,"about_ca_topic_score_gemma":0.009034391,"teacher_disagreement_score":0.006270755,"about_ca_system_score_codex":0.0014299061,"about_ca_system_score_gemma":0.00079032825,"threshold_uncertainty_score":0.012468517},"labels":[],"label_agreement":null},{"id":"W1515882292","doi":"10.1186/1471-2105-7-343","title":"Multivariate curve resolution of time course microarray data","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":119,"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; National Science Foundation","keywords":"Principal component analysis; Multivariate statistics; Linear model; Data mining; Computer science; Least-squares function approximation; Gene chip analysis; DNA microarray; Missing data; Algorithm; Biological data; Statistics; Mathematics; Bioinformatics; Biology; Gene expression; Gene; Genetics","score_opus":0.025184432124388444,"score_gpt":0.27798983067147187,"score_spread":0.25280539854708345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1515882292","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012010327,0.00013241355,0.98593605,0.00007065915,0.000016736893,0.000040816263,0.000326472,0.0011641679,0.0003023375],"genre_scores_gemma":[0.12362941,0.0004574329,0.8721257,0.0000714075,0.00004223892,0.00022938235,0.0018508335,0.00059487124,0.0009988232],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986192,0.00037539986,0.00007456229,0.0003329006,0.00051881117,0.000079121746],"domain_scores_gemma":[0.99622226,0.0018485761,0.00045647466,0.0006598182,0.0007347005,0.00007823031],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022397884,0.0010273923,0.0006634858,0.0015908662,0.00026013286,0.0007529057,0.0010223716,0.0005700326,0.002528966],"category_scores_gemma":[0.0062010097,0.00033047647,0.0011470895,0.0022883194,0.0005097317,0.0009522679,0.0006382512,0.0017163589,0.0012592786],"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":[0.00045052211,0.0002645088,0.005077242,0.0007699792,0.0002134379,0.00016603255,0.00024072353,0.14955807,0.2907583,0.012883214,0.003925243,0.53569275],"study_design_scores_gemma":[0.000027608237,0.00013087313,0.0077301026,0.000034806053,0.000039592866,0.00027057226,0.00005709621,0.834135,0.1314297,0.016468523,0.009573281,0.00010295319],"about_ca_topic_score_codex":0.0011010651,"about_ca_topic_score_gemma":0.0009960519,"teacher_disagreement_score":0.002528966,"about_ca_system_score_codex":0.0006053065,"about_ca_system_score_gemma":0.00081710354,"threshold_uncertainty_score":0.011845291},"labels":[],"label_agreement":null},{"id":"W1518614040","doi":"10.1186/1471-2105-7-338","title":"Cluster analysis of protein array results via similarity of Gene Ontology annotation","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research; University of Toronto","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada; Mitacs; Canadian Institutes of Health Research; Terry Fox Foundation","keywords":"Annotation; Gene ontology; Computational biology; Set (abstract data type); Ontology; Gene Annotation; Computer science; Protein microarray; Similarity (geometry); DNA microarray; Proteomics; Graph; Protein function prediction; Biology; Genome; Information retrieval; Data mining; Gene; Bioinformatics; Genetics; Image (mathematics); Theoretical computer science; Protein function; Artificial intelligence; Gene expression","score_opus":0.008225236861544173,"score_gpt":0.24896429969994288,"score_spread":0.24073906283839872,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1518614040","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32741904,0.00071238406,0.6452131,0.00032573775,0.00012772866,0.0013165552,0.013523242,0.0077926805,0.0035695175],"genre_scores_gemma":[0.44601864,0.00026791354,0.53778714,0.00006759567,0.00005995547,0.0015176099,0.012968248,0.00068286655,0.0006299314],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99590635,0.00058826,0.00047230482,0.0013365408,0.0014434401,0.00025317766],"domain_scores_gemma":[0.99374557,0.002314137,0.0014211015,0.0007179954,0.0015340236,0.00026724712],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031583328,0.000988448,0.0011870351,0.014128694,0.0011197232,0.0022796004,0.001226525,0.0005266031,0.0028003263],"category_scores_gemma":[0.009552647,0.0002952047,0.0017668465,0.008949015,0.0010336495,0.000929496,0.0017374461,0.00097079657,0.00089586363],"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":[0.0038137003,0.0013405974,0.17942084,0.003831388,0.0030666923,0.00080345187,0.0032166224,0.036035575,0.2747909,0.015981097,0.011729331,0.4659699],"study_design_scores_gemma":[0.00028052682,0.0012385914,0.28184226,0.0003410427,0.0012976725,0.0015916127,0.0030077873,0.49252528,0.12891722,0.058850657,0.029521402,0.0005859425],"about_ca_topic_score_codex":0.002742226,"about_ca_topic_score_gemma":0.0026441806,"teacher_disagreement_score":0.014128694,"about_ca_system_score_codex":0.0014745761,"about_ca_system_score_gemma":0.0018643261,"threshold_uncertainty_score":0.01670307},"labels":[],"label_agreement":null},{"id":"W1525672751","doi":"10.1186/1471-2105-6-75","title":"Ranking the whole MEDLINE database according to a large training set using text indexing","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":58,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Genomics","funders":"U.S. National Library of Medicine; Universität Stuttgart; Ontario Genomics Institute; Stem Cell Network; Ontario Genomics; Ontario Innovation Trust","keywords":"MEDLINE; Computer science; Information retrieval; Relevance (law); Ranking (information retrieval); Set (abstract data type); Controlled vocabulary; Vocabulary; Subject (documents); National library; Natural language processing; Artificial intelligence; World Wide Web; Library science; Linguistics","score_opus":0.07540264134123546,"score_gpt":0.33009792757829903,"score_spread":0.25469528623706356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1525672751","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6029789,0.01529621,0.2663768,0.0032113479,0.0007644142,0.0034106793,0.027630622,0.064177886,0.016153194],"genre_scores_gemma":[0.4762374,0.0033073677,0.433378,0.00089942076,0.00042826158,0.0013468164,0.07880161,0.0010976559,0.004503501],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99491453,0.0012763981,0.00083021686,0.0012926705,0.0014765309,0.00020968019],"domain_scores_gemma":[0.9768553,0.015145066,0.0007023145,0.0016398005,0.005106782,0.0005507214],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0065587447,0.0022607248,0.0022724213,0.012004533,0.0021024223,0.0027839455,0.002712545,0.0022587196,0.004679297],"category_scores_gemma":[0.03719905,0.0006405343,0.0014677542,0.0074469377,0.0007812581,0.003825879,0.0019834114,0.001191104,0.0039206813],"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":[0.0012984201,0.0012891775,0.021950414,0.0032653955,0.00045450267,0.0016973673,0.0008803419,0.019718748,0.057365034,0.0012504266,0.041609563,0.8492205],"study_design_scores_gemma":[0.0007037664,0.0035949056,0.07097629,0.0011468179,0.0017749479,0.0049333484,0.0021364088,0.6957645,0.14027867,0.007595102,0.070745125,0.00035007807],"about_ca_topic_score_codex":0.008930406,"about_ca_topic_score_gemma":0.01041051,"teacher_disagreement_score":0.012004533,"about_ca_system_score_codex":0.0016675576,"about_ca_system_score_gemma":0.0024856238,"threshold_uncertainty_score":0.034686387},"labels":[],"label_agreement":null},{"id":"W1531430623","doi":"10.1186/1471-2105-3-1","title":"Identification and characterization of subfamily-specific signatures in a large protein superfamily by a hidden Markov model approach","year":2002,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":134,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research","funders":"National Cancer Institute; Canadian Institutes of Health Research; Howard Hughes Medical Institute","keywords":"Hidden Markov model; Subfamily; Biology; Structural Classification of Proteins database; Computational biology; Threading (protein sequence); Sequence alignment; Sequence motif; GenBank; Multiple sequence alignment; Sequence database; Protein family; Structural motif; Genetics; Protein structure; Artificial intelligence; Computer science; Peptide sequence; Gene","score_opus":0.008643251258559427,"score_gpt":0.19888992884917417,"score_spread":0.19024667759061475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1531430623","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35622454,0.00042793053,0.6396078,0.00017960802,0.000014477806,0.00008744701,0.00074647035,0.0015525209,0.0011592269],"genre_scores_gemma":[0.756962,0.00022277817,0.23987392,0.00004730328,0.000014385114,0.00013073267,0.0018970007,0.00011317574,0.0007388118],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998191,0.000049935836,0.000013931684,0.00005576236,0.000037544913,0.000023785382],"domain_scores_gemma":[0.99924976,0.00042953403,0.00009521339,0.00008373986,0.00008572831,0.00005601637],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058446743,0.0002978457,0.00034900263,0.0010484508,0.0003823779,0.00037956832,0.0004425898,0.00045930853,0.0011067358],"category_scores_gemma":[0.0014893997,0.00023406619,0.0006233755,0.0005365259,0.0002757301,0.00047562143,0.00037550877,0.0004406212,0.0004854517],"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":[0.001270772,0.0005184981,0.12901041,0.0006082606,0.00042798073,0.0008389283,0.0012202691,0.19992279,0.2005631,0.018295748,0.0035577093,0.4437656],"study_design_scores_gemma":[0.00002437867,0.00007209707,0.014509264,0.000019032554,0.00006160981,0.0002211928,0.00007578635,0.96854436,0.00736321,0.008206159,0.00088044384,0.000022577611],"about_ca_topic_score_codex":0.0031306662,"about_ca_topic_score_gemma":0.003902465,"teacher_disagreement_score":0.0031306662,"about_ca_system_score_codex":0.0005637382,"about_ca_system_score_gemma":0.0007541185,"threshold_uncertainty_score":0.0062249303},"labels":[],"label_agreement":null},{"id":"W1533736623","doi":"10.1186/1471-2105-3-39","title":"Species-specific protein sequence and fold optimizations","year":2002,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Sinai Hospital; University of Toronto; St. Michael's Hospital","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"ORFS; Genome; Biology; Archaea; Amino acid; Eukaryote; Computational biology; Genetics; Homology (biology); Open reading frame; Bacteria; Peptide sequence; Gene","score_opus":0.04602734988357537,"score_gpt":0.22612767535671227,"score_spread":0.1801003254731369,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1533736623","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89730936,0.0009223943,0.09248862,0.0001484931,0.000032110704,0.00019842338,0.002720369,0.0032961324,0.0028840906],"genre_scores_gemma":[0.8655009,0.00036590386,0.12210885,0.000081894745,0.000015007467,0.00023136436,0.009723934,0.00069399015,0.0012781577],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99919385,0.00022945878,0.00008017529,0.0002278523,0.00019288877,0.000075802105],"domain_scores_gemma":[0.99879056,0.0003520587,0.00024416577,0.00017324698,0.00037001108,0.00006986139],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001984501,0.0012041602,0.0006499032,0.0014413224,0.0004421915,0.0006549147,0.0006435574,0.0004566542,0.002000143],"category_scores_gemma":[0.0042536333,0.00020061147,0.0011494111,0.0010836126,0.0002949397,0.00072891195,0.0007102093,0.00052464334,0.0010077803],"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":[0.0029342426,0.0004955999,0.100987084,0.0011389904,0.0006428812,0.00031860382,0.00043187453,0.08071741,0.53168064,0.0019064632,0.003331728,0.27541453],"study_design_scores_gemma":[0.000087455504,0.0012497801,0.117724665,0.000093783834,0.0004582992,0.0017233382,0.00030562226,0.502497,0.3575985,0.005746017,0.01238946,0.00012599575],"about_ca_topic_score_codex":0.0005856203,"about_ca_topic_score_gemma":0.00083269895,"teacher_disagreement_score":0.002000143,"about_ca_system_score_codex":0.00056161283,"about_ca_system_score_gemma":0.0004033016,"threshold_uncertainty_score":0.010495186},"labels":[],"label_agreement":null},{"id":"W1541953909","doi":"10.1186/1471-2105-7-521","title":"Dynamic variable selection in SNP genotype autocalling from APEX microarray data","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Paul's Hospital; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; British Columbia Lung Association; National Sanitarium Association","keywords":"Single-nucleotide polymorphism; SNP genotyping; DNA microarray; Genotyping; Genotype; SNP array; Genetics; SNP; Biology; Tag SNP; Molecular Inversion Probe; Sanger sequencing; Computational biology; DNA sequencing; Algorithm; Computer science; DNA; Gene","score_opus":0.021810520933346858,"score_gpt":0.26371961140742356,"score_spread":0.24190909047407672,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1541953909","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11077553,0.00010467369,0.8847272,0.00008632965,0.000016786695,0.00010274265,0.00025644113,0.003505715,0.0004246629],"genre_scores_gemma":[0.35248178,0.00007232314,0.6448586,0.00014275164,0.000028005003,0.00045402106,0.00092822255,0.00036190622,0.00067238486],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970824,0.001405309,0.00013067308,0.00063350785,0.0006028673,0.00014521385],"domain_scores_gemma":[0.9938891,0.004753899,0.00029867765,0.00041332297,0.00057221955,0.000072687835],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042646956,0.00059242244,0.0009855683,0.0013648195,0.00045421591,0.0006743686,0.0010974617,0.00056200963,0.0009089044],"category_scores_gemma":[0.007474575,0.0003113781,0.00061998726,0.00089310214,0.00044137746,0.00047817716,0.0009817661,0.0009004081,0.0005920895],"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":[0.0009758845,0.00023669076,0.028205702,0.0001579483,0.0002533344,0.00027464385,0.0003972706,0.16373095,0.125146,0.0020189849,0.0022288081,0.6763737],"study_design_scores_gemma":[0.000018103981,0.000063499545,0.0061118538,0.000006489857,0.000015523583,0.00009455289,0.000028406364,0.963224,0.027441911,0.002005684,0.00095943233,0.000030477297],"about_ca_topic_score_codex":0.0015395406,"about_ca_topic_score_gemma":0.0020787348,"teacher_disagreement_score":0.0042646956,"about_ca_system_score_codex":0.00052177376,"about_ca_system_score_gemma":0.00057603687,"threshold_uncertainty_score":0.02255416},"labels":[],"label_agreement":null},{"id":"W1542595575","doi":"10.1186/1471-2105-7-270","title":"Improving the specificity of high-throughput ortholog prediction","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":108,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; Simon Fraser University; University of British Columbia","funders":"Genome Prairie; Canadian Institutes of Health Research; Genome British Columbia; Michael Smith Health Research BC; Genome Canada","keywords":"Throughput; Computational biology; DNA microarray; Computer science; Biology; Bioinformatics; Genetics; Gene; Gene expression","score_opus":0.010276379109183264,"score_gpt":0.20080798536633135,"score_spread":0.19053160625714807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1542595575","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6778835,0.00078048866,0.3028048,0.0004932539,0.000094161645,0.00026973968,0.0010038422,0.013681559,0.0029886693],"genre_scores_gemma":[0.81050485,0.00015939835,0.18607427,0.00022265839,0.00002718825,0.00019067098,0.001856083,0.0004265294,0.0005383185],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99748945,0.0010109177,0.00014101547,0.00060448993,0.0005475173,0.0002066422],"domain_scores_gemma":[0.9889043,0.008499587,0.00042323468,0.0009406364,0.0010148361,0.00021734499],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004333162,0.001213834,0.0014401849,0.0010057689,0.00089021656,0.0015433928,0.0017498254,0.0014761271,0.0019075422],"category_scores_gemma":[0.01615438,0.0005941596,0.0011866054,0.0009229937,0.0006716634,0.0016354556,0.0014956838,0.001503981,0.000958964],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027940287,0.0015068874,0.08026169,0.0014395332,0.00079941016,0.000984099,0.0006296912,0.5422181,0.12960772,0.004189073,0.009927614,0.22564213],"study_design_scores_gemma":[0.000043875054,0.000094809715,0.0027440053,0.000009960397,0.000036502865,0.00014554113,0.00004272899,0.97985786,0.015215069,0.0010587435,0.00073029124,0.000020601628],"about_ca_topic_score_codex":0.003842259,"about_ca_topic_score_gemma":0.004197079,"teacher_disagreement_score":0.004333162,"about_ca_system_score_codex":0.00092319027,"about_ca_system_score_gemma":0.0013476067,"threshold_uncertainty_score":0.022916257},"labels":[],"label_agreement":null},{"id":"W1553029142","doi":"10.1186/1471-2105-8-54","title":"BIRCH: A user-oriented, locally-customizable, bioinformatics system","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Genome Prairie; Genome Canada","keywords":"Computer science; Installation; Graphical user interface; Documentation; Software; User interface; Betula pendula; Set (abstract data type); Hierarchy; World Wide Web; Software engineering; Data science; Operating system","score_opus":0.018125852863450337,"score_gpt":0.26769001621134875,"score_spread":0.2495641633478984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1553029142","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036808115,0.00036846483,0.07989922,0.0005104752,0.00023606903,0.0004561357,0.0039266143,0.8913569,0.019565301],"genre_scores_gemma":[0.15275097,0.0019146458,0.47459945,0.0063696997,0.0012605867,0.0031897754,0.08907116,0.15980296,0.11104085],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9941831,0.0009757615,0.0003328459,0.0015123929,0.0021673953,0.0008285336],"domain_scores_gemma":[0.99061567,0.0016886168,0.0005240791,0.0031795383,0.0017600859,0.0022319448],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0072900266,0.0024904616,0.0020024574,0.005020159,0.0018820552,0.0048861173,0.008170959,0.0017672798,0.049728114],"category_scores_gemma":[0.011925608,0.0019771822,0.0010179509,0.0038524803,0.0021630947,0.009795742,0.010770624,0.0051125404,0.05476931],"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":[0.0024022285,0.00047325104,0.0034126937,0.0006531983,0.0001279327,0.000839471,0.00075263577,0.0031789804,0.015352294,0.015113876,0.7837932,0.17390019],"study_design_scores_gemma":[0.0018901069,0.0008737608,0.013228235,0.0005124606,0.00029663346,0.0019948,0.00041399625,0.08422785,0.04332791,0.038634114,0.8134365,0.001163603],"about_ca_topic_score_codex":0.008082564,"about_ca_topic_score_gemma":0.0059907674,"teacher_disagreement_score":0.049728114,"about_ca_system_score_codex":0.0026115233,"about_ca_system_score_gemma":0.0053806053,"threshold_uncertainty_score":0.1663571},"labels":[],"label_agreement":null},{"id":"W1554361839","doi":"10.1186/1471-2105-3-32","title":"SeqHound: biological sequence and structure database as a platform for bioinformatics research","year":2002,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Computer science; Annotation; Perl; Biological database; GenBank; XML; Application programming interface; Information retrieval; World Wide Web; Database; UniProt; User interface; Web server; Bioinformatics; Biology; The Internet; Programming language","score_opus":0.15206778089041978,"score_gpt":0.3391928206073035,"score_spread":0.1871250397168837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1554361839","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007878164,0.004066387,0.27867082,0.0019466461,0.0019066539,0.0014975477,0.22703156,0.45203793,0.024964247],"genre_scores_gemma":[0.018362889,0.0022552193,0.34626114,0.0022030822,0.0003048723,0.0023128653,0.5762212,0.03696765,0.01511102],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99654216,0.00059329136,0.00036510543,0.0008001085,0.001401555,0.0002977387],"domain_scores_gemma":[0.9961201,0.0011234739,0.0003360603,0.00088424335,0.00067322084,0.0008629463],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0066860607,0.002523483,0.0029480683,0.0045494987,0.0015584759,0.005540422,0.007797846,0.002373326,0.042449906],"category_scores_gemma":[0.008381864,0.002286032,0.0019237853,0.0058737467,0.0012317331,0.00597027,0.0057197367,0.004213941,0.049743205],"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":[0.0024742675,0.0002710312,0.0018504795,0.003551818,0.00034453627,0.0006636273,0.00040756425,0.0051428443,0.039972253,0.022597881,0.7852993,0.1374244],"study_design_scores_gemma":[0.0013372763,0.00035245865,0.0041687945,0.00061877683,0.00022216071,0.00094909105,0.00013693885,0.033277992,0.039652847,0.045061644,0.87383324,0.00038869356],"about_ca_topic_score_codex":0.0035143779,"about_ca_topic_score_gemma":0.0035096866,"teacher_disagreement_score":0.042449906,"about_ca_system_score_codex":0.0021298523,"about_ca_system_score_gemma":0.0048628626,"threshold_uncertainty_score":0.14200914},"labels":[],"label_agreement":null},{"id":"W1554825545","doi":"10.1186/1471-2105-7-216","title":"A factor analysis model for functional genomics","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; University of Toronto; Toronto Public Health","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Functional genomics; Computer science; Genomics; Factor (programming language); Gene ontology; Expression (computer science); DNA microarray; Computational biology; Structural genomics; Data mining; Biological data; Computation; Genome; Artificial intelligence; Machine learning; Bioinformatics; Gene; Biology; Algorithm; Genetics; Gene expression","score_opus":0.01901459151223892,"score_gpt":0.22530185389627383,"score_spread":0.20628726238403491,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1554825545","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040592942,0.00022322808,0.99307257,0.0004300397,0.000038339145,0.0000408085,0.00024149535,0.00034630374,0.0015479568],"genre_scores_gemma":[0.47404262,0.001251193,0.5091281,0.0004955636,0.00041979193,0.0009254507,0.0017015232,0.00035580306,0.011679915],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981048,0.0008813095,0.000067529276,0.00047666678,0.0003196677,0.0001498714],"domain_scores_gemma":[0.99337065,0.005109356,0.00036393377,0.00035899607,0.00066379644,0.00013335554],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004380298,0.0016609312,0.0011116607,0.0015139449,0.0006773182,0.0014300225,0.002115793,0.0016461327,0.0071015474],"category_scores_gemma":[0.011487977,0.0004886446,0.0023045363,0.001807123,0.00166444,0.002330201,0.0009327853,0.0021694761,0.0025469519],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015631295,0.00010506481,0.0030215944,0.00016161296,0.00018426511,0.00020071476,0.00022658869,0.6197206,0.0011968829,0.29475087,0.0069752573,0.07330029],"study_design_scores_gemma":[0.000012996351,0.000020028518,0.00020239237,0.000009583237,0.000018414974,0.00004341444,0.000012211597,0.8766664,0.00014380254,0.121078685,0.0017802016,0.0000118739745],"about_ca_topic_score_codex":0.009045881,"about_ca_topic_score_gemma":0.0051132175,"teacher_disagreement_score":0.009045881,"about_ca_system_score_codex":0.00213364,"about_ca_system_score_gemma":0.0015558358,"threshold_uncertainty_score":0.02375698},"labels":[],"label_agreement":null},{"id":"W1563388055","doi":"10.1186/1471-2105-5-103","title":"Improving the scaling normalization for high-density oligonucleotide GeneChip expression microarrays","year":2004,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; Hospital for Sick Children","funders":"Hospital for Sick Children","keywords":"DNA microarray; Normalization (sociology); Computational biology; Gene chip analysis; Microarray; Oligonucleotide; Biology; Gene expression profiling; Computer science; Bioinformatics; Gene expression; Genetics; Gene","score_opus":0.013614672881765124,"score_gpt":0.2318689874051802,"score_spread":0.21825431452341507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1563388055","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02289749,0.0011774147,0.96582776,0.00037382724,0.00049072463,0.00037924532,0.00067967485,0.006592232,0.0015817643],"genre_scores_gemma":[0.040761907,0.0010780396,0.9507061,0.0003142221,0.00012966941,0.0012027308,0.002127979,0.0017251086,0.001954164],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9916488,0.0026411614,0.00061749277,0.0014593182,0.0033341828,0.00029894972],"domain_scores_gemma":[0.9927248,0.0030298023,0.0004124331,0.0013412407,0.0024043282,0.000087333436],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008869875,0.002466563,0.0020265866,0.0022710748,0.001225243,0.0020328967,0.0021205936,0.0014171313,0.00627162],"category_scores_gemma":[0.024532124,0.0010864359,0.0017036874,0.0043672104,0.0011628667,0.0018001221,0.0011622915,0.0026948815,0.005858383],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034106552,0.00025488646,0.0056408583,0.0014485541,0.00018874797,0.00019111062,0.00043436405,0.005795317,0.7051613,0.004181007,0.012536168,0.26382667],"study_design_scores_gemma":[0.00008026265,0.00053363375,0.02524263,0.0002491395,0.0002672056,0.0012403878,0.00024370263,0.07162515,0.81844616,0.011418895,0.07040697,0.00024584227],"about_ca_topic_score_codex":0.0010311853,"about_ca_topic_score_gemma":0.0022811193,"teacher_disagreement_score":0.008869875,"about_ca_system_score_codex":0.0011792223,"about_ca_system_score_gemma":0.001338038,"threshold_uncertainty_score":0.046908915},"labels":[],"label_agreement":null},{"id":"W1563772569","doi":"10.1186/1471-2105-7-185","title":"Ebbie: automated analysis and storage of small RNA cloning data using a dynamic web server","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Chromosomal and Genetic Variations","field":"Agricultural and Biological Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Canadian Institutes of Health Research; Simon Fraser University; Michael Smith Health Research BC","keywords":"Cloning (programming); Substring; Insert (composites); Computer science; Computational biology; Sequence analysis; DNA sequencing; Biology; Database; Sequence database; Genetics; Data mining; DNA; Gene; Data structure; Programming language","score_opus":0.03417064336361586,"score_gpt":0.24395543796955318,"score_spread":0.20978479460593732,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1563772569","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0119666895,0.00042151005,0.3045929,0.0003344011,0.00017941908,0.0012757315,0.025144199,0.65226173,0.0038233022],"genre_scores_gemma":[0.08396622,0.00096674525,0.7186562,0.00067131635,0.00018678154,0.005868631,0.1404883,0.039270964,0.009924824],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972819,0.00044505362,0.00032562623,0.0006384767,0.0010811621,0.00022782464],"domain_scores_gemma":[0.99502206,0.0016096588,0.0005010315,0.0011839002,0.0010220233,0.0006614033],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0058088265,0.0035696423,0.002193503,0.005278134,0.0011028397,0.0031351605,0.004542449,0.0011881109,0.017660487],"category_scores_gemma":[0.009072717,0.0014250686,0.0010980327,0.003730646,0.0007861291,0.0046322807,0.0032959573,0.002325509,0.024464455],"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":[0.009095048,0.0013936107,0.009551315,0.0022356987,0.00074283034,0.0015350961,0.0012413916,0.0074356,0.14490557,0.007927536,0.30432487,0.5096115],"study_design_scores_gemma":[0.0024403448,0.00097148004,0.022290954,0.0007956299,0.0002977745,0.0016462944,0.0006285955,0.37848765,0.32179308,0.017103128,0.2526605,0.0008845954],"about_ca_topic_score_codex":0.0020064588,"about_ca_topic_score_gemma":0.001116236,"teacher_disagreement_score":0.017660487,"about_ca_system_score_codex":0.0011092447,"about_ca_system_score_gemma":0.0014816555,"threshold_uncertainty_score":0.059080243},"labels":[],"label_agreement":null},{"id":"W1564554862","doi":"10.1186/1471-2105-13-s17-s1","title":"InCoB2012 Conference: from biological data to knowledge to technological breakthroughs","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Center for Genetic Engineering and Biotechnology; Hospital for Sick Children; Macquarie University; National Science and Technology Development Agency; King Mongkut's University of Technology Thonburi; Danmarks Tekniske Universitet; Chinese Academy of Sciences; Thailand Science Park; National University of Singapore","keywords":"Asia pacific; Dissemination; Theme (computing); China; Library science; Data science; Political science; Bioinformatics; Biology; World Wide Web; Computer science; History","score_opus":0.13239455089816796,"score_gpt":0.35720306245475947,"score_spread":0.2248085115565915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1564554862","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007987403,0.089006215,0.0022804786,0.25415972,0.6324541,0.00011286168,0.0013952955,0.0004825688,0.019310107],"genre_scores_gemma":[0.010409954,0.079736724,0.005460562,0.1664377,0.6074448,0.00064685434,0.0048972885,0.0011427848,0.12382329],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9934377,0.0019612568,0.0004481621,0.00075448194,0.002619167,0.00077927526],"domain_scores_gemma":[0.9763554,0.005174059,0.0014003614,0.0006831585,0.007924252,0.008462731],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0148375705,0.0022743565,0.0016117042,0.0047410624,0.0039578727,0.014719615,0.003027478,0.0075978437,0.03166147],"category_scores_gemma":[0.023577824,0.00083056604,0.0014049395,0.0035688793,0.0028576357,0.007905134,0.006636415,0.011905174,0.016515177],"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":[0.00003864543,0.000010307291,0.000046156205,0.00019256087,0.000008014749,0.00003924907,0.00004703792,0.000027900585,0.00018547595,0.0009641551,0.99071395,0.0077264486],"study_design_scores_gemma":[0.000013741934,0.000013731676,0.00033533058,0.0002868834,0.000008885973,0.000049627157,0.000065749315,0.000036044254,0.00017542967,0.0009580141,0.9980434,0.000013120901],"about_ca_topic_score_codex":0.0035524534,"about_ca_topic_score_gemma":0.009968386,"teacher_disagreement_score":0.03166147,"about_ca_system_score_codex":0.0072448426,"about_ca_system_score_gemma":0.008941571,"threshold_uncertainty_score":0.10591823},"labels":[],"label_agreement":null},{"id":"W1574079093","doi":"10.1186/1471-2105-4-18","title":"Genome wide identification of regulatory motifs in Bacillus subtilis","year":2003,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bacterial Genetics and Biotechnology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Division of Materials Research; Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Regulon; Operon; Biology; Genetics; Genome; Gene; Computational biology; DNA binding site; Transcription factor; Promoter; Gene expression","score_opus":0.009240679745021633,"score_gpt":0.2097476990422918,"score_spread":0.20050701929727016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1574079093","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99011785,0.0006364403,0.0056301206,0.000042337015,0.00000844086,0.000040879608,0.002653842,0.0002325582,0.0006376417],"genre_scores_gemma":[0.9630075,0.00027220193,0.024220757,0.000041317748,0.00000827246,0.000056573957,0.011979947,0.000044057575,0.00036934085],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998153,0.00002092469,0.00001555372,0.00006319095,0.000061469706,0.000023623747],"domain_scores_gemma":[0.9996227,0.00010969328,0.000114007715,0.000013554351,0.00006438156,0.00007566596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029932513,0.00040242635,0.00037383338,0.0009020675,0.00031180886,0.00035277408,0.00015462944,0.00028201175,0.0006107131],"category_scores_gemma":[0.0006875546,0.00016166939,0.00027162684,0.00082018017,0.00011027502,0.00010136551,0.00026000192,0.00040054845,0.00029566436],"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":[0.0014342462,0.00018872597,0.048595954,0.00036810274,0.00008901141,0.00027267248,0.00014162961,0.0022711777,0.9195982,0.0001990437,0.00053738063,0.026303882],"study_design_scores_gemma":[0.0002136416,0.0016846069,0.6054409,0.00014112057,0.00032663232,0.002616924,0.00029010166,0.041816678,0.336587,0.0010856758,0.009715011,0.00008169457],"about_ca_topic_score_codex":0.0012950815,"about_ca_topic_score_gemma":0.0016982711,"teacher_disagreement_score":0.0012950815,"about_ca_system_score_codex":0.00020674925,"about_ca_system_score_gemma":0.00027684384,"threshold_uncertainty_score":0.0025750995},"labels":[],"label_agreement":null},{"id":"W1575415973","doi":"10.1186/1471-2105-7-502","title":"A correlated motif approach for finding short linear motifs from protein interaction networks","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National University of Singapore; Agency for Science, Technology and Research","keywords":"Motif (music); Sequence motif; Computational biology; Network motif; Structural motif; Protein–protein interaction; Computer science; Biology; DNA microarray; Binding site; Genetics; Biological network; Gene; Physics; Biochemistry","score_opus":0.016896112930759988,"score_gpt":0.23701226446665197,"score_spread":0.22011615153589198,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1575415973","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024101363,0.00045744222,0.9735999,0.00008421931,0.000014746418,0.000077233584,0.00048850436,0.0008061398,0.0003704685],"genre_scores_gemma":[0.22608992,0.00031329592,0.76910526,0.00014711176,0.000059654772,0.00030841166,0.0028974505,0.00015754231,0.0009213563],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99901366,0.00026109946,0.00007626988,0.0003438202,0.00022636239,0.0000787658],"domain_scores_gemma":[0.9978642,0.0010265063,0.0003711103,0.00026492696,0.00033790607,0.00013534617],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009843919,0.0010095282,0.0013050193,0.0032009096,0.0005588801,0.00076101866,0.0018033106,0.0012347996,0.001694792],"category_scores_gemma":[0.0041485894,0.00046160608,0.0011928458,0.003317874,0.00060313137,0.0013688542,0.0011402137,0.00123961,0.0009064828],"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":[0.00066318,0.00043766777,0.015418759,0.00068460696,0.00040471746,0.0006345101,0.00028892644,0.4136608,0.027904002,0.02116834,0.0069082743,0.51182634],"study_design_scores_gemma":[0.00001740259,0.00004662734,0.0005913874,0.000010489177,0.000016385668,0.0001476524,0.000027049788,0.9841458,0.0016371275,0.0124233505,0.0009249249,0.000011824617],"about_ca_topic_score_codex":0.0025303457,"about_ca_topic_score_gemma":0.004633114,"teacher_disagreement_score":0.0032009096,"about_ca_system_score_codex":0.0006203085,"about_ca_system_score_gemma":0.0011803207,"threshold_uncertainty_score":0.0056696534},"labels":[],"label_agreement":null},{"id":"W1579098064","doi":"10.1186/1471-2105-7-150","title":"Development of an unbiased statistical method for the analysis of unigenic evolution","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Evolution and Genetic Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Computational biology; Mutagenesis; Protein function; Identification (biology); Biology; Genetics; Function (biology); Selection (genetic algorithm); Mutation; Algorithm; Computer science; Statistics; Mathematics; Gene; Artificial intelligence","score_opus":0.01333470820897769,"score_gpt":0.2973163542991686,"score_spread":0.2839816460901909,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1579098064","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008802998,0.000023699318,0.9986241,0.000012466482,0.000009349206,0.000022368818,0.000034429824,0.00034690666,0.00004634944],"genre_scores_gemma":[0.017926002,0.000044169068,0.9807519,0.00004880387,0.000043312903,0.0003272014,0.00034912347,0.00025090986,0.00025864266],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99235356,0.0036846974,0.00035471178,0.0011002818,0.0022817445,0.00022510756],"domain_scores_gemma":[0.97502476,0.01761742,0.0012115338,0.0023230533,0.003486814,0.00033639808],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011561141,0.0010522386,0.001235705,0.003864786,0.0009866628,0.0013603509,0.0026229662,0.001307604,0.0023328841],"category_scores_gemma":[0.035661835,0.00070573605,0.0016582909,0.0026275783,0.0010947644,0.0013428394,0.0019008929,0.002801464,0.001391977],"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":[0.00027634166,0.00030173053,0.0141177485,0.00045744109,0.0010800142,0.00049123843,0.0004800452,0.14786406,0.040449824,0.09015964,0.006133606,0.69818836],"study_design_scores_gemma":[0.00004284977,0.000112744776,0.0033858595,0.000032950702,0.00007801815,0.00025452487,0.000029944045,0.9421654,0.009355615,0.03772376,0.0067425496,0.00007579843],"about_ca_topic_score_codex":0.0021378796,"about_ca_topic_score_gemma":0.0028701595,"teacher_disagreement_score":0.011561141,"about_ca_system_score_codex":0.000797553,"about_ca_system_score_gemma":0.002642242,"threshold_uncertainty_score":0.06114191},"labels":[],"label_agreement":null},{"id":"W1582408600","doi":"10.1186/1471-2105-16-s4-s3","title":"The relative vertex clustering value - a new criterion for the fast discovery of functional modules in protein interaction networks","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada; National Institute for Health and Care Research; Menzies Centre for Australian Studies, King's College London, University of London; Maudsley Charity","keywords":"Cluster analysis; Computer science; Hierarchical clustering; Data mining; Node (physics); Vertex (graph theory); Modular design; Similarity (geometry); Gene ontology; False positive paradox; Theoretical computer science; Computational biology; Artificial intelligence; Biology; Gene; Graph; Engineering","score_opus":0.027339656887565112,"score_gpt":0.2520429527433197,"score_spread":0.2247032958557546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1582408600","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08132721,0.0015013603,0.91173655,0.00031044448,0.00012696118,0.00028938748,0.0008277363,0.0013181225,0.0025622346],"genre_scores_gemma":[0.48817623,0.00045813547,0.50789124,0.0001098411,0.00013319704,0.000356575,0.0014258919,0.00026513758,0.0011837067],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99606967,0.0008159668,0.0003529639,0.0007501577,0.0017829188,0.00022832418],"domain_scores_gemma":[0.99143314,0.0040955604,0.001377339,0.0006089029,0.0021101902,0.0003747725],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003206399,0.0008993894,0.0012404001,0.008266089,0.0011046323,0.0021754764,0.002105038,0.0018218394,0.0014457082],"category_scores_gemma":[0.01471221,0.00032805715,0.0012132019,0.0038227218,0.0014830594,0.0021062614,0.0013581062,0.0011142456,0.0006957531],"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":[0.0012821787,0.00030652288,0.07130759,0.0015189244,0.0007747706,0.0007434728,0.0007993455,0.26593074,0.060939215,0.050907854,0.012973131,0.5325163],"study_design_scores_gemma":[0.00006405302,0.0003188866,0.013744938,0.00013403757,0.00013111751,0.001004747,0.0002136726,0.9207544,0.028368605,0.028813146,0.0063269236,0.00012540493],"about_ca_topic_score_codex":0.0020214578,"about_ca_topic_score_gemma":0.0017828167,"teacher_disagreement_score":0.008266089,"about_ca_system_score_codex":0.0016947187,"about_ca_system_score_gemma":0.0012481724,"threshold_uncertainty_score":0.016957283},"labels":[],"label_agreement":null},{"id":"W1583563537","doi":"10.1186/1471-2105-8-21","title":"GraphDNA: a Java program for graphical display of DNA composition analyses","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Fractal and DNA sequence analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"National Institute of Allergy and Infectious Diseases; Natural Sciences and Engineering Research Council of Canada; U.S. Public Health Service","keywords":"GenBank; Genome; DNA sequencing; DNA; Biology; Computational biology; Java; Computer science; Genetics; Programming language; Gene","score_opus":0.024989114800006554,"score_gpt":0.3339482154069852,"score_spread":0.3089591006069787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1583563537","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024376127,0.0003306672,0.47381142,0.00029529142,0.0002041026,0.00042789022,0.022146804,0.49692625,0.0034199143],"genre_scores_gemma":[0.021800838,0.0008563999,0.8323426,0.0006752115,0.00015232328,0.0025585964,0.03670576,0.093534745,0.011373486],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.998879,0.00018471981,0.00019524968,0.0002780255,0.00036850243,0.00009438211],"domain_scores_gemma":[0.99678767,0.0019031026,0.00034625203,0.00023036824,0.00048610804,0.00024644766],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022169065,0.0027519125,0.001922297,0.003444866,0.00066924875,0.001813677,0.003788505,0.0016051602,0.06484895],"category_scores_gemma":[0.005834988,0.0018280161,0.0015152285,0.0019598922,0.00062092574,0.0027778668,0.0022638235,0.0025852164,0.022836007],"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":[0.0019394964,0.00055431185,0.0040933467,0.0065149763,0.0007787923,0.0015863993,0.0010917147,0.0072017172,0.08240454,0.0110249575,0.42239583,0.46041396],"study_design_scores_gemma":[0.0014412856,0.0004097194,0.010145353,0.00094864256,0.00037969934,0.0027561155,0.00024198147,0.11892045,0.08570415,0.03294854,0.74540496,0.000699157],"about_ca_topic_score_codex":0.0015899627,"about_ca_topic_score_gemma":0.0018408044,"teacher_disagreement_score":0.06484895,"about_ca_system_score_codex":0.00062624103,"about_ca_system_score_gemma":0.0014892132,"threshold_uncertainty_score":0.21694136},"labels":[],"label_agreement":null},{"id":"W1585902742","doi":"10.1186/1471-2105-7-193","title":"An interactive tool for visualization of relationships between gene expression profiles","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","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":"Canada's Michael Smith Genome Sciences Centre; Genome British Columbia; Occupational Cancer Research Centre","funders":"Michael Smith Health Research BC; Genome British Columbia; Canada's Michael Smith Genome Sciences Centre; BC Cancer Foundation; Genome Canada","keywords":"DNA microarray; Visualization; Computational biology; Gene expression; Expression (computer science); Gene expression profiling; Biology; Gene; Computer science; Data science; Genetics; Data mining; Programming language","score_opus":0.030013852555015635,"score_gpt":0.3056036402523903,"score_spread":0.27558978769737463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1585902742","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0056316056,0.0006343842,0.7292474,0.0003730448,0.00017930305,0.00030345845,0.014423916,0.24483906,0.00436781],"genre_scores_gemma":[0.04490518,0.0009360316,0.8996816,0.00047553628,0.00011203019,0.001752314,0.02222519,0.02058332,0.009328872],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99934536,0.00016424926,0.00006141247,0.00011707643,0.00025084298,0.000060906546],"domain_scores_gemma":[0.9969613,0.0020605607,0.00012956552,0.00020172383,0.00041963984,0.00022719083],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015129016,0.0023670741,0.0013435667,0.003908362,0.000584536,0.0015281666,0.0021161826,0.0014995885,0.055547014],"category_scores_gemma":[0.004528318,0.00096626347,0.0011870543,0.0019117338,0.0003981072,0.0018880564,0.002140523,0.0021714196,0.012105208],"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":[0.0016382654,0.0004985164,0.0028645946,0.003053553,0.00032497264,0.0016613521,0.001480824,0.0062635993,0.13909169,0.009477395,0.31382224,0.5198229],"study_design_scores_gemma":[0.0011135613,0.00051177654,0.013077597,0.0009149744,0.0003968265,0.0044455924,0.00040393876,0.21703011,0.118279025,0.029061709,0.61411464,0.00065018533],"about_ca_topic_score_codex":0.0013420538,"about_ca_topic_score_gemma":0.0014052097,"teacher_disagreement_score":0.055547014,"about_ca_system_score_codex":0.00038100776,"about_ca_system_score_gemma":0.00067959836,"threshold_uncertainty_score":0.18582326},"labels":[],"label_agreement":null},{"id":"W1593404939","doi":"10.1186/1471-2105-5-37","title":"Structural characterization of genomes by large scale sequence-structure threading","year":2004,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Fractal and DNA sequence analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"Genome Prairie; Genome British Columbia; Michael Smith Health Research BC","keywords":"Threading (protein sequence); Proteome; Computational biology; Biology; Sequence motif; Genome; DNA microarray; Gene; Genetics; Protein structure; Gene expression; Biochemistry","score_opus":0.009893237619123097,"score_gpt":0.2328918501546392,"score_spread":0.22299861253551612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1593404939","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9597002,0.0003789994,0.038590346,0.000034404264,0.0000042232277,0.000025641972,0.00064861076,0.000283266,0.00033430825],"genre_scores_gemma":[0.95351994,0.00014570505,0.043532096,0.000009443158,0.000004993604,0.000038978138,0.002589997,0.0000546445,0.00010406865],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99969196,0.00007986878,0.000029430066,0.000100615354,0.000065773056,0.00003238172],"domain_scores_gemma":[0.99876994,0.00055327214,0.00027210498,0.00014821615,0.0001603837,0.000096153206],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008848251,0.00027303724,0.00036581227,0.0012107008,0.00027251526,0.00052616856,0.00030736366,0.0002323029,0.00078305847],"category_scores_gemma":[0.002734733,0.0001302234,0.0004891113,0.0011156533,0.0002446682,0.00075499393,0.0003465077,0.00033362117,0.00013734875],"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":[0.0011045891,0.0002999143,0.13521048,0.0010542385,0.00032414493,0.0003099287,0.0007914223,0.047077745,0.67716974,0.004040606,0.0005972215,0.13202],"study_design_scores_gemma":[0.00007227294,0.00086820056,0.205205,0.00005986988,0.00022866424,0.0011193057,0.00038233004,0.5516893,0.22478528,0.01062873,0.0048974636,0.00006360207],"about_ca_topic_score_codex":0.00051062915,"about_ca_topic_score_gemma":0.00050345145,"teacher_disagreement_score":0.0012107008,"about_ca_system_score_codex":0.0003002122,"about_ca_system_score_gemma":0.00025796486,"threshold_uncertainty_score":0.004679501},"labels":[],"label_agreement":null},{"id":"W1595684610","doi":"10.1186/1471-2105-5-61","title":"An approach to large scale identification of non-obvious structural similarities between proteins","year":2004,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","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":"BC Cancer Agency; University of British Columbia","funders":"Genome Prairie; Genome British Columbia; Michael Smith Health Research BC","keywords":"Threading (protein sequence); Computational biology; Biology; Genome; Sequence alignment; Genetics; Structural similarity; Peptide sequence; Protein structure; Sequence (biology); Protein sequencing; Gene; DNA microarray; Virulence; Gene expression","score_opus":0.009320389599279316,"score_gpt":0.26985422941676046,"score_spread":0.2605338398174811,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1595684610","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.046265036,0.00018398905,0.9502268,0.0000754154,0.000019158482,0.00010543599,0.00028822795,0.0023257453,0.0005102102],"genre_scores_gemma":[0.17780128,0.0000840091,0.82028306,0.000059997554,0.000015743994,0.00017610179,0.000870787,0.00014270558,0.0005663418],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99878484,0.00025279747,0.000103545644,0.00034578424,0.00044772794,0.000065290726],"domain_scores_gemma":[0.99802554,0.00077895075,0.00036311353,0.00032420657,0.00036940235,0.00013882491],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016104417,0.00065020367,0.00070498086,0.0018178248,0.00054055254,0.00093805656,0.0009170792,0.0006739865,0.0014648178],"category_scores_gemma":[0.0040199556,0.00036760463,0.00081583153,0.0016086019,0.00071466423,0.0010430253,0.0014390922,0.001197149,0.0006706975],"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":[0.0009321552,0.0004978744,0.010862934,0.00082247466,0.00031660407,0.0005587837,0.00036690934,0.025084581,0.5320612,0.012424845,0.0023813203,0.4136902],"study_design_scores_gemma":[0.00015320774,0.00060043065,0.0116188405,0.000060356553,0.00013778555,0.0021686822,0.00013981195,0.752207,0.18541397,0.036544967,0.010878908,0.000075992626],"about_ca_topic_score_codex":0.00043437327,"about_ca_topic_score_gemma":0.0006041621,"teacher_disagreement_score":0.0018178248,"about_ca_system_score_codex":0.0005620297,"about_ca_system_score_gemma":0.0008485876,"threshold_uncertainty_score":0.008516967},"labels":[],"label_agreement":null},{"id":"W1597403892","doi":"10.1186/1471-2105-7-497","title":"cPath: open source software for collecting, storing, and querying biological pathways","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":126,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Cancer Institute; Oregon Health and Science University; GlaxoSmithKline","keywords":"Computer science; SBML; Identifier; Software; Data exchange; World Wide Web; Visualization; Web service; Application programming interface; Database; XML; Data mining; Markup language","score_opus":0.03728236492655906,"score_gpt":0.25595017992542096,"score_spread":0.2186678149988619,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1597403892","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019821443,0.00029688716,0.36788112,0.0002844364,0.00017493613,0.0004429431,0.045468617,0.5788131,0.004655903],"genre_scores_gemma":[0.03373544,0.0018152882,0.5011503,0.000933398,0.00016865683,0.0039343555,0.33091876,0.11571483,0.0116289845],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970745,0.00031706571,0.0005118731,0.000692706,0.0012044274,0.00019939175],"domain_scores_gemma":[0.99482757,0.0017566732,0.00049838657,0.001252604,0.0012441339,0.0004204875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004571566,0.003253034,0.0014407515,0.0060639847,0.0016305315,0.00554676,0.007345812,0.002146373,0.034593176],"category_scores_gemma":[0.0099426415,0.0022191955,0.0026981735,0.0060609626,0.0011456988,0.005212082,0.0043983436,0.0043553356,0.030839752],"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":[0.0015091022,0.00033204997,0.0042975196,0.0047162506,0.00068194704,0.0012740593,0.0008524139,0.020809982,0.033267744,0.024438914,0.65196925,0.25585073],"study_design_scores_gemma":[0.00063615205,0.00019461742,0.0047454746,0.0007120568,0.0002683841,0.002008005,0.00033586173,0.15342785,0.079222895,0.05565738,0.7022725,0.00051886076],"about_ca_topic_score_codex":0.005596879,"about_ca_topic_score_gemma":0.00265901,"teacher_disagreement_score":0.034593176,"about_ca_system_score_codex":0.0014985579,"about_ca_system_score_gemma":0.0045511317,"threshold_uncertainty_score":0.11572564},"labels":[],"label_agreement":null},{"id":"W1600834905","doi":"10.1186/1471-2105-6-78","title":"CGMIM: Automated text-mining of Online Mendelian Inheritance in Man (OMIM) to identify genetically-associated cancers and candidate genes","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency","funders":"Michael Smith Health Research BC","keywords":"OMIM : Online Mendelian Inheritance in Man; CDKN2A; Cancer; Gene; Mendelian inheritance; Biology; Genetics; Candidate gene; Computational biology; Bioinformatics; Phenotype","score_opus":0.020657280603231,"score_gpt":0.3130826807367318,"score_spread":0.29242540013350077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1600834905","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14531863,0.002850515,0.34396848,0.0022535808,0.00044323003,0.003698173,0.293784,0.19814014,0.009543291],"genre_scores_gemma":[0.1022668,0.0010407532,0.6842239,0.00053873414,0.000263787,0.0022161992,0.20263533,0.004027626,0.0027869313],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979668,0.0005103051,0.00039794104,0.0007026901,0.00034138543,0.00008072059],"domain_scores_gemma":[0.9878312,0.0080949385,0.0018104934,0.0009933438,0.00089129416,0.00037873967],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044888128,0.001851922,0.0012394015,0.011970907,0.0008136193,0.001680872,0.0017755734,0.00094957656,0.012144503],"category_scores_gemma":[0.018004075,0.0006044346,0.0016459423,0.006036262,0.00044287406,0.001436278,0.0018481867,0.000754341,0.004495848],"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":[0.0028491386,0.00070495374,0.09342497,0.0055010845,0.0015346216,0.004517383,0.0023662215,0.008360124,0.033807572,0.0065141413,0.22918841,0.6112314],"study_design_scores_gemma":[0.0019594196,0.0013168658,0.19202846,0.0017670087,0.0019318786,0.011334677,0.0018974029,0.34182325,0.07702866,0.039318893,0.3291217,0.00047174725],"about_ca_topic_score_codex":0.0026298524,"about_ca_topic_score_gemma":0.0043395255,"teacher_disagreement_score":0.012144503,"about_ca_system_score_codex":0.00086336344,"about_ca_system_score_gemma":0.0020665575,"threshold_uncertainty_score":0.04062742},"labels":[],"label_agreement":null},{"id":"W1602695191","doi":"10.1186/s12859-015-0633-x","title":"PredSTP: a highly accurate SVM based model to predict sequential cystine stabilized peptides","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Antimicrobial Peptides and Activities","field":"Immunology and Microbiology","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Baylor University","keywords":"Computational biology; Peptide; Leverage (statistics); Support vector machine; Computer science; Combinatorial chemistry; Biological system; Chemistry; Bioinformatics; Biology; Biochemistry; Artificial intelligence","score_opus":0.05321804551242116,"score_gpt":0.26556696284134373,"score_spread":0.21234891732892258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1602695191","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43557903,0.0020322406,0.5457723,0.00091186294,0.00027641922,0.00035743992,0.0030975365,0.008674619,0.0032984854],"genre_scores_gemma":[0.88679004,0.00030044638,0.10570142,0.00028730236,0.000058239573,0.0003160073,0.0037244903,0.00011556339,0.0027065922],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996799,0.00006628863,0.000031405783,0.0001003778,0.000074658084,0.000047416383],"domain_scores_gemma":[0.99904615,0.00054624275,0.000070237045,0.000033602573,0.00026101008,0.00004264893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010188542,0.0012145772,0.000849015,0.00074425165,0.000299441,0.0006683529,0.0011917191,0.0010774703,0.0018868274],"category_scores_gemma":[0.0015931171,0.00033670652,0.0008014082,0.00039070813,0.0001983725,0.0006179205,0.0004712074,0.0011746091,0.0006779178],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006583931,0.00041981164,0.012866724,0.00018098266,0.00019526127,0.00019824618,0.00004417286,0.7839208,0.010793574,0.00053863,0.006301647,0.18388174],"study_design_scores_gemma":[0.000004885046,0.000042203737,0.00028929336,0.0000028835461,0.0000056770677,0.000012373879,0.0000029289445,0.9987507,0.0006529802,0.00009901412,0.0001343252,0.0000027200813],"about_ca_topic_score_codex":0.006492451,"about_ca_topic_score_gemma":0.004185838,"teacher_disagreement_score":0.006492451,"about_ca_system_score_codex":0.00068384444,"about_ca_system_score_gemma":0.0010249849,"threshold_uncertainty_score":0.012909293},"labels":[],"label_agreement":null},{"id":"W1605701032","doi":"10.1186/1471-2105-6-274","title":"A stepwise framework for the normalization of array CGH data","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomic variations and chromosomal abnormalities","field":"Biochemistry, Genetics and Molecular Biology","cited_by":93,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Centre for Applied Research in Cancer Control; University of British Columbia","funders":"National Institute of Dental and Craniofacial Research; Genome British Columbia; Genome Canada","keywords":"Normalization (sociology); DNA microarray; Comparative genomic hybridization; Biology; Copy-number variation; Computational biology; Microarray; Genetics; Computer science; Pattern recognition (psychology); Chromosome; Gene; Artificial intelligence; Gene expression; Genome","score_opus":0.03866257181589215,"score_gpt":0.2817151930408506,"score_spread":0.2430526212249584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1605701032","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00082575117,0.00005280364,0.9984724,0.000026224816,0.000010858648,0.000046163714,0.0000450571,0.00040156508,0.00011901583],"genre_scores_gemma":[0.018816993,0.00015902313,0.9795217,0.00006686289,0.000027709364,0.00042119858,0.00034019534,0.00019778898,0.0004486546],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98946476,0.0037921462,0.0006599894,0.0020035512,0.0037179112,0.00036169868],"domain_scores_gemma":[0.99077004,0.0038944161,0.0007849753,0.0017120871,0.0026672583,0.00017127916],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012090152,0.0021732822,0.001438284,0.0025235454,0.0008979936,0.0023316038,0.004142178,0.0011536205,0.0015144013],"category_scores_gemma":[0.016748002,0.0011064274,0.0028458633,0.0026312447,0.0023654588,0.0017721705,0.0030828773,0.0027887472,0.0014635086],"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":[0.00043147072,0.0002877183,0.0049672914,0.0009904235,0.0006897049,0.00065223145,0.0009245366,0.23785095,0.19663255,0.12714295,0.0032902097,0.4261399],"study_design_scores_gemma":[0.00005176318,0.0005164965,0.0033747642,0.00010654979,0.00022597762,0.0005686814,0.000104895094,0.79191226,0.09399843,0.09038771,0.018515458,0.00023693907],"about_ca_topic_score_codex":0.0043721832,"about_ca_topic_score_gemma":0.006781136,"teacher_disagreement_score":0.012090152,"about_ca_system_score_codex":0.0016336272,"about_ca_system_score_gemma":0.0039406517,"threshold_uncertainty_score":0.06393957},"labels":[],"label_agreement":null},{"id":"W1606410455","doi":"10.1186/1471-2105-7-301","title":"Improving the accuracy of protein secondary structure prediction using structural alignment","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":148,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Genome Prairie; Genome Canada","keywords":"Sequence (biology); Protein secondary structure; Computer science; Structural genomics; Protein structure database; Set (abstract data type); Alignment-free sequence analysis; Structural alignment; Sequence alignment; Protein structure prediction; Multiple sequence alignment; Data mining; Protein structure; Test set; Computational biology; Artificial intelligence; Sequence database; Peptide sequence; Biology; Genetics","score_opus":0.006201983545477943,"score_gpt":0.21759728903657752,"score_spread":0.21139530549109958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1606410455","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48824576,0.0024271575,0.49405038,0.000706737,0.00015677334,0.0001361547,0.0006860989,0.008957074,0.0046338933],"genre_scores_gemma":[0.8010172,0.00041496122,0.19567738,0.00012871705,0.000083231134,0.000047093767,0.0014014809,0.00023926224,0.0009905589],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99539053,0.0013070097,0.00030178562,0.00086349604,0.0019304216,0.00020670354],"domain_scores_gemma":[0.9809348,0.01124208,0.0015899381,0.0014479635,0.004437894,0.000347332],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007127223,0.00097275886,0.00091854925,0.0024465583,0.00058204366,0.0011885081,0.0012265636,0.0012255926,0.0014698908],"category_scores_gemma":[0.01929488,0.00035722478,0.00068802683,0.0011666246,0.0005061759,0.0013954113,0.0009944987,0.0010732879,0.001841324],"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":[0.0017527246,0.00048223356,0.15676168,0.0006162596,0.00055229216,0.0003591362,0.00036136364,0.1310618,0.1407195,0.0014806001,0.0087590115,0.55709344],"study_design_scores_gemma":[0.00007301469,0.00031078543,0.026245227,0.00006479159,0.00011725989,0.000386394,0.00008198919,0.8572997,0.10938689,0.0020973375,0.0038790298,0.000057618643],"about_ca_topic_score_codex":0.002370775,"about_ca_topic_score_gemma":0.0020227712,"teacher_disagreement_score":0.007127223,"about_ca_system_score_codex":0.0006716832,"about_ca_system_score_gemma":0.0008884473,"threshold_uncertainty_score":0.037692845},"labels":[],"label_agreement":null},{"id":"W1608637158","doi":"10.1186/s12859-015-0584-2","title":"Probing long-range interactions by extracting free energies from genome-wide chromosome conformation capture data","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Chromosome conformation capture; Chromatin; Pairwise comparison; Normalization (sociology); Genome; Biological system; Principal component analysis; Computational biology; Distance matrix; Biology; DNA; Physics; Computer science; Genetics; Algorithm; Artificial intelligence; Transcription factor; Gene","score_opus":0.028626476542384725,"score_gpt":0.24887909791723126,"score_spread":0.22025262137484652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1608637158","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60023147,0.0008746697,0.3879415,0.00024981797,0.000032422635,0.00012224418,0.006240535,0.0022849883,0.00202237],"genre_scores_gemma":[0.84906685,0.0005072968,0.13806055,0.000091713766,0.000030405536,0.00019621267,0.011025875,0.00032350988,0.00069762144],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99935704,0.00015351664,0.000035030476,0.0001806143,0.00022440671,0.00004931221],"domain_scores_gemma":[0.9973781,0.0015503214,0.0004262894,0.0003157761,0.00025168157,0.00007783901],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011373141,0.0010079358,0.0004968835,0.002849163,0.00043722353,0.00073849474,0.00071723474,0.00082369574,0.0012060842],"category_scores_gemma":[0.0035607931,0.00032440491,0.0009167975,0.0029207657,0.00037901493,0.000536261,0.0006009392,0.0011770979,0.00065886223],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005505985,0.0005399517,0.15345696,0.0012888657,0.0016791745,0.00054005574,0.0004464009,0.3956248,0.2648199,0.006217969,0.003751507,0.17108384],"study_design_scores_gemma":[0.000026021087,0.00016479431,0.1987013,0.000056087054,0.00023943931,0.00056414853,0.00015247801,0.7383919,0.048140835,0.009064505,0.0043157507,0.00018273314],"about_ca_topic_score_codex":0.004003298,"about_ca_topic_score_gemma":0.0061352416,"teacher_disagreement_score":0.004003298,"about_ca_system_score_codex":0.00051123794,"about_ca_system_score_gemma":0.0004704193,"threshold_uncertainty_score":0.007959962},"labels":[],"label_agreement":null},{"id":"W1615242748","doi":"10.1186/1471-2105-6-236","title":"SIMPROT: Using an empirically determined indel distribution in simulations of protein evolution","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; University of Toronto; Ontario Institute for Cancer Research","funders":"Canadian Institutes of Health Research; Genome Canada","keywords":"Indel; Alignment-free sequence analysis; Multiple sequence alignment; Sequence (biology); Phylogenetic tree; INDEL Mutation; Sequence alignment; Sequence analysis; Computational biology; Biology; Genetics; Molecular evolution; Protein family; Computer science; Algorithm; Peptide sequence; Gene","score_opus":0.02861468696996599,"score_gpt":0.28027649220881806,"score_spread":0.25166180523885207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1615242748","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3511471,0.00032334344,0.62507045,0.00052440516,0.00014141956,0.00027405436,0.0020583991,0.01392209,0.006538785],"genre_scores_gemma":[0.64432657,0.00020314491,0.35064417,0.00018968734,0.000035467318,0.00067073415,0.0015054316,0.0016114706,0.0008132565],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99910164,0.00051799964,0.00004250058,0.00012053176,0.00015330626,0.00006401961],"domain_scores_gemma":[0.9935336,0.005036877,0.0003059385,0.000449392,0.0004443172,0.00022996463],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032748934,0.0007293396,0.0007903606,0.0008938969,0.0010502648,0.0008578639,0.0020957103,0.0016530465,0.0031618583],"category_scores_gemma":[0.009755727,0.0006991669,0.0005777662,0.001028131,0.00092615705,0.0013025128,0.00077459234,0.0013242825,0.0005297521],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041809515,0.00013121653,0.00627848,0.00017021409,0.000093029324,0.0002754071,0.00019662087,0.9591662,0.0038063386,0.013393994,0.0032239791,0.012846444],"study_design_scores_gemma":[0.000046645422,0.000026632997,0.00024631954,0.0000069503494,0.000006667501,0.000041869152,0.000012236004,0.9944906,0.0013480515,0.0030407023,0.0007227259,0.000010601667],"about_ca_topic_score_codex":0.004437762,"about_ca_topic_score_gemma":0.0039646686,"teacher_disagreement_score":0.004437762,"about_ca_system_score_codex":0.0011649983,"about_ca_system_score_gemma":0.0010222747,"threshold_uncertainty_score":0.01731944},"labels":[],"label_agreement":null},{"id":"W1619065037","doi":"10.1186/1471-2105-16-s14-s4","title":"Reconstructing a SuperGeneTree minimizing reconciliation","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Université de Montréal","funders":"","keywords":"Supertree; Phylogenetic tree; Tree (set theory); Tree rearrangement; Set (abstract data type); Heuristic; Computer science; Computational phylogenetics; Algorithm; Theoretical computer science; Mathematics; Phylogenetic network; Combinatorics; Biology; Artificial intelligence; Gene; Genetics","score_opus":0.051889195989607555,"score_gpt":0.24952029348179056,"score_spread":0.197631097492183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1619065037","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14016922,0.0007467009,0.85311526,0.00094233995,0.00004563131,0.00016973955,0.000978509,0.00082441675,0.0030081605],"genre_scores_gemma":[0.24100219,0.000401636,0.7525486,0.00028923224,0.000050777162,0.00022888141,0.0033926533,0.00037069686,0.0017152934],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99862576,0.00043693944,0.000071619594,0.0004385822,0.000279453,0.00014761458],"domain_scores_gemma":[0.9940445,0.003813015,0.00048690272,0.0010287362,0.00042297173,0.00020392613],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022526304,0.00090310595,0.0017189542,0.0016070642,0.0010361592,0.001455505,0.0025025203,0.0020750358,0.0031428481],"category_scores_gemma":[0.0101890005,0.0008689206,0.0014628767,0.0025531931,0.0013370431,0.004016917,0.0024306793,0.0019395836,0.0008328465],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038119705,0.00017655754,0.005769096,0.00080296537,0.00014063969,0.00052597665,0.00081170554,0.6524811,0.013232043,0.08947318,0.010127806,0.2260778],"study_design_scores_gemma":[0.00003442088,0.00007863411,0.0010576061,0.000046063913,0.00004062824,0.00031966646,0.0002873239,0.8466185,0.0038791613,0.14382061,0.00379256,0.000024917465],"about_ca_topic_score_codex":0.0014905987,"about_ca_topic_score_gemma":0.0031596979,"teacher_disagreement_score":0.0031428481,"about_ca_system_score_codex":0.0013622184,"about_ca_system_score_gemma":0.0017122305,"threshold_uncertainty_score":0.01191318},"labels":[],"label_agreement":null},{"id":"W1640378004","doi":"10.1186/1471-2105-6-30","title":"An ant colony optimisation algorithm for the 2D and 3D hydrophobic polar protein folding problem","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":261,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Protein folding; Polar; Protein structure prediction; Computer science; Folding (DSP implementation); Ant colony optimization algorithms; Ant colony; Computational biology; DNA microarray; Algorithm; Chemistry; Artificial intelligence; Protein structure; Biology; Engineering; Biochemistry; Physics; Gene","score_opus":0.007372782569299728,"score_gpt":0.23658003288229887,"score_spread":0.22920725031299913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1640378004","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04055007,0.0004527789,0.9502529,0.000469533,0.00008284332,0.00015223246,0.00011168814,0.0005009517,0.00742705],"genre_scores_gemma":[0.4038884,0.00026930126,0.58973116,0.00027297923,0.0000541308,0.0004752822,0.00031290328,0.00014767218,0.004848193],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99961925,0.00013394635,0.000020967684,0.00008115336,0.000098418335,0.000046168097],"domain_scores_gemma":[0.99898607,0.00066315854,0.00009319959,0.000049068676,0.00014844161,0.000060026643],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006671686,0.00087128015,0.0009103531,0.00053271145,0.0005203558,0.0006180616,0.0012745619,0.0013266957,0.0025036098],"category_scores_gemma":[0.0019775142,0.00034258925,0.00065643317,0.00066636724,0.000680771,0.0005818421,0.0010382106,0.000986574,0.0004110975],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035946796,0.000029477691,0.00043409163,0.000048297028,0.000018909166,0.00006425773,0.000039436105,0.97019356,0.0007288823,0.003406435,0.0010440464,0.02395654],"study_design_scores_gemma":[0.000010517125,0.000009776551,0.000036921418,0.0000022919048,0.0000026811726,0.000012455532,0.0000043122573,0.9985341,0.000087042514,0.0009799356,0.00031807844,0.0000018570504],"about_ca_topic_score_codex":0.0063164625,"about_ca_topic_score_gemma":0.0048687365,"teacher_disagreement_score":0.0063164625,"about_ca_system_score_codex":0.0006533007,"about_ca_system_score_gemma":0.0011931588,"threshold_uncertainty_score":0.012559354},"labels":[],"label_agreement":null},{"id":"W1649804825","doi":"10.1186/1471-2105-7-523","title":"BioMoby extensions to the Taverna workflow management and enactment software","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":70,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Paul's Hospital; University of British Columbia","funders":"Engineering and Physical Sciences Research Council; Natural Sciences and Engineering Research Council of Canada; Genome Alberta; Genome Canada","keywords":"Workflow; Computer science; Interoperability; Web service; World Wide Web; Workflow management system; Software; Software engineering; Plug-in; Service (business); Data science; Database; Programming language","score_opus":0.06956754340785506,"score_gpt":0.3193051713387781,"score_spread":0.24973762793092305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1649804825","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005458352,0.0003733379,0.5732825,0.0011345196,0.00023717112,0.00062257465,0.004687485,0.4020002,0.0122039085],"genre_scores_gemma":[0.043537725,0.0009163905,0.8167881,0.0015439829,0.00017192758,0.002278611,0.030843355,0.085363455,0.018556442],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9948531,0.0011602752,0.0010238641,0.0010329548,0.0013381753,0.0005915953],"domain_scores_gemma":[0.987823,0.00314778,0.0011053373,0.004833644,0.0022669905,0.0008232183],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011425026,0.0018654995,0.0014721812,0.0024997746,0.0017935837,0.006527711,0.005262375,0.0024958383,0.022735603],"category_scores_gemma":[0.01849836,0.0031168924,0.005026503,0.0016631142,0.0019272922,0.0068613566,0.009498557,0.005183719,0.02362679],"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":[0.0046084533,0.0009407559,0.012848385,0.003941049,0.0009670947,0.0020482915,0.008213742,0.035354197,0.046795513,0.22563604,0.37931365,0.27933276],"study_design_scores_gemma":[0.0004588296,0.00012771702,0.0022822882,0.00050360576,0.00012819671,0.0006921715,0.0002451326,0.08320232,0.021083798,0.033802453,0.85713035,0.0003432304],"about_ca_topic_score_codex":0.01304136,"about_ca_topic_score_gemma":0.008756751,"teacher_disagreement_score":0.022735603,"about_ca_system_score_codex":0.0030106052,"about_ca_system_score_gemma":0.006198072,"threshold_uncertainty_score":0.07605815},"labels":[],"label_agreement":null},{"id":"W1659685982","doi":"10.1186/1471-2105-16-s11-s1","title":"Highlights from the 5th Symposium on Biological Data Visualization: Part 1","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"","keywords":"Visualization; Data science; Computer science; Data visualization; Process (computing); Creative visualization; Soundness; Data mining","score_opus":0.10683240757574981,"score_gpt":0.2995042047459029,"score_spread":0.1926717971701531,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1659685982","genre_codex":"editorial","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00079230015,0.07335405,0.0053720567,0.11618322,0.7858947,0.0006007794,0.000712806,0.00045302676,0.016637024],"genre_scores_gemma":[0.008266631,0.14292635,0.007912413,0.052111868,0.6776469,0.0013295792,0.0031458836,0.0012652915,0.10539517],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98300445,0.0034297951,0.0018126891,0.001677547,0.008883083,0.0011924137],"domain_scores_gemma":[0.9223691,0.0069008395,0.0033869692,0.0016348991,0.052377712,0.013330455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021013135,0.002579752,0.0019161536,0.007013499,0.002890639,0.013478513,0.0037967146,0.007159693,0.03804614],"category_scores_gemma":[0.03392306,0.0010232369,0.0034437173,0.0036291971,0.0017189139,0.006092784,0.005778066,0.009079025,0.026167445],"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":[0.00008170912,0.00003501743,0.00018435733,0.001541025,0.000037276463,0.00015500624,0.00018757634,0.000080930105,0.00090361293,0.001081618,0.9460265,0.049685337],"study_design_scores_gemma":[0.0000130625285,0.00006095244,0.00039645078,0.0010781008,0.00003183709,0.00019394027,0.0001364306,0.00006392544,0.00038414975,0.0010776474,0.99653375,0.000029762332],"about_ca_topic_score_codex":0.0019676914,"about_ca_topic_score_gemma":0.004382135,"teacher_disagreement_score":0.03804614,"about_ca_system_score_codex":0.0044886637,"about_ca_system_score_gemma":0.011747086,"threshold_uncertainty_score":0.12727708},"labels":[],"label_agreement":null},{"id":"W1689468366","doi":"10.1186/1471-2105-6-6","title":"Cyclic nucleotide binding proteins in the Arabidopsis thaliana and Oryza sativa genomes","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Kinase Regulation and GTPase Signaling","field":"Biochemistry, Genetics and Molecular Biology","cited_by":90,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; University of Lethbridge","funders":"Natural Sciences and Engineering Research Council of Canada; Fondation pour la Recherche Médicale","keywords":"Oryza sativa; Nucleotide; Biology; Arabidopsis thaliana; Arabidopsis; Cyclic nucleotide; Effector; Protein kinase A; Genome; Second messenger system; Cyclic nucleotide-binding domain; Oryza; Genetics; Biochemistry; Cell biology; Kinase; Signal transduction; Gene; Mutant","score_opus":0.017012467508508936,"score_gpt":0.24554592737879735,"score_spread":0.22853345987028842,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1689468366","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9290426,0.004585027,0.0043547517,0.0006253568,0.000031171057,0.00005122646,0.057291858,0.00077426736,0.003243773],"genre_scores_gemma":[0.7907126,0.0028616672,0.032554902,0.00031893165,0.000035022196,0.00011099133,0.17096463,0.00020916946,0.0022320529],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999027,0.000008314213,0.0000060043085,0.000050111954,0.000016845508,0.000016026905],"domain_scores_gemma":[0.9997644,0.000087537934,0.00006979318,0.000015548301,0.000029099403,0.000033629618],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020528604,0.00027994768,0.00025744297,0.0009811008,0.00032069703,0.00027522008,0.000316836,0.00031148354,0.0026398166],"category_scores_gemma":[0.00053675123,0.00012650678,0.00033547834,0.0013910811,0.00012015045,0.00023443336,0.00027887945,0.00028821902,0.0004856754],"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":[0.004136743,0.00013277003,0.05729632,0.0028800843,0.00043716887,0.0014524027,0.0018925513,0.00593939,0.7462265,0.007812529,0.012389653,0.15940386],"study_design_scores_gemma":[0.0004251452,0.00031089457,0.7896593,0.00028496634,0.00082677987,0.0019928017,0.0008077962,0.012156952,0.03410241,0.006393416,0.15294716,0.00009230615],"about_ca_topic_score_codex":0.006222675,"about_ca_topic_score_gemma":0.008155065,"teacher_disagreement_score":0.006222675,"about_ca_system_score_codex":0.0008416197,"about_ca_system_score_gemma":0.0007110809,"threshold_uncertainty_score":0.012372911},"labels":[],"label_agreement":null},{"id":"W1691146018","doi":"10.1186/1471-2105-7-305","title":"Taking U out, with two nucleases?","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA regulation and disease","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Institute of Allergy and Infectious Diseases; National Institute on Aging; National Institutes of Health; U.S. Department of Energy","keywords":"Trypanosoma brucei; Biology; Computational biology; Subfamily; RNA editing; RNA; Function (biology); Genetics; Protein domain; Gene","score_opus":0.011830757204466818,"score_gpt":0.2450078684551008,"score_spread":0.23317711125063398,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1691146018","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21634383,0.013359661,0.47896525,0.022999825,0.006342088,0.0006200806,0.0013152395,0.007430373,0.25262368],"genre_scores_gemma":[0.57382995,0.0026908359,0.32907897,0.00581383,0.0004099149,0.0003031128,0.0010121862,0.00062920875,0.086231954],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984742,0.00032558638,0.000096305776,0.00055274676,0.00029948665,0.00025166976],"domain_scores_gemma":[0.99854064,0.0005953898,0.00016841992,0.00031820798,0.00017477613,0.00020255716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020756044,0.00077169464,0.0009110147,0.00045058117,0.0013050274,0.0027689585,0.0011253961,0.0022565243,0.030263597],"category_scores_gemma":[0.0049469834,0.0003350162,0.0010391135,0.00053642615,0.001887545,0.0036375504,0.0019044462,0.0014019061,0.008245587],"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":[0.0024024772,0.00048257178,0.016853688,0.0011618972,0.00019789526,0.0037607164,0.002460242,0.004220335,0.073999986,0.38139734,0.035903126,0.4771597],"study_design_scores_gemma":[0.00028419442,0.0009138813,0.0029016843,0.00029110955,0.00021681385,0.010159205,0.002761573,0.01791433,0.11039963,0.2726027,0.58131266,0.0002422064],"about_ca_topic_score_codex":0.0006823702,"about_ca_topic_score_gemma":0.0006324367,"teacher_disagreement_score":0.030263597,"about_ca_system_score_codex":0.0007565673,"about_ca_system_score_gemma":0.0011433068,"threshold_uncertainty_score":0.10124183},"labels":[],"label_agreement":null},{"id":"W1755797074","doi":"10.1186/s12859-015-0581-5","title":"GENLIB: an R package for the analysis of genealogical data","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa; Université du Québec à Chicoutimi; Université de Montréal; Centre Hospitalier Universitaire Sainte-Justine","funders":"Canadian Institutes of Health Research","keywords":"Pedigree chart; Kinship; Population; Inbreeding; Genealogy; Sample (material); R package; Software; Computer science; Flexibility (engineering); Genetic genealogy; Selection (genetic algorithm); Data science; Biology; Genetics; Demography; Artificial intelligence; Statistics; Mathematics","score_opus":0.15548907319973773,"score_gpt":0.3560723914392484,"score_spread":0.20058331823951067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1755797074","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00536662,0.0026128876,0.2977745,0.0014441976,0.00073259143,0.0005322894,0.3395265,0.3439354,0.008075058],"genre_scores_gemma":[0.039962087,0.0019198642,0.44042298,0.0022135656,0.00039399814,0.0045530135,0.23973607,0.2614031,0.009395228],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99623233,0.0014723097,0.00036239438,0.00083400053,0.0008160343,0.0002829928],"domain_scores_gemma":[0.98079485,0.013457779,0.0014448487,0.0020195602,0.0017815189,0.0005013995],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0060392725,0.0034718039,0.0032827302,0.0037319863,0.00092542364,0.004130948,0.0060183876,0.0012705432,0.09763578],"category_scores_gemma":[0.035630465,0.0020129776,0.0029510004,0.004585681,0.0014876209,0.002749491,0.0033649092,0.0036472168,0.05756155],"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":[0.00046531725,0.000050077128,0.0076481677,0.003800519,0.0015325174,0.00060269557,0.00045991872,0.010735422,0.0018831507,0.013184693,0.89313626,0.06650129],"study_design_scores_gemma":[0.00069875165,0.00012117601,0.010998119,0.0011158899,0.00079032057,0.0011129396,0.00018107869,0.047002804,0.0051078177,0.06075918,0.8717883,0.00032370075],"about_ca_topic_score_codex":0.013070742,"about_ca_topic_score_gemma":0.013440141,"teacher_disagreement_score":0.09763578,"about_ca_system_score_codex":0.0014512505,"about_ca_system_score_gemma":0.0059072226,"threshold_uncertainty_score":0.3266242},"labels":[],"label_agreement":null},{"id":"W1756130223","doi":"10.1186/1471-2105-4-63","title":"AnaBench: a Web/CORBA-based workbench for biomolecular sequence analysis","year":2003,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Montréal; Canadian Institute for Advanced Research","funders":"Canadian Institutes of Health Research","keywords":"Workbench; Computer science; Java; Common Object Request Broker Architecture; Software engineering; Software; Middleware (distributed applications); Data management; World Wide Web; Identification (biology); Flexibility (engineering); Protocol (science); Database; Data science; Operating system; Data mining; Visualization","score_opus":0.028738048256720827,"score_gpt":0.26600156579285333,"score_spread":0.2372635175361325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1756130223","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0042638322,0.00074159045,0.8083281,0.0002756185,0.00028665914,0.0010217506,0.014303238,0.16356388,0.0072153364],"genre_scores_gemma":[0.014426434,0.001016952,0.9018307,0.00043327553,0.0001448534,0.0034519846,0.0505543,0.022101315,0.0060401573],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972063,0.0004569944,0.0004233957,0.0005289406,0.0010719104,0.00031244184],"domain_scores_gemma":[0.9953584,0.0013742927,0.0005943637,0.0009906115,0.0011533794,0.0005289805],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040916163,0.004032704,0.0016541557,0.0040613967,0.0019141766,0.003807557,0.005145329,0.0013874321,0.020393306],"category_scores_gemma":[0.005968069,0.0014645068,0.0021833938,0.0029891746,0.0010753543,0.002098752,0.0018627085,0.0036083127,0.03006426],"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":[0.0020318269,0.0008727206,0.004106821,0.00481949,0.00054047094,0.0013568765,0.0013735768,0.01863471,0.31948707,0.025300799,0.21431215,0.40716338],"study_design_scores_gemma":[0.00050833094,0.00043138769,0.0024486834,0.0007213538,0.00018849662,0.0012918646,0.00024376369,0.063208625,0.20916755,0.020454112,0.700927,0.00040884645],"about_ca_topic_score_codex":0.0037135738,"about_ca_topic_score_gemma":0.0025528143,"teacher_disagreement_score":0.020393306,"about_ca_system_score_codex":0.0013252117,"about_ca_system_score_gemma":0.004115765,"threshold_uncertainty_score":0.0682224},"labels":[],"label_agreement":null},{"id":"W1758070551","doi":"10.1186/1471-2105-7-152","title":"Domain-based small molecule binding site annotation","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Sinai Hospital; Carleton University","funders":"Genome Canada","keywords":"Computational biology; Annotation; DNA microarray; Domain (mathematical analysis); Computer science; Biology; Genetics; Gene; Mathematics; Gene expression","score_opus":0.02041210304383086,"score_gpt":0.253512328128054,"score_spread":0.23310022508422315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1758070551","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13966276,0.0102843195,0.39985716,0.00080803665,0.00049358036,0.0014656556,0.3422702,0.0535461,0.05161232],"genre_scores_gemma":[0.18704629,0.0033924156,0.3635535,0.00050445716,0.000080784914,0.0009513476,0.42986137,0.0020773774,0.0125325145],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999539,0.00004298401,0.00006447873,0.00009627966,0.0001900313,0.000067185385],"domain_scores_gemma":[0.99893504,0.00025494344,0.00017586678,0.00017893243,0.00035674637,0.00009841599],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005897147,0.000918362,0.0007887765,0.0027906136,0.0007184884,0.0008690465,0.0011547492,0.00071876677,0.02932978],"category_scores_gemma":[0.0018186123,0.00026349243,0.0008632874,0.0027098195,0.0002207364,0.0008633117,0.00082827924,0.0009266359,0.019738287],"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":[0.0027584545,0.00040482185,0.024092903,0.008151185,0.00016025885,0.0023863215,0.00040479677,0.01245488,0.336717,0.014499227,0.15504228,0.44292787],"study_design_scores_gemma":[0.00014898508,0.00026866287,0.019956889,0.0006127339,0.00017066147,0.0036334957,0.00018433646,0.043849606,0.16672657,0.008169769,0.75612235,0.00015594708],"about_ca_topic_score_codex":0.0019279959,"about_ca_topic_score_gemma":0.0020324849,"teacher_disagreement_score":0.02932978,"about_ca_system_score_codex":0.00057702133,"about_ca_system_score_gemma":0.0011997443,"threshold_uncertainty_score":0.09811789},"labels":[],"label_agreement":null},{"id":"W1759632117","doi":"10.1186/1471-2105-5-24","title":"Biochemical Network Stochastic Simulator (BioNetS): software for stochastic modeling of biochemical networks","year":2004,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":150,"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":"Defense Advanced Research Projects Agency; Alfred P. Sloan Foundation","keywords":"Computer science; Software; Stochastic modelling; Simulation; Programming language; Mathematics; Statistics","score_opus":0.014494119066310335,"score_gpt":0.2385294678884628,"score_spread":0.22403534882215245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1759632117","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0110107595,0.00038472452,0.9300786,0.00031985278,0.00015913854,0.00018339945,0.007042371,0.04341148,0.00740964],"genre_scores_gemma":[0.19406992,0.0020421327,0.75156087,0.0005316566,0.00013590706,0.0026375987,0.02221916,0.014499971,0.012302766],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995765,0.000117831114,0.000047093017,0.000064902764,0.00015779443,0.000035975307],"domain_scores_gemma":[0.99848574,0.00087578857,0.00014050279,0.00014870752,0.00025561036,0.000093780254],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011306426,0.0012302638,0.00090025965,0.00075743475,0.0005132532,0.0009118228,0.0023894613,0.0015588773,0.014629115],"category_scores_gemma":[0.0036480487,0.0009626082,0.0012835102,0.00074369117,0.00056629465,0.0014645437,0.0012169228,0.0019932229,0.003818016],"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":[0.000109935325,0.00008915698,0.002105997,0.00066025264,0.00014232252,0.00018708924,0.0001586032,0.8875412,0.006451505,0.04544745,0.030233119,0.026873415],"study_design_scores_gemma":[0.0000458064,0.00001301724,0.00014833294,0.000024734936,0.00001178465,0.000051956755,0.0000067207775,0.9736805,0.0018930394,0.008227409,0.01587951,0.000017189592],"about_ca_topic_score_codex":0.0059832023,"about_ca_topic_score_gemma":0.0056944243,"teacher_disagreement_score":0.014629115,"about_ca_system_score_codex":0.00095138326,"about_ca_system_score_gemma":0.002272828,"threshold_uncertainty_score":0.048939288},"labels":[],"label_agreement":null},{"id":"W1775447850","doi":"10.1186/1471-2105-7-471","title":"The accuracy of several multiple sequence alignment programs for proteins","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":170,"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; University of Toronto; Ontario Institute for Cancer Research","funders":"Canadian Institutes of Health Research","keywords":"Multiple sequence alignment; Alignment-free sequence analysis; Indel; Sequence alignment; Computer science; Benchmark (surveying); Inference; Software; Data mining; Range (aeronautics); Sequence (biology); Machine learning; Artificial intelligence; Biology; Genetics; Gene; Peptide sequence","score_opus":0.015664792955574713,"score_gpt":0.2533747827090948,"score_spread":0.2377099897535201,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1775447850","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7928572,0.00367012,0.19085729,0.00044472553,0.00011779775,0.00017174977,0.0018320115,0.0067175645,0.0033315874],"genre_scores_gemma":[0.7695832,0.00083480636,0.22489357,0.000093847666,0.000020067733,0.0001605816,0.0033262607,0.00069951854,0.00038805252],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99376476,0.0023989466,0.00076577713,0.001053279,0.0017841124,0.0002330818],"domain_scores_gemma":[0.9733055,0.019209016,0.0023637407,0.0016544953,0.0032230676,0.00024413767],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008068946,0.0010502868,0.0007453315,0.0024252846,0.0009954006,0.0016171157,0.0016457848,0.0013392364,0.0012229233],"category_scores_gemma":[0.028144743,0.0004034337,0.0010069031,0.0027565763,0.000664504,0.0017338968,0.0010206281,0.001296252,0.0005502924],"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":[0.0033504763,0.0008298916,0.17698784,0.002915339,0.0018349903,0.0004970546,0.0011613067,0.36168844,0.061982226,0.00785287,0.0051083616,0.3757912],"study_design_scores_gemma":[0.00013316413,0.0008764409,0.028068542,0.0002561057,0.0003523637,0.0009404094,0.00023608845,0.878216,0.07854539,0.005777977,0.006486869,0.000110639565],"about_ca_topic_score_codex":0.002176198,"about_ca_topic_score_gemma":0.0028903037,"teacher_disagreement_score":0.008068946,"about_ca_system_score_codex":0.0012896139,"about_ca_system_score_gemma":0.0012222863,"threshold_uncertainty_score":0.04267317},"labels":[],"label_agreement":null},{"id":"W1781293113","doi":"10.1186/1471-2105-7-159","title":"Amplification of the Gene Ontology annotation of Affymetrix probe sets","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Genomics","funders":"Stem Cell Network; Ontario Genomics; Genome Canada","keywords":"Annotation; Computer science; DNA microarray; Gene ontology; Gene nomenclature; Microarray; Scripting language; Microarray databases; Computational biology; Correctness; Microarray analysis techniques; Gene; Biology; Genetics; Artificial intelligence; Gene expression; Programming language","score_opus":0.010993362669437,"score_gpt":0.2287200413035721,"score_spread":0.21772667863413508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1781293113","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07536846,0.0023404201,0.87048364,0.001041077,0.0006343042,0.0020261488,0.029803982,0.008771908,0.009530059],"genre_scores_gemma":[0.0630271,0.0011082322,0.8441326,0.00074929267,0.00014550096,0.005730086,0.07581317,0.0026353996,0.0066586584],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9955961,0.00065539137,0.0005452128,0.0012521725,0.0014406652,0.0005103923],"domain_scores_gemma":[0.9928498,0.0030971922,0.0008568834,0.0012642111,0.0017034678,0.00022837947],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029607941,0.0020936101,0.0016739347,0.0041801,0.0019492899,0.0012288059,0.0016096322,0.0011201537,0.009207429],"category_scores_gemma":[0.009234627,0.0016351381,0.002238558,0.0044443123,0.0011552337,0.001272376,0.002107662,0.005121046,0.007918233],"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":[0.00055520615,0.0001076579,0.0015185369,0.0013448251,0.00009376568,0.00041291694,0.00040893795,0.0006210381,0.95664954,0.0027458593,0.004560743,0.030981116],"study_design_scores_gemma":[0.00009833648,0.00021852551,0.012017879,0.00024140615,0.0003249796,0.0008094167,0.0002507903,0.0046815053,0.8458724,0.006352636,0.12902676,0.00010540791],"about_ca_topic_score_codex":0.0010661102,"about_ca_topic_score_gemma":0.0020546792,"teacher_disagreement_score":0.009207429,"about_ca_system_score_codex":0.0009373611,"about_ca_system_score_gemma":0.0020518983,"threshold_uncertainty_score":0.030801892},"labels":[],"label_agreement":null},{"id":"W1793987388","doi":"10.1186/s12859-015-0663-4","title":"Sealer: a scalable gap-closing application for finishing draft genomes","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":156,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Canada's Michael Smith Genome Sciences Centre; BC Cancer Agency","funders":"National Human Genome Research Institute; National Institutes of Health; Genome British Columbia; Genome Canada","keywords":"Closing (real estate); Scalability; DNA microarray; Computer science; Genome; Computational biology; Biology; Genetics; Database; Business; Gene","score_opus":0.04185362854053402,"score_gpt":0.2695208117224522,"score_spread":0.22766718318191817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1793987388","genre_codex":"software","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008691485,0.0005677408,0.37014654,0.00021040588,0.00020474545,0.0003197173,0.008305163,0.6089101,0.0026441559],"genre_scores_gemma":[0.05840451,0.0006113591,0.8526796,0.00044281737,0.00010310537,0.00091296696,0.030810637,0.050950352,0.0050847325],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99774027,0.00034391336,0.00025785004,0.00067744,0.00082069513,0.00015978684],"domain_scores_gemma":[0.99536467,0.0023938648,0.00048554185,0.000860031,0.0006253512,0.00027057095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035842413,0.0023856077,0.0014715426,0.0022553802,0.0011593838,0.002003895,0.0027478756,0.0015729032,0.029012252],"category_scores_gemma":[0.013360503,0.0015658857,0.002200559,0.0016470819,0.0007637954,0.003174286,0.003482994,0.0022378424,0.016892336],"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":[0.0024211265,0.0002642729,0.005372021,0.0039691194,0.0005769114,0.001440881,0.0022917397,0.021724498,0.07823249,0.008084456,0.32929313,0.54632944],"study_design_scores_gemma":[0.0011070913,0.0009627846,0.0069831605,0.0008189294,0.00023812233,0.002015693,0.0008167081,0.3286654,0.20452303,0.024375793,0.42875212,0.00074119266],"about_ca_topic_score_codex":0.0017901934,"about_ca_topic_score_gemma":0.0020846773,"teacher_disagreement_score":0.029012252,"about_ca_system_score_codex":0.0007449527,"about_ca_system_score_gemma":0.0015358705,"threshold_uncertainty_score":0.09705567},"labels":[],"label_agreement":null},{"id":"W1802390868","doi":"10.1186/1471-2105-3-20","title":"Kangaroo – A pattern-matching program for biological sequences","year":2002,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomic variations and chromosomal abnormalities","field":"Biochemistry, Genetics and Molecular Biology","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; University of Toronto; Mount Sinai Hospital","funders":"National Cancer Institute","keywords":"Matching (statistics); DNA microarray; Computational biology; Computer science; Biology; Genetics; Mathematics; Statistics; Gene","score_opus":0.03534831055626175,"score_gpt":0.2560530521769923,"score_spread":0.22070474162073056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1802390868","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015283003,0.00046716456,0.7228914,0.00031767762,0.00009484245,0.0004546156,0.01085487,0.24468878,0.0049476465],"genre_scores_gemma":[0.07891945,0.0005439553,0.86505467,0.00042677223,0.000041503594,0.0015427979,0.025408598,0.022780266,0.0052819895],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99922717,0.00012926976,0.000116375784,0.00024342205,0.0002121143,0.00007158179],"domain_scores_gemma":[0.9983693,0.0010199741,0.00022677238,0.0001615378,0.00014154235,0.00008102762],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014664934,0.0014446354,0.00075489504,0.0023185925,0.00063342386,0.0011298218,0.0020862164,0.0011939536,0.018761013],"category_scores_gemma":[0.0047492776,0.00088370574,0.0016789648,0.002098747,0.0007300858,0.0021346372,0.001862775,0.0012776642,0.005560989],"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":[0.004871254,0.0006483611,0.012312875,0.005090809,0.0006906067,0.0022845394,0.0020566983,0.026557965,0.13534386,0.042841222,0.16233966,0.60496217],"study_design_scores_gemma":[0.001102573,0.00067421433,0.008431836,0.0006520273,0.00029938112,0.0021324833,0.00040554543,0.39033583,0.13138242,0.11033712,0.3539306,0.00031603736],"about_ca_topic_score_codex":0.001396774,"about_ca_topic_score_gemma":0.0015483135,"teacher_disagreement_score":0.018761013,"about_ca_system_score_codex":0.0006733843,"about_ca_system_score_gemma":0.0010639228,"threshold_uncertainty_score":0.06276184},"labels":[],"label_agreement":null},{"id":"W1804740371","doi":"10.1186/1471-2105-7-462","title":"Java GUI for InterProScan (JIPS): A tool to help process multiple InterProScans and perform ortholog analysis","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"National Institute of Allergy and Infectious Diseases; Natural Sciences and Engineering Research Council of Canada; U.S. Public Health Service; National Institutes of Health","keywords":"Java; Computer science; Biological database; Function (biology); Data mining; DNA microarray; Process (computing); Computational biology; Database; Bioinformatics; Biology; Gene; Genetics; Programming language","score_opus":0.005128141935829156,"score_gpt":0.244131908550931,"score_spread":0.23900376661510184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1804740371","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023009994,0.00029373364,0.47380835,0.00021963795,0.00014096734,0.00024440937,0.0053947987,0.51486546,0.0027315742],"genre_scores_gemma":[0.029528065,0.00084515853,0.8182592,0.00094243523,0.00016072979,0.0015853526,0.028708657,0.10585359,0.014116833],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989171,0.00018966671,0.00015561556,0.00020586676,0.00040480006,0.00012695353],"domain_scores_gemma":[0.996296,0.0019281317,0.0003113337,0.00042829578,0.00066407654,0.0003722468],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002508893,0.0033377905,0.0016762122,0.002912954,0.00079309894,0.0016153882,0.0040519414,0.0014714431,0.053632826],"category_scores_gemma":[0.0053892913,0.0015690051,0.0014051087,0.0013794295,0.0005805334,0.0025282803,0.0025075602,0.0026815876,0.029224481],"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":[0.003032495,0.0007209852,0.00538181,0.0028505633,0.0005729814,0.0020047326,0.0009367706,0.0042916513,0.092012,0.0057340884,0.43514493,0.44731703],"study_design_scores_gemma":[0.0019189258,0.0007739856,0.017096646,0.00069366593,0.0004241742,0.005502958,0.00027884456,0.15236232,0.16678117,0.021015704,0.632146,0.001005696],"about_ca_topic_score_codex":0.0024761893,"about_ca_topic_score_gemma":0.0027646245,"teacher_disagreement_score":0.053632826,"about_ca_system_score_codex":0.0005891364,"about_ca_system_score_gemma":0.0012286719,"threshold_uncertainty_score":0.1794197},"labels":[],"label_agreement":null},{"id":"W1807494956","doi":"10.1186/1471-2105-6-138","title":"libcov: A C++ bioinformatic library to manipulate protein structures, sequence alignments and phylogeny","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Advanced Research; Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Genome Atlantic","keywords":"Phylogenetic tree; Phylogenetics; Mega-; Tree (set theory); Computational biology; Multiple sequence alignment; Selection (genetic algorithm); Biology; Computer science; Sequence (biology); Alignment-free sequence analysis; Computational phylogenetics; Sequence alignment; Bioinformatics; Phylogenetic network; Data mining; Machine learning; Genetics; Gene; Mathematics; Peptide sequence","score_opus":0.019746366193102268,"score_gpt":0.236738358717995,"score_spread":0.21699199252489274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1807494956","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021291825,0.0003864087,0.5796018,0.0002438737,0.00015518138,0.00036637054,0.009238587,0.40004775,0.0078307595],"genre_scores_gemma":[0.032226294,0.001632474,0.72854394,0.0018817869,0.00022302751,0.002809936,0.045685183,0.16457683,0.022420526],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982582,0.0002571669,0.00020713937,0.0003386842,0.0007477541,0.00019095789],"domain_scores_gemma":[0.99568486,0.0019078016,0.00040144162,0.00076463947,0.00090894586,0.00033231708],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027847122,0.003625523,0.0015884202,0.002936674,0.0013646368,0.0031241756,0.007195988,0.0014419209,0.057959076],"category_scores_gemma":[0.008920657,0.002262329,0.0022039015,0.0030378597,0.001149098,0.0038589176,0.0034225138,0.004338862,0.044388898],"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":[0.001352533,0.0003291131,0.002364323,0.0025417183,0.0004578327,0.0012567068,0.0005028352,0.017283643,0.027955025,0.026440846,0.49477807,0.4247374],"study_design_scores_gemma":[0.0010354455,0.00033711485,0.0040085698,0.00085856504,0.00022489642,0.0022988524,0.00014037975,0.20298435,0.09160289,0.063294485,0.63254094,0.0006735394],"about_ca_topic_score_codex":0.003963742,"about_ca_topic_score_gemma":0.0043791817,"teacher_disagreement_score":0.057959076,"about_ca_system_score_codex":0.0013848613,"about_ca_system_score_gemma":0.0023750134,"threshold_uncertainty_score":0.19389242},"labels":[],"label_agreement":null},{"id":"W1813034246","doi":"10.1186/1471-2105-6-23","title":"Recent Hits Acquired by BLAST (ReHAB): A tool to identify new hits in sequence similarity searches","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"National Institute of Allergy and Infectious Diseases; Natural Sciences and Engineering Research Council of Canada; Defense Advanced Research Projects Agency","keywords":"Computer science; Similarity (geometry); Sequence (biology); Alignment-free sequence analysis; Information retrieval; Table (database); Interface (matter); Graphics; Data mining; Genome; Sequence alignment; Sequence database; Software; Multiple sequence alignment; Database; Artificial intelligence; Biology; Genetics; Programming language; Computer graphics (images)","score_opus":0.03302620209898142,"score_gpt":0.3249614275038759,"score_spread":0.29193522540489447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1813034246","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023395102,0.0024720044,0.54074866,0.0009781206,0.00058826676,0.0009672167,0.035286363,0.38664648,0.008917797],"genre_scores_gemma":[0.043915905,0.0012666242,0.89160115,0.00047472143,0.0001725854,0.0012438971,0.042242136,0.015402127,0.0036808897],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9974831,0.00078804704,0.00043584695,0.00038177558,0.00075612986,0.00015515494],"domain_scores_gemma":[0.9948767,0.0029742043,0.0006506983,0.000610587,0.0005552101,0.0003326302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004892423,0.0032578753,0.0020966907,0.009282675,0.0012968015,0.0022834516,0.003356347,0.0016878438,0.026599837],"category_scores_gemma":[0.013599045,0.0016782648,0.0015730918,0.005697097,0.0007803519,0.003728412,0.0029830062,0.0024264455,0.018778859],"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":[0.004269455,0.0006264812,0.010618173,0.006485608,0.0007440762,0.0030433459,0.0015257061,0.00446184,0.06696562,0.010117349,0.4221869,0.46895537],"study_design_scores_gemma":[0.003177892,0.0022413726,0.023548879,0.0017929749,0.0010636345,0.014195008,0.0011139344,0.11958766,0.1693653,0.058221314,0.6044336,0.0012584442],"about_ca_topic_score_codex":0.000636563,"about_ca_topic_score_gemma":0.0010944068,"teacher_disagreement_score":0.026599837,"about_ca_system_score_codex":0.0004972052,"about_ca_system_score_gemma":0.001211356,"threshold_uncertainty_score":0.088985264},"labels":[],"label_agreement":null},{"id":"W1819319716","doi":"10.1186/1471-2105-6-36","title":"GANN: Genetic algorithm neural networks for the detection of conserved combinations of features in DNA","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University; University of Ottawa","funders":"","keywords":"DNA microarray; Sequence (biology); Computer science; Artificial intelligence; DNA sequencing; Computational biology; Feature (linguistics); Machine learning; Protein sequencing; Artificial neural network; Algorithm; Data mining; Sequence analysis; Biology; Genetics; Peptide sequence; DNA; Gene","score_opus":0.007048980703530255,"score_gpt":0.21883051175330298,"score_spread":0.21178153104977274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1819319716","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03351456,0.0013195297,0.95223135,0.00042788906,0.0001369036,0.00020649759,0.00063343317,0.009150015,0.0023798777],"genre_scores_gemma":[0.33698043,0.00050477753,0.6556733,0.00069840834,0.00009136527,0.0007291037,0.0018836858,0.00050838105,0.00293044],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99944824,0.00021484707,0.000029755185,0.0001464011,0.00011538098,0.000045363842],"domain_scores_gemma":[0.99870765,0.00095647736,0.000077515724,0.00006520255,0.00015888394,0.0000341964],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016578474,0.0013293651,0.00089505553,0.0009455506,0.00031516363,0.0005582096,0.0017639181,0.0013747149,0.0025682843],"category_scores_gemma":[0.00394649,0.00052349194,0.0009747266,0.0007558848,0.0005812525,0.0005859963,0.00076865475,0.0018266123,0.0007465385],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017963533,0.00010112344,0.001584881,0.00014601018,0.00013676079,0.0000858985,0.000037317324,0.81767184,0.0026245965,0.0026069013,0.005159564,0.16966552],"study_design_scores_gemma":[0.000008714303,0.0000162383,0.00008188372,0.0000058062233,0.0000051192264,0.000010644606,0.0000021952753,0.99754673,0.00038370755,0.0016897678,0.00024568455,0.0000034483373],"about_ca_topic_score_codex":0.006021934,"about_ca_topic_score_gemma":0.007867356,"teacher_disagreement_score":0.006021934,"about_ca_system_score_codex":0.0009476773,"about_ca_system_score_gemma":0.00085973495,"threshold_uncertainty_score":0.011973798},"labels":[],"label_agreement":null},{"id":"W1819658147","doi":"10.1186/1471-2105-6-68","title":"Feature selection and nearest centroid classification for protein mass spectrometry","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":171,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada; University of Alberta","keywords":"Feature selection; Computer science; Dimensionality reduction; Artificial intelligence; Principal component analysis; Pattern recognition (psychology); Linear discriminant analysis; Data mining; k-nearest neighbors algorithm; Curse of dimensionality; Centroid; Machine learning; Classifier (UML); Boosting (machine learning); Support vector machine","score_opus":0.013658956795105424,"score_gpt":0.24366443813738542,"score_spread":0.23000548134228,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1819658147","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09430326,0.0018463236,0.8993361,0.00026568313,0.00016354657,0.00016749077,0.00039723061,0.0025132506,0.0010070496],"genre_scores_gemma":[0.55717736,0.00045046434,0.43971205,0.000081012695,0.00011961431,0.00027160023,0.0009629304,0.00010102193,0.0011239335],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99808073,0.00045478536,0.00011886708,0.00038620533,0.0008244867,0.00013493227],"domain_scores_gemma":[0.9973711,0.0011244396,0.00030141984,0.00020844105,0.000919109,0.00007553059],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00278554,0.0009525084,0.0013648772,0.002563887,0.0007108962,0.00081178977,0.001122159,0.000909389,0.001410529],"category_scores_gemma":[0.00668798,0.0002134756,0.0010671864,0.002503031,0.00050728465,0.0009115583,0.00074945897,0.0007691269,0.0008722653],"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":[0.0006482264,0.00033537942,0.007027515,0.0002842795,0.00020310545,0.00019925035,0.00014103629,0.13255005,0.022022206,0.0031597263,0.0049311854,0.828498],"study_design_scores_gemma":[0.000041396666,0.0002941201,0.0063600773,0.000028478631,0.000049574206,0.0002663735,0.00003875647,0.96889853,0.01573904,0.005861995,0.0023796435,0.000042094267],"about_ca_topic_score_codex":0.0021508418,"about_ca_topic_score_gemma":0.0012042606,"teacher_disagreement_score":0.00278554,"about_ca_system_score_codex":0.000806447,"about_ca_system_score_gemma":0.0008209195,"threshold_uncertainty_score":0.014731467},"labels":[],"label_agreement":null},{"id":"W1820242896","doi":"10.1186/1471-2105-6-271","title":"The yeast kinome displays scale free topology with functional hub clusters","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Canadian Institutes of Health Research; Heart and Stroke Foundation of Canada","keywords":"Kinome; Interactome; Computational biology; In silico; Degree distribution; Biology; Systems biology; Biological network; Computer science; Network topology; Modularity (biology); Function (biology); Distributed computing; Kinase; Complex network; Genetics; Computer network","score_opus":0.007692424662991029,"score_gpt":0.20040175836108556,"score_spread":0.19270933369809454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1820242896","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98729837,0.00011935843,0.0105819,0.000065997694,0.0000028448953,0.0000098205865,0.00056130846,0.00024970275,0.0011106395],"genre_scores_gemma":[0.99683726,0.000050485745,0.0021534516,0.000012239615,0.000002599719,0.000008558395,0.0006860858,0.000017434633,0.0002318255],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999093,0.000014634666,0.000005851145,0.000028576656,0.000025884778,0.000015848163],"domain_scores_gemma":[0.9991547,0.00036518005,0.00021102878,0.00009500307,0.0000802638,0.000093745046],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012711223,0.00016112183,0.000179965,0.0009360223,0.0003386511,0.00052287505,0.00022274486,0.0002978562,0.0015587696],"category_scores_gemma":[0.0009352325,0.00015498193,0.00021403402,0.0007070987,0.0003404162,0.00054138195,0.00031811054,0.00020930675,0.00024218297],"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":[0.002039894,0.00029104023,0.20810609,0.0011516667,0.0004903841,0.0051545254,0.0019259815,0.22613917,0.4501989,0.032405537,0.0070394836,0.06505737],"study_design_scores_gemma":[0.00012696734,0.00036125124,0.4359,0.00005616636,0.00023783048,0.007039615,0.0009710024,0.41594797,0.052538846,0.07855657,0.008145392,0.0001183434],"about_ca_topic_score_codex":0.0010872952,"about_ca_topic_score_gemma":0.0014588285,"teacher_disagreement_score":0.0015587696,"about_ca_system_score_codex":0.00031531692,"about_ca_system_score_gemma":0.00018715425,"threshold_uncertainty_score":0.0052146316},"labels":[],"label_agreement":null},{"id":"W1860906034","doi":"10.1186/1471-2105-8-34","title":"Computational RNA secondary structure design: empirical complexity and improved methods","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Mitacs; Consejo Nacional de Ciencia y Tecnología; Government of Canada","keywords":"Nucleic acid secondary structure; Computer science; Algorithm; Nucleic acid structure; RNA; Scaling; Sequence (biology); Basis (linear algebra); Protein secondary structure; Theoretical computer science; Mathematics","score_opus":0.052991430173054535,"score_gpt":0.3410353599498488,"score_spread":0.28804392977679427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1860906034","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024024023,0.0018374576,0.96929234,0.001062969,0.00006317328,0.00010529798,0.0001586948,0.00057517894,0.0028809262],"genre_scores_gemma":[0.34494525,0.0016814271,0.6491231,0.00036816165,0.0003843006,0.00058253604,0.0007121753,0.00045560312,0.0017474248],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9955134,0.0022175217,0.0001997989,0.00055565446,0.0013679883,0.00014565389],"domain_scores_gemma":[0.9324596,0.0585821,0.002329754,0.0034908538,0.002665685,0.00047206657],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007849339,0.0011729118,0.0013693991,0.0019430113,0.0006686603,0.0018847004,0.002363748,0.0019620182,0.003839506],"category_scores_gemma":[0.045043994,0.00091639365,0.0016198107,0.0016234609,0.0023768875,0.0036236977,0.001928295,0.0032913976,0.00058282085],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010253381,0.000094486866,0.0020871516,0.00039219335,0.000104760526,0.0000448883,0.00008038353,0.9099428,0.0010351918,0.049043085,0.001428394,0.03564403],"study_design_scores_gemma":[0.000017482553,0.00001761164,0.00016586273,0.000012965975,0.000006418115,0.00001195587,0.0000035336059,0.9795297,0.00031801866,0.019466432,0.00044492612,0.000005132426],"about_ca_topic_score_codex":0.0028733462,"about_ca_topic_score_gemma":0.0022991376,"teacher_disagreement_score":0.007849339,"about_ca_system_score_codex":0.0029622174,"about_ca_system_score_gemma":0.0020883945,"threshold_uncertainty_score":0.041511774},"labels":[],"label_agreement":null},{"id":"W1863852050","doi":"10.1186/1471-2105-7-79","title":"Taxonomic colouring of phylogenetic trees of protein sequences","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Ontario Genomics","funders":"Ontario Genomics","keywords":"Phylogenetic tree; GenBank; Tree (set theory); Biology; Phylogenetic network; Phylogenetics; Taxonomic rank; Identification (biology); Documentation; Identifier; Computer science; Taxon; Genetics; Ecology; Combinatorics; Mathematics; Gene; Programming language","score_opus":0.01295903067258679,"score_gpt":0.21109257663741315,"score_spread":0.19813354596482635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1863852050","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08529172,0.0027798065,0.8688264,0.0011220133,0.00065446366,0.0004179009,0.004954286,0.019601721,0.016351726],"genre_scores_gemma":[0.20822218,0.0014477258,0.7781456,0.00033665658,0.00014416396,0.00029782747,0.006049518,0.003019993,0.0023363407],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9980552,0.00082963624,0.00016323928,0.00027699306,0.00051069015,0.00016428427],"domain_scores_gemma":[0.9907622,0.0046242764,0.0009726822,0.0013402266,0.0017655228,0.00053514546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003952902,0.0006825966,0.0005424579,0.0054794666,0.0011154191,0.0023230696,0.0010510344,0.00081203226,0.009577701],"category_scores_gemma":[0.017812947,0.00054428197,0.0008955866,0.0034537567,0.0011305177,0.0032701045,0.0018771661,0.0017747469,0.0026937798],"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":[0.0016434119,0.00013492635,0.01607438,0.0026434548,0.00016308209,0.00089571415,0.0041006384,0.011700161,0.1261138,0.05955534,0.03855056,0.7384244],"study_design_scores_gemma":[0.00035372798,0.0005338887,0.044191048,0.0019622003,0.00040601706,0.0043211165,0.0019525188,0.1490455,0.17362465,0.25949812,0.3636088,0.0005023534],"about_ca_topic_score_codex":0.0009772652,"about_ca_topic_score_gemma":0.0010698946,"teacher_disagreement_score":0.009577701,"about_ca_system_score_codex":0.001091267,"about_ca_system_score_gemma":0.00069505593,"threshold_uncertainty_score":0.032040596},"labels":[],"label_agreement":null},{"id":"W1869957243","doi":"10.1186/1471-2105-6-183","title":"Inconsistencies over time in 5% of NetAffx probe-to-gene annotations","year":2005,"lang":"en","type":"letter","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Genomics","funders":"Ministry of Education, India","keywords":"DNA microarray; Microarray; Microarray databases; Annotation; Microarray analysis techniques; Computational biology; Biology; Gene; Gene Annotation; Genetics; Set (abstract data type); Genome; Bioinformatics; Computer science; Gene expression","score_opus":0.016330462683547417,"score_gpt":0.2503158012860126,"score_spread":0.23398533860246518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1869957243","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12333737,0.028226914,0.1341795,0.610298,0.041220378,0.00028548884,0.010643454,0.006708781,0.045100093],"genre_scores_gemma":[0.3958881,0.01153562,0.12997052,0.40587232,0.014137094,0.0006738409,0.013516563,0.0033819736,0.02502397],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9773078,0.006462074,0.00331764,0.0033039497,0.008762326,0.00084624306],"domain_scores_gemma":[0.89214826,0.06899514,0.006803056,0.009164126,0.021898516,0.0009909259],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027963536,0.0004105829,0.0006525857,0.0023618133,0.0016896365,0.002087419,0.0022628875,0.0031771106,0.0045963153],"category_scores_gemma":[0.08080688,0.00042533485,0.0006369256,0.004139596,0.0015588447,0.0022249424,0.0014019723,0.004025639,0.003962682],"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":[0.0010062472,0.000106270745,0.028878992,0.0014636489,0.00015386313,0.0045425715,0.0037873506,0.0012556919,0.014811591,0.019954402,0.402454,0.5215854],"study_design_scores_gemma":[0.000028794184,0.00010769831,0.017650213,0.000622151,0.000108654334,0.010855232,0.0010077679,0.0026764215,0.013568567,0.01676216,0.9365296,0.0000827429],"about_ca_topic_score_codex":0.002881788,"about_ca_topic_score_gemma":0.0046400046,"teacher_disagreement_score":0.027963536,"about_ca_system_score_codex":0.0035378272,"about_ca_system_score_gemma":0.001633809,"threshold_uncertainty_score":0.14788705},"labels":[],"label_agreement":null},{"id":"W1870437443","doi":"10.1186/s12859-015-0655-4","title":"An investigation into inter- and intragenomic variations of graphic genomic signatures","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Fractal and DNA sequence analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Saint Mary's University; Western University","funders":"","keywords":"Biology; Genome; Genetics; Homo sapiens; genomic DNA; Chromosome; Genome evolution; Phylogenetic tree; Comparative genomics; DNA sequencing; Genomics; Evolutionary biology; Computational biology; Gene","score_opus":0.013938743161031018,"score_gpt":0.2398146198718001,"score_spread":0.22587587671076909,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1870437443","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9931358,0.00027752868,0.0034200465,0.000031797783,0.0000039682786,0.000010860663,0.002426893,0.00006435316,0.0006287052],"genre_scores_gemma":[0.9860277,0.00012072125,0.0071037835,0.000041174208,0.000011540121,0.000026057403,0.0064221974,0.00002987217,0.00021702486],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99959606,0.000054892196,0.000024673893,0.00020862713,0.00006918349,0.000046530673],"domain_scores_gemma":[0.99806553,0.0008479786,0.00053517916,0.00023151336,0.0001883325,0.00013145045],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040423073,0.00018814746,0.00023484322,0.0017888347,0.00023770871,0.00050567486,0.00023582263,0.00035117284,0.0012622897],"category_scores_gemma":[0.0016875466,0.00008538737,0.00030462083,0.0020693769,0.00036324744,0.00036642185,0.0004574572,0.00035867695,0.00030886824],"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":[0.0007734476,0.00020588834,0.45056108,0.00056336605,0.00040409827,0.00034098636,0.0005934334,0.0029140045,0.47490093,0.0011124149,0.00078962976,0.066840805],"study_design_scores_gemma":[0.00001235635,0.00018729083,0.9653365,0.000024966896,0.00013016806,0.0008121899,0.00026148133,0.0076365266,0.02031704,0.00095269637,0.0043085134,0.000020391539],"about_ca_topic_score_codex":0.00040157157,"about_ca_topic_score_gemma":0.0006716138,"teacher_disagreement_score":0.0017888347,"about_ca_system_score_codex":0.00020536335,"about_ca_system_score_gemma":0.00014234673,"threshold_uncertainty_score":0.0042227507},"labels":[],"label_agreement":null},{"id":"W1870764676","doi":"10.1186/1471-2105-5-156","title":"Modeling of cell signaling pathways in macrophages by semantic networks","year":2004,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Michael Smith Health Research BC; University of British Columbia","funders":"Canadian Institutes of Health Research; Michael Smith Health Research BC; Faculty of Medicine, University of British Columbia","keywords":"Context (archaeology); Biological pathway; Cell signaling; Systems biology; Computer science; Signal transduction; Computational biology; Biology; Biological network; Semantic network; Cell biology; Artificial intelligence; Gene; Genetics; Gene expression","score_opus":0.010357711615998142,"score_gpt":0.20501339145718342,"score_spread":0.1946556798411853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1870764676","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0671382,0.00031287214,0.9260435,0.00036086497,0.000036242665,0.00014278205,0.0006724883,0.0005609751,0.00473204],"genre_scores_gemma":[0.57439595,0.0010208994,0.41948777,0.00010831611,0.00003639613,0.00056049257,0.0014911054,0.00010341856,0.0027955747],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995542,0.00019005557,0.000039301394,0.0000847695,0.000094279596,0.000037389662],"domain_scores_gemma":[0.9995079,0.0002988168,0.000054273823,0.000039636223,0.00007285936,0.000026485099],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008075671,0.000706514,0.00036553494,0.001116305,0.0005153391,0.00108669,0.00081720203,0.0008331104,0.001300039],"category_scores_gemma":[0.0011815295,0.0002681306,0.001720792,0.00080406066,0.0007822023,0.0015418101,0.0009241157,0.00057289837,0.0002101849],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009331278,0.00006339803,0.002198044,0.00017291652,0.00006444734,0.00032806513,0.00025868282,0.90835685,0.0050168596,0.071515106,0.00045903688,0.011473274],"study_design_scores_gemma":[0.0000112427315,0.000022819495,0.00024474776,0.000018134875,0.000032944572,0.000064743996,0.00005442904,0.96370447,0.0016205336,0.030336633,0.0038814698,0.000007818614],"about_ca_topic_score_codex":0.0051811775,"about_ca_topic_score_gemma":0.004251023,"teacher_disagreement_score":0.0051811775,"about_ca_system_score_codex":0.0009519468,"about_ca_system_score_gemma":0.0011876537,"threshold_uncertainty_score":0.010302007},"labels":[],"label_agreement":null},{"id":"W1878664294","doi":"10.1186/s12859-015-0597-x","title":"ISOpureR: an R implementation of a computational purification algorithm of mixed tumour profiles","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sinai Health System; Canada Research Chairs; University of Toronto; Ontario Institute for Cancer Research","funders":"","keywords":"Lung cancer; R package; Prostate cancer; Cancer; Fraction (chemistry); Tumour heterogeneity; Computer science; DNA microarray; Computational biology; Algorithm; Bioinformatics; Data mining; Biology; Oncology; Computational science; Medicine; Gene; Gene expression; Chemistry; Genetics","score_opus":0.023086360785979296,"score_gpt":0.2899811739000443,"score_spread":0.266894813114065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1878664294","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030971563,0.00021450325,0.8723003,0.00020240429,0.00009672016,0.00014440373,0.006785005,0.11574302,0.0014164576],"genre_scores_gemma":[0.042161368,0.00026231274,0.880542,0.00043479213,0.00008419467,0.0013426935,0.014673172,0.05701413,0.003485365],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976847,0.0008503314,0.00020217116,0.00060503394,0.00051581895,0.00014194568],"domain_scores_gemma":[0.9942668,0.0038813069,0.00040804522,0.0007977025,0.000502238,0.00014389359],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039103692,0.002726883,0.0014605061,0.0014880274,0.0005984329,0.0020887423,0.0031301142,0.001257883,0.030530917],"category_scores_gemma":[0.021301085,0.0017144971,0.0030633542,0.0013288237,0.00087701064,0.00144718,0.002617711,0.0032727043,0.020757066],"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":[0.0022418404,0.0002562799,0.012942606,0.003483627,0.0025002598,0.0012354694,0.0011686418,0.14714125,0.026001427,0.034374308,0.33063468,0.43801954],"study_design_scores_gemma":[0.00086341973,0.00030721037,0.0053127534,0.00026218922,0.00041642992,0.0011228536,0.00012037682,0.7297187,0.032094732,0.047439378,0.18202452,0.0003175035],"about_ca_topic_score_codex":0.0025155914,"about_ca_topic_score_gemma":0.003206224,"teacher_disagreement_score":0.030530917,"about_ca_system_score_codex":0.000653877,"about_ca_system_score_gemma":0.002228868,"threshold_uncertainty_score":0.102136135},"labels":[],"label_agreement":null},{"id":"W1879935290","doi":"10.1186/1471-2105-6-139","title":"PentaPlot: A software tool for the illustration of genome mosaicism","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"National Aeronautics and Space Administration; National Science Foundation","keywords":"Computational biology; DNA microarray; Software; Genome; Computer science; Biology; Genetics; Bioinformatics; Programming language; Gene; Gene expression","score_opus":0.019939113460943753,"score_gpt":0.2429802835424754,"score_spread":0.22304117008153163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1879935290","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008799916,0.00037247082,0.68043405,0.00043776302,0.00024017146,0.00026089593,0.017265089,0.28556255,0.0066269883],"genre_scores_gemma":[0.08114571,0.0006816982,0.8337934,0.00044447728,0.00005913353,0.0012581879,0.033150762,0.04172583,0.0077408175],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9996451,0.000083878345,0.000043140077,0.00006533611,0.00011886063,0.000043693413],"domain_scores_gemma":[0.9984193,0.0010855203,0.00012138013,0.00012407124,0.00015153964,0.00009822101],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012947329,0.0013540908,0.0009385796,0.0026069556,0.00076498167,0.001845952,0.0029437838,0.0012463827,0.08129339],"category_scores_gemma":[0.004119486,0.001092471,0.0013826981,0.001539465,0.00045366396,0.001885461,0.002649766,0.0020000811,0.012057283],"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":[0.0016930287,0.00031772195,0.0049882038,0.004428632,0.0005072469,0.0024683087,0.0015646104,0.044880856,0.04168286,0.041013926,0.51592356,0.340531],"study_design_scores_gemma":[0.0007242729,0.00023168013,0.00538925,0.00052812055,0.00014070494,0.002479536,0.00037340945,0.40076828,0.02908208,0.069105364,0.49087614,0.0003012109],"about_ca_topic_score_codex":0.0025105688,"about_ca_topic_score_gemma":0.0031631645,"teacher_disagreement_score":0.08129339,"about_ca_system_score_codex":0.00067195215,"about_ca_system_score_gemma":0.0011376971,"threshold_uncertainty_score":0.27195346},"labels":[],"label_agreement":null},{"id":"W1882963036","doi":"10.1186/1471-2105-3-13","title":"NBLAST: a cluster variant of BLAST for NxN comparisons","year":2002,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; University of Toronto; Mount Sinai Hospital","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Sequence (biology); Sequence alignment; Multiple sequence alignment; Perl; Cluster (spacecraft); Set (abstract data type); Sequence database; Task (project management); Cluster analysis; Smith–Waterman algorithm; Sequence logo; Heuristic; Data mining; Biology; Artificial intelligence; Genetics; Peptide sequence; Programming language","score_opus":0.02975952710185699,"score_gpt":0.23632033118439383,"score_spread":0.20656080408253685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1882963036","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0076877135,0.0010471919,0.7468875,0.0003111863,0.0005773852,0.0008804006,0.015089637,0.21521528,0.012303697],"genre_scores_gemma":[0.021911753,0.0003843744,0.9273603,0.00018527693,0.00009433492,0.0012699389,0.024089761,0.020059932,0.004644455],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.996354,0.0008900873,0.000583945,0.0009274112,0.001002655,0.00024198435],"domain_scores_gemma":[0.9976501,0.00082278886,0.0002287894,0.00063203566,0.0005367343,0.00012958398],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044435905,0.0026192525,0.0025215766,0.0045213117,0.002352013,0.0021361734,0.0045523676,0.0015568361,0.03666948],"category_scores_gemma":[0.008641375,0.0017165248,0.001523467,0.005074721,0.00080893724,0.0029761982,0.0027860366,0.0024705422,0.0343612],"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":[0.0047658314,0.0004154353,0.006503281,0.005770708,0.001048198,0.0015656102,0.0014925357,0.010100823,0.09267291,0.023172349,0.33793044,0.5145619],"study_design_scores_gemma":[0.0009234388,0.0006317703,0.0064533195,0.00072112394,0.00045360797,0.0034800796,0.0005134562,0.18508846,0.07172574,0.05176844,0.6778124,0.00042819732],"about_ca_topic_score_codex":0.0024669406,"about_ca_topic_score_gemma":0.0036304388,"teacher_disagreement_score":0.03666948,"about_ca_system_score_codex":0.0007324088,"about_ca_system_score_gemma":0.0016835027,"threshold_uncertainty_score":0.122671664},"labels":[],"label_agreement":null},{"id":"W1886580489","doi":"10.1186/1471-2105-6-145","title":"Satellog: A database for the identification and prioritization of satellite repeats in disease association studies","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic Neurodegenerative Diseases","field":"Neuroscience","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"BC Cancer Agency; Canadian Institutes of Health Research; Canada's Michael Smith Genome Sciences Centre","keywords":"Genetics; Biology; Tandem repeat; Microsatellite; UniGene; Trinucleotide repeat expansion; Human genome; Direct repeat; RefSeq; Genome; UniProt; dbSNP; Gene; Expressed sequence tag; Single-nucleotide polymorphism; Allele; Genotype","score_opus":0.07048138815232072,"score_gpt":0.3252781653655949,"score_spread":0.2547967772132742,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1886580489","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011818957,0.0076997057,0.030888053,0.00043717131,0.00021483129,0.0006387113,0.90198815,0.04138244,0.0049319514],"genre_scores_gemma":[0.019683078,0.0028687932,0.08893606,0.00065221486,0.00014047277,0.001589063,0.88000584,0.0044070417,0.0017175364],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99795866,0.0005613616,0.00056558254,0.00044048057,0.00033127156,0.00014265189],"domain_scores_gemma":[0.9901211,0.005460447,0.0018754008,0.0011259011,0.00068740925,0.00072973286],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003993873,0.0027243749,0.003198434,0.011608978,0.00078228844,0.002804304,0.0032557887,0.0022330564,0.043621145],"category_scores_gemma":[0.016009154,0.001392638,0.0017874967,0.011416456,0.00050571945,0.0021881005,0.0038916734,0.0014938854,0.022213696],"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":[0.0053345547,0.00028609709,0.03627167,0.032169104,0.0031581894,0.002956721,0.0012952503,0.0046002553,0.03551484,0.007922888,0.672546,0.19794437],"study_design_scores_gemma":[0.0034351759,0.0007195279,0.063563466,0.003923025,0.0020143972,0.004442505,0.0005609557,0.009136333,0.012687621,0.019478342,0.8795633,0.00047532909],"about_ca_topic_score_codex":0.001564283,"about_ca_topic_score_gemma":0.0038485443,"teacher_disagreement_score":0.043621145,"about_ca_system_score_codex":0.000608464,"about_ca_system_score_gemma":0.0024545162,"threshold_uncertainty_score":0.14592731},"labels":[],"label_agreement":null},{"id":"W1918663757","doi":"10.1186/1471-2105-13-s19-s4","title":"A flexible ancestral genome reconstruction method based on gapped adjacencies","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université de Montréal","funders":"","keywords":"Synteny; Genome; Phylogenetic tree; Biology; Tree (set theory); Adjacency list; Extant taxon; Phylogenetics; Set (abstract data type); Phylogenetic network; Computational biology; Data mining; Evolutionary biology; Genetics; Computer science; Gene; Algorithm; Mathematics; Combinatorics","score_opus":0.031277767100683175,"score_gpt":0.28122426960227037,"score_spread":0.2499465025015872,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1918663757","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011796114,0.00015968375,0.9831034,0.000083215564,0.000046141235,0.00006103889,0.00044931326,0.0031155671,0.0011855146],"genre_scores_gemma":[0.084533736,0.00013890395,0.90966535,0.000081958955,0.00003582889,0.00013034417,0.0029494197,0.0008876133,0.0015769291],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994141,0.000087688546,0.00003358771,0.00021811643,0.00018888181,0.000057643727],"domain_scores_gemma":[0.99918145,0.00031917714,0.00006038038,0.00021509432,0.00014945627,0.00007444898],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008799402,0.00087888114,0.0010277702,0.0023351172,0.00089167675,0.0014199453,0.0022232113,0.0012648171,0.008806879],"category_scores_gemma":[0.0029915061,0.00066046324,0.0017025312,0.0017486655,0.00058037904,0.0013056515,0.0021523884,0.0019370274,0.0026476914],"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":[0.0005630547,0.00018478918,0.005313705,0.00055462914,0.0003192195,0.0012658398,0.0007775476,0.23657693,0.04144832,0.048142564,0.0130556375,0.65179783],"study_design_scores_gemma":[0.000074015894,0.00007449879,0.0011427928,0.000048902348,0.00007357547,0.0006368937,0.00010545001,0.9513507,0.008985594,0.02578259,0.011676155,0.000048805858],"about_ca_topic_score_codex":0.0025157975,"about_ca_topic_score_gemma":0.0029962056,"teacher_disagreement_score":0.008806879,"about_ca_system_score_codex":0.0005431372,"about_ca_system_score_gemma":0.0012203977,"threshold_uncertainty_score":0.02946198},"labels":[],"label_agreement":null},{"id":"W1926090033","doi":"10.1186/1471-2105-4-51","title":"A knowledge discovery object model API for Java","year":2003,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; BC Cancer Agency","funders":"Genome Canada","keywords":"Computer science; Application programming interface; Java; Documentation; Ontology; Software engineering; Software; Software mining; Interface (matter); Database; Software development; Programming language; Software construction; Operating system","score_opus":0.03862548388309531,"score_gpt":0.2979191660009343,"score_spread":0.259293682117839,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1926090033","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009842096,0.00030588254,0.751685,0.00054373284,0.00013258368,0.00060301414,0.009898438,0.22465503,0.011192108],"genre_scores_gemma":[0.021866677,0.001074994,0.82830244,0.0016790422,0.00017014405,0.0030655721,0.061599288,0.06367046,0.018571483],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99764687,0.00028876893,0.00044601163,0.000431862,0.0009687356,0.00021777311],"domain_scores_gemma":[0.9957535,0.001989078,0.00044955843,0.000703116,0.00084003276,0.00026464535],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004545225,0.0017282063,0.0013721981,0.0028877475,0.0009928542,0.004543394,0.0049923644,0.0021087204,0.02293569],"category_scores_gemma":[0.008284583,0.0020479127,0.0029174776,0.0024809723,0.00077951717,0.005371934,0.0037195135,0.0038583335,0.02465017],"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":[0.0011532914,0.000779229,0.004713144,0.0026623285,0.00034574282,0.0010803294,0.000925762,0.005808966,0.018203529,0.09131889,0.42824087,0.44476795],"study_design_scores_gemma":[0.00075218943,0.00013403773,0.0028783542,0.0005621311,0.00017431406,0.0014816893,0.00013880018,0.067423806,0.018319096,0.08270475,0.8251466,0.00028421017],"about_ca_topic_score_codex":0.004103476,"about_ca_topic_score_gemma":0.0035423788,"teacher_disagreement_score":0.02293569,"about_ca_system_score_codex":0.0014132801,"about_ca_system_score_gemma":0.0028145702,"threshold_uncertainty_score":0.07672751},"labels":[],"label_agreement":null},{"id":"W1950772819","doi":"10.1186/1471-2105-7-326","title":"A maximum likelihood framework for protein design","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Canadian Institute for Advanced Research","funders":"Natural Sciences and Engineering Research Council of Canada; Université de Montréal; Canadian Institutes of Health Research; Centre National de la Recherche Scientifique","keywords":"Pairwise comparison; Computer science; Inference; Markov chain; Markov chain Monte Carlo; Model selection; Mathematical optimization; Algorithm; Machine learning; Artificial intelligence; Mathematics","score_opus":0.010899072567568748,"score_gpt":0.23688803867762806,"score_spread":0.2259889661100593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1950772819","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00090671354,0.0011626234,0.99428105,0.0005295127,0.00002913798,0.000038862996,0.00012867416,0.00019306997,0.002730338],"genre_scores_gemma":[0.14751256,0.0027433268,0.8381998,0.00039922423,0.0003075444,0.0010090754,0.0010334583,0.00039237796,0.008402654],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963917,0.002381836,0.00012814923,0.0003235971,0.0006462287,0.00012842403],"domain_scores_gemma":[0.9934001,0.0052404418,0.00036947493,0.00029035233,0.0005433784,0.0001563875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0065394975,0.002222895,0.0015523067,0.0018160138,0.00070898025,0.002590086,0.0029513529,0.0025761297,0.009010621],"category_scores_gemma":[0.011450868,0.0010602963,0.0020308788,0.0020183001,0.002324624,0.0022876519,0.0023567104,0.0025728594,0.0023718511],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045517463,0.00005061638,0.00042791438,0.00034137673,0.00009186559,0.000106297986,0.000095618154,0.6250475,0.00038519385,0.3318233,0.003782022,0.037802853],"study_design_scores_gemma":[0.0000224688,0.000021569123,0.000051025174,0.000039733633,0.000010524791,0.000028488137,0.000010449242,0.7206961,0.000106867774,0.27441663,0.00458573,0.00001048102],"about_ca_topic_score_codex":0.0038812105,"about_ca_topic_score_gemma":0.0030659968,"teacher_disagreement_score":0.009010621,"about_ca_system_score_codex":0.0026908542,"about_ca_system_score_gemma":0.002673315,"threshold_uncertainty_score":0.03458458},"labels":[],"label_agreement":null},{"id":"W1951428955","doi":"10.1186/1471-2105-13-s19-s7","title":"Multiple genome comparison based on overlap regions of pairwise local alignments","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Deutscher Akademischer Austauschdienst","keywords":"Pairwise comparison; Genome; Computational biology; DNA microarray; Biology; Genetics; Computer science; Artificial intelligence; Gene; Gene expression","score_opus":0.026902683882040798,"score_gpt":0.2514885947358425,"score_spread":0.2245859108538017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1951428955","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08530141,0.001114264,0.91024673,0.00017662914,0.000040248746,0.00016414467,0.00036407032,0.0012407956,0.0013517208],"genre_scores_gemma":[0.39200187,0.00028429867,0.60544664,0.00006857364,0.00008327265,0.00020462983,0.0010844825,0.00032732188,0.00049891206],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99151117,0.0028529277,0.0005813637,0.0022333746,0.0024769176,0.0003441368],"domain_scores_gemma":[0.9811996,0.0127533935,0.0025981464,0.0014247514,0.0014996553,0.0005244577],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0068321396,0.0010552689,0.0023417738,0.0057539092,0.0010448074,0.002209366,0.0027871907,0.0014095039,0.0028663734],"category_scores_gemma":[0.026655823,0.000616834,0.0016193327,0.0049333433,0.0017609558,0.003607123,0.0035519304,0.0014753958,0.00088658545],"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":[0.0041115675,0.0006152729,0.043885734,0.0027323994,0.0010820982,0.0017958777,0.0013582356,0.23875163,0.09588988,0.06305708,0.00566733,0.5410529],"study_design_scores_gemma":[0.00012304372,0.0005213123,0.009826118,0.00011926784,0.0002513625,0.0019383838,0.0003238978,0.8502419,0.04798413,0.082380876,0.006155085,0.00013459277],"about_ca_topic_score_codex":0.0007825725,"about_ca_topic_score_gemma":0.0007398007,"teacher_disagreement_score":0.0068321396,"about_ca_system_score_codex":0.0010093345,"about_ca_system_score_gemma":0.00090669445,"threshold_uncertainty_score":0.036132216},"labels":[],"label_agreement":null},{"id":"W1964430425","doi":"10.1186/1471-2105-11-563","title":"TESTLoc: protein subcellular localization prediction from EST data","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","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":"Université de Montréal","funders":"Canadian Institutes of Health Research; Université de Montréal; Canadian Institute for Advanced Research","keywords":"Subcellular localization; Computational biology; Support vector machine; Sequence (biology); Function (biology); Protein sequencing; Protein function prediction; Computer science; Biology; DNA microarray; Data mining; Protein function; Artificial intelligence; Peptide sequence; Biochemistry; Genetics; Cytoplasm; Gene","score_opus":0.015299169738053143,"score_gpt":0.24581988314883316,"score_spread":0.23052071341078,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1964430425","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32057446,0.0013394934,0.408071,0.00082801527,0.00021542817,0.00031151032,0.10540397,0.15978494,0.003471144],"genre_scores_gemma":[0.51019394,0.00050352357,0.2703651,0.00028900398,0.000105173014,0.0007874875,0.21224025,0.0034054955,0.0021100685],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999201,0.0002815403,0.00007160674,0.00019631001,0.0001763041,0.00007323406],"domain_scores_gemma":[0.99490756,0.003403904,0.0005472998,0.00034823446,0.0005920268,0.000200931],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017677754,0.0014651358,0.0007663369,0.0021942558,0.00047391732,0.0009761429,0.00096142944,0.00085732783,0.005175886],"category_scores_gemma":[0.0074122455,0.00035081513,0.00068391906,0.002524142,0.00034388292,0.00091139803,0.00083856325,0.00095401437,0.003651378],"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":[0.008147464,0.0008395223,0.085700855,0.0040140157,0.0008570144,0.0025624684,0.0004239615,0.12728512,0.09652834,0.004517583,0.27243033,0.39669338],"study_design_scores_gemma":[0.00039847684,0.0006762368,0.022598645,0.00013459951,0.00014734475,0.001120905,0.00017081795,0.8607603,0.07634758,0.005853718,0.03168416,0.000107205706],"about_ca_topic_score_codex":0.0011907127,"about_ca_topic_score_gemma":0.0014818432,"teacher_disagreement_score":0.005175886,"about_ca_system_score_codex":0.0003995904,"about_ca_system_score_gemma":0.0008540884,"threshold_uncertainty_score":0.01731509},"labels":[],"label_agreement":null},{"id":"W1964514748","doi":"10.1186/1471-2105-11-226","title":"Partitioning of copy-number genotypes in pedigrees","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomic variations and chromosomal abnormalities","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier Universitaire Sainte-Justine; Université de Montréal; Montreal Heart Institute; Institut national de psychiatrie légale Philippe-Pinel","funders":"Canadian Institutes of Health Research; Heart and Stroke Foundation of Canada","keywords":"Pedigree chart; Copy-number variation; Genetics; Biology; Copy number analysis; Genotype; SNP array; Single-nucleotide polymorphism; Computational biology; Genome; Gene","score_opus":0.007366957130148598,"score_gpt":0.23088223053548929,"score_spread":0.2235152734053407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1964514748","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3835943,0.0005998577,0.6069829,0.00022690104,0.00003957366,0.00025427202,0.0028778538,0.0039081858,0.0015161393],"genre_scores_gemma":[0.45938608,0.0004079668,0.5324991,0.000100485675,0.000024289118,0.000281774,0.0053824126,0.0007529723,0.001164948],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99908185,0.00033217398,0.000064953594,0.00031794654,0.00014413129,0.000058989852],"domain_scores_gemma":[0.9975706,0.0016707275,0.00023132353,0.00023958534,0.0001936611,0.00009409905],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020627151,0.00063354406,0.0005350347,0.0018862833,0.0005050393,0.0008620675,0.00058517564,0.00036777323,0.0019995149],"category_scores_gemma":[0.006845408,0.00044566704,0.0006918355,0.0011449396,0.00034492274,0.00049333356,0.00097049365,0.00032678392,0.00045861246],"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":[0.0009926044,0.00017595626,0.1998536,0.00057401427,0.00059162406,0.0017608156,0.0021143968,0.23790379,0.023842217,0.009214804,0.008609927,0.51436627],"study_design_scores_gemma":[0.0002917828,0.000221318,0.11261055,0.00019855646,0.0004542749,0.002556709,0.0003931965,0.7865252,0.019081648,0.052319817,0.025238818,0.00010818289],"about_ca_topic_score_codex":0.0054514743,"about_ca_topic_score_gemma":0.0068715997,"teacher_disagreement_score":0.0054514743,"about_ca_system_score_codex":0.00058884866,"about_ca_system_score_gemma":0.0009865452,"threshold_uncertainty_score":0.0109087825},"labels":[],"label_agreement":null},{"id":"W1965560116","doi":"10.1186/1471-2105-9-515","title":"Improved machine learning method for analysis of gas phase chemistry of peptides","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","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 Alberta","funders":"Army Research Office; National Cancer Institute; National Institutes of Health","keywords":"Computer science; Feature selection; Artificial intelligence; Normalization (sociology); Machine learning; Data mining; Mass spectrometry; Fragmentation (computing); Proteomics; Software; Database search engine; Mass spectrum; Chemistry; Search engine; Chromatography; Information retrieval","score_opus":0.02971369162966547,"score_gpt":0.3309501063571692,"score_spread":0.30123641472750373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1965560116","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037876233,0.00013284438,0.9937989,0.00004116524,0.000029055493,0.000046898127,0.00013188287,0.0017568026,0.00027482744],"genre_scores_gemma":[0.045476515,0.00011582851,0.9526296,0.00005323918,0.000032965097,0.0003054266,0.00042788027,0.00009929897,0.00085914304],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99870515,0.00039008437,0.00012580033,0.00030607005,0.00041613542,0.00005673207],"domain_scores_gemma":[0.99751186,0.001454637,0.00015242009,0.00022443735,0.000617256,0.000039341117],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019873402,0.000977389,0.0009166005,0.002018985,0.0005336323,0.0007929686,0.0014052598,0.00087663427,0.003253309],"category_scores_gemma":[0.0055640675,0.00028057562,0.00091855455,0.0017455934,0.0003471237,0.00093405443,0.0006317337,0.0013659066,0.0016323227],"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":[0.00032905283,0.00030534086,0.0034134276,0.00036636743,0.00022969366,0.00025705315,0.00012723076,0.11131284,0.03344104,0.014377379,0.005630821,0.8302097],"study_design_scores_gemma":[0.000026867798,0.00005173163,0.0007984144,0.0000115293215,0.000028963655,0.00014383828,0.000008352215,0.97907704,0.008848602,0.0073985346,0.0035830925,0.000023031094],"about_ca_topic_score_codex":0.0012989313,"about_ca_topic_score_gemma":0.0009592555,"teacher_disagreement_score":0.003253309,"about_ca_system_score_codex":0.0005083917,"about_ca_system_score_gemma":0.0010402962,"threshold_uncertainty_score":0.010883391},"labels":[],"label_agreement":null},{"id":"W1965744864","doi":"10.1186/1471-2105-12-s9-s14","title":"Origin and evolution of gene families in Bacteria and Archaea","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","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":"Laurentian University; McMaster University","funders":"","keywords":"Genome; Biology; Gene; Horizontal gene transfer; Archaea; Gene duplication; Genetics; Gene family; Genome evolution; Bacterial genome size; Gene cluster; Genome size; Evolutionary biology; Computational biology","score_opus":0.02074680044134661,"score_gpt":0.22023558622248285,"score_spread":0.19948878578113624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1965744864","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99273807,0.0011971833,0.0052246326,0.000052037845,0.0000020394518,0.0000123896,0.0002796451,0.00004209064,0.00045193636],"genre_scores_gemma":[0.9942316,0.0004605606,0.0045280494,0.000017893135,0.0000036774443,0.000024332412,0.0005761707,0.000021576448,0.00013622997],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99957603,0.00010354548,0.000024131119,0.00014777662,0.00009261172,0.000055826746],"domain_scores_gemma":[0.99788433,0.0011769072,0.00044630715,0.00015666944,0.00019150323,0.00014421727],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007445251,0.00034892347,0.00041650562,0.0017788386,0.00061619084,0.0006551051,0.0005177983,0.0008107476,0.00088579056],"category_scores_gemma":[0.0042403406,0.00030820814,0.0005827986,0.0011490324,0.0008318012,0.0009961744,0.00063672895,0.00039713946,0.00031402634],"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":[0.0006622819,0.00010737939,0.821588,0.0004360797,0.00037150097,0.0006315149,0.0014055577,0.07742052,0.04253925,0.006481203,0.0004516708,0.04790501],"study_design_scores_gemma":[0.000045444936,0.00032310575,0.77958333,0.0001597171,0.00016185119,0.0034552254,0.00077089365,0.17359622,0.009090197,0.026335679,0.0063730944,0.00010533988],"about_ca_topic_score_codex":0.002355269,"about_ca_topic_score_gemma":0.0014444869,"teacher_disagreement_score":0.002355269,"about_ca_system_score_codex":0.0010787694,"about_ca_system_score_gemma":0.00042929093,"threshold_uncertainty_score":0.0078270435},"labels":[],"label_agreement":null},{"id":"W1966813277","doi":"10.1186/1471-2105-15-205","title":"A model-based information sharing protocol for profile Hidden Markov Models used for HIV-1 recombination detection","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"HIV Research and Treatment","field":"Immunology and Microbiology","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 Guelph","funders":"National Institute of Allergy and Infectious Diseases; National Institutes of Health; Deutsche Forschungsgemeinschaft","keywords":"Hidden Markov model; Subfamily; Inference; Biology; Computer science; Subtyping; Computational biology; Markov chain; Data mining; Artificial intelligence; Genetics; Machine learning; Gene","score_opus":0.04325172657652011,"score_gpt":0.2975769257119991,"score_spread":0.254325199135479,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1966813277","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002542148,0.000021450192,0.9957728,0.00005391683,0.000014075861,0.00012870313,0.00011476803,0.0011552046,0.00019688562],"genre_scores_gemma":[0.1526483,0.00008725226,0.842938,0.00014449691,0.000037740672,0.0013732993,0.0013326731,0.00039351292,0.0010447112],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9938591,0.0024386775,0.0006826606,0.0011170926,0.0016443611,0.0002581532],"domain_scores_gemma":[0.9886339,0.0056421864,0.0005996455,0.0032683676,0.0015957138,0.00026017087],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006941231,0.0014348911,0.0012105475,0.0015092266,0.0011881868,0.0015245925,0.0034349344,0.0028649117,0.004720524],"category_scores_gemma":[0.0275446,0.0011301355,0.0016237065,0.0014202928,0.000980956,0.0034455603,0.0042810086,0.003574822,0.0018731616],"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":[0.0014652102,0.0006592616,0.004748719,0.00046021113,0.0005747377,0.001207432,0.00070723897,0.37891534,0.06053039,0.09570554,0.008711217,0.44631475],"study_design_scores_gemma":[0.000030838295,0.00005087135,0.000158422,0.000011718254,0.000022371518,0.000102375205,0.00001868501,0.97236055,0.007640658,0.018140266,0.00143377,0.00002937785],"about_ca_topic_score_codex":0.0018801624,"about_ca_topic_score_gemma":0.0018978257,"teacher_disagreement_score":0.006941231,"about_ca_system_score_codex":0.0012785535,"about_ca_system_score_gemma":0.002764025,"threshold_uncertainty_score":0.03670919},"labels":[],"label_agreement":null},{"id":"W1967609592","doi":"10.1186/1471-2105-9-388","title":"Sequence based residue depth prediction using evolutionary information and predicted secondary structure","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Nankai University; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computational biology; DNA microarray; Sequence (biology); Computer science; Bioinformatics; Biology; Artificial intelligence; Data mining; Genetics; Gene; Gene expression","score_opus":0.013576292047910131,"score_gpt":0.22304533816159058,"score_spread":0.20946904611368045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1967609592","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78809446,0.0011098273,0.20692037,0.000106738415,0.00002770442,0.00010424763,0.0011243847,0.0012009185,0.0013113478],"genre_scores_gemma":[0.8712393,0.00029352683,0.12548824,0.000036149362,0.000020371985,0.000045529083,0.0024330856,0.000064335196,0.0003795009],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999498,0.00012022179,0.000039712108,0.00016581242,0.00013491258,0.00004138702],"domain_scores_gemma":[0.99865615,0.0004991656,0.00036115033,0.000107385655,0.00027028564,0.00010578251],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012892976,0.00089625805,0.0007664071,0.0016457527,0.00024810754,0.0005564054,0.00039254065,0.00060017564,0.0008220984],"category_scores_gemma":[0.0023942548,0.00030850625,0.000714107,0.0008256882,0.00027563286,0.00069053355,0.00056358025,0.00056179054,0.00064711575],"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":[0.0025532735,0.0005824903,0.18764277,0.0008975188,0.00065989816,0.0005067017,0.00025808415,0.16081575,0.29888025,0.0014653766,0.002800916,0.3429371],"study_design_scores_gemma":[0.000062380575,0.00029896223,0.048123717,0.00005523214,0.00011990858,0.0005241599,0.00003703064,0.9140881,0.03385526,0.0015543993,0.0012362326,0.000044622564],"about_ca_topic_score_codex":0.0010349941,"about_ca_topic_score_gemma":0.0013061608,"teacher_disagreement_score":0.0016457527,"about_ca_system_score_codex":0.00046724963,"about_ca_system_score_gemma":0.00061132835,"threshold_uncertainty_score":0.006818533},"labels":[],"label_agreement":null},{"id":"W1968385806","doi":"10.1186/1471-2105-12-s11-a1","title":"Highlights from the Student Council Symposium 2011 at the International Conference on Intelligent Systems for Molecular Biology and European Conference on Computational Biology","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Oxford; Iowa State University; European Bioinformatics Institute; Genome Canada","keywords":"Context (archaeology); Computational biology; Engineering ethics; Research council; Library science; Systems biology; Biology; Computer science; Engineering; Philosophy","score_opus":0.09850664232369968,"score_gpt":0.31348265163778444,"score_spread":0.21497600931408475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1968385806","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0050599515,0.03687427,0.004294714,0.32618883,0.54522,0.00056845736,0.0038164658,0.00046405298,0.07751324],"genre_scores_gemma":[0.039957542,0.05211966,0.004779308,0.038085256,0.36864194,0.00064345653,0.007891463,0.0013625846,0.48651877],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99453366,0.00089855684,0.0002887383,0.00063966116,0.0026810223,0.0009583632],"domain_scores_gemma":[0.9776625,0.0011213049,0.00082251965,0.00035986223,0.009279778,0.010754102],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011100552,0.0018242238,0.0011148279,0.0018383048,0.0039766356,0.008884597,0.0016741027,0.0038527604,0.044881355],"category_scores_gemma":[0.009544863,0.0005101988,0.0012669325,0.002031214,0.000773018,0.0029983702,0.004663666,0.005880182,0.02741833],"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":[0.000107134336,0.00006639953,0.00024606855,0.00021256036,0.000007317268,0.000054893906,0.00014258262,0.00008828857,0.0002661346,0.0008045074,0.9662191,0.03178507],"study_design_scores_gemma":[0.000018218983,0.000076978205,0.0016222639,0.00019620701,0.00001321926,0.000032752258,0.00024771286,0.00008459184,0.00029894436,0.0005636254,0.99682695,0.000018473886],"about_ca_topic_score_codex":0.00436956,"about_ca_topic_score_gemma":0.013402355,"teacher_disagreement_score":0.044881355,"about_ca_system_score_codex":0.0033518362,"about_ca_system_score_gemma":0.009090096,"threshold_uncertainty_score":0.15014303},"labels":[],"label_agreement":null},{"id":"W1969973065","doi":"10.1186/1471-2105-15-11","title":"kruX: matrix-based non-parametric eQTL discovery","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Biotechnology and Biological Sciences Research Council","keywords":"Expression quantitative trait loci; Parametric statistics; Computer science; Test statistic; Statistical hypothesis testing; Robustness (evolution); Quantitative trait locus; Multiple comparisons problem; Outlier; Computational biology; Biology; Genetics; Mathematics; Statistics; Artificial intelligence; Genotype; Single-nucleotide polymorphism; Gene","score_opus":0.011050091680946818,"score_gpt":0.2604783079881021,"score_spread":0.2494282163071553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969973065","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0086157955,0.0004705949,0.9328811,0.00041042143,0.00016271812,0.00032847447,0.007073079,0.048830293,0.0012275962],"genre_scores_gemma":[0.093511686,0.00028624941,0.8852733,0.00076326553,0.000099764286,0.0021140515,0.008695201,0.0065613915,0.0026951868],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99523395,0.0022371768,0.00031085298,0.0011744587,0.0008397005,0.00020382386],"domain_scores_gemma":[0.9822717,0.014858729,0.00065749435,0.0015003027,0.00050093,0.00021084964],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0092033455,0.0016499019,0.002098197,0.0023328376,0.001112636,0.0027365542,0.003548405,0.0014846036,0.02749328],"category_scores_gemma":[0.036989205,0.0013375042,0.0037128842,0.0020531816,0.001544733,0.0015849401,0.004362438,0.002880051,0.006689134],"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":[0.0030104269,0.0004696978,0.027004007,0.0041560116,0.003203469,0.0022735696,0.0012316304,0.10491983,0.017862728,0.082151674,0.1401117,0.6136052],"study_design_scores_gemma":[0.0011001859,0.00046091827,0.0063806516,0.00022376767,0.00044742375,0.0016115721,0.00020945148,0.77332425,0.012276165,0.15165232,0.0520663,0.0002469241],"about_ca_topic_score_codex":0.0018032523,"about_ca_topic_score_gemma":0.0028317769,"teacher_disagreement_score":0.02749328,"about_ca_system_score_codex":0.0007539579,"about_ca_system_score_gemma":0.002553764,"threshold_uncertainty_score":0.09197414},"labels":[],"label_agreement":null},{"id":"W1970025484","doi":"10.1186/1471-2105-11-s10-p1","title":"Human protein-protein interaction prediction","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Biotechnology and Biological Sciences Research Council; Canadian Institutes of Health Research","keywords":"Computer science; UniProt; Interactome; RefSeq; Gene ontology; Data mining; Set (abstract data type); Feature (linguistics); Similarity (geometry); Domain (mathematical analysis); Bayesian probability; Information retrieval; Machine learning; Artificial intelligence; Biology; Gene; Mathematics; Genome","score_opus":0.010798290032959106,"score_gpt":0.24204393179336045,"score_spread":0.23124564176040135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1970025484","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.078319885,0.020560548,0.10518588,0.0017718659,0.00086617615,0.0008403879,0.71494657,0.023438353,0.054070424],"genre_scores_gemma":[0.18862025,0.0037903597,0.09326645,0.0010638648,0.0002648315,0.00064564456,0.70195603,0.0007937217,0.009598842],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992466,0.00013277108,0.000054086253,0.00022861049,0.00023788285,0.00010012534],"domain_scores_gemma":[0.9995572,0.00017176807,0.000037706177,0.00007537184,0.000112333604,0.000045587596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008465846,0.001229225,0.0011918797,0.00268037,0.0007876412,0.00091242156,0.001006147,0.0011932787,0.03898544],"category_scores_gemma":[0.0019813068,0.0003494341,0.0013101277,0.0036277734,0.00024600452,0.00065749226,0.0010460394,0.0008071532,0.038097933],"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":[0.0014495009,0.00030162508,0.03331571,0.0039338353,0.00034668526,0.0020781576,0.0001363004,0.008927558,0.018065045,0.0043009226,0.7244041,0.20274068],"study_design_scores_gemma":[0.00045610228,0.000692531,0.078126654,0.0009929533,0.00060420885,0.0087251365,0.00034579707,0.09775957,0.027365122,0.020968549,0.7637873,0.00017611834],"about_ca_topic_score_codex":0.0021119143,"about_ca_topic_score_gemma":0.0023462065,"teacher_disagreement_score":0.03898544,"about_ca_system_score_codex":0.00043318424,"about_ca_system_score_gemma":0.0010301945,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W1970439912","doi":"10.1186/1471-2105-14-87","title":"Empirical Bayes estimation of posterior probabilities of enrichment: A comparative study of five estimators of the local false discovery rate","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; University of Ottawa","keywords":"False discovery rate; Estimator; Bonferroni correction; Multiple comparisons problem; Statistics; Mathematics; Bayes' theorem; Histogram; Computer science; Bayesian probability; Biology; Artificial intelligence; Genetics","score_opus":0.017311316872554647,"score_gpt":0.2692022317274214,"score_spread":0.25189091485486675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1970439912","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033962958,0.0061970185,0.9569492,0.00046289616,0.00010636798,0.00022726854,0.0001851522,0.00042867134,0.0014804323],"genre_scores_gemma":[0.4862412,0.0048313253,0.5048415,0.00051099085,0.00045712935,0.0009303475,0.00080094225,0.00047050987,0.00091601507],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9207301,0.057734556,0.0039480003,0.008307892,0.008329541,0.00094981893],"domain_scores_gemma":[0.2550783,0.7143049,0.012313025,0.009533774,0.007894103,0.0008758888],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.15316734,0.002241318,0.0032918984,0.0068869535,0.0013340838,0.0051852786,0.004422443,0.0040358095,0.0022385493],"category_scores_gemma":[0.44828695,0.0011447415,0.0030526053,0.00476268,0.0055629727,0.008337237,0.0031471893,0.0042981347,0.0004952132],"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":[0.0019977598,0.00037902337,0.119497746,0.004156131,0.0056591714,0.0010893856,0.002751411,0.28118473,0.0034003686,0.13810033,0.0035214063,0.43826264],"study_design_scores_gemma":[0.0003859979,0.0011033112,0.043834258,0.0018959546,0.002339561,0.0025314135,0.0011764534,0.74464643,0.0054460135,0.18824956,0.007817429,0.0005735613],"about_ca_topic_score_codex":0.002312984,"about_ca_topic_score_gemma":0.0012456576,"teacher_disagreement_score":0.15316734,"about_ca_system_score_codex":0.0024143714,"about_ca_system_score_gemma":0.0022307446,"threshold_uncertainty_score":0.810036},"labels":[],"label_agreement":null},{"id":"W1970616250","doi":"10.1186/1471-2105-13-123","title":"Quartet decomposition server: a platform for analyzing phylogenetic trees","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; West Virginia University; National Science Foundation","keywords":"Phylogenetic tree; Phylogenetic network; Tree (set theory); Phylogenetics; Decomposition; Biology; Web server; Genomics; Identification (biology); Genome; Computer science; Evolutionary biology; Data mining; Gene; Computational biology; The Internet; Genetics; Ecology; Mathematics; Combinatorics; World Wide Web","score_opus":0.023527810550278343,"score_gpt":0.2710020579131435,"score_spread":0.2474742473628652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1970616250","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014084708,0.000622332,0.5334521,0.00033916565,0.00035808107,0.00045906228,0.035870675,0.4109362,0.0038776423],"genre_scores_gemma":[0.10139493,0.00094355165,0.6837231,0.00035573877,0.00023468184,0.0014123619,0.1574859,0.04827369,0.0061760657],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990613,0.00022049708,0.00012062774,0.0002252918,0.00025786663,0.000114438204],"domain_scores_gemma":[0.99723923,0.0010009574,0.00026741,0.0005299937,0.0005031373,0.00045937786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032290402,0.0022341115,0.0016404205,0.0035182592,0.0013983459,0.0030569402,0.0034468703,0.0014608469,0.030461062],"category_scores_gemma":[0.008693984,0.0015975162,0.0017045991,0.0037281215,0.00064079836,0.0031817998,0.0026574854,0.0030377284,0.020545522],"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":[0.005222512,0.0009915016,0.014951737,0.0037318736,0.001044628,0.0022162555,0.0021045953,0.019973218,0.08380404,0.018458027,0.44752008,0.39998153],"study_design_scores_gemma":[0.001992258,0.0006556825,0.016802803,0.00069717417,0.0004330042,0.0026173953,0.00074008625,0.57356495,0.05462043,0.08730982,0.25984645,0.0007199671],"about_ca_topic_score_codex":0.0017313904,"about_ca_topic_score_gemma":0.0017033467,"teacher_disagreement_score":0.030461062,"about_ca_system_score_codex":0.00070404925,"about_ca_system_score_gemma":0.0017406564,"threshold_uncertainty_score":0.101902425},"labels":[],"label_agreement":null},{"id":"W1971536409","doi":"10.1186/1471-2105-11-s4-o3","title":"Genomic analysis of a rare human tumor","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Degradation and Inhibitors","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vancouver General Hospital; Provincial Health Services Authority; BC Cancer Agency","funders":"","keywords":"Art history; Classics; Philosophy; Art","score_opus":0.010321697484914799,"score_gpt":0.2472995598436294,"score_spread":0.2369778623587146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1971536409","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98551756,0.0010570098,0.0073780143,0.0001470255,0.000023255692,0.00007816266,0.0028117648,0.00012479225,0.002862468],"genre_scores_gemma":[0.98997515,0.0006679537,0.0051195137,0.00007004773,0.000009105184,0.00003156067,0.002737486,0.000012177799,0.0013770327],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9998859,0.000011049813,0.000007716559,0.000040608316,0.00003680476,0.000017843999],"domain_scores_gemma":[0.99989283,0.000031175,0.00002227312,0.000017624763,0.000020019164,0.000016023583],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005815479,0.00009729356,0.00013763219,0.0005658336,0.0002103521,0.00020233596,0.00008393591,0.000204041,0.0009134628],"category_scores_gemma":[0.00028077923,0.000069390764,0.0001607842,0.00033274444,0.00014175022,0.00005816067,0.00015567642,0.00016974739,0.00021727433],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016822889,0.000022800376,0.016556555,0.000076044686,0.000029519584,0.0040831715,0.00013190204,0.00023383861,0.95786333,0.00040203263,0.0002721546,0.020160321],"study_design_scores_gemma":[0.000028123519,0.0010169082,0.48840865,0.000034744742,0.00019335668,0.05844205,0.00042978622,0.0030941982,0.41683725,0.0011076401,0.03038085,0.000026415797],"about_ca_topic_score_codex":0.0010242483,"about_ca_topic_score_gemma":0.0017276584,"teacher_disagreement_score":0.0010242483,"about_ca_system_score_codex":0.00016089769,"about_ca_system_score_gemma":0.00017989108,"threshold_uncertainty_score":0.0030558705},"labels":[],"label_agreement":null},{"id":"W1972818612","doi":"10.1186/1471-2105-12-s1-s4","title":"On the PATHGROUPS approach to rapid small phylogeny","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Université de Montréal; Computer Research Institute of Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Heuristic; Simulated annealing; Computer science; Genome; Phylogenetics; Set (abstract data type); Computational biology; Sequence (biology); Greedy algorithm; DNA microarray; Data mining; Algorithm; Biology; Theoretical computer science; Artificial intelligence; Gene; Genetics","score_opus":0.05217310429469563,"score_gpt":0.20729530492198414,"score_spread":0.15512220062728851,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1972818612","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0067032943,0.00017492,0.9901869,0.00031578456,0.000029342165,0.000066252425,0.000112758724,0.00070788164,0.0017029161],"genre_scores_gemma":[0.059607197,0.0002870419,0.93617696,0.00016881968,0.000064628766,0.00028551713,0.000510204,0.00047747727,0.002422062],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989436,0.00047474046,0.000041474268,0.0001980766,0.00026769747,0.00007447514],"domain_scores_gemma":[0.99628663,0.0020903312,0.00022189795,0.0008470333,0.00039402765,0.00016012185],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021819284,0.00082075293,0.00088696915,0.002050245,0.001532781,0.0013987948,0.0021608027,0.0012533183,0.008660936],"category_scores_gemma":[0.009253174,0.0006415754,0.00096173916,0.002331432,0.0017141968,0.0033732941,0.0036417143,0.002345934,0.0023626934],"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":[0.0003716851,0.00014760782,0.0014558613,0.0002872597,0.00007916675,0.0002304477,0.00072407373,0.2979069,0.010608015,0.35109407,0.00722886,0.32986614],"study_design_scores_gemma":[0.00006795024,0.0001436838,0.0003529819,0.00004795157,0.000022839235,0.000144014,0.00009768918,0.59349674,0.003814361,0.37853083,0.023232218,0.000048761725],"about_ca_topic_score_codex":0.003313835,"about_ca_topic_score_gemma":0.005003103,"teacher_disagreement_score":0.008660936,"about_ca_system_score_codex":0.0011301124,"about_ca_system_score_gemma":0.0014409039,"threshold_uncertainty_score":0.028973758},"labels":[],"label_agreement":null},{"id":"W1973231190","doi":"10.1186/1471-2105-15-82","title":"Transient protein-protein interface prediction: datasets, features, algorithms, and the RAD-T predictor","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":58,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"McGill University","keywords":"Machine learning; Computer science; Artificial intelligence; Docking (animal); Protein–protein interaction; Set (abstract data type); Predictive modelling; Interface (matter); Data mining; Algorithm; Biology","score_opus":0.005182954369622684,"score_gpt":0.21526032901183562,"score_spread":0.21007737464221293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1973231190","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84040505,0.0075389044,0.055523857,0.0030867937,0.00045360014,0.00091917295,0.07748557,0.010871468,0.00371563],"genre_scores_gemma":[0.6500512,0.0010386345,0.11988802,0.00051542016,0.00014166514,0.0008975141,0.22617714,0.00021034857,0.0010801625],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977043,0.0006350439,0.00029634812,0.0005901803,0.00062880164,0.00014526508],"domain_scores_gemma":[0.99606943,0.0017085054,0.0004428543,0.00072131143,0.00071218214,0.00034559378],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0052296007,0.0014365914,0.0007197789,0.0026069467,0.0009938438,0.001555967,0.0023280627,0.0020066795,0.0010893366],"category_scores_gemma":[0.0077289524,0.00021535541,0.0011567903,0.0028004663,0.0007071364,0.0013640319,0.0013029837,0.0022557054,0.00094266987],"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":[0.0039187768,0.0062691853,0.24564926,0.0031744817,0.0013197713,0.0014109467,0.00023651174,0.20351687,0.016800249,0.0036431712,0.16526045,0.34880033],"study_design_scores_gemma":[0.0007520744,0.0019177294,0.09944368,0.00025960032,0.00035140407,0.0018444312,0.00039936506,0.8336238,0.029690452,0.0064495793,0.025110878,0.00015696978],"about_ca_topic_score_codex":0.004491121,"about_ca_topic_score_gemma":0.0046602786,"teacher_disagreement_score":0.0052296007,"about_ca_system_score_codex":0.0012338919,"about_ca_system_score_gemma":0.0015075569,"threshold_uncertainty_score":0.027657151},"labels":[],"label_agreement":null},{"id":"W1974821006","doi":"10.1186/1471-2105-14-167","title":"Identifying cancer mutation targets across thousands of samples: MuteProc, a high throughput mutation analysis pipeline","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Cancer Genomics and Diagnostics","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":true,"ca_institutions":"BC Cancer Agency","funders":"","keywords":"Mutation; Pipeline (software); DNA microarray; Throughput; Computational biology; Mutation testing; Genetics; Biology; Cancer; Mutation rate; Computer science; Gene; Gene expression; Programming language","score_opus":0.019643209953688755,"score_gpt":0.29781806443139286,"score_spread":0.2781748544777041,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1974821006","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047385044,0.0019427154,0.67778474,0.0011209571,0.00027908,0.0011005497,0.06981111,0.19534305,0.0052328007],"genre_scores_gemma":[0.080031656,0.0005314587,0.83863074,0.0006734959,0.0000889227,0.0010813872,0.06629502,0.008244046,0.0044232192],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982566,0.00015820707,0.00012940938,0.00068008306,0.0006516487,0.00012408511],"domain_scores_gemma":[0.99756193,0.0009853415,0.00018142718,0.00043242442,0.0006579288,0.0001808685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003170027,0.001780032,0.0011366052,0.0031972774,0.0013404385,0.0023499564,0.0019784172,0.0009856517,0.007949624],"category_scores_gemma":[0.00673451,0.0012007459,0.0018555596,0.0024687883,0.0004928678,0.0012343586,0.0023701335,0.0016501971,0.005848544],"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":[0.0022901257,0.00038724765,0.028922569,0.0018850163,0.0011397842,0.0014312904,0.00083997945,0.022677798,0.16486755,0.005048076,0.17509197,0.59541863],"study_design_scores_gemma":[0.0008016571,0.0007441576,0.050076798,0.00024740226,0.00080706895,0.0036833347,0.00046323382,0.41791445,0.27778265,0.034019664,0.21290483,0.0005547224],"about_ca_topic_score_codex":0.008269458,"about_ca_topic_score_gemma":0.012339035,"teacher_disagreement_score":0.008269458,"about_ca_system_score_codex":0.0011844153,"about_ca_system_score_gemma":0.0032357525,"threshold_uncertainty_score":0.026594102},"labels":[],"label_agreement":null},{"id":"W1976093396","doi":"10.1186/1471-2105-13-151","title":"Towards a theoretical understanding of false positives in DNA motif finding","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Motif (music); False positive paradox; DNA microarray; Computational biology; Sequence motif; DNA; Computer science; True positive rate; DNA sequencing; Biology; Artificial intelligence; Genetics; Gene; Gene expression","score_opus":0.02154658368688884,"score_gpt":0.25463714486312017,"score_spread":0.23309056117623134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1976093396","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022677088,0.0011870328,0.97028446,0.002186927,0.00011213185,0.000091573565,0.00013293668,0.00051323633,0.0028145674],"genre_scores_gemma":[0.55589753,0.0021814378,0.4347646,0.0025710799,0.0006441847,0.0010291673,0.0005606789,0.00058294454,0.0017683534],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9699314,0.014121316,0.0015048535,0.004157886,0.009067167,0.0012173422],"domain_scores_gemma":[0.39799297,0.558378,0.015642531,0.01644189,0.009957822,0.0015868425],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.049488798,0.0028410556,0.0028251868,0.0058697555,0.0019487807,0.0064465934,0.008583241,0.0068736468,0.0043531754],"category_scores_gemma":[0.33616874,0.0023685317,0.0030650746,0.003107875,0.013930923,0.015840469,0.0058151665,0.010477111,0.0009147492],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002663452,0.00029245796,0.015973076,0.0011494135,0.000261027,0.0009061917,0.0008517885,0.52051544,0.0038318222,0.40463498,0.003494275,0.04782321],"study_design_scores_gemma":[0.000030225463,0.00008119026,0.0007785112,0.00016540539,0.000038294398,0.00040272434,0.000064913125,0.7380286,0.0019736958,0.25779212,0.0005921141,0.000052170057],"about_ca_topic_score_codex":0.0019003846,"about_ca_topic_score_gemma":0.001132775,"teacher_disagreement_score":0.049488798,"about_ca_system_score_codex":0.005066419,"about_ca_system_score_gemma":0.0037132262,"threshold_uncertainty_score":0.2617249},"labels":[],"label_agreement":null},{"id":"W1976192231","doi":"10.1186/1471-2105-11-546","title":"Optimizing transformations for automated, high throughput analysis of flow cytometry data","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":105,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Terry Fox Research Institute; Montreal Clinical Research Institute","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health","keywords":"Bioconductor; Computer science; Outlier; Data transformation; Transformation (genetics); Preprocessor; Throughput; Normalization (sociology); Data mining; Context (archaeology); Data conversion; Data pre-processing; Artificial intelligence; Biology","score_opus":0.03282107336187351,"score_gpt":0.2891452926312239,"score_spread":0.2563242192693504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1976192231","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022985002,0.00015037229,0.9619662,0.00024088759,0.000042830932,0.00026494195,0.00078325253,0.0128417825,0.0007247391],"genre_scores_gemma":[0.13000414,0.00019344504,0.86249965,0.00017830818,0.000035176487,0.0008635769,0.002822766,0.0027143932,0.0006885022],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9941221,0.0022386224,0.0005436583,0.0010899738,0.0017069216,0.0002987149],"domain_scores_gemma":[0.98054254,0.0116435625,0.0015564108,0.0030918303,0.0029042554,0.00026150563],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0115199,0.0016607778,0.0009391691,0.0022491599,0.0009770767,0.002387273,0.0025637762,0.0010931528,0.003429858],"category_scores_gemma":[0.0473611,0.0005724437,0.0016437335,0.0026019984,0.0012986171,0.0018097854,0.0022131063,0.002514093,0.0028446813],"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":[0.00095039717,0.0005640201,0.020550126,0.0010919829,0.00034023088,0.0006476934,0.0010367834,0.3929362,0.09284469,0.025135225,0.018806158,0.44509658],"study_design_scores_gemma":[0.00008014096,0.00024033476,0.005394717,0.00006547899,0.000058493766,0.00034262027,0.00020446532,0.8760664,0.07104977,0.033314176,0.0130926715,0.00009077308],"about_ca_topic_score_codex":0.0024008546,"about_ca_topic_score_gemma":0.0029243897,"teacher_disagreement_score":0.0115199,"about_ca_system_score_codex":0.001817207,"about_ca_system_score_gemma":0.003100422,"threshold_uncertainty_score":0.060923755},"labels":[],"label_agreement":null},{"id":"W1979217166","doi":"10.1186/1471-2105-13-54","title":"Mining biological information from 3D short time-series gene expression data: the OPTricluster algorithm","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Plant Biotechnology Institute; National Research Council Canada","funders":"National Research Council Canada","keywords":"Cluster analysis; Biological data; Data mining; Computer science; Arabidopsis thaliana; Data set; DNA microarray; Algorithm; Computational biology; Biology; Artificial intelligence; Pattern recognition (psychology); Bioinformatics; Gene; Gene expression; Genetics","score_opus":0.04298185814857665,"score_gpt":0.27080440351767165,"score_spread":0.22782254536909502,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979217166","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045579586,0.000535506,0.9515175,0.00018952096,0.000027972612,0.00010306622,0.00048636104,0.0012246292,0.00033577142],"genre_scores_gemma":[0.19946031,0.0003198329,0.7962267,0.0001713136,0.000045093537,0.00028666915,0.0025223808,0.0001463492,0.00082146894],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99927753,0.00014116039,0.000082561746,0.00024352604,0.00019807082,0.000057188958],"domain_scores_gemma":[0.9987192,0.0006809451,0.00015574922,0.00014679546,0.00025486454,0.000042385895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001569253,0.0009789856,0.0015203811,0.0026419996,0.00052134274,0.0008459694,0.0016486212,0.0011806728,0.0010018154],"category_scores_gemma":[0.0031215702,0.00039584245,0.0017047639,0.0024431718,0.0006080916,0.000861457,0.0010996562,0.0008103232,0.00056921627],"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":[0.00052049255,0.00018229877,0.009264454,0.0003123645,0.00039479605,0.0002958259,0.0002485608,0.41294304,0.010691891,0.0050670365,0.004841626,0.55523765],"study_design_scores_gemma":[0.000013834104,0.000031755793,0.0006097348,0.000008804711,0.000016810409,0.00008902311,0.000020918358,0.99497247,0.0012607158,0.002344362,0.0006223308,0.000009181226],"about_ca_topic_score_codex":0.0034474193,"about_ca_topic_score_gemma":0.003234255,"teacher_disagreement_score":0.0034474193,"about_ca_system_score_codex":0.0005431519,"about_ca_system_score_gemma":0.0010446183,"threshold_uncertainty_score":0.008299112},"labels":[],"label_agreement":null},{"id":"W1979486483","doi":"10.1186/1471-2105-9-293","title":"Indel PDB: A database of structural insertions and deletions derived from sequence alignments of closely related proteins","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Genome British Columbia; Michael Smith Health Research BC; Genome Canada","keywords":"Indel; Protein Data Bank (RCSB PDB); INDEL Mutation; Protein Data Bank; Biology; Sequence (biology); Sequence alignment; Computational biology; Multiple sequence alignment; Genetics; Protein structure; Protein secondary structure; Peptide sequence; Gene; Biochemistry","score_opus":0.020820656183266284,"score_gpt":0.24764042432717712,"score_spread":0.22681976814391083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979486483","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031045904,0.00657575,0.03511106,0.00042584108,0.000266936,0.00041550247,0.8609109,0.055212338,0.01003578],"genre_scores_gemma":[0.019549213,0.0016268569,0.038175162,0.00015275947,0.000047967613,0.00027412473,0.93703663,0.0020401252,0.0010971822],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99886775,0.0001560424,0.0001672565,0.00032197253,0.00038882517,0.000098198696],"domain_scores_gemma":[0.9983632,0.0004117354,0.0004790511,0.00024714152,0.00029381993,0.00020501927],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012485939,0.0027240368,0.0027826063,0.0053451825,0.0012699497,0.0019329772,0.0035588224,0.0020218906,0.018672673],"category_scores_gemma":[0.003926522,0.0010504724,0.0010866931,0.007881877,0.0004529251,0.0023560578,0.0013975531,0.0023119156,0.019385481],"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":[0.0040932405,0.00073232065,0.021221025,0.01521836,0.0008318287,0.003808433,0.000629069,0.00604436,0.08991503,0.0066221235,0.74369603,0.10718818],"study_design_scores_gemma":[0.0013385715,0.0005144148,0.028519575,0.0008077583,0.00064718875,0.0058042128,0.00035914988,0.014282142,0.031397775,0.006537849,0.90952677,0.00026474323],"about_ca_topic_score_codex":0.0020615512,"about_ca_topic_score_gemma":0.003998094,"teacher_disagreement_score":0.018672673,"about_ca_system_score_codex":0.0010250849,"about_ca_system_score_gemma":0.0026752849,"threshold_uncertainty_score":0.062466323},"labels":[],"label_agreement":null},{"id":"W1979595209","doi":"10.1186/1471-2105-14-61","title":"ETHNOPRED: a novel machine learning method for accurate continental and sub-continental ancestry identification and population stratification correction","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Health Services; Alberta Innovates; University of Alberta","funders":"Alberta Innovates; University of Alberta; Alberta Cancer Foundation","keywords":"International HapMap Project; Population stratification; Ancestry-informative marker; Single-nucleotide polymorphism; Population; Biology; Allele frequency; Classifier (UML); Evolutionary biology; Artificial intelligence; Genetics; Computational biology; Computer science; Genotype; Demography; Gene","score_opus":0.027115380264424675,"score_gpt":0.30137540958180353,"score_spread":0.27426002931737886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979595209","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038702626,0.00084430043,0.9547751,0.00040780654,0.00019763652,0.0001426678,0.0009217711,0.002870204,0.0011378963],"genre_scores_gemma":[0.35636505,0.00031427728,0.6340738,0.0008701904,0.00022141731,0.000527986,0.0040944926,0.00031356982,0.0032191812],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983381,0.00058197696,0.00013779283,0.000491975,0.00032997172,0.00012010736],"domain_scores_gemma":[0.99789375,0.0010347404,0.0001585602,0.00032985664,0.00048783325,0.00009521749],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003631227,0.0010668153,0.0012006264,0.0019414852,0.00082620647,0.0008740878,0.0019433515,0.0011038892,0.0015337331],"category_scores_gemma":[0.006862585,0.0003880661,0.0011086551,0.0012383052,0.00050571293,0.00075904204,0.001883791,0.002282901,0.00074452575],"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":[0.00032467706,0.00019764437,0.028494129,0.00010759253,0.00041580986,0.0002315234,0.00022252677,0.10255099,0.004154543,0.0037453321,0.014311907,0.84524333],"study_design_scores_gemma":[0.000058408372,0.00005541016,0.0031577346,0.000028565555,0.000047815858,0.0001367228,0.000054135257,0.9824906,0.0018375014,0.007374756,0.004731692,0.000026543423],"about_ca_topic_score_codex":0.004694877,"about_ca_topic_score_gemma":0.0067988676,"teacher_disagreement_score":0.004694877,"about_ca_system_score_codex":0.000669747,"about_ca_system_score_gemma":0.0011984371,"threshold_uncertainty_score":0.01920402},"labels":[],"label_agreement":null},{"id":"W1980415335","doi":"10.1186/1471-2105-8-282","title":"Statistical analysis and significance testing of serial analysis of gene expression data using a Poisson mixture model","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Occupational Cancer Research Centre","funders":"Michael Smith Health Research BC; Canadian Institutes of Health Research; Western Canada Research Grid","keywords":"Negative binomial distribution; Poisson distribution; Mixture model; Count data; Statistics; Binomial test; Expression (computer science); Variance (accounting); Binomial distribution; Goodness of fit; Statistical model; Poisson regression; Statistical hypothesis testing; Computer science; Quasi-likelihood; Mathematics","score_opus":0.06164966361484645,"score_gpt":0.3232141807709215,"score_spread":0.26156451715607504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1980415335","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.092512816,0.0004431222,0.9009395,0.00022814372,0.0001901127,0.0012302789,0.0013352896,0.0018911121,0.0012296748],"genre_scores_gemma":[0.41173324,0.00030629517,0.5781743,0.0002201776,0.00008943133,0.005390726,0.0020289787,0.0007949198,0.001261859],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9643561,0.021678805,0.001824689,0.005481498,0.00579177,0.0008671691],"domain_scores_gemma":[0.86262774,0.12086519,0.004667545,0.007237816,0.0039061352,0.000695635],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.045099784,0.0015544173,0.0028096656,0.002893773,0.001498336,0.0022855285,0.0035749958,0.0021174005,0.008367434],"category_scores_gemma":[0.122868545,0.00079180574,0.0043001533,0.0034541816,0.0029881003,0.0018396124,0.0018969192,0.004351545,0.0010244636],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0077247685,0.0017472957,0.14229578,0.004677021,0.007831359,0.0033630452,0.003164466,0.35602286,0.04227016,0.07815136,0.015442043,0.33730972],"study_design_scores_gemma":[0.00020531817,0.0019272824,0.033331387,0.00026369258,0.00061734265,0.0008676883,0.0004960682,0.9104287,0.016084708,0.02742678,0.008175432,0.00017566416],"about_ca_topic_score_codex":0.0026161838,"about_ca_topic_score_gemma":0.0012492554,"teacher_disagreement_score":0.045099784,"about_ca_system_score_codex":0.00163632,"about_ca_system_score_gemma":0.002492671,"threshold_uncertainty_score":0.23851329},"labels":[],"label_agreement":null},{"id":"W1981890639","doi":"10.1186/1471-2105-10-206","title":"Representative transcript sets for evaluating a translational initiation sites predictor","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Calgary Laboratory Services","keywords":"Benchmark (surveying); Set (abstract data type); Population; Computer science; Data mining; Data set; Expression (computer science); Sequence (biology); Test set; Computational biology; Algorithm; Biology; Machine learning; Artificial intelligence; Genetics","score_opus":0.04719615713034547,"score_gpt":0.35682675967505173,"score_spread":0.30963060254470626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981890639","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.63406014,0.001083627,0.34062088,0.00028065452,0.00010435245,0.00063630164,0.016479004,0.0049481764,0.0017868663],"genre_scores_gemma":[0.5364089,0.00048010814,0.39231145,0.00008107931,0.00006936496,0.0014476975,0.06829531,0.0002562674,0.00064977957],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99765116,0.00057962746,0.00029910397,0.00040973394,0.0009262107,0.00013410937],"domain_scores_gemma":[0.98876804,0.0065501384,0.00090355234,0.0008961627,0.0025544472,0.00032758346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037488102,0.0010852133,0.0007208796,0.0034787597,0.0007979388,0.0010774743,0.0013507556,0.0010494621,0.0013470434],"category_scores_gemma":[0.011481184,0.0002681362,0.0009235629,0.0036697725,0.00066951185,0.00096651714,0.0009570376,0.000879633,0.0008129161],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002709844,0.0013772076,0.12551649,0.0019251971,0.00059785694,0.0008812135,0.0004219434,0.40817538,0.0705333,0.005256532,0.012999351,0.36960572],"study_design_scores_gemma":[0.00013308106,0.0015973755,0.021501472,0.00007736874,0.0001923299,0.00061768363,0.00028263737,0.89310294,0.070622124,0.0042826273,0.0075189443,0.00007138848],"about_ca_topic_score_codex":0.0019865618,"about_ca_topic_score_gemma":0.0020859751,"teacher_disagreement_score":0.0037488102,"about_ca_system_score_codex":0.00092634995,"about_ca_system_score_gemma":0.0015586293,"threshold_uncertainty_score":0.019825816},"labels":[],"label_agreement":null},{"id":"W1983546999","doi":"10.1186/1471-2105-9-s12-s7","title":"Extracting transcription factor binding sites from unaligned gene sequences with statistical models","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alpha Technologies (Canada)","funders":"National Science Council","keywords":"DNA binding site; Chromatin immunoprecipitation; Computational biology; DNA microarray; Transcription factor; Computer science; False positive paradox; Bayes' theorem; Genetics; Binding site; Biology; Statistical model; Gene; Data mining; Bayesian probability; Gene expression; Artificial intelligence; Promoter","score_opus":0.03288224196300695,"score_gpt":0.2342696851814729,"score_spread":0.20138744321846594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1983546999","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026127035,0.00008868775,0.97224045,0.000040892166,0.000004284124,0.000034236677,0.00028359436,0.0010480206,0.00013276434],"genre_scores_gemma":[0.17678817,0.00024080895,0.81874585,0.000075118856,0.000021734733,0.0002912259,0.0029378405,0.00025512866,0.0006441162],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99954885,0.0001249101,0.000032201162,0.00014191284,0.00012341,0.000028697421],"domain_scores_gemma":[0.9973158,0.0022255084,0.00014667981,0.00010754099,0.00015900077,0.000045461868],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010387864,0.00095872284,0.0007959673,0.0018128512,0.0003658222,0.00055749447,0.0010801603,0.0007353857,0.0013023285],"category_scores_gemma":[0.0051469356,0.0008258636,0.0012536359,0.001316245,0.00045185798,0.0006235615,0.00059015077,0.001096247,0.0007269602],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027633712,0.00013747686,0.0071470668,0.00022272854,0.00016231393,0.00022856558,0.00009930344,0.8507462,0.015937349,0.004270644,0.0007949027,0.1199771],"study_design_scores_gemma":[0.000009961378,0.000013942487,0.00053826463,0.000004799637,0.000015528714,0.000036629874,0.000004998321,0.9932603,0.0021201505,0.0036525836,0.00033390406,0.000008897223],"about_ca_topic_score_codex":0.005602872,"about_ca_topic_score_gemma":0.0076240273,"teacher_disagreement_score":0.005602872,"about_ca_system_score_codex":0.00073348865,"about_ca_system_score_gemma":0.0018501749,"threshold_uncertainty_score":0.011140525},"labels":[],"label_agreement":null},{"id":"W1984586858","doi":"10.1186/1471-2105-12-245","title":"In-silico prediction of disorder content using hybrid sequence representation","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":64,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; Killam Trusts","keywords":"Computer science; Correlation; In silico; Proteome; Artificial intelligence; Pattern recognition (psychology); Computational biology; Mathematics; Biology; Bioinformatics; Genetics","score_opus":0.09182528233705196,"score_gpt":0.2713163947888129,"score_spread":0.17949111245176097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1984586858","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8305651,0.0002874129,0.1642072,0.00012903199,0.000026459502,0.00009086512,0.0008947546,0.002724371,0.0010747422],"genre_scores_gemma":[0.9330837,0.00010307216,0.06341573,0.00007464519,0.000012499636,0.00008723494,0.0026935437,0.00007173794,0.00045778364],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999684,0.00008964877,0.000023269791,0.00009226291,0.0000769622,0.00003392532],"domain_scores_gemma":[0.9983877,0.0009776438,0.00020320812,0.00009503721,0.0002501255,0.000086253815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011077257,0.0007664173,0.0007125706,0.0013428323,0.0002312651,0.00065487385,0.0007253233,0.00063417986,0.0007195292],"category_scores_gemma":[0.0024457008,0.00018960657,0.0005290532,0.00076075,0.00028970974,0.00054101774,0.00060020626,0.00048011434,0.00025769568],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014672248,0.00060553505,0.05087219,0.0002364943,0.00023643389,0.00029890065,0.000091942005,0.8409626,0.03371193,0.0011292028,0.0013667401,0.06902073],"study_design_scores_gemma":[0.000013006933,0.00006860761,0.00097085175,0.0000034234295,0.000012725904,0.000030302044,0.000006826161,0.9953595,0.0031957184,0.00023226418,0.0001022739,0.000004469735],"about_ca_topic_score_codex":0.0024263116,"about_ca_topic_score_gemma":0.0030305926,"teacher_disagreement_score":0.0024263116,"about_ca_system_score_codex":0.0007475954,"about_ca_system_score_gemma":0.00066575146,"threshold_uncertainty_score":0.0058582425},"labels":[],"label_agreement":null},{"id":"W1984599252","doi":"10.1186/1471-2105-12-299","title":"Ranking insertion, deletion and nonsense mutations based on their effect on genetic information","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Evolution and Genetic Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Biology; Genetics; Nonsense mutation; Indel; INDEL Mutation; Coding region; Mutation; Context (archaeology); Computational biology; Single-nucleotide polymorphism; Gene; Missense mutation; Genotype","score_opus":0.010218176418838525,"score_gpt":0.20795641678705967,"score_spread":0.19773824036822116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1984599252","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8584221,0.0017375271,0.13330506,0.00072785094,0.000073141535,0.00019328258,0.002666525,0.0010855377,0.0017889879],"genre_scores_gemma":[0.89010966,0.00061493804,0.10516681,0.00017908042,0.000050421135,0.000094645635,0.0031952136,0.000090162095,0.0004990738],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991271,0.00026554926,0.000086411164,0.00014736426,0.00030423026,0.00006929659],"domain_scores_gemma":[0.9935189,0.004854913,0.00069301756,0.00017653326,0.00048155006,0.0002750596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019756828,0.0006916038,0.00090168347,0.002960638,0.0004357209,0.0010164009,0.0007097718,0.00070360187,0.0016352074],"category_scores_gemma":[0.006548491,0.00015773784,0.00070068374,0.0016494399,0.00050348457,0.00052191206,0.00036336292,0.00056964316,0.00035402417],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027260089,0.000891009,0.30086243,0.0017867258,0.0011526237,0.0007172933,0.00024129933,0.32956073,0.07045374,0.0076019606,0.005635221,0.278371],"study_design_scores_gemma":[0.00020636138,0.000941916,0.08444728,0.00011028961,0.0004397257,0.00082171237,0.000135473,0.86860234,0.0251207,0.015581454,0.0034984928,0.00009426438],"about_ca_topic_score_codex":0.0019329948,"about_ca_topic_score_gemma":0.005921981,"teacher_disagreement_score":0.002960638,"about_ca_system_score_codex":0.00067491597,"about_ca_system_score_gemma":0.0012023328,"threshold_uncertainty_score":0.010448575},"labels":[],"label_agreement":null},{"id":"W1985380607","doi":"10.1186/1471-2105-14-s6-s10","title":"Analytical results on the Beauchemin model of lymphocyte migration","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Mathematical Biology Tumor Growth","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Waterloo; Nederlandse Organisatie voor Wetenschappelijk Onderzoek","keywords":"Simple (philosophy); Computer science; Stochastic modelling; Displacement (psychology); Point (geometry); Lymphocyte; Applied mathematics; Biological system; Statistical physics; Mathematics; Immunology; Biology; Statistics; Physics; Geometry","score_opus":0.0844187858694037,"score_gpt":0.2880181692788446,"score_spread":0.2035993834094409,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1985380607","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08784142,0.0033093055,0.86980563,0.0022335814,0.00018805813,0.000059026766,0.00016208779,0.00024086468,0.036160093],"genre_scores_gemma":[0.89140123,0.0043139784,0.06716303,0.00091468904,0.00030613653,0.00022568443,0.00023555903,0.00021226541,0.035227437],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996779,0.00010083392,0.000010305402,0.00004088109,0.000102746424,0.000067423505],"domain_scores_gemma":[0.9988611,0.0006276071,0.00019676007,0.000060082304,0.00016350874,0.00009109367],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007800761,0.00066509953,0.00057539734,0.0010532817,0.0007426554,0.0009387911,0.0012579694,0.0014184923,0.0023942068],"category_scores_gemma":[0.0042353785,0.00024832407,0.0008751283,0.00074338645,0.0013515243,0.0014012026,0.0010464131,0.0010917473,0.0005818207],"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":[0.000046271405,0.00003012572,0.0009852888,0.000095701915,0.000019145677,0.00023908542,0.00018764286,0.46340278,0.0055396287,0.5207185,0.0026878829,0.0060478374],"study_design_scores_gemma":[0.000006563589,0.000015149813,0.00023135067,0.000012186237,0.000006091576,0.000081572194,0.000023508972,0.9496117,0.0005201269,0.047689274,0.0017886637,0.000013832106],"about_ca_topic_score_codex":0.006136571,"about_ca_topic_score_gemma":0.0026939923,"teacher_disagreement_score":0.006136571,"about_ca_system_score_codex":0.0015125925,"about_ca_system_score_gemma":0.0008047071,"threshold_uncertainty_score":0.012201667},"labels":[],"label_agreement":null},{"id":"W1985592898","doi":"10.1186/1471-2105-12-s4-s6","title":"Deploying mutation impact text-mining software with the SADI Semantic Web Services framework","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada; New Brunswick Innovation Foundation; Canarie","keywords":"Computer science; World Wide Web; Context (archaeology); SPARQL; Web service; Semantic Web; Data science; Ontology; Reuse; Information retrieval; RDF; Biology","score_opus":0.021306098551409337,"score_gpt":0.2603210407245414,"score_spread":0.23901494217313204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1985592898","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040408824,0.00030759443,0.6510556,0.0021895359,0.00014066098,0.0012588432,0.011405466,0.28113803,0.01209551],"genre_scores_gemma":[0.16732313,0.00055474124,0.7846834,0.001088363,0.00007860704,0.00083847065,0.03011129,0.012154502,0.0031674274],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99720335,0.00035103157,0.00041175235,0.0004454527,0.0014281736,0.00016027926],"domain_scores_gemma":[0.9940724,0.002727233,0.0005772977,0.0012428019,0.0010289373,0.00035125983],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0061041457,0.00097065466,0.0007195738,0.003567818,0.0008654605,0.0025658596,0.0022272936,0.0009123677,0.0029429595],"category_scores_gemma":[0.010339154,0.00072759535,0.002080248,0.0019520099,0.0011331646,0.0031819905,0.0036461202,0.0018381648,0.0017218614],"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":[0.0021933212,0.0015176177,0.05219638,0.0041213804,0.0011722118,0.004494139,0.008292006,0.044608433,0.11503734,0.09012713,0.112501405,0.5637387],"study_design_scores_gemma":[0.00039567257,0.0002736964,0.012249374,0.00055365753,0.00041435452,0.002039154,0.001303513,0.4378112,0.1281177,0.075971045,0.34043726,0.00043343098],"about_ca_topic_score_codex":0.008307038,"about_ca_topic_score_gemma":0.008028181,"teacher_disagreement_score":0.008307038,"about_ca_system_score_codex":0.0023227911,"about_ca_system_score_gemma":0.003862672,"threshold_uncertainty_score":0.032282174},"labels":[],"label_agreement":null},{"id":"W1986157690","doi":"10.1186/1471-2105-15-318","title":"Metabolic network prediction through pairwise rational kernels","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Microbial Metabolic Engineering and Bioproduction","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Winnipeg; University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pairwise comparison; Computer science; Kernel (algebra); Support vector machine; Similarity (geometry); Artificial intelligence; Sequence (biology); Machine learning; Data mining; Pattern recognition (psychology); Mathematics; Biology","score_opus":0.009871139652815736,"score_gpt":0.21106332019350568,"score_spread":0.20119218054068994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986157690","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14943431,0.00018197352,0.84567314,0.0001366206,0.000027951048,0.000040171857,0.00027512084,0.0025382896,0.0016924441],"genre_scores_gemma":[0.9056077,0.000084563944,0.09243041,0.000026222708,0.000010667179,0.000038945047,0.000608338,0.000094585,0.001098581],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999603,0.00007320535,0.000026450865,0.00012228702,0.00012305084,0.00005202009],"domain_scores_gemma":[0.998442,0.0007819856,0.00018462,0.00017108233,0.00036106477,0.000059234357],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045153074,0.00067721226,0.00056949985,0.0009929191,0.0002659109,0.0006112311,0.0006714672,0.0005670162,0.0014902586],"category_scores_gemma":[0.0035281512,0.00024278846,0.00060459465,0.00069200894,0.00035785604,0.0015923413,0.00066495506,0.0008340441,0.00039391377],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018207257,0.000101567566,0.0035154885,0.00006855399,0.000045698038,0.00008398217,0.000040214312,0.8533165,0.0067319726,0.007336853,0.0009370309,0.12763996],"study_design_scores_gemma":[0.0000011366428,0.0000045427446,0.00010592505,7.0626265e-7,0.0000016447083,0.0000059782024,0.0000017521141,0.9975368,0.00078159414,0.0015000611,0.000057788788,0.0000020169402],"about_ca_topic_score_codex":0.0057932585,"about_ca_topic_score_gemma":0.0038636206,"teacher_disagreement_score":0.0057932585,"about_ca_system_score_codex":0.00088491867,"about_ca_system_score_gemma":0.0009507373,"threshold_uncertainty_score":0.011519134},"labels":[],"label_agreement":null},{"id":"W1987067655","doi":"10.1186/1471-2105-12-67","title":"MIR@NT@N: a framework integrating transcription factors, microRNAs and their targets to identify sub-network motifs in a meta-regulation network model","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":70,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Child and Family Research Institute; Institute for Research in Immunology and Cancer; University of British Columbia","funders":"Canadian Institutes of Health Research; National Institute of General Medical Sciences; Centre National de la Recherche Scientifique; Fonds National de la Recherche Luxembourg; Michael Smith Health Research BC; Université de Montréal; Child and Family Research Institute; Institute of Genetics; Institut National de la Santé et de la Recherche Médicale; Université du Luxembourg","keywords":"Computational biology; Gene regulatory network; microRNA; Biology; Computer science; Biological network; Systems biology; Transcription factor; Gene; Bioinformatics; Genetics; Gene expression","score_opus":0.039982651521636915,"score_gpt":0.25350007155950977,"score_spread":0.21351742003787286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987067655","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025435241,0.00018275791,0.98685247,0.00017575941,0.000028532253,0.00011472802,0.0018914407,0.0069462643,0.0012645269],"genre_scores_gemma":[0.05490677,0.0005182475,0.93547195,0.00010936919,0.000027297769,0.00064560724,0.0062974184,0.0008718005,0.0011515319],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99934584,0.00023702529,0.000063827596,0.0001573906,0.00015441471,0.00004153959],"domain_scores_gemma":[0.9991297,0.000518177,0.00009476489,0.00011408426,0.00008019317,0.00006304214],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017711064,0.0017466655,0.00094863126,0.0023716819,0.0006969639,0.0020481865,0.0022320843,0.0011009622,0.0059638554],"category_scores_gemma":[0.0030423687,0.00083977793,0.003955736,0.0011842997,0.0007378813,0.0018719443,0.0017709647,0.0013090489,0.0013379552],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029407584,0.00012193464,0.0025728417,0.0013984789,0.0005317026,0.0008716791,0.00044028493,0.71013725,0.012343646,0.18336454,0.011027024,0.07689648],"study_design_scores_gemma":[0.00003796888,0.00002417238,0.0001687518,0.000061420105,0.0000699131,0.00013069446,0.000038479073,0.93617886,0.0017029856,0.041540947,0.02002355,0.000022281874],"about_ca_topic_score_codex":0.008428083,"about_ca_topic_score_gemma":0.015751468,"teacher_disagreement_score":0.008428083,"about_ca_system_score_codex":0.0015340421,"about_ca_system_score_gemma":0.0018119297,"threshold_uncertainty_score":0.019951105},"labels":[],"label_agreement":null},{"id":"W1987588530","doi":"10.1186/1471-2105-15-329","title":"trieFinder: an efficient program for annotating Digital Gene Expression (DGE) tags","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","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 Human Genome Research Institute; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"UniGene; Computer science; DNA microarray; Annotation; Computational biology; Bioconductor; Gene Annotation; Data mining; Biology; Information retrieval; Expressed sequence tag; Gene; Genome; Genetics; Gene expression; Artificial intelligence","score_opus":0.017640864083337947,"score_gpt":0.28031880291463246,"score_spread":0.26267793883129453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987588530","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004915286,0.00050586706,0.68140227,0.0002868441,0.0002211243,0.000490291,0.02962114,0.27975422,0.0028029515],"genre_scores_gemma":[0.015233805,0.0005067084,0.8875562,0.00048121504,0.000066828165,0.002893672,0.053963352,0.03526776,0.0040304307],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99753124,0.00047219382,0.00030818974,0.0008500323,0.00065391994,0.00018447166],"domain_scores_gemma":[0.9966961,0.0019517865,0.00047562606,0.00034613936,0.00037419627,0.00015621778],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0049237674,0.0038541202,0.0019286923,0.0037509955,0.001565803,0.0029073972,0.0051282616,0.002248458,0.023151146],"category_scores_gemma":[0.0073746378,0.002414609,0.002175344,0.0026838724,0.0012722355,0.0029905674,0.0029074703,0.0056927907,0.021532249],"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":[0.004376565,0.00067809713,0.0068811183,0.0058626104,0.00084502454,0.0016630985,0.0018831112,0.019501263,0.20578155,0.016128177,0.37497315,0.36142635],"study_design_scores_gemma":[0.0010122844,0.00053434476,0.005267511,0.0010731552,0.00028892813,0.0021552371,0.00047751173,0.24434616,0.29781184,0.04034331,0.40600118,0.00068858225],"about_ca_topic_score_codex":0.0010683374,"about_ca_topic_score_gemma":0.0013632268,"teacher_disagreement_score":0.023151146,"about_ca_system_score_codex":0.0011617175,"about_ca_system_score_gemma":0.0018592965,"threshold_uncertainty_score":0.07744837},"labels":[],"label_agreement":null},{"id":"W1988766191","doi":"10.1186/1471-2105-10-244","title":"ETISEQ – an algorithm for automated elution time ion sequencing of concurrently fragmented peptides for mass spectrometry-based proteomics","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Sydney; Australian Government; Ontario Ministry of Natural Resources and Forestry","keywords":"Fragmentation (computing); Shotgun proteomics; Proteomics; Peptide; Mass spectrometry; Data acquisition; Computer science; Quantitative proteomics; Tandem mass spectrometry; Chemistry; Computational biology; Chromatography; Biology; Biochemistry","score_opus":0.02039169974329908,"score_gpt":0.2938443584831975,"score_spread":0.27345265873989844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1988766191","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005276166,0.00017244651,0.9869415,0.000052807212,0.00005097786,0.00015815272,0.00017541256,0.006852701,0.00031980895],"genre_scores_gemma":[0.01167306,0.0000790532,0.98666894,0.0000636031,0.000021116679,0.00027053384,0.00054473255,0.0002486629,0.00043032528],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998716,0.00031371776,0.00018057763,0.000292113,0.0004368939,0.00006062476],"domain_scores_gemma":[0.99850297,0.0006760078,0.00022436722,0.00013647576,0.00038248135,0.00007774212],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030358385,0.0016274677,0.00079602835,0.001660336,0.0006933807,0.0012619152,0.0021003627,0.0011307115,0.002878062],"category_scores_gemma":[0.0039424063,0.0007180897,0.0008886055,0.001103579,0.0006701704,0.0012139821,0.0013419554,0.0017525227,0.0022444713],"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":[0.001692569,0.0004166905,0.0047247917,0.0005979769,0.00034663462,0.00061716145,0.00031114146,0.044468038,0.16582426,0.008577473,0.01948019,0.7529431],"study_design_scores_gemma":[0.0003346175,0.0005322847,0.002150027,0.000068990026,0.000090705566,0.0012098252,0.000067455396,0.8337325,0.12383244,0.009654541,0.02818613,0.00014045578],"about_ca_topic_score_codex":0.0006421504,"about_ca_topic_score_gemma":0.00093810266,"teacher_disagreement_score":0.0030358385,"about_ca_system_score_codex":0.000701542,"about_ca_system_score_gemma":0.0012888354,"threshold_uncertainty_score":0.016055286},"labels":[],"label_agreement":null},{"id":"W1989871058","doi":"10.1186/s12859-014-0435-6","title":"Pollux: platform independent error correction of single and mixed genomes","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Error detection and correction; Ion semiconductor sequencing; Computer science; Software; Sequence assembly; k-mer; Word error rate; Data mining; Algorithm; Computational biology; DNA sequencing; Biology; Genetics; Artificial intelligence; Operating system; DNA; Gene","score_opus":0.03855053966665911,"score_gpt":0.24253673561506203,"score_spread":0.20398619594840292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1989871058","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04714583,0.0012339351,0.78263015,0.00035945798,0.001130539,0.00069987803,0.006243938,0.15730199,0.0032542308],"genre_scores_gemma":[0.092886455,0.00038916152,0.8743465,0.0004920007,0.00015102625,0.0010248015,0.010975052,0.014944737,0.004790317],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99234456,0.0016203918,0.0007010054,0.0020313123,0.0029170613,0.00038559653],"domain_scores_gemma":[0.9885739,0.003552304,0.0022183352,0.0032037473,0.0020987578,0.0003529283],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010027255,0.002738224,0.0016918732,0.0032767039,0.002002462,0.0029940584,0.0038076474,0.0018378682,0.0066026635],"category_scores_gemma":[0.020435272,0.0018607529,0.0021647555,0.0018769965,0.0013436327,0.002050127,0.0046542925,0.00295992,0.004303287],"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":[0.0032274604,0.0003538027,0.03446374,0.0046414873,0.0021184094,0.0013954932,0.0015100237,0.023805698,0.23026146,0.009768311,0.09856354,0.5898906],"study_design_scores_gemma":[0.00034078155,0.000667159,0.011766688,0.00048353,0.0005573118,0.0020751294,0.0002076414,0.15844317,0.7126765,0.005499002,0.10679229,0.00049074343],"about_ca_topic_score_codex":0.0015130831,"about_ca_topic_score_gemma":0.002549412,"teacher_disagreement_score":0.010027255,"about_ca_system_score_codex":0.0010237981,"about_ca_system_score_gemma":0.0024574285,"threshold_uncertainty_score":0.053029835},"labels":[],"label_agreement":null},{"id":"W1990193053","doi":"10.1186/1471-2105-11-s1-s11","title":"Fast motif recognition via application of statistical thresholds","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of Waterloo","funders":"","keywords":"Pairwise comparison; Hamming distance; Computer science; String (physics); String metric; Bounded function; Motif (music); Bottleneck; Theoretical computer science; String searching algorithm; Algorithm; Mathematics; Artificial intelligence; Pattern matching; Physics","score_opus":0.006674848646587189,"score_gpt":0.22524083350032448,"score_spread":0.2185659848537373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1990193053","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016778354,0.00015882167,0.977697,0.00016205241,0.00003221115,0.00007615908,0.00011463095,0.004080043,0.0009006583],"genre_scores_gemma":[0.25146985,0.00012312259,0.74576575,0.00025146292,0.000048000686,0.00031464733,0.0005688618,0.0004046678,0.0010535868],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99726886,0.0007155499,0.00022190034,0.0007478438,0.0008623586,0.00018343031],"domain_scores_gemma":[0.9907679,0.0059991064,0.0006673567,0.00105002,0.0012298918,0.00028576085],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026639602,0.0007282624,0.0012942478,0.0018559155,0.00063970184,0.0012688839,0.0029345946,0.001345506,0.0041964613],"category_scores_gemma":[0.016867135,0.00052666303,0.0009429331,0.0022576968,0.00094878394,0.002313149,0.0023563213,0.0021467581,0.0016017488],"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":[0.00061750284,0.0002557163,0.0062570334,0.00041419934,0.000115249924,0.00021360374,0.00026780367,0.2610442,0.029986193,0.036323227,0.007275779,0.6572295],"study_design_scores_gemma":[0.000024688637,0.000054653658,0.0003121432,0.000010163204,0.000006759805,0.000071488634,0.000019308898,0.974412,0.0050823973,0.018906455,0.0010876276,0.000012285275],"about_ca_topic_score_codex":0.00214651,"about_ca_topic_score_gemma":0.0021895159,"teacher_disagreement_score":0.0041964613,"about_ca_system_score_codex":0.0010595446,"about_ca_system_score_gemma":0.0019475875,"threshold_uncertainty_score":0.0140885115},"labels":[],"label_agreement":null},{"id":"W1991529077","doi":"10.1186/1471-2105-11-127","title":"Effects of scanning sensitivity and multiple scan algorithms on microarray data quality","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Canada","funders":"Health Canada","keywords":"Reproducibility; Scanner; Computer science; Signal-to-noise ratio (imaging); Noise (video); Sensitivity (control systems); SIGNAL (programming language); Pattern recognition (psychology); Dynamic range; Algorithm; Artificial intelligence; Data mining; Statistics; Mathematics; Computer vision","score_opus":0.028665305716843514,"score_gpt":0.3006832648283446,"score_spread":0.2720179591115011,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991529077","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26916757,0.0070898896,0.71630937,0.0015649057,0.0004140794,0.0004967612,0.0006517127,0.0019973766,0.0023083382],"genre_scores_gemma":[0.53763455,0.0016721274,0.45627198,0.00062162266,0.00012161471,0.0009694685,0.0008260743,0.001138075,0.0007444644],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.91135836,0.04900996,0.007867154,0.009433317,0.02120987,0.0011213922],"domain_scores_gemma":[0.70529366,0.25488284,0.011398536,0.014364645,0.013407972,0.00065238477],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06976224,0.0016828018,0.001368181,0.0017987791,0.0011035984,0.0034943293,0.0021829284,0.0022261497,0.0016949647],"category_scores_gemma":[0.14520477,0.0010759948,0.002123911,0.002452994,0.0022718203,0.001754734,0.0022682576,0.0020886818,0.00071973255],"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":[0.004087335,0.0004887568,0.120217554,0.0046023657,0.003327972,0.00081605406,0.002237874,0.07364821,0.4909113,0.005980708,0.0024884245,0.29119337],"study_design_scores_gemma":[0.00018657753,0.002072344,0.10017961,0.00078814325,0.0014745041,0.0026371889,0.00036426279,0.23839478,0.63005036,0.01202693,0.011311745,0.0005136363],"about_ca_topic_score_codex":0.0013403472,"about_ca_topic_score_gemma":0.0018276672,"teacher_disagreement_score":0.06976224,"about_ca_system_score_codex":0.0016669601,"about_ca_system_score_gemma":0.0013137532,"threshold_uncertainty_score":0.36894238},"labels":[],"label_agreement":null},{"id":"W1991732078","doi":"10.1186/1471-2105-12-168","title":"More accurate recombination prediction in HIV-1 using a robust decoding algorithm for HMMs","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"HIV Research and Treatment","field":"Immunology and Microbiology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo","keywords":"Hidden Markov model; Decoding methods; Breakpoint; Algorithm; Viterbi algorithm; Computer science; Markov chain; Task (project management); Artificial intelligence; Genetics; Biology; Machine learning; Engineering; Gene","score_opus":0.09920860630598254,"score_gpt":0.29572549804740794,"score_spread":0.1965168917414254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991732078","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019123197,0.00015593176,0.9776088,0.00023872657,0.000028769255,0.000026281632,0.00020141825,0.0021966572,0.00042019665],"genre_scores_gemma":[0.22827455,0.00023490208,0.76682943,0.00020770227,0.00007302336,0.00010323736,0.0017338482,0.00093768106,0.0016056363],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99840987,0.0006653881,0.00013178845,0.000384316,0.00031639924,0.000092258844],"domain_scores_gemma":[0.991901,0.0058594136,0.00028075522,0.0010689505,0.0007403006,0.00014957113],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029472918,0.0009699581,0.0013106108,0.0010455796,0.0007154649,0.0012687021,0.0017125012,0.0020653622,0.0029667895],"category_scores_gemma":[0.016707374,0.0006074894,0.00095395156,0.0012031496,0.0006308408,0.0023051274,0.0014275773,0.0025245058,0.0021046945],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038250527,0.00017320174,0.0043729744,0.00018015387,0.00012551091,0.00015685272,0.00027646232,0.72831744,0.015840923,0.010836679,0.0037727605,0.23556459],"study_design_scores_gemma":[0.0000149180805,0.000011587451,0.00019061138,0.0000069014027,0.000008787854,0.000025391711,0.0000071064205,0.99233854,0.0022470437,0.004709619,0.00042896252,0.000010505865],"about_ca_topic_score_codex":0.0054590493,"about_ca_topic_score_gemma":0.005258694,"teacher_disagreement_score":0.0054590493,"about_ca_system_score_codex":0.0009671703,"about_ca_system_score_gemma":0.0012736334,"threshold_uncertainty_score":0.015586913},"labels":[],"label_agreement":null},{"id":"W1991777830","doi":"10.1186/1471-2105-11-64","title":"ICC-CLASS: isotopically-coded cleavable crosslinking analysis software suite","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Mass Spectrometry Techniques and Applications","field":"Chemistry","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Genome British Columbia; University of Victoria","funders":"Genome British Columbia; Genome Canada","keywords":"Reagent; Software suite; Mass spectrometry; Software; Combinatorial chemistry; Chemistry; Isotopic labeling; Computer science; Peptide; Chromatography; Programming language; Organic chemistry; Biochemistry","score_opus":0.012206019377268406,"score_gpt":0.2581573950639124,"score_spread":0.245951375686644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991777830","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00395747,0.0003400758,0.25513116,0.00013189019,0.00012982624,0.00051609473,0.023753876,0.70926887,0.006770737],"genre_scores_gemma":[0.040299445,0.0011217799,0.5586192,0.0010998163,0.00015258673,0.007188123,0.16922463,0.20710257,0.015191886],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99832755,0.00028180837,0.00022005438,0.00037793833,0.0005869113,0.00020566404],"domain_scores_gemma":[0.9977494,0.0008635034,0.000351268,0.00033632232,0.0005026243,0.00019694411],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037058739,0.0028861265,0.0012946245,0.0027271332,0.0006621564,0.0021143337,0.003847539,0.0014080033,0.031582143],"category_scores_gemma":[0.004574405,0.0016047789,0.0015754768,0.0012520344,0.0006425275,0.0015145707,0.0021544113,0.0031489355,0.028807499],"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":[0.0019836328,0.0004319553,0.0048351376,0.0027026443,0.0006309056,0.000577817,0.00046298368,0.008980452,0.08299231,0.01190288,0.71971315,0.16478607],"study_design_scores_gemma":[0.0010318182,0.00056160486,0.00823419,0.00052802946,0.00030601266,0.0012414771,0.00014159906,0.16044945,0.22259346,0.019646015,0.5845939,0.0006724403],"about_ca_topic_score_codex":0.0016224472,"about_ca_topic_score_gemma":0.0018395748,"teacher_disagreement_score":0.031582143,"about_ca_system_score_codex":0.00096366764,"about_ca_system_score_gemma":0.002423104,"threshold_uncertainty_score":0.10565281},"labels":[],"label_agreement":null},{"id":"W1993373022","doi":"10.1186/1471-2105-11-550","title":"Localizing triplet periodicity in DNA and cDNA sequences","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Fractal and DNA sequence analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"National Human Genome Research Institute; National Institutes of Health; National Science Foundation","keywords":"Complementary DNA; DNA microarray; Computational biology; DNA; Genetics; Biology; DNA sequencing; Gene; Gene expression","score_opus":0.009263907348636287,"score_gpt":0.23615520734689918,"score_spread":0.2268912999982629,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993373022","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8789695,0.00019201238,0.11917817,0.00004599165,0.000021347712,0.000027824326,0.00018897638,0.0003400965,0.0010360163],"genre_scores_gemma":[0.88021785,0.00013995176,0.118715145,0.000021653146,0.000012378108,0.000044245942,0.0003600003,0.00005643878,0.00043226982],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999212,0.000008993386,0.000004616366,0.000029043522,0.000026895781,0.00000914146],"domain_scores_gemma":[0.9995394,0.00019563496,0.00011717323,0.000046452486,0.000069785994,0.000031558917],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018367422,0.000156529,0.00016767865,0.0006210876,0.00013453132,0.00018636182,0.00022810245,0.000356036,0.0008041549],"category_scores_gemma":[0.0011595847,0.00012627189,0.00017383596,0.0005352841,0.00026601387,0.0003423202,0.00021666776,0.00029279105,0.00023167691],"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":[0.00018459928,0.000041067764,0.004249129,0.00016978566,0.0000136804765,0.00034154387,0.0000929266,0.020312546,0.93753034,0.0020223362,0.00018244759,0.034859676],"study_design_scores_gemma":[0.000046051257,0.0003501027,0.032559115,0.000037089787,0.000036870882,0.0013331431,0.00013185687,0.47119835,0.48641828,0.0048341737,0.003014967,0.000039997438],"about_ca_topic_score_codex":0.0005523536,"about_ca_topic_score_gemma":0.000678279,"teacher_disagreement_score":0.0008041549,"about_ca_system_score_codex":0.00025765784,"about_ca_system_score_gemma":0.0002334221,"threshold_uncertainty_score":0.002690196},"labels":[],"label_agreement":null},{"id":"W1995701890","doi":"10.1186/s12859-015-0515-2","title":"aTRAM - automated target restricted assembly method: a fast method for assembling loci across divergent taxa from next-generation sequencing data","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":82,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; University of Illinois at Urbana-Champaign; Genome Canada; National Science Foundation","keywords":"Biology; Sequence assembly; Genome; Taxon; Computational biology; Gene; Evolutionary biology; Genetics; Ecology","score_opus":0.20391782201242342,"score_gpt":0.37389083172445037,"score_spread":0.16997300971202695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995701890","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01021114,0.0004681434,0.9323806,0.00012039737,0.00016452996,0.00027201688,0.003049008,0.052010577,0.0013236124],"genre_scores_gemma":[0.018495494,0.00019834262,0.9683205,0.0001515545,0.0000455479,0.00080287637,0.005750071,0.005224807,0.0010108395],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9970726,0.0006327493,0.00034732115,0.0008965405,0.0009205614,0.00013025201],"domain_scores_gemma":[0.99705124,0.0012260295,0.00058922305,0.0004934099,0.0005370852,0.00010301941],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003981268,0.0024422691,0.0016645691,0.004081005,0.00180785,0.0019002552,0.0032654821,0.002011929,0.0098039275],"category_scores_gemma":[0.009663228,0.0020130398,0.0035051804,0.0025044158,0.0007650346,0.0020632804,0.0023440209,0.0038621156,0.009411518],"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":[0.001400478,0.00030407478,0.010390004,0.0039871675,0.0014625987,0.0015531059,0.0019232108,0.0174734,0.34275413,0.011486988,0.083118945,0.52414584],"study_design_scores_gemma":[0.00051565917,0.00060591544,0.011475256,0.0005949581,0.00057201064,0.0027176684,0.0003593957,0.39212024,0.3613852,0.014984857,0.21408379,0.0005850616],"about_ca_topic_score_codex":0.0011301474,"about_ca_topic_score_gemma":0.0021271554,"teacher_disagreement_score":0.0098039275,"about_ca_system_score_codex":0.0007973873,"about_ca_system_score_gemma":0.0015314732,"threshold_uncertainty_score":0.032797396},"labels":[],"label_agreement":null},{"id":"W1995803230","doi":"10.1186/1471-2105-12-s11-a4","title":"Variant detection and the Autism sequencing project","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Autism Spectrum Disorder Research","field":"Neuroscience","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"","keywords":"Autism; Computational biology; DNA microarray; DNA sequencing; Biology; Genetics; Computer science; Medicine; Gene; Gene expression","score_opus":0.09087766062733735,"score_gpt":0.2811225290659108,"score_spread":0.19024486843857344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995803230","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15706289,0.02931169,0.13229871,0.019564921,0.0018015836,0.0015141945,0.6097871,0.009161349,0.039497554],"genre_scores_gemma":[0.26530397,0.009167978,0.23223624,0.0047193537,0.0011353367,0.0030848216,0.4714058,0.0017780032,0.011168538],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9916898,0.0030256913,0.00058332237,0.002210694,0.0020904741,0.00040007304],"domain_scores_gemma":[0.990114,0.0049636764,0.0013206649,0.0010853845,0.001384598,0.0011316882],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0086080525,0.0012643539,0.00095624244,0.0042538354,0.0011040443,0.0018299617,0.0015128792,0.0021057834,0.008241155],"category_scores_gemma":[0.021295153,0.0005423385,0.0006162681,0.004986713,0.00064050104,0.00081200287,0.0027966641,0.0014795145,0.0036451505],"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":[0.0045295293,0.00035957547,0.14013591,0.0027102658,0.0017507162,0.0018934162,0.00069981144,0.018540038,0.008828963,0.03176705,0.33396783,0.45481688],"study_design_scores_gemma":[0.0015534085,0.00091586966,0.1819847,0.002163232,0.0014356133,0.0072801965,0.00036924068,0.045273803,0.010553903,0.1897833,0.55839443,0.00029232362],"about_ca_topic_score_codex":0.0077539156,"about_ca_topic_score_gemma":0.0062570516,"teacher_disagreement_score":0.0086080525,"about_ca_system_score_codex":0.00087742985,"about_ca_system_score_gemma":0.0028737327,"threshold_uncertainty_score":0.0455243},"labels":[],"label_agreement":null},{"id":"W1996392240","doi":"10.1186/1471-2105-12-s11-a13","title":"Spectral classification of short numerical exon and intron sequences","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Fractal and DNA sequence analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor; Queen's University; University of Ottawa","funders":"","keywords":"Intron; Exon; Computational biology; Genome; Annotation; Representation (politics); Human genome; Genome project; Genetics; Computer science; Biology; Gene","score_opus":0.03505932177159128,"score_gpt":0.252325421605623,"score_spread":0.21726609983403172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1996392240","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28697276,0.000331313,0.7063443,0.00018997304,0.00014148084,0.000052530806,0.00044481302,0.0007080116,0.0048147202],"genre_scores_gemma":[0.62258893,0.00024011763,0.3737135,0.00006535454,0.00008544985,0.00008274694,0.0010891801,0.00013621447,0.001998462],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996332,0.000087128115,0.000039391485,0.00007131326,0.00013217788,0.000036745485],"domain_scores_gemma":[0.99849045,0.0005333922,0.00023470465,0.00021046554,0.00042815207,0.000102778045],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045322263,0.00027382452,0.00025137773,0.0025334938,0.0003234217,0.0007895837,0.00038760394,0.00046307387,0.0017870399],"category_scores_gemma":[0.0030412364,0.00008645297,0.0002598815,0.0013374583,0.00053396047,0.0013572276,0.00037660127,0.00040087735,0.0006744048],"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":[0.0007056841,0.00014409574,0.011206733,0.0003158934,0.00003571334,0.00035303965,0.0005164767,0.026448317,0.2735709,0.091539346,0.0026093503,0.5925545],"study_design_scores_gemma":[0.000044518496,0.00037464141,0.018290969,0.00012071034,0.000056503115,0.0018319514,0.0006156644,0.74953556,0.09095883,0.12118979,0.016822428,0.00015842715],"about_ca_topic_score_codex":0.00026212932,"about_ca_topic_score_gemma":0.00023700467,"teacher_disagreement_score":0.0025334938,"about_ca_system_score_codex":0.00026985735,"about_ca_system_score_gemma":0.00023849419,"threshold_uncertainty_score":0.0059782267},"labels":[],"label_agreement":null},{"id":"W1996644160","doi":"10.1186/1471-2105-12-s5-s5","title":"Unsupervised fuzzy pattern discovery in gene expression data","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Gene; DNA microarray; Gene cluster; Gene expression; Cluster analysis; Computational biology; Set (abstract data type); Fuzzy logic; Biology; Class (philosophy); Expression (computer science); Discretization; Gene regulatory network; Data mining; Genetics; Computer science; Mathematics; Artificial intelligence","score_opus":0.07563724883632382,"score_gpt":0.27097313619929536,"score_spread":0.19533588736297153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1996644160","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.118419915,0.00027430378,0.8792354,0.00019870224,0.000019979625,0.00016025882,0.00044211844,0.0004681812,0.0007812034],"genre_scores_gemma":[0.41080365,0.00018036897,0.58727765,0.00006542694,0.000028670385,0.00025865977,0.00084115803,0.00003409778,0.00051034894],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99805105,0.00052195025,0.00013088963,0.0003918323,0.00080695655,0.000097446806],"domain_scores_gemma":[0.99460196,0.0037240186,0.00045937535,0.00035243676,0.0007883939,0.000073994765],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022951781,0.00044038644,0.00096053776,0.0021978656,0.00052091485,0.0008399147,0.0011163162,0.0006783712,0.00048896],"category_scores_gemma":[0.0069221635,0.00026247595,0.0008226039,0.0020712377,0.000824197,0.0006606108,0.00056785234,0.00083234394,0.00015914846],"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":[0.00060909614,0.00041749259,0.027540246,0.00074004056,0.00034629344,0.0009412926,0.0007620545,0.4182138,0.04247139,0.016994758,0.0018981189,0.48906544],"study_design_scores_gemma":[0.000022426704,0.000048307247,0.004650669,0.000018480137,0.000020869724,0.00020765784,0.0000691877,0.9689331,0.011728747,0.01339785,0.00088431337,0.000018404578],"about_ca_topic_score_codex":0.002435524,"about_ca_topic_score_gemma":0.0022197624,"teacher_disagreement_score":0.002435524,"about_ca_system_score_codex":0.0009386047,"about_ca_system_score_gemma":0.0010324793,"threshold_uncertainty_score":0.0121382475},"labels":[],"label_agreement":null},{"id":"W1996936565","doi":"10.1186/1471-2105-12-s5-s6","title":"A robust approach to optimizing multi-source information for enhancing genomics retrieval performance","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Ranking (information retrieval); Information retrieval; Context (archaeology); Learning to rank; Reciprocal; Data mining; Mean reciprocal rank; Rank (graph theory); Baseline (sea)","score_opus":0.1088627182265075,"score_gpt":0.24921181395124425,"score_spread":0.14034909572473675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1996936565","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025535068,0.0011055224,0.9687363,0.00027647405,0.00003936741,0.00011514947,0.00029476575,0.0028412968,0.0010561799],"genre_scores_gemma":[0.381508,0.0005490275,0.6140406,0.00023524875,0.00014498377,0.00026399718,0.0014304529,0.0004275303,0.0014002166],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971529,0.000871688,0.00021618902,0.00058894523,0.0010114439,0.00015873378],"domain_scores_gemma":[0.99750096,0.0011020256,0.00028521192,0.00037864884,0.0006627102,0.000070451584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042048944,0.00235847,0.0015680328,0.0040651923,0.00066630787,0.0014932234,0.0021731413,0.0018512567,0.0016704743],"category_scores_gemma":[0.008646618,0.00058825436,0.0018018442,0.0034826978,0.0007594624,0.0029643883,0.0021178036,0.0012289908,0.0009793768],"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":[0.00062009215,0.0004222016,0.0029934524,0.00047733175,0.0004067676,0.00024736053,0.00024326397,0.38483843,0.05257759,0.0064493706,0.0055516358,0.54517245],"study_design_scores_gemma":[0.00004330139,0.00016482134,0.0009275142,0.000013363223,0.00012036115,0.00013500935,0.000049562925,0.97722197,0.015989149,0.0036406196,0.0016542118,0.000040255614],"about_ca_topic_score_codex":0.0041739093,"about_ca_topic_score_gemma":0.004030347,"teacher_disagreement_score":0.0042048944,"about_ca_system_score_codex":0.0012798072,"about_ca_system_score_gemma":0.0019240745,"threshold_uncertainty_score":0.022237897},"labels":[],"label_agreement":null},{"id":"W1997463836","doi":"10.1186/1471-2105-10-s8-i1","title":"Between proteins and phenotypes: annotation and interpretation of mutations","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Annotation; Phenotype; Computational biology; Population; Relevance (law); Biology; Mutation; Ontology; Genetics; Computer science; Bioinformatics; Gene; Medicine","score_opus":0.014369674518912403,"score_gpt":0.2682694366990187,"score_spread":0.2538997621801063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997463836","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042695973,0.011790206,0.84467906,0.0066312756,0.0010527252,0.0011593603,0.04712456,0.024261793,0.02060504],"genre_scores_gemma":[0.19317496,0.006554077,0.73818547,0.0020007172,0.00057406106,0.0006505864,0.05052581,0.0039358586,0.004398483],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99376243,0.001756341,0.001095355,0.0014421031,0.001736268,0.00020754531],"domain_scores_gemma":[0.99104017,0.0048241382,0.0013527481,0.0014182656,0.0011079551,0.0002567847],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005698211,0.0018411531,0.0014325831,0.00984331,0.00107258,0.005108659,0.0028619396,0.0020993722,0.0064947954],"category_scores_gemma":[0.018150348,0.0006577314,0.0016031356,0.008116954,0.0017119307,0.0041024885,0.00451118,0.0017413326,0.00290667],"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":[0.0012399292,0.00048539965,0.02914921,0.007051465,0.0008337199,0.013339774,0.008501736,0.017134216,0.044572458,0.07665678,0.08665514,0.7143802],"study_design_scores_gemma":[0.00014473987,0.00014825989,0.03213742,0.0034711573,0.00074820174,0.009967394,0.0032856234,0.07013856,0.024514295,0.34908304,0.5059645,0.00039683562],"about_ca_topic_score_codex":0.003507168,"about_ca_topic_score_gemma":0.0018092857,"teacher_disagreement_score":0.00984331,"about_ca_system_score_codex":0.0011293332,"about_ca_system_score_gemma":0.0021748284,"threshold_uncertainty_score":0.030135334},"labels":[],"label_agreement":null},{"id":"W1998271648","doi":"10.1186/1471-2105-15-s12-s2","title":"Discovering co-occurring patterns and their biological significance in protein families","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Amino acid; Biology; Conserved sequence; Computational biology; Peptide sequence; Phylogenetic tree; Sequence alignment; Closeness; Genetics; Protein sequencing; Multiple sequence alignment; Taxonomic rank; Evolutionary biology; Bioinformatics; Gene; Ecology","score_opus":0.01057686144615,"score_gpt":0.2285720905072953,"score_spread":0.2179952290611453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998271648","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90533847,0.0016955031,0.08893724,0.00025395854,0.000030155603,0.00013425996,0.0015021849,0.0005158199,0.0015924786],"genre_scores_gemma":[0.93971443,0.00033687975,0.05770634,0.000024471283,0.000035875968,0.00009004349,0.0018180112,0.000045360037,0.00022863744],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981158,0.00033565584,0.00020929192,0.0006993681,0.0004610792,0.00017884761],"domain_scores_gemma":[0.98813766,0.007024296,0.0026513713,0.0006582732,0.0010573093,0.0004710949],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016243228,0.0004766808,0.00058723113,0.008117464,0.0010412139,0.0013607511,0.0007280969,0.00073170173,0.001437281],"category_scores_gemma":[0.0089667225,0.00027623796,0.00087521086,0.006576182,0.0011087481,0.0015069512,0.000995586,0.0007620401,0.00050979096],"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":[0.0010051613,0.0004281369,0.7268288,0.0010026166,0.0005939352,0.0016497846,0.0018117821,0.01304442,0.03647539,0.006471784,0.0020633484,0.20862488],"study_design_scores_gemma":[0.00009738743,0.00043276427,0.57018954,0.00022800986,0.0005791689,0.00671757,0.0029517636,0.32686287,0.025092266,0.05795601,0.008754235,0.00013843788],"about_ca_topic_score_codex":0.0020919412,"about_ca_topic_score_gemma":0.0018069932,"teacher_disagreement_score":0.008117464,"about_ca_system_score_codex":0.00078094436,"about_ca_system_score_gemma":0.0008393715,"threshold_uncertainty_score":0.008590281},"labels":[],"label_agreement":null},{"id":"W1998617521","doi":"10.1186/1471-2105-13-204","title":"Enabling dynamic network analysis through visualization in TVNViewer","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; National Science Foundation; National Institutes of Health; Advanced Research Projects Agency; U.S. Public Health Service; Defense Advanced Research Projects Agency","keywords":"Visualization; Computer science; DNA microarray; Data science; Computational biology; Biology; Data mining; Genetics; Gene expression","score_opus":0.013569325778311854,"score_gpt":0.2731328761428668,"score_spread":0.2595635503645549,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998617521","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009778357,0.00033515407,0.8390176,0.0006535082,0.00012413517,0.000137449,0.0061583896,0.13956778,0.004227655],"genre_scores_gemma":[0.12387515,0.001085214,0.8404359,0.00044039442,0.00013079304,0.00085163536,0.013095392,0.016278563,0.0038070534],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99922013,0.00022778878,0.00008489607,0.00013426381,0.00026815824,0.00006477007],"domain_scores_gemma":[0.995171,0.0033228514,0.00031213945,0.0005499423,0.00044276385,0.00020127711],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022930074,0.0014214125,0.00075453834,0.003132606,0.00045907282,0.0022409768,0.0019836787,0.0010718533,0.02061614],"category_scores_gemma":[0.008289407,0.0006212933,0.0011658281,0.001483608,0.0005339684,0.0027890308,0.0031605887,0.0019703356,0.0031640865],"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":[0.0016348979,0.0003899725,0.00724533,0.0028255186,0.00055098854,0.0021231552,0.0045015127,0.06847048,0.10199287,0.06335406,0.22188553,0.5250257],"study_design_scores_gemma":[0.00039592164,0.00013760009,0.004097019,0.00062197645,0.00011564469,0.0010095217,0.00035840928,0.6218535,0.07548099,0.08320179,0.21242887,0.00029881572],"about_ca_topic_score_codex":0.0025311331,"about_ca_topic_score_gemma":0.002817122,"teacher_disagreement_score":0.02061614,"about_ca_system_score_codex":0.00056786125,"about_ca_system_score_gemma":0.0009066111,"threshold_uncertainty_score":0.06896788},"labels":[],"label_agreement":null},{"id":"W1999079801","doi":"10.1186/1471-2105-8-206","title":"Selecting dissimilar genes for multi-class classification, an application in cancer subtyping","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; University of Alberta","keywords":"Subtyping; Classifier (UML); Support vector machine; DNA microarray; Gene expression profiling; Microarray analysis techniques; Microarray; Cluster analysis; Gene chip analysis; Computational biology; Computer science; Artificial intelligence; Pattern recognition (psychology); Gene; Data mining; Biology; Gene expression; Genetics","score_opus":0.0687708537069852,"score_gpt":0.35891243433735676,"score_spread":0.29014158063037154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1999079801","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32464257,0.001057953,0.6710579,0.00044923526,0.00011628103,0.00027855544,0.0003404844,0.00075246807,0.0013045811],"genre_scores_gemma":[0.7162152,0.00020671648,0.2812723,0.00013605146,0.000067503395,0.0002528089,0.00076470914,0.00008164531,0.0010029963],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99877936,0.00026247906,0.00009351431,0.00030733887,0.00046316636,0.0000942598],"domain_scores_gemma":[0.9981243,0.000896954,0.00021138672,0.00016952258,0.0004954311,0.00010228508],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016532368,0.00064596225,0.00081481604,0.0019686758,0.0006908482,0.0005947596,0.00070421404,0.0010200308,0.0011168331],"category_scores_gemma":[0.0037533166,0.00014659068,0.00085722405,0.002089461,0.0006555433,0.0005212235,0.00056771055,0.0006775118,0.00031078025],"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":[0.00089276687,0.0005111548,0.023765622,0.0003943184,0.00017624468,0.00036974807,0.00026411904,0.06584748,0.14265083,0.0038758342,0.0027026478,0.75854915],"study_design_scores_gemma":[0.000073691626,0.0004177938,0.025444334,0.00003280432,0.00013841012,0.00061262486,0.00018916166,0.8843832,0.07369139,0.01007753,0.0048709423,0.00006805171],"about_ca_topic_score_codex":0.0010214691,"about_ca_topic_score_gemma":0.0008151372,"teacher_disagreement_score":0.0019686758,"about_ca_system_score_codex":0.0005815776,"about_ca_system_score_gemma":0.00057673344,"threshold_uncertainty_score":0.008743286},"labels":[],"label_agreement":null},{"id":"W2000165838","doi":"10.1186/1471-2105-9-373","title":"Increasing the efficiency of bacterial transcription simulations: When to exclude the genome without loss of accuracy","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bacterial Genetics and Biotechnology","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":"College of Family Physicians of Canada; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Computational biology; DNA microarray; Genome; Computer science; Genetics; Biology; Bioinformatics; Gene; Gene expression","score_opus":0.022106200086113265,"score_gpt":0.24717745227963084,"score_spread":0.22507125219351756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2000165838","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9061194,0.0023576205,0.07842489,0.0024747176,0.00016638894,0.00012246611,0.0006278846,0.0020983776,0.007608319],"genre_scores_gemma":[0.94356513,0.00086841884,0.053421583,0.00030196205,0.000028997662,0.00011553458,0.00046623513,0.0005750796,0.000657061],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988972,0.00047960412,0.00009217562,0.00011993281,0.0002618774,0.00014923446],"domain_scores_gemma":[0.9849225,0.011654682,0.00054403365,0.0015032294,0.0010336073,0.00034191326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022835669,0.0011069978,0.0009135172,0.000419124,0.0004604547,0.0012284735,0.0014025251,0.0015090248,0.0016960931],"category_scores_gemma":[0.021285048,0.00045350875,0.00076147064,0.00053110125,0.00080785266,0.0018030617,0.001239509,0.001791368,0.00043588105],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013090352,0.00044503037,0.013548568,0.0005802104,0.00019613643,0.00022690641,0.0004782201,0.92352605,0.029832546,0.003613416,0.0012078286,0.025036016],"study_design_scores_gemma":[0.00010546919,0.00019141419,0.00194939,0.00009059159,0.000070289054,0.000044249067,0.00013440482,0.97250587,0.021347353,0.0022801019,0.0012413709,0.000039618484],"about_ca_topic_score_codex":0.008734969,"about_ca_topic_score_gemma":0.0057258825,"teacher_disagreement_score":0.008734969,"about_ca_system_score_codex":0.0008200199,"about_ca_system_score_gemma":0.00087049184,"threshold_uncertainty_score":0.017368257},"labels":[],"label_agreement":null},{"id":"W2001869885","doi":"10.1186/1471-2105-13-3","title":"Self-organizing ontology of biochemically relevant small molecules","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; European Bioinformatics Institute","keywords":"Computer science; Ontology; Annotation; Class (philosophy); Automation; Data science; Information retrieval; Artificial intelligence","score_opus":0.028460466526800444,"score_gpt":0.2657235007835735,"score_spread":0.23726303425677303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2001869885","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051128093,0.00076328695,0.91873085,0.001231016,0.00017570012,0.000665944,0.007183682,0.0030817955,0.017039532],"genre_scores_gemma":[0.20797597,0.0013028637,0.7672557,0.00034695864,0.00014589558,0.00084262085,0.015361519,0.00030776436,0.006460653],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987012,0.00019257443,0.00020449632,0.0003029026,0.00050841854,0.00009033342],"domain_scores_gemma":[0.998187,0.0004983602,0.00026117815,0.00044492556,0.00047866793,0.00012974537],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012443762,0.00049831613,0.00045643054,0.004749016,0.001033364,0.0019193104,0.0012717993,0.00081879215,0.0017503402],"category_scores_gemma":[0.0022881068,0.00031234056,0.0017119909,0.0033589911,0.0012557271,0.0033058987,0.0010033065,0.0009558002,0.0005602911],"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":[0.0001620742,0.00038244293,0.013355713,0.0011614474,0.00021074893,0.0015020452,0.0018814281,0.032553177,0.039954297,0.71412194,0.012559092,0.18215565],"study_design_scores_gemma":[0.0000613293,0.00010418726,0.011169127,0.00040798797,0.00037122107,0.0018316526,0.00074143993,0.2787581,0.024653392,0.3306203,0.35118786,0.00009343731],"about_ca_topic_score_codex":0.009116566,"about_ca_topic_score_gemma":0.010290083,"teacher_disagreement_score":0.009116566,"about_ca_system_score_codex":0.002261637,"about_ca_system_score_gemma":0.0037597173,"threshold_uncertainty_score":0.018126965},"labels":[],"label_agreement":null},{"id":"W2002496559","doi":"10.1186/1471-2105-13-s3-s6","title":"Detection of gene expression changes at chromosomal rearrangement breakpoints in evolution","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Breakpoint; Biology; Genetics; Gene; Genome; Gene duplication; Chromosomal rearrangement; Chromosome; Computational biology; Karyotype","score_opus":0.013626995074313983,"score_gpt":0.2269050628505561,"score_spread":0.21327806777624211,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2002496559","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99025625,0.00066564267,0.007749649,0.000070884016,0.0000062173544,0.000008517086,0.0006230448,0.00010188839,0.0005180299],"genre_scores_gemma":[0.9904612,0.00020597827,0.0072397157,0.000041225994,0.000009572007,0.00001777737,0.0017491373,0.000029558916,0.00024586442],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99953187,0.000073889736,0.000026299402,0.00022939897,0.00007908349,0.000059374444],"domain_scores_gemma":[0.99819356,0.001049835,0.00038478518,0.00011564689,0.00014944597,0.00010667219],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000591723,0.00019034962,0.00036755222,0.0014578631,0.00028653236,0.0005825848,0.00030817496,0.00056039955,0.0017456291],"category_scores_gemma":[0.002853412,0.0001373794,0.00030907235,0.0014413059,0.00048119266,0.00034067026,0.00043667643,0.0005065053,0.00034102524],"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":[0.001320404,0.0000959194,0.5498107,0.0005249638,0.00036666557,0.0004185849,0.00059315254,0.006820493,0.38334545,0.0011348061,0.0003731723,0.055195544],"study_design_scores_gemma":[0.000024328127,0.00019058443,0.95151246,0.000023138822,0.000109302506,0.00089574,0.0002320628,0.010684004,0.032944802,0.0015914482,0.0017710527,0.000021023821],"about_ca_topic_score_codex":0.0012057235,"about_ca_topic_score_gemma":0.0015741909,"teacher_disagreement_score":0.0017456291,"about_ca_system_score_codex":0.0004282176,"about_ca_system_score_gemma":0.00015908701,"threshold_uncertainty_score":0.005839765},"labels":[],"label_agreement":null},{"id":"W2003601914","doi":"10.1186/1471-2105-13-s11-s7","title":"Biological event composition","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Coreference; Biomedical text mining; Event (particle physics); Natural language processing; Task (project management); Artificial intelligence; Parsing; Information extraction; Resolution (logic); Information retrieval; Text mining","score_opus":0.037038019145623165,"score_gpt":0.29050173312038574,"score_spread":0.2534637139747626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2003601914","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019223448,0.0031819867,0.81951714,0.0024194191,0.0014720901,0.0017726934,0.021422029,0.041982863,0.08900823],"genre_scores_gemma":[0.12164637,0.002492975,0.74837387,0.0017702867,0.0009804828,0.0011088335,0.06608334,0.006235595,0.051308207],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962991,0.00047772794,0.0005056218,0.001419633,0.0010885213,0.00020949956],"domain_scores_gemma":[0.99540955,0.001676575,0.00032661628,0.00095096056,0.0013207037,0.0003156383],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002791653,0.0021153179,0.0009919921,0.004507674,0.0025092822,0.0037032675,0.0025538139,0.001604769,0.052531287],"category_scores_gemma":[0.007792289,0.0007551303,0.0021883827,0.0029499526,0.0011232782,0.005725375,0.0051589967,0.0018536487,0.023854062],"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":[0.0014811446,0.00033417266,0.0078016785,0.00387417,0.00020839521,0.0026691244,0.0023466498,0.0047345846,0.04282884,0.11427283,0.113189496,0.7062589],"study_design_scores_gemma":[0.00009456349,0.0001255109,0.0033281907,0.00037577472,0.00024052506,0.0025797363,0.00061889907,0.027403766,0.052821185,0.10138873,0.8109006,0.00012257363],"about_ca_topic_score_codex":0.002744809,"about_ca_topic_score_gemma":0.0027359389,"teacher_disagreement_score":0.052531287,"about_ca_system_score_codex":0.0015332878,"about_ca_system_score_gemma":0.0026674226,"threshold_uncertainty_score":0.17573464},"labels":[],"label_agreement":null},{"id":"W2004206064","doi":"10.1186/1471-2105-10-s1-s17","title":"Short read DNA fragment anchoring algorithm","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Waterloo","keywords":"Fragment (logic); DNA microarray; Computer science; Computational biology; Anchoring; DNA; Algorithm; Genetics; Biology; Gene; Engineering; Gene expression","score_opus":0.015695801694614292,"score_gpt":0.24388270002834928,"score_spread":0.22818689833373498,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2004206064","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0072442545,0.000491785,0.98018974,0.00008360149,0.00007118833,0.00014546025,0.0010847113,0.009619647,0.0010696372],"genre_scores_gemma":[0.033774793,0.00024982798,0.9582511,0.00013012429,0.00004675944,0.000338573,0.004067827,0.00044988107,0.0026911423],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987055,0.00023689782,0.00014106424,0.00042221294,0.00041487903,0.00007942048],"domain_scores_gemma":[0.99649894,0.001271308,0.00036556218,0.00044812326,0.0013138207,0.00010220259],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014597839,0.0013373806,0.0010818106,0.0017463488,0.0006496412,0.0010686702,0.0018569212,0.0015563337,0.0088003045],"category_scores_gemma":[0.0070622275,0.0003531072,0.000814662,0.0019381202,0.00036036375,0.0013408758,0.00070357806,0.0011509142,0.008876022],"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":[0.00093120686,0.0001788786,0.003423207,0.0012046616,0.00017310478,0.0003664305,0.00019272671,0.03653103,0.090594225,0.0049197883,0.01420441,0.8472803],"study_design_scores_gemma":[0.0002624905,0.00058582204,0.0046433164,0.00016271787,0.00016754256,0.0020640178,0.00010907611,0.70558286,0.20834592,0.016501697,0.06140263,0.00017196286],"about_ca_topic_score_codex":0.0015793781,"about_ca_topic_score_gemma":0.0012238579,"teacher_disagreement_score":0.0088003045,"about_ca_system_score_codex":0.00048632428,"about_ca_system_score_gemma":0.0010694503,"threshold_uncertainty_score":0.029439926},"labels":[],"label_agreement":null},{"id":"W2004594378","doi":"10.1186/1471-2105-15-s9-s14","title":"A better sequence-read simulator program for metagenomics","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":53,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal University Hospital; University of Saskatchewan","funders":"","keywords":"Metagenomics; Computer science; Shotgun sequencing; Data mining; Emulation; Sequence (biology); Flexibility (engineering); Data quality; DNA sequencing; Biology; Metric (unit); Statistics; Engineering","score_opus":0.028154508968319534,"score_gpt":0.2794824156312894,"score_spread":0.25132790666296984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2004594378","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01702756,0.00018470445,0.6885565,0.00032369158,0.00019916326,0.00037703608,0.0059710643,0.2820249,0.005335304],"genre_scores_gemma":[0.119469665,0.00033758857,0.8047752,0.000788531,0.000092761635,0.0020210377,0.01796077,0.047164284,0.0073902165],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99931633,0.00015075688,0.00006520857,0.00019048626,0.00022052182,0.00005681911],"domain_scores_gemma":[0.9983652,0.0008244666,0.00012708927,0.0002693427,0.0003046969,0.00010922397],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00266385,0.0014989725,0.0006359284,0.0006800263,0.0004105324,0.0007796049,0.00308739,0.001179087,0.025175307],"category_scores_gemma":[0.005271273,0.0008474366,0.001470553,0.00061167456,0.0004396809,0.0017369278,0.0012417117,0.0025156825,0.0064637163],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003027982,0.0013738219,0.019959437,0.0029665001,0.0009632437,0.00088451325,0.0012923018,0.33188444,0.10291951,0.03636166,0.21836662,0.2799999],"study_design_scores_gemma":[0.00046479062,0.00028096393,0.0013351464,0.0000884572,0.000101975704,0.00017802934,0.000030942705,0.8430527,0.0503348,0.008382084,0.09564106,0.00010902609],"about_ca_topic_score_codex":0.001417757,"about_ca_topic_score_gemma":0.0013670569,"teacher_disagreement_score":0.025175307,"about_ca_system_score_codex":0.00089453085,"about_ca_system_score_gemma":0.001413523,"threshold_uncertainty_score":0.084219754},"labels":[],"label_agreement":null},{"id":"W2005255873","doi":"10.1186/1471-2105-13-249","title":"Quantitative biomedical annotation using medical subject heading over-representation profiles (MeSHOPs)","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research; Child and Family Research Institute; University of British Columbia","funders":"National Institute of General Medical Sciences; Michael Smith Health Research BC; Canadian Institutes of Health Research; Government of Ontario; Ontario Institute for Cancer Research","keywords":"Computer science; Controlled vocabulary; Annotation; Information retrieval; Vocabulary; Ontology; Representation (politics); Subject (documents); Set (abstract data type); Unified Medical Language System; Open Biomedical Ontologies; Visualization; Data science; Natural language processing; Data mining; Artificial intelligence; World Wide Web; Ontology alignment","score_opus":0.06687942214877576,"score_gpt":0.36950989404859996,"score_spread":0.30263047189982417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005255873","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38684264,0.005214366,0.48613676,0.00179646,0.00042013446,0.0015388272,0.08782367,0.011826316,0.018400803],"genre_scores_gemma":[0.58341676,0.00156488,0.37228045,0.00025540398,0.00027409315,0.0015434977,0.038164143,0.00079300965,0.0017077288],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961357,0.0011231304,0.00063081173,0.0007801522,0.0011946241,0.00013557718],"domain_scores_gemma":[0.9685819,0.018551156,0.0070342887,0.0018058647,0.0035303696,0.00049632805],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0049366476,0.0008310185,0.000526594,0.020400852,0.0005758585,0.002716861,0.0005932952,0.00065408106,0.0038750689],"category_scores_gemma":[0.03929156,0.00022612563,0.00080432725,0.017590737,0.0005121866,0.0021691096,0.0021484084,0.0006333671,0.0012573034],"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":[0.0014731222,0.00021322707,0.1533525,0.0075052464,0.00080489944,0.0007127451,0.00421479,0.017171679,0.060120415,0.038207605,0.035500113,0.68072367],"study_design_scores_gemma":[0.00024414936,0.0010159435,0.34352642,0.0019069915,0.0011436472,0.0030465052,0.004781225,0.21259485,0.067704156,0.15010817,0.213346,0.0005819705],"about_ca_topic_score_codex":0.0015657322,"about_ca_topic_score_gemma":0.001622492,"teacher_disagreement_score":0.020400852,"about_ca_system_score_codex":0.0010147169,"about_ca_system_score_gemma":0.0010706751,"threshold_uncertainty_score":0.026107788},"labels":[],"label_agreement":null},{"id":"W2005713653","doi":"10.1186/1471-2105-14-s15-s8","title":"Practical aliquoting of flowering plant genomes","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Chromosomal and Genetic Variations","field":"Agricultural and Biological Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Genome; Biology; Polyploid; Gene; Computational biology; Genetics","score_opus":0.03713003583218182,"score_gpt":0.23705449844082743,"score_spread":0.1999244626086456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005713653","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21799925,0.00039559454,0.7713416,0.00047579175,0.00010409659,0.00022904147,0.00047081758,0.0041004294,0.004883376],"genre_scores_gemma":[0.4079029,0.00024290557,0.5856365,0.00016580825,0.000054811153,0.00015956213,0.0011002638,0.00084558944,0.0038916704],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992631,0.00014470107,0.000046323403,0.0002931255,0.00018534258,0.00006733103],"domain_scores_gemma":[0.99652064,0.0017222805,0.00018047889,0.0010930601,0.00033882906,0.00014481129],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012109863,0.0005204751,0.0006910415,0.00086452503,0.00086735265,0.001260233,0.0015747981,0.0006653753,0.0061349603],"category_scores_gemma":[0.0070419493,0.00045471298,0.0008145665,0.0010511831,0.0006490521,0.0015383434,0.0020524804,0.00093608565,0.0012170202],"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":[0.00090263656,0.00015910812,0.008270768,0.0005794458,0.00010820482,0.00086363975,0.0014706167,0.27950028,0.1990424,0.04145569,0.0038037966,0.4638435],"study_design_scores_gemma":[0.00016346484,0.00044066954,0.003937565,0.000050904095,0.000096690965,0.00054378435,0.0007354375,0.74497014,0.16550611,0.06309019,0.02038837,0.000076746204],"about_ca_topic_score_codex":0.0020707499,"about_ca_topic_score_gemma":0.0031772824,"teacher_disagreement_score":0.0061349603,"about_ca_system_score_codex":0.00091896864,"about_ca_system_score_gemma":0.0007350792,"threshold_uncertainty_score":0.020523489},"labels":[],"label_agreement":null},{"id":"W2006899413","doi":"10.1186/1471-2105-8-185","title":"160-fold acceleration of the Smith-Waterman algorithm using a field programmable gate array (FPGA)","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":138,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Field-programmable gate array; Smith–Waterman algorithm; Computer science; Computation; Gate array; Algorithm; Hardware acceleration; Parallel computing; Speedup; Software; Computer hardware; Sequence alignment; Biology","score_opus":0.02210297259056926,"score_gpt":0.2562518568089582,"score_spread":0.23414888421838892,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2006899413","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44780052,0.0006359593,0.51803875,0.00041919074,0.00028621516,0.00018062453,0.00031636356,0.008442773,0.023879565],"genre_scores_gemma":[0.61351746,0.00021886842,0.3791898,0.000096413016,0.000029815792,0.000098548335,0.00044386333,0.00009842031,0.0063067926],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9998259,0.000031866723,0.0000115831745,0.000032445627,0.00006534513,0.00003292205],"domain_scores_gemma":[0.99963784,0.00015853117,0.00002760042,0.00005569969,0.00010136265,0.00001885122],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027773768,0.00047569646,0.00017665818,0.00037700773,0.00012841249,0.00033266356,0.00059818395,0.00023336758,0.008408845],"category_scores_gemma":[0.0007957481,0.00013571994,0.00018368717,0.00033390307,0.00013484302,0.0004449216,0.00018656344,0.00030378037,0.0011420725],"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":[0.0013451877,0.00030488623,0.0059126993,0.0004036042,0.0001327495,0.0005123157,0.0001884539,0.056270607,0.29659012,0.016157962,0.009639434,0.6125419],"study_design_scores_gemma":[0.00057503144,0.002317971,0.0117300665,0.00010610254,0.00017149225,0.0014926763,0.00012684554,0.5191661,0.39442188,0.005342641,0.06446886,0.00008038785],"about_ca_topic_score_codex":0.0016121814,"about_ca_topic_score_gemma":0.0014980108,"teacher_disagreement_score":0.008408845,"about_ca_system_score_codex":0.0004382661,"about_ca_system_score_gemma":0.00045010375,"threshold_uncertainty_score":0.028130412},"labels":[],"label_agreement":null},{"id":"W2007139266","doi":"10.1186/1471-2105-10-260","title":"MULTI-K: accurate classification of microarray subtypes using ensemble k-means clustering","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":68,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"National Institute for Materials Science; Natural Sciences and Engineering Research Council of Canada; Korea Research Council of Fundamental Science and Technology","keywords":"Cluster analysis; Computer science; Data mining; Rand index; Pattern recognition (psychology); Single-linkage clustering; Microarray analysis techniques; Clustering high-dimensional data; DNA microarray; Artificial intelligence; Ensemble learning; Gene chip analysis; CURE data clustering algorithm; Correlation clustering; Biology; Gene; Genetics; Gene expression","score_opus":0.05225903524028005,"score_gpt":0.30353862350213234,"score_spread":0.2512795882618523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2007139266","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05265279,0.00039393335,0.9403897,0.00019321946,0.00009709793,0.00012097178,0.0008637465,0.0043774215,0.00091115566],"genre_scores_gemma":[0.29023406,0.00018850574,0.7058903,0.000098984805,0.000055108998,0.00023441223,0.0019401337,0.00037822206,0.0009802796],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99817264,0.00040592687,0.00014273486,0.00053697673,0.0005851507,0.00015642114],"domain_scores_gemma":[0.9970703,0.0009392933,0.00026606544,0.0006747949,0.0009409784,0.00010860937],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002717777,0.0011953783,0.0017265257,0.0025793605,0.00112656,0.0014170079,0.0016879926,0.0012210307,0.0013445754],"category_scores_gemma":[0.00762042,0.00055660086,0.0013964276,0.002023168,0.00042665543,0.0017838496,0.0014554468,0.0012908273,0.0009805667],"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":[0.00085283123,0.00019474792,0.016517144,0.00028025702,0.00054266537,0.00017433931,0.00037875367,0.28857195,0.026078187,0.0038182244,0.011396433,0.6511945],"study_design_scores_gemma":[0.000019969877,0.00003389098,0.0032950975,0.000013066972,0.000041575808,0.00008295863,0.00004215569,0.9852814,0.00578932,0.0039627976,0.0013970195,0.000040671155],"about_ca_topic_score_codex":0.0062882863,"about_ca_topic_score_gemma":0.0071363733,"teacher_disagreement_score":0.0062882863,"about_ca_system_score_codex":0.001073218,"about_ca_system_score_gemma":0.0011674544,"threshold_uncertainty_score":0.014373183},"labels":[],"label_agreement":null},{"id":"W2009153021","doi":"10.1186/1471-2105-10-243","title":"Core Hunter: an algorithm for sampling genetic resources based on multiple genetic measures","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":169,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; International Fund for Agricultural Development; European Commission","keywords":"Core (optical fiber); Genetic diversity; Representativeness heuristic; Computer science; Genetic algorithm; Sampling (signal processing); Preference; Data mining; Machine learning; Statistics; Mathematics; Population","score_opus":0.06288921997742554,"score_gpt":0.30332164333721656,"score_spread":0.24043242335979104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2009153021","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02373839,0.00015267706,0.9713377,0.00009585399,0.000027747767,0.000291009,0.00037680607,0.0029002212,0.001079636],"genre_scores_gemma":[0.059641022,0.0000630644,0.93672955,0.00013143074,0.000020871617,0.00058972026,0.0012183483,0.0004844998,0.0011213673],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986675,0.00042746536,0.00008902174,0.00034483327,0.00035392426,0.00011728983],"domain_scores_gemma":[0.9960788,0.0023122255,0.0002531476,0.00055318675,0.0006309204,0.00017173214],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038509103,0.001302759,0.00158628,0.0032736484,0.0010037333,0.0013486595,0.0026743768,0.0012100973,0.004090812],"category_scores_gemma":[0.009907615,0.0009341866,0.0012225133,0.0024288462,0.0011089367,0.0017607664,0.002714167,0.0012029707,0.0012969682],"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":[0.00069959526,0.00036780283,0.015646392,0.00046975387,0.00048673575,0.0002781699,0.0010164364,0.19496349,0.010652212,0.013605639,0.022871636,0.73894215],"study_design_scores_gemma":[0.00018917718,0.00013322952,0.0018746781,0.000053582364,0.00007805443,0.00022968047,0.00018549465,0.96486825,0.0046416647,0.020425526,0.0072863502,0.000034344685],"about_ca_topic_score_codex":0.0037608193,"about_ca_topic_score_gemma":0.006910596,"teacher_disagreement_score":0.004090812,"about_ca_system_score_codex":0.0009506498,"about_ca_system_score_gemma":0.0024076584,"threshold_uncertainty_score":0.020365775},"labels":[],"label_agreement":null},{"id":"W2009474665","doi":"10.1186/1471-2105-10-145","title":"flowClust: a Bioconductor package for automated gating of flow cytometry data","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":201,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Montreal Clinical Research Institute; Terry Fox Research Institute; University of British Columbia","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institutes of Health; Michael Smith Health Research BC","keywords":"Bioconductor; Computer science; Software; Cluster analysis; Data mining; Data transformation; Throughput; Outlier; Workflow; Artificial intelligence; Database; Data warehouse","score_opus":0.05296027501363074,"score_gpt":0.3019501064415164,"score_spread":0.24898983142788564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2009474665","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003086679,0.0022655502,0.44650817,0.001744951,0.0015175245,0.001205004,0.13778007,0.39928076,0.0066113207],"genre_scores_gemma":[0.021508146,0.0017415152,0.6861557,0.002202435,0.0005465917,0.013521981,0.12562019,0.1396884,0.009015011],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98819447,0.0039469306,0.0014930064,0.0029479123,0.0027110127,0.00070672005],"domain_scores_gemma":[0.9738019,0.015848415,0.0022377244,0.003267422,0.004054995,0.0007895686],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017321266,0.006798736,0.006943312,0.010270633,0.0032778878,0.007311065,0.012927139,0.005268631,0.10295835],"category_scores_gemma":[0.052956566,0.0036465446,0.0064035812,0.009136859,0.0022455854,0.0046680355,0.006071255,0.009132141,0.07241656],"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":[0.0009062961,0.00016574978,0.0034359628,0.0070549645,0.0019727906,0.00059053674,0.0008664688,0.007585214,0.006707011,0.021464778,0.8815827,0.067667484],"study_design_scores_gemma":[0.0011156729,0.00021428695,0.006298349,0.0014365397,0.0009218445,0.0009719891,0.0002444064,0.09053008,0.016320953,0.08760641,0.79374856,0.0005908504],"about_ca_topic_score_codex":0.0050045704,"about_ca_topic_score_gemma":0.005896514,"teacher_disagreement_score":0.10295835,"about_ca_system_score_codex":0.0018948221,"about_ca_system_score_gemma":0.010899983,"threshold_uncertainty_score":0.34442997},"labels":[],"label_agreement":null},{"id":"W2010854125","doi":"10.1186/s12859-014-0383-1","title":"Efficient prediction of human protein-protein interactions at a global scale","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina; University of Toronto; Carleton University","funders":"National Institute on Minority Health and Health Disparities; National Institute on Alcohol Abuse and Alcoholism; National Energy Research Scientific Computing Center; Sahlgrenska Akademin; Natural Sciences and Engineering Research Council of Canada; Office of Science; Saskatchewan Health Research Foundation; Linköpings Universitet; National Science Foundation; Canadian Institutes of Health Research; U.S. Department of Energy; National Institutes of Health; Vetenskapsrådet","keywords":"Computer science; Computational biology; Precision and recall; DNA microarray; Scale (ratio); Protein Interaction Networks; Range (aeronautics); Protein–protein interaction; Recall; Systems biology; Data mining; Machine learning; Artificial intelligence; Bioinformatics; Biology; Genetics; Gene; Engineering","score_opus":0.00988622166715788,"score_gpt":0.23572342032781868,"score_spread":0.2258371986606608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2010854125","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.50243115,0.0025021345,0.46382356,0.0005018021,0.00004158029,0.000157704,0.013988986,0.012405504,0.00414749],"genre_scores_gemma":[0.81396115,0.0006604793,0.16650183,0.00010169371,0.000039601666,0.00011156626,0.017037762,0.0002977993,0.0012881277],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996476,0.000086015294,0.000015103534,0.00015237746,0.00007543511,0.000023477201],"domain_scores_gemma":[0.99885046,0.0007122742,0.00012708097,0.0001259018,0.00013183239,0.00005245641],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000644616,0.00086741924,0.0006543747,0.0013851817,0.00029932597,0.000615796,0.00043026498,0.00054984645,0.0017408014],"category_scores_gemma":[0.002956511,0.00032317665,0.00055427465,0.00087060966,0.00023128519,0.000874706,0.0008099238,0.00059123256,0.0011005921],"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":[0.0014626422,0.00031364526,0.13597465,0.0013147389,0.0008217459,0.0011542893,0.0002890483,0.36484605,0.09396353,0.0036965874,0.026095077,0.37006795],"study_design_scores_gemma":[0.000050505147,0.00015236015,0.029830156,0.000031838954,0.00011354267,0.0006436294,0.000068724345,0.9398596,0.01648783,0.008227024,0.0045098453,0.000024985511],"about_ca_topic_score_codex":0.0011796952,"about_ca_topic_score_gemma":0.0018923979,"teacher_disagreement_score":0.0017408014,"about_ca_system_score_codex":0.00028878674,"about_ca_system_score_gemma":0.0004511859,"threshold_uncertainty_score":0.005823612},"labels":[],"label_agreement":null},{"id":"W2012121247","doi":"10.1186/1471-2105-9-430","title":"Prediction of beta-turns at over 80% accuracy based on an ensemble of predicted secondary structures and multiple alignments","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"DNA microarray; BETA (programming language); Computational biology; Computer science; Bioinformatics; Biology; Genetics; Gene","score_opus":0.014985455898290522,"score_gpt":0.23092082131133007,"score_spread":0.21593536541303954,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012121247","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8642593,0.0035971084,0.1163962,0.00034448004,0.00018899346,0.00014830957,0.002169988,0.007948295,0.0049473974],"genre_scores_gemma":[0.92353594,0.0005491725,0.06634915,0.00016093606,0.00012648663,0.00008053563,0.0074848714,0.00022349536,0.0014893987],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986004,0.00032299463,0.00010455434,0.00037430212,0.0004145546,0.00018324466],"domain_scores_gemma":[0.997274,0.001080531,0.00027330866,0.0002819368,0.0008833262,0.00020694856],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028584905,0.0015759974,0.0015264977,0.002236033,0.0006392947,0.00082947506,0.0007878833,0.0010047924,0.0012880359],"category_scores_gemma":[0.0037407456,0.00031982228,0.0011140837,0.0009819963,0.0002600136,0.0010110404,0.00067651406,0.00092522,0.0015899288],"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":[0.0027126698,0.0011041615,0.11127669,0.00057565613,0.0011807226,0.0012692263,0.00024340562,0.29051703,0.053767532,0.0010011946,0.021264903,0.5150869],"study_design_scores_gemma":[0.000037214653,0.000205437,0.013067253,0.000036917823,0.00011234058,0.00023270272,0.00004712756,0.97652924,0.0077040247,0.0008184834,0.0011885627,0.000020536696],"about_ca_topic_score_codex":0.0032239489,"about_ca_topic_score_gemma":0.0037964224,"teacher_disagreement_score":0.0032239489,"about_ca_system_score_codex":0.00050933,"about_ca_system_score_gemma":0.0009333164,"threshold_uncertainty_score":0.015117347},"labels":[],"label_agreement":null},{"id":"W2013290977","doi":"10.1186/1471-2105-11-487","title":"Analysis of lifestyle and metabolic predictors of visceral obesity with Bayesian Networks","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Bayesian network; Robustness (evolution); Causal inference; Obesity; Inference; Bayesian probability; Statistical inference; Computer science; Visceral fat; Artificial intelligence; Machine learning; Computational biology; Bioinformatics; Biology; Mathematics; Econometrics; Statistics; Endocrinology; Gene; Genetics","score_opus":0.008201214320869888,"score_gpt":0.2172830842938133,"score_spread":0.2090818699729434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013290977","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07099406,0.0006332197,0.92623436,0.0003529801,0.000025385665,0.00011370645,0.0005449738,0.0002567975,0.0008444971],"genre_scores_gemma":[0.66360086,0.00085489854,0.33142784,0.00015702598,0.0001257392,0.00037877075,0.0020629272,0.00008454855,0.0013074322],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99836916,0.0009842587,0.00007358016,0.00030873407,0.00017776799,0.00008647079],"domain_scores_gemma":[0.9866263,0.011384499,0.00096585916,0.00027362382,0.0005779748,0.0001717439],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044629467,0.0010833266,0.00093661743,0.0023855586,0.0005472709,0.0010987567,0.0013382356,0.0011116687,0.0019451169],"category_scores_gemma":[0.018288285,0.0007385563,0.0014531569,0.001219101,0.0005740993,0.0012783696,0.0010687979,0.0014675439,0.00033037597],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020107922,0.00009752623,0.02167963,0.00014269887,0.00024559282,0.0001746009,0.00017680178,0.8962358,0.0009146434,0.009959884,0.0008048797,0.06936679],"study_design_scores_gemma":[0.000008334215,0.00001691319,0.0014555205,0.000020715655,0.000029062867,0.000026889653,0.0000130907065,0.990818,0.00015378318,0.0071527762,0.00029720156,0.0000075813423],"about_ca_topic_score_codex":0.011744258,"about_ca_topic_score_gemma":0.009907003,"teacher_disagreement_score":0.011744258,"about_ca_system_score_codex":0.0009490204,"about_ca_system_score_gemma":0.0012169692,"threshold_uncertainty_score":0.023602605},"labels":[],"label_agreement":null},{"id":"W2013577952","doi":"10.1186/1471-2105-10-78","title":"Performance of random forest when SNPs are in linkage disequilibrium","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":99,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Center for Research Resources; Canadian Institutes of Health Research; National Institute on Aging; National Institutes of Health","keywords":"Linkage disequilibrium; Single-nucleotide polymorphism; Tag SNP; Haplotype; Genetics; SNP; Linkage (software); SNP genotyping; Genetic association; Biology; Tree (set theory); Computational biology; Mathematics; Allele; Genotype; Gene","score_opus":0.013178378750088178,"score_gpt":0.2384478062535839,"score_spread":0.2252694275034957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013577952","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49221492,0.0055759773,0.4889727,0.0014125599,0.00046418197,0.000287428,0.0015705351,0.004669058,0.0048326477],"genre_scores_gemma":[0.8748334,0.0004461613,0.121204175,0.0002451091,0.00013645994,0.00014447956,0.0021379837,0.00021184224,0.0006404138],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9940222,0.003555782,0.00032694274,0.00094765256,0.0005891596,0.00055823935],"domain_scores_gemma":[0.9670218,0.02696888,0.0011921967,0.0016805559,0.002564643,0.00057188806],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0144484015,0.0015850993,0.0019030754,0.0018447206,0.0011924566,0.0012826743,0.0015886403,0.0017993228,0.0015320459],"category_scores_gemma":[0.03186515,0.0004795826,0.0012052441,0.0014627172,0.00071868696,0.0022592496,0.0008036994,0.0012343128,0.00079749676],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012880124,0.0002644268,0.026260754,0.0003187048,0.00043641307,0.00019618549,0.00012131085,0.86255926,0.0013087337,0.0015446718,0.0046277815,0.10107376],"study_design_scores_gemma":[0.000059301616,0.00009250285,0.0016740188,0.00002381863,0.0000425422,0.00010043571,0.00001980127,0.99443084,0.00059287227,0.0026335344,0.0003137205,0.000016546552],"about_ca_topic_score_codex":0.014050733,"about_ca_topic_score_gemma":0.008348634,"teacher_disagreement_score":0.0144484015,"about_ca_system_score_codex":0.0010238055,"about_ca_system_score_gemma":0.0018006561,"threshold_uncertainty_score":0.07641137},"labels":[],"label_agreement":null},{"id":"W2013823401","doi":"10.1186/1471-2105-10-162","title":"Hydra: software for tailored processing of H/D exchange data from MS or tandem MS analyses","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Mass Spectrometry Techniques and Applications","field":"Chemistry","cited_by":76,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Heritage Foundation for Medical Research; Fondation pour la Recherche Médicale","keywords":"Computer science; Workflow; Software; Graphical user interface; Tandem mass spectrometry; Interface (matter); Database; Hydrogen–deuterium exchange; Visualization; Data visualization; Mass spectrometry; Data mining; Chemistry; Operating system; Chromatography","score_opus":0.131345965573557,"score_gpt":0.36589770495487595,"score_spread":0.23455173938131896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013823401","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004801849,0.00027611197,0.33051747,0.00019440822,0.00011936424,0.00046667428,0.014468937,0.6467634,0.0023917248],"genre_scores_gemma":[0.040680222,0.0007558957,0.7657436,0.0007719094,0.00012818436,0.003547226,0.054557145,0.12721376,0.0066020787],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99856275,0.0002548798,0.00020960803,0.00031732526,0.00051793084,0.0001375224],"domain_scores_gemma":[0.9972805,0.0013532151,0.00025205564,0.00046103945,0.00044920843,0.00020395413],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042381124,0.0029062568,0.0015520523,0.0026772246,0.00096229784,0.0019177536,0.003994395,0.0012417365,0.032147475],"category_scores_gemma":[0.006850727,0.0027512333,0.0021221894,0.001357082,0.0010405926,0.0025858288,0.0038293262,0.0026698783,0.019773334],"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":[0.0032104587,0.00045464988,0.0072742216,0.0035087971,0.0010754109,0.0020411792,0.0012782634,0.015147816,0.092244625,0.010290696,0.588135,0.2753389],"study_design_scores_gemma":[0.0016962113,0.0004420251,0.015288464,0.0006970657,0.000395691,0.002468321,0.0003297963,0.23988263,0.17718805,0.027963044,0.5326467,0.001002031],"about_ca_topic_score_codex":0.0020498675,"about_ca_topic_score_gemma":0.0017787954,"teacher_disagreement_score":0.032147475,"about_ca_system_score_codex":0.0006824219,"about_ca_system_score_gemma":0.002151851,"threshold_uncertainty_score":0.107544005},"labels":[],"label_agreement":null},{"id":"W2014097763","doi":"10.1186/1471-2105-13-264","title":"Sifting through genomes with iterative-sequence clustering produces a large, phylogenetically diverse protein-family resource","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Joint Genome Institute; Gordon and Betty Moore Foundation; U.S. Department of Energy; National Science Foundation","keywords":"Genome; Computational biology; Cluster analysis; Identification (biology); Protein family; Phylogenetic tree; Computer science; Biology; Genomics; Comparative genomics; Sequence alignment; Genetics; Gene; Machine learning; Peptide sequence","score_opus":0.034131985975596454,"score_gpt":0.25701719782298676,"score_spread":0.2228852118473903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014097763","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23222396,0.00069213304,0.70359445,0.00061658915,0.00011427839,0.00040913562,0.016905867,0.041450832,0.00399278],"genre_scores_gemma":[0.1587212,0.00035898245,0.8035308,0.00018062034,0.000018335335,0.00030427187,0.033535562,0.0024807486,0.0008694368],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99898046,0.0001792251,0.00007572335,0.00033472836,0.000319535,0.00011029793],"domain_scores_gemma":[0.9980627,0.00064223865,0.0002065737,0.00047677782,0.00048179063,0.0001300488],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021192105,0.0011959102,0.0011762858,0.00326336,0.001170132,0.0013196216,0.0014845231,0.0006599683,0.004425898],"category_scores_gemma":[0.004235982,0.0006847852,0.002296975,0.005029373,0.0005425277,0.0014734118,0.0015857908,0.0010657915,0.0034924687],"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":[0.002065916,0.0007034196,0.058146484,0.0020245255,0.0013751563,0.0011987741,0.0011652474,0.10539266,0.21650068,0.017139096,0.06697071,0.52731735],"study_design_scores_gemma":[0.00034003367,0.00050264905,0.031946536,0.00020726971,0.00052710413,0.0015032039,0.0007213734,0.7321458,0.119667865,0.0411512,0.071045995,0.00024099054],"about_ca_topic_score_codex":0.005704893,"about_ca_topic_score_gemma":0.009217832,"teacher_disagreement_score":0.005704893,"about_ca_system_score_codex":0.00143976,"about_ca_system_score_gemma":0.0025995232,"threshold_uncertainty_score":0.014806151},"labels":[],"label_agreement":null},{"id":"W2014141753","doi":"10.1186/s12859-015-0508-1","title":"Classification of bioinformatics workflows using weighted versions of partitioning and hierarchical clustering algorithms","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Workflow; Computer science; Cluster analysis; Hierarchical clustering; Data mining; Pairwise comparison; Software; Algorithm; Artificial intelligence; Database; Programming language","score_opus":0.2720426029070439,"score_gpt":0.38204230321551835,"score_spread":0.10999970030847445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014141753","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07338229,0.00045565167,0.92315644,0.00016509181,0.00006434303,0.0005798399,0.0005053358,0.0007822754,0.0009086928],"genre_scores_gemma":[0.24753954,0.00029661332,0.7487269,0.000048650465,0.00005880064,0.0007027941,0.0019299663,0.00014675822,0.00054989086],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9946898,0.0014505556,0.00085747446,0.0010890824,0.0016626103,0.00025052277],"domain_scores_gemma":[0.989908,0.0043929764,0.0013963387,0.00091630337,0.0031413008,0.0002450697],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005272746,0.0012588,0.0010015044,0.0066716955,0.0011227578,0.002101547,0.0020585095,0.0010186261,0.00086173945],"category_scores_gemma":[0.022456896,0.00034378556,0.0019275317,0.004854484,0.00068146846,0.0021770122,0.0013712693,0.000954367,0.00042695407],"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":[0.000726214,0.00035107989,0.020421857,0.00068913226,0.0006351969,0.00016462788,0.0009780711,0.47241676,0.0073488196,0.018894617,0.0032072728,0.47416636],"study_design_scores_gemma":[0.000020577632,0.000082042425,0.0026854551,0.000038629194,0.00006159579,0.00008293316,0.00013626763,0.98198974,0.0021811232,0.011598395,0.0010874076,0.000035853544],"about_ca_topic_score_codex":0.008698489,"about_ca_topic_score_gemma":0.0058981297,"teacher_disagreement_score":0.008698489,"about_ca_system_score_codex":0.0020612923,"about_ca_system_score_gemma":0.0025344493,"threshold_uncertainty_score":0.027885258},"labels":[],"label_agreement":null},{"id":"W2014519657","doi":"10.1186/1471-2105-8-483","title":"PARPs database: A LIMS systems for protein-protein interaction data mining or laboratory information management system","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Caprion (Canada); Université Laval; Bausch Health (Canada)","funders":"Canadian Institutes of Health Research","keywords":"Proteomics; Proteome; Pipeline (software); Computer science; Database search engine; Annotation; Computational biology; Database; Data management; Tandem mass spectrometry; Bioinformatics; Data mining; Mass spectrometry; Information retrieval; Chemistry; Biology; Search engine","score_opus":0.04278753517543161,"score_gpt":0.3111294744298611,"score_spread":0.2683419392544295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014519657","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007393673,0.0012127368,0.27808598,0.001359778,0.00036910168,0.0012378028,0.17379165,0.5271558,0.009393535],"genre_scores_gemma":[0.061523233,0.0021367432,0.37359703,0.0028304998,0.0003347204,0.0038879213,0.5187489,0.02273598,0.014204971],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983714,0.0002980333,0.00034314708,0.0004278002,0.00045813087,0.00010152603],"domain_scores_gemma":[0.9963923,0.0011382428,0.0005971785,0.0008618566,0.00056754926,0.00044286984],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004672244,0.0019095477,0.0017759714,0.0032012218,0.00096611894,0.0031803607,0.0059019136,0.0012651742,0.04011083],"category_scores_gemma":[0.008502069,0.0011266635,0.0014755854,0.0029913199,0.0006302927,0.0034314266,0.0036365911,0.0017547373,0.027691342],"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":[0.004339682,0.00057817576,0.009206753,0.0054850345,0.00078084477,0.0014479347,0.00058527343,0.0051374533,0.027539557,0.013468883,0.6849779,0.24645248],"study_design_scores_gemma":[0.0015123993,0.0006773406,0.01252097,0.0007079731,0.0005795742,0.0016969759,0.00039114154,0.100218624,0.07550094,0.027518244,0.7782434,0.0004324281],"about_ca_topic_score_codex":0.0018274749,"about_ca_topic_score_gemma":0.0011493904,"teacher_disagreement_score":0.04011083,"about_ca_system_score_codex":0.0010566919,"about_ca_system_score_gemma":0.0021060319,"threshold_uncertainty_score":0.13418406},"labels":[],"label_agreement":null},{"id":"W2015341379","doi":"10.1186/1471-2105-8-141","title":"Relating destabilizing regions to known functional sites in proteins","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children","funders":"","keywords":"Computational biology; DNA microarray; Biology; Evolutionary biology; Genetics; Bioinformatics; Gene; Gene expression","score_opus":0.019282405537499377,"score_gpt":0.25215638115509176,"score_spread":0.23287397561759238,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015341379","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94818693,0.0012929252,0.04696876,0.000035768415,0.0000106974285,0.00010383488,0.0017433313,0.0008499212,0.0008077088],"genre_scores_gemma":[0.9488556,0.00040131478,0.045452747,0.000022095395,0.000010962899,0.00008933569,0.0048464527,0.00015448958,0.0001671146],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986444,0.0002176726,0.00015861697,0.00042628532,0.00045656972,0.00009650462],"domain_scores_gemma":[0.9944437,0.002625326,0.0014413779,0.0006238753,0.0006874741,0.0001782508],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018104152,0.0007701203,0.0007231943,0.0041740937,0.0007834335,0.00084116985,0.0007392763,0.0006768832,0.0015109737],"category_scores_gemma":[0.005590264,0.00024439074,0.000781471,0.0023158544,0.00069537293,0.00059843314,0.000955183,0.000496127,0.00042326254],"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":[0.0026627113,0.0006090576,0.2982582,0.0033247739,0.0010135638,0.0012297988,0.00091095635,0.13806242,0.40669283,0.002274553,0.001939124,0.14302213],"study_design_scores_gemma":[0.00008466595,0.0010503168,0.34413502,0.0001520016,0.00057533215,0.003183141,0.0005379322,0.32282272,0.31536055,0.0072227195,0.0047230194,0.00015268632],"about_ca_topic_score_codex":0.0014002383,"about_ca_topic_score_gemma":0.0017278618,"teacher_disagreement_score":0.0041740937,"about_ca_system_score_codex":0.0005874915,"about_ca_system_score_gemma":0.00058816123,"threshold_uncertainty_score":0.0095745325},"labels":[],"label_agreement":null},{"id":"W2016231246","doi":"10.1186/1471-2105-10-s6-s14","title":"iBarcode.org: web-based molecular biodiversity analysis","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Environmental DNA in Biodiversity Studies","field":"Environmental Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Barcode; DNA barcoding; USable; Suite; Computer science; World Wide Web; Data science; Identification (biology); Web application; Set (abstract data type); SPARK (programming language); Information retrieval; Biology; Ecology; Geography","score_opus":0.01350209054431941,"score_gpt":0.2078110036386016,"score_spread":0.1943089130942822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016231246","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043115704,0.0014152116,0.37512305,0.0009811928,0.0005270049,0.001119453,0.081130885,0.5088331,0.026558576],"genre_scores_gemma":[0.019403728,0.0012585638,0.712968,0.0011968712,0.00020528001,0.003978922,0.1927985,0.05419385,0.013996332],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979063,0.00048157596,0.0002167656,0.00045044272,0.0007526642,0.00019232722],"domain_scores_gemma":[0.99601716,0.0014697621,0.0004849588,0.0006910693,0.00073103374,0.0006060948],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004944264,0.0026753398,0.0021017303,0.006740538,0.0011967466,0.00498899,0.0048911697,0.0018558104,0.042166464],"category_scores_gemma":[0.009874977,0.0015890108,0.0015377743,0.004889752,0.0007092563,0.0041861082,0.0044835657,0.0034171299,0.05119162],"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":[0.0014172638,0.0005186024,0.004207738,0.0029490872,0.00048208496,0.0006023856,0.00061603205,0.0036116692,0.019705426,0.011855817,0.61161315,0.3424208],"study_design_scores_gemma":[0.0006640266,0.00020408849,0.009781054,0.0011254484,0.00024702598,0.001528547,0.00030951927,0.06551011,0.036317628,0.042496353,0.8413026,0.0005136608],"about_ca_topic_score_codex":0.0022066936,"about_ca_topic_score_gemma":0.0015476561,"teacher_disagreement_score":0.042166464,"about_ca_system_score_codex":0.0008962883,"about_ca_system_score_gemma":0.0019337981,"threshold_uncertainty_score":0.14106089},"labels":[],"label_agreement":null},{"id":"W2016984855","doi":"10.1186/1471-2105-15-157","title":"Multidimensional mutual information methods for the analysis of covariation in multiple sequence alignments","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; University of Toronto; Ontario Institute for Cancer Research","funders":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; U.S. Public Health Service; Wayne State University","keywords":"Mutual information; Computer science; Set (abstract data type); Sequence (biology); Multiple sequence alignment; Data mining; Entropy (arrow of time); Multivariate statistics; Computational biology; Biology; Sequence alignment; Statistics; Artificial intelligence; Mathematics; Genetics; Machine learning","score_opus":0.02160173717026669,"score_gpt":0.31280156449726515,"score_spread":0.29119982732699845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016984855","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005219581,0.0013168743,0.9905442,0.00015629792,0.000042851043,0.00015255093,0.0005770298,0.0015351424,0.00045544343],"genre_scores_gemma":[0.084141605,0.00075085275,0.9111386,0.00011115229,0.00015662046,0.0010058963,0.0016214438,0.00048228048,0.00059161655],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9871623,0.006505625,0.0011872179,0.0014797304,0.0033984904,0.0002666192],"domain_scores_gemma":[0.9651747,0.026592765,0.003678415,0.0023493702,0.0017968379,0.00040800494],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01430343,0.0022402636,0.0023879975,0.0100366175,0.0012068133,0.0027549618,0.0036227026,0.0019349811,0.0029229717],"category_scores_gemma":[0.03788975,0.0011511204,0.003287483,0.0075318622,0.0020396584,0.0037909695,0.004005921,0.0032628013,0.0015248916],"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":[0.0008518494,0.00038815002,0.019356007,0.0024321817,0.0031371713,0.0009552587,0.0011282137,0.30485252,0.01702117,0.07741371,0.010609119,0.5618546],"study_design_scores_gemma":[0.000042222873,0.00012299241,0.0040561007,0.000115663264,0.00012275662,0.00034410614,0.00011026209,0.9052665,0.0038340895,0.07833455,0.007503573,0.0001470626],"about_ca_topic_score_codex":0.0023351393,"about_ca_topic_score_gemma":0.0024202713,"teacher_disagreement_score":0.01430343,"about_ca_system_score_codex":0.0019815313,"about_ca_system_score_gemma":0.00214821,"threshold_uncertainty_score":0.07564467},"labels":[],"label_agreement":null},{"id":"W2017149761","doi":"10.1186/1471-2105-9-121","title":"SciDBMaker: new software for computer-aided design of specialized biological databases","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Agriculture and Agri-Food Canada","funders":"","keywords":"Biological database; Database; Computer science; Software; Biological data; Protein structure database; Variety (cybernetics); Scope (computer science); Interface (matter); Data mining; Sequence database; Data science; Bioinformatics; Biology; Programming language","score_opus":0.06878778794084801,"score_gpt":0.2769601502345303,"score_spread":0.2081723622936823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017149761","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024764836,0.0013382835,0.62140757,0.00044438077,0.00037714088,0.00088030496,0.018063542,0.34966037,0.0053519597],"genre_scores_gemma":[0.015022594,0.002155458,0.88655984,0.0008469924,0.0001672974,0.005601539,0.04598348,0.036895256,0.0067674825],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9966888,0.00082580687,0.0005498392,0.0005103335,0.0012512696,0.0001739926],"domain_scores_gemma":[0.9938153,0.0038351454,0.00045906895,0.00052382814,0.0010281709,0.00033842973],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008615251,0.003542729,0.0034070297,0.0060502198,0.0013423918,0.00465448,0.006803645,0.001969488,0.049316704],"category_scores_gemma":[0.012493629,0.0031709266,0.0028638274,0.0047494196,0.0010122871,0.004024699,0.003694522,0.00448994,0.021721648],"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":[0.0032830492,0.0003663634,0.0027041216,0.009317097,0.0017341998,0.0018628577,0.0009922694,0.021415483,0.030104421,0.025643136,0.5295929,0.37298414],"study_design_scores_gemma":[0.0024179036,0.00037827174,0.002893703,0.0011923327,0.0005988071,0.0017236018,0.00025689712,0.17897056,0.051032405,0.045250595,0.7147969,0.00048802557],"about_ca_topic_score_codex":0.0023619898,"about_ca_topic_score_gemma":0.0025920924,"teacher_disagreement_score":0.049316704,"about_ca_system_score_codex":0.0013067301,"about_ca_system_score_gemma":0.0039262683,"threshold_uncertainty_score":0.16498083},"labels":[],"label_agreement":null},{"id":"W2017229033","doi":"10.1186/1471-2105-9-226","title":"SCPRED: Accurate prediction of protein structural class for sequences of twilight-zone similarity with predicting sequences","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":151,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pairwise comparison; Support vector machine; Artificial intelligence; Pattern recognition (psychology); Structural alignment; Protein structure prediction; Computer science; Structural similarity; Similarity (geometry); Classifier (UML); Protein secondary structure; Structural Classification of Proteins database; Protein structure; Sequence alignment; Mathematics; Biology; Peptide sequence; Genetics","score_opus":0.019655015260110244,"score_gpt":0.243559004356052,"score_spread":0.22390398909594175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017229033","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6914071,0.0018508808,0.24211672,0.0005638056,0.00019489971,0.000560361,0.02137296,0.037229124,0.0047040763],"genre_scores_gemma":[0.69006485,0.0005480454,0.25758335,0.00020528413,0.000084291096,0.0005259846,0.048042137,0.00049766275,0.0024483392],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993073,0.00008397484,0.00006361306,0.00021177232,0.00027060043,0.000062698484],"domain_scores_gemma":[0.9988128,0.00037039217,0.00025580282,0.00014725977,0.00032803442,0.00008575589],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009098896,0.0012774117,0.0006621523,0.001488505,0.00048770788,0.0007631305,0.0008867887,0.00080271816,0.0035307102],"category_scores_gemma":[0.0023720677,0.00030992186,0.0008360601,0.0010132003,0.00023965031,0.00090821105,0.000533804,0.00085821055,0.0028908355],"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":[0.0031219078,0.0009809083,0.16067722,0.0015489283,0.0005712809,0.0011778603,0.0001952406,0.04497714,0.16567981,0.0013545058,0.08828839,0.53142685],"study_design_scores_gemma":[0.00014193407,0.0006992319,0.038171504,0.00009453414,0.00009431531,0.0010132196,0.00010676894,0.86972916,0.07725751,0.0014654677,0.011175671,0.000050732],"about_ca_topic_score_codex":0.0014151791,"about_ca_topic_score_gemma":0.0022621579,"teacher_disagreement_score":0.0035307102,"about_ca_system_score_codex":0.00040693293,"about_ca_system_score_gemma":0.00081041246,"threshold_uncertainty_score":0.011811376},"labels":[],"label_agreement":null},{"id":"W2017880952","doi":"10.1186/1471-2105-11-s1-s28","title":"Decoding HMMs using the k best paths: algorithms and applications","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pruning; Algorithm; Computer science; Sequence (biology); Decoding methods; Path (computing); Hidden Markov model; Markov chain; Sequence labeling; Feature (linguistics); State (computer science); Artificial intelligence; Machine learning; Task (project management)","score_opus":0.048164553412059975,"score_gpt":0.28816161978516885,"score_spread":0.23999706637310889,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017880952","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0073172525,0.0003512547,0.9887067,0.00025847513,0.000017713213,0.00005523718,0.00024541747,0.0024920506,0.0005560056],"genre_scores_gemma":[0.08935501,0.00044071802,0.9077428,0.00009139239,0.00003943872,0.00014461347,0.0008998128,0.00046432693,0.0008218857],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99864346,0.00060303946,0.00011681002,0.00029739464,0.0002562595,0.00008304949],"domain_scores_gemma":[0.9848282,0.013024368,0.00054699025,0.0008113302,0.00063374056,0.0001554246],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026429044,0.0014910671,0.0011564213,0.0024196438,0.001195631,0.0015340676,0.0022447607,0.0029930195,0.0056450125],"category_scores_gemma":[0.019008044,0.0012122449,0.0011883248,0.0031446202,0.0011279081,0.0030140637,0.0018985594,0.0022033972,0.0024008136],"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":[0.00055617077,0.00015178119,0.005314454,0.00039889602,0.00019209716,0.00027026897,0.0005566035,0.3602762,0.0028486059,0.037359897,0.0070781475,0.5849969],"study_design_scores_gemma":[0.00005029763,0.000020867312,0.00036690166,0.00005274108,0.00003583359,0.00015302702,0.00006641238,0.8799463,0.0021694372,0.11535216,0.0017521601,0.00003394323],"about_ca_topic_score_codex":0.004998157,"about_ca_topic_score_gemma":0.0071699237,"teacher_disagreement_score":0.0056450125,"about_ca_system_score_codex":0.0014574962,"about_ca_system_score_gemma":0.0022644869,"threshold_uncertainty_score":0.01888442},"labels":[],"label_agreement":null},{"id":"W2019000099","doi":"10.1186/1471-2105-12-205","title":"A scan statistic to extract causal gene clusters from case-control genome-wide rare CNV data","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomic variations and chromosomal abnormalities","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children; SickKids Foundation","funders":"","keywords":"Scan statistic; False positive paradox; Cluster analysis; Computational biology; Statistic; Statistical power; Statistical hypothesis testing; Computer science; Data mining; Test statistic; Gene; Genome; False discovery rate; Genetics; Biology; Statistics; Artificial intelligence; Mathematics","score_opus":0.03702735802862018,"score_gpt":0.23824663090773626,"score_spread":0.2012192728791161,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019000099","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06304467,0.00016138553,0.93340105,0.00018876986,0.000029721054,0.00015910136,0.0009146923,0.0017001769,0.00040053387],"genre_scores_gemma":[0.38741642,0.00012458033,0.60895085,0.00012117548,0.000058328063,0.000583454,0.00217096,0.0002768528,0.0002973167],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99638593,0.0019489664,0.00031118013,0.00046876023,0.00078586343,0.00009926659],"domain_scores_gemma":[0.9557047,0.038816508,0.0017543003,0.0015235158,0.0017857644,0.00041532857],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007699912,0.0006973828,0.0008204029,0.005366805,0.00034260884,0.0007886468,0.0012742347,0.0009266073,0.0021010423],"category_scores_gemma":[0.035590827,0.00036235008,0.0011845038,0.0030020745,0.0010592262,0.00067723583,0.00088259036,0.0009613649,0.00048680423],"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":[0.0028934109,0.00046719846,0.17378828,0.0010453926,0.0019551562,0.0018426699,0.00046283868,0.17925462,0.0394777,0.03345499,0.00969156,0.5556661],"study_design_scores_gemma":[0.00045123903,0.0008657706,0.023093306,0.00006635426,0.00032783067,0.0018002931,0.00017018843,0.9241989,0.013856156,0.03060672,0.0044417246,0.00012145768],"about_ca_topic_score_codex":0.001064847,"about_ca_topic_score_gemma":0.0011185394,"teacher_disagreement_score":0.007699912,"about_ca_system_score_codex":0.00044109166,"about_ca_system_score_gemma":0.001475178,"threshold_uncertainty_score":0.040721476},"labels":[],"label_agreement":null},{"id":"W2019590688","doi":"10.1186/1471-2105-14-139","title":"Ensemble-based prediction of RNA secondary structures","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Michael Smith Health Research BC","keywords":"Pseudoknot; Computer science; Machine learning; Resampling; Set (abstract data type); Data mining; Protein secondary structure; Exploit; Artificial intelligence; Nucleic acid secondary structure; Function (biology); RNA","score_opus":0.012940037251274156,"score_gpt":0.21182215388137687,"score_spread":0.19888211663010272,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019590688","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24838386,0.0034878482,0.7373896,0.00026159224,0.00019712387,0.00009767035,0.0023673538,0.0051304293,0.002684516],"genre_scores_gemma":[0.7738841,0.0010803946,0.21615109,0.0001601086,0.0001767624,0.00014039152,0.0070420415,0.00023908292,0.0011260874],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99908125,0.00023841872,0.000047502373,0.00025810086,0.00031033036,0.000064380765],"domain_scores_gemma":[0.99696285,0.0017050492,0.0003007972,0.00031894012,0.00059910363,0.00011320675],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017807573,0.0008845524,0.0010845079,0.0017508834,0.00038223798,0.0005431799,0.0009060105,0.00065104204,0.00083685864],"category_scores_gemma":[0.0039262013,0.0002637043,0.0011805434,0.0009024445,0.00028303557,0.00083991274,0.0005894944,0.0009914251,0.00059353927],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023846816,0.00014715435,0.01920869,0.00025379792,0.00041572697,0.000146526,0.00008045642,0.761954,0.013279704,0.0018195442,0.006506032,0.19594988],"study_design_scores_gemma":[0.000005569571,0.000033743567,0.0016404864,0.000010877416,0.000025138103,0.000035233013,0.0000059840595,0.9938153,0.0026416574,0.0011615962,0.00061582396,0.000008570862],"about_ca_topic_score_codex":0.0034053447,"about_ca_topic_score_gemma":0.005279092,"teacher_disagreement_score":0.0034053447,"about_ca_system_score_codex":0.00043267687,"about_ca_system_score_gemma":0.00065956335,"threshold_uncertainty_score":0.009417713},"labels":[],"label_agreement":null},{"id":"W2021166311","doi":"10.1186/1471-2105-12-s11-a9","title":"Computational purification of tumor gene expression data","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Gene expression profiling; Concordance; DNA microarray; Gene expression; Biology; Gene; Computational biology; Bioinformatics; Genetics","score_opus":0.06824587109555594,"score_gpt":0.2790169882799327,"score_spread":0.21077111718437677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2021166311","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08770315,0.0017232888,0.86809206,0.002517496,0.00023661947,0.00031189897,0.02113703,0.013606548,0.0046718507],"genre_scores_gemma":[0.4205195,0.0013861173,0.504727,0.00080786116,0.00022998573,0.00082914333,0.06610848,0.0013944366,0.003997558],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999371,0.00015928861,0.000041364954,0.00021007298,0.00015263078,0.000065675165],"domain_scores_gemma":[0.99807054,0.0013407342,0.00007680034,0.00022195358,0.00022002103,0.00007007503],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009545475,0.0009344741,0.0011638957,0.0010247496,0.00062045036,0.0016674958,0.0016259421,0.0008525126,0.0048579522],"category_scores_gemma":[0.004539427,0.0005480614,0.0015493496,0.0017418416,0.00067514245,0.0008323844,0.00088249875,0.0017940549,0.0021344796],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00055069756,0.00020418859,0.0062330896,0.00070449064,0.00020184477,0.00043790336,0.00007216557,0.86157,0.006312512,0.011565563,0.01772216,0.09442542],"study_design_scores_gemma":[0.000027942975,0.000026699938,0.00046832958,0.000014728649,0.000018818262,0.000069320246,0.000017983211,0.9799788,0.0018894952,0.0135319615,0.0039474783,0.000008431391],"about_ca_topic_score_codex":0.005860883,"about_ca_topic_score_gemma":0.0065327287,"teacher_disagreement_score":0.005860883,"about_ca_system_score_codex":0.00092468417,"about_ca_system_score_gemma":0.0018588603,"threshold_uncertainty_score":0.016251504},"labels":[],"label_agreement":null},{"id":"W2022059553","doi":"10.1186/1471-2105-12-379","title":"GOmotif: A web server for investigating the biological role of protein sequence motifs","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; Public Health Agency of Canada","funders":"","keywords":"Gene ontology; Sequence motif; Computer science; Biological database; Computational biology; Web server; Biological data; Ontology; Motif (music); Biological network; Gene; Data mining; Biology; Bioinformatics; Genetics; The Internet; World Wide Web; Gene expression","score_opus":0.05431194829961473,"score_gpt":0.24357366344891151,"score_spread":0.1892617151492968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2022059553","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04839562,0.0041102646,0.13305016,0.0013097901,0.00037431184,0.0010838646,0.31710562,0.48119494,0.013375457],"genre_scores_gemma":[0.06720384,0.0025048323,0.27520934,0.0006615583,0.00013514663,0.0024620227,0.62729096,0.018763369,0.005769015],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.999419,0.0000847746,0.000060475308,0.00015263242,0.00018449953,0.000098551885],"domain_scores_gemma":[0.9986864,0.00045605082,0.00018172803,0.00014939804,0.00026895775,0.00025752955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015228862,0.00322155,0.0027029573,0.008008205,0.0015567584,0.0015588995,0.0034805737,0.0024908008,0.026220812],"category_scores_gemma":[0.0042755664,0.0011859286,0.0016304362,0.004719099,0.0006252567,0.002413874,0.0023382073,0.0020604646,0.017370153],"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":[0.005507818,0.0007796987,0.012392986,0.00971447,0.00079808524,0.0023729233,0.0014230779,0.0039551,0.13516112,0.009568145,0.63965154,0.17867498],"study_design_scores_gemma":[0.0031039498,0.0012096664,0.044733,0.0016908029,0.000791174,0.0060217506,0.0010219661,0.089201845,0.06844914,0.04388634,0.7390148,0.00087557145],"about_ca_topic_score_codex":0.0039710496,"about_ca_topic_score_gemma":0.0053517222,"teacher_disagreement_score":0.026220812,"about_ca_system_score_codex":0.0010195043,"about_ca_system_score_gemma":0.0024755264,"threshold_uncertainty_score":0.087717295},"labels":[],"label_agreement":null},{"id":"W2024909802","doi":"10.1186/s12859-015-0551-y","title":"A network model for angiogenesis in ovarian cancer","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":73,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre","funders":"National Heart, Lung, and Blood Institute","keywords":"Biology; Angiogenesis; DNA microarray; DNA methylation; Computational biology; Ovarian cancer; Gene regulatory network; Gene; Transcription factor; Regulation of gene expression; Gene expression profiling; Gene expression; Bioinformatics; Genetics; Cancer","score_opus":0.04038979658660576,"score_gpt":0.26778370292767345,"score_spread":0.22739390634106768,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2024909802","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06830185,0.0017250623,0.9065348,0.0032936942,0.00014670413,0.00016373664,0.0025900549,0.0005820134,0.016662097],"genre_scores_gemma":[0.7996477,0.003036692,0.1762725,0.0005365094,0.00025699014,0.0009628592,0.0023730686,0.0001803285,0.016733367],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995622,0.00019927102,0.000013623755,0.00010809202,0.00006956399,0.0000472048],"domain_scores_gemma":[0.99875104,0.0008268103,0.00015687222,0.000055107834,0.00011948741,0.00009061768],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00093814323,0.00071540114,0.0006555348,0.001417707,0.0005549513,0.0011814332,0.0011332138,0.0010077093,0.0040669804],"category_scores_gemma":[0.0033426685,0.0003083328,0.0011622681,0.0010963822,0.00091485557,0.0014374377,0.00085118145,0.0011372821,0.00053626],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008762697,0.00003629307,0.001978777,0.000119153345,0.00007495432,0.0001652442,0.0001544754,0.7513082,0.0021074133,0.2301854,0.002723585,0.011058891],"study_design_scores_gemma":[0.000015139666,0.000016700456,0.00038942386,0.000009963191,0.000017308304,0.000044534205,0.00001915944,0.8926372,0.00009864294,0.10401249,0.002732502,0.000007009298],"about_ca_topic_score_codex":0.0077627106,"about_ca_topic_score_gemma":0.009334233,"teacher_disagreement_score":0.0077627106,"about_ca_system_score_codex":0.0018793116,"about_ca_system_score_gemma":0.0009149009,"threshold_uncertainty_score":0.01543504},"labels":[],"label_agreement":null},{"id":"W2025117991","doi":"10.1186/1471-2105-8-420","title":"'Unite and conquer': enhanced prediction of protein subcellular localization by integrating multiple specialized tools","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Canadian Institutes of Health Research; Canadian Institute for Advanced Research","keywords":"Interconnectivity; Computer science; Subcellular localization; Proteome; Function (biology); Computational biology; Protein function prediction; Identification (biology); Protein subcellular localization prediction; Set (abstract data type); Machine learning; Artificial intelligence; Biology; Bioinformatics; Protein function; Genetics","score_opus":0.010598265984508089,"score_gpt":0.2339617152942268,"score_spread":0.22336344930971871,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2025117991","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12905313,0.0007477492,0.85654986,0.0005230102,0.00007680171,0.00013793031,0.00044391234,0.011209662,0.0012579933],"genre_scores_gemma":[0.32336405,0.00020735544,0.6732007,0.00027407982,0.000039961582,0.00013002753,0.0011370915,0.00045469412,0.0011920072],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984635,0.00044679176,0.000074228796,0.00043374082,0.00041856858,0.00016311929],"domain_scores_gemma":[0.99758863,0.0013243153,0.00026513002,0.0002971004,0.00035908117,0.00016586382],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036018433,0.0021456787,0.0014280371,0.0020000022,0.00046088104,0.0010970926,0.00175666,0.001838618,0.0015585574],"category_scores_gemma":[0.004806015,0.0005846585,0.001088949,0.0014300075,0.0006710044,0.0019163396,0.0020815765,0.0013887978,0.000757482],"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":[0.0015503048,0.00080209,0.02153794,0.00053037616,0.0005452929,0.0008413635,0.00034940403,0.15258773,0.1066369,0.00443844,0.007758587,0.70242167],"study_design_scores_gemma":[0.00007091117,0.00016899846,0.0015928743,0.000013006916,0.00007417393,0.0002310054,0.00003533671,0.96116555,0.032340877,0.0023126793,0.0019560305,0.000038521648],"about_ca_topic_score_codex":0.0020441923,"about_ca_topic_score_gemma":0.0027090982,"teacher_disagreement_score":0.0036018433,"about_ca_system_score_codex":0.0006569079,"about_ca_system_score_gemma":0.0009894529,"threshold_uncertainty_score":0.019048631},"labels":[],"label_agreement":null},{"id":"W2025846584","doi":"10.1186/1471-2105-13-320","title":"Multiple-platform data integration method with application to combined analysis of microarray and proteomic data","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; York University","funders":"","keywords":"Data mining; Computer science; Data integration; False discovery rate; Statistical hypothesis testing; Test statistic; Statistic; Selection (genetic algorithm); DNA microarray; Computational biology; Statistics; Biology; Mathematics; Machine learning; Gene","score_opus":0.04850726272005896,"score_gpt":0.3225575594628057,"score_spread":0.2740502967427467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2025846584","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0062271478,0.00009051408,0.9924206,0.000053665368,0.000021393016,0.000083883824,0.00005021932,0.00093845406,0.0001141205],"genre_scores_gemma":[0.06675325,0.00005930772,0.93220645,0.000052952753,0.000036927162,0.0002762692,0.00021350302,0.0001022197,0.0002991299],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9925916,0.0029952093,0.00055195874,0.0010894516,0.0025478806,0.00022381387],"domain_scores_gemma":[0.9875987,0.006939587,0.00091957126,0.0014527803,0.0027729827,0.00031632278],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011432235,0.0012324677,0.0016051319,0.0037775214,0.0007675586,0.001448238,0.0015609054,0.0012386735,0.001561857],"category_scores_gemma":[0.020470213,0.0006908637,0.0018841748,0.004381496,0.0007305441,0.0016770444,0.0023907174,0.0017837647,0.0006813477],"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":[0.0006523201,0.00047539241,0.0120246755,0.00041969522,0.0009098376,0.00074881286,0.0003945135,0.091833144,0.031255733,0.010074366,0.003381516,0.84783],"study_design_scores_gemma":[0.000061947794,0.00016285993,0.002824916,0.000020615507,0.00015341704,0.00043836646,0.000036665104,0.9713597,0.011203014,0.010930261,0.0027441876,0.0000640635],"about_ca_topic_score_codex":0.0011835317,"about_ca_topic_score_gemma":0.0014620919,"teacher_disagreement_score":0.011432235,"about_ca_system_score_codex":0.00066175574,"about_ca_system_score_gemma":0.0016922285,"threshold_uncertainty_score":0.06046015},"labels":[],"label_agreement":null},{"id":"W2026012474","doi":"10.1186/1471-2105-8-431","title":"Comparative evaluation of gene-set analysis methods","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":106,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Canadian Institutes of Health Research; Fondation pour la Recherche Médicale","keywords":"Permutation (music); Statistical inference; Null distribution; Inference; Resampling; Statistical hypothesis testing; Statistics; Statistical power; Type I and type II errors; Sample size determination; Mathematics; Gene expression profiling; Analysis of covariance; Multiple comparisons problem; False discovery rate; Asymptotic distribution; Biology; Test statistic; Computer science; Genetics; Gene expression; Gene; Artificial intelligence","score_opus":0.12111852523511878,"score_gpt":0.4413828526334908,"score_spread":0.320264327398372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026012474","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043641843,0.0087759085,0.9320044,0.0010266551,0.0007468192,0.00080554734,0.0032743956,0.003745366,0.005979019],"genre_scores_gemma":[0.241787,0.0023409545,0.7450573,0.00043724588,0.00024997865,0.0028556425,0.0048937122,0.0012831679,0.0010949934],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.948534,0.035106886,0.002777051,0.0040124976,0.009001382,0.0005681555],"domain_scores_gemma":[0.82192343,0.14793964,0.0032804618,0.010424256,0.015623361,0.000808887],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.055208378,0.0022239857,0.0022281024,0.008260157,0.0012227946,0.0032664617,0.003453855,0.0018635642,0.0063057262],"category_scores_gemma":[0.11174069,0.00051161327,0.00402544,0.0063452832,0.0014074744,0.0025543629,0.0027625612,0.0022969411,0.0016918886],"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":[0.0033206705,0.00050834747,0.03033502,0.0043213326,0.0046203514,0.00026071782,0.0006938565,0.12073192,0.007546938,0.032948025,0.017366046,0.77734685],"study_design_scores_gemma":[0.00064193615,0.0021413835,0.03305045,0.0012279564,0.0021161227,0.0013588538,0.00081625354,0.81313545,0.027929613,0.079638764,0.03746095,0.00048223833],"about_ca_topic_score_codex":0.001367897,"about_ca_topic_score_gemma":0.0012354979,"teacher_disagreement_score":0.9447916,"about_ca_system_score_codex":0.002561241,"about_ca_system_score_gemma":0.0024475174,"threshold_uncertainty_score":0.29197323},"labels":[],"label_agreement":null},{"id":"W2027878425","doi":"10.1186/1471-2105-12-400","title":"MetaboHunter: an automatic approach for identification of metabolites from 1H-NMR spectra of complex mixtures","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":117,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Allison University; National Research Council Canada; Université de Moncton","funders":"Mount Allison University","keywords":"Identification (biology); Metabolite; Metabolomics; Computer science; NMR spectra database; Data mining; Spectral line; Task (project management); Biological system; Database; Chemistry; Biology; Physics; Chromatography","score_opus":0.0462357203708497,"score_gpt":0.2672659518200872,"score_spread":0.22103023144923753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2027878425","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014557133,0.0008008271,0.8500257,0.00017238127,0.00011806795,0.0003514962,0.007846939,0.12502074,0.0011066464],"genre_scores_gemma":[0.027979506,0.00042679743,0.95169663,0.00013062771,0.000061714345,0.00042465213,0.013133593,0.0046604034,0.0014861327],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99867046,0.00025115453,0.00011885793,0.00042404485,0.00045031263,0.000085217944],"domain_scores_gemma":[0.99844754,0.0005845189,0.00024979055,0.00024163914,0.00037338136,0.0001030338],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025917941,0.0038039538,0.001785869,0.006597661,0.0010016637,0.0023426565,0.0021870607,0.0014663531,0.009979395],"category_scores_gemma":[0.004659847,0.0011538217,0.0020650416,0.0026704913,0.0005604465,0.0023976772,0.0027233388,0.0013020012,0.006642157],"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":[0.0020133627,0.0005558328,0.008532195,0.002678247,0.0009003208,0.0012373273,0.00046137586,0.008747493,0.22374973,0.003555361,0.05181643,0.69575226],"study_design_scores_gemma":[0.00047910007,0.00079082925,0.01854459,0.000311494,0.00047174768,0.003979366,0.0003988933,0.5615307,0.28837052,0.017755304,0.10675202,0.0006155476],"about_ca_topic_score_codex":0.0012323544,"about_ca_topic_score_gemma":0.0021937434,"teacher_disagreement_score":0.009979395,"about_ca_system_score_codex":0.0004485522,"about_ca_system_score_gemma":0.00135059,"threshold_uncertainty_score":0.033384383},"labels":[],"label_agreement":null},{"id":"W2028126042","doi":"10.1186/1471-2105-9-463","title":"Information-based methods for predicting gene function from systematic gene knock-downs","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetics, Aging, and Longevity in Model Organisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Division of Biological Infrastructure; Alfred P. Sloan Foundation; National Science Foundation","keywords":"Biology; Phenotype; Computational biology; Gene; RNA interference; Functional genomics; Genetics; Caenorhabditis elegans; Gene regulatory network; DNA microarray; Function (biology); Gene prediction; Genome; Gene knockout; Genomics; Gene expression; RNA","score_opus":0.021769513734404333,"score_gpt":0.2629218602858384,"score_spread":0.24115234655143408,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2028126042","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07173058,0.0013856235,0.9195504,0.00020751455,0.000044712244,0.00020201832,0.0031600895,0.002897189,0.0008218638],"genre_scores_gemma":[0.3437942,0.000741028,0.64818037,0.00013880496,0.000063656174,0.00062219455,0.0059176725,0.00024923633,0.00029296224],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971826,0.0010226808,0.0003409165,0.0004982687,0.00087574107,0.00007982519],"domain_scores_gemma":[0.9795028,0.015879925,0.00201577,0.0010610262,0.0012598641,0.0002805724],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0049183057,0.0015743535,0.0015988568,0.008790028,0.0005853985,0.0013962561,0.0014097717,0.0012321367,0.0010242747],"category_scores_gemma":[0.023949463,0.00056213065,0.0013970567,0.004751293,0.00096485467,0.0016017922,0.0011090116,0.0014551966,0.00043196653],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012536251,0.0004702081,0.041441657,0.002423028,0.0013657716,0.0005938743,0.00039727803,0.48648727,0.031317793,0.016218359,0.0033098375,0.41472134],"study_design_scores_gemma":[0.00006856271,0.00024617912,0.008021585,0.0001103963,0.00020162694,0.00021527096,0.000055763627,0.9372932,0.009299254,0.041931372,0.0024781507,0.00007867172],"about_ca_topic_score_codex":0.0014456799,"about_ca_topic_score_gemma":0.0015826757,"teacher_disagreement_score":0.008790028,"about_ca_system_score_codex":0.0011760298,"about_ca_system_score_gemma":0.0008244004,"threshold_uncertainty_score":0.026010811},"labels":[],"label_agreement":null},{"id":"W2028245735","doi":"10.1186/1471-2105-9-305","title":"MAID : An effect size based model for microarray data integration across laboratories and platforms","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto General Hospital; Toronto Western Hospital; Canada Research Chairs; University of Toronto","funders":"Canadian Institutes of Health Research; Ontario Genomics; Ontario Genomics Institute; Genome Canada","keywords":"Replicate; DNA microarray; Sample size determination; Data mining; Computational biology; Computer science; Statistical power; Gene expression profiling; Permutation (music); Gene chip analysis; Microarray; False discovery rate; Microarray analysis techniques; Gene expression; Biology; Gene; Statistics; Mathematics; Genetics","score_opus":0.05440643697646198,"score_gpt":0.3195363113182625,"score_spread":0.2651298743418005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2028245735","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0137255415,0.00052234007,0.9815305,0.0006085876,0.00013312882,0.0007636271,0.0008297869,0.00075347634,0.0011330259],"genre_scores_gemma":[0.37988797,0.00078865635,0.5989609,0.0012813724,0.00028301473,0.009638362,0.0025813302,0.00037592713,0.0062024905],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.96785873,0.02192723,0.0010256406,0.005296382,0.003126041,0.0007659908],"domain_scores_gemma":[0.8756097,0.11025206,0.004331879,0.0055443556,0.003425898,0.0008360999],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05309867,0.0035673908,0.0041566463,0.003343161,0.0009049144,0.0025434992,0.006282134,0.004078289,0.00665949],"category_scores_gemma":[0.09337727,0.0019156493,0.0057690935,0.002132561,0.0042127445,0.0032823244,0.00405669,0.0057292767,0.001121592],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0029330724,0.0006394406,0.022889867,0.0012744397,0.0029752422,0.0008701303,0.00082922925,0.69356805,0.0064699454,0.12472379,0.004867889,0.13795887],"study_design_scores_gemma":[0.0004223381,0.0008447596,0.0033375078,0.00009975057,0.0005229478,0.00021716148,0.000044099765,0.9296634,0.0013618798,0.059960794,0.0034474407,0.00007777293],"about_ca_topic_score_codex":0.0041210004,"about_ca_topic_score_gemma":0.0023799492,"teacher_disagreement_score":0.05309867,"about_ca_system_score_codex":0.003212906,"about_ca_system_score_gemma":0.0026972562,"threshold_uncertainty_score":0.28081596},"labels":[],"label_agreement":null},{"id":"W2029036185","doi":"10.1186/1471-2105-10-120","title":"Multichromosomal median and halving problems under different genomic distances","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":160,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Centre National de la Recherche Scientifique; Agence Nationale de la Recherche","keywords":"Genome; Breakpoint; Context (archaeology); Generalization; Time complexity; Biology; Computer science; Computational biology; Genetics; Combinatorics; Mathematics; Chromosome; Gene","score_opus":0.012402740614968691,"score_gpt":0.22283285140290676,"score_spread":0.21043011078793808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029036185","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20678316,0.0023125361,0.7688207,0.004163487,0.00017477701,0.0002122409,0.000889545,0.0006937685,0.015949829],"genre_scores_gemma":[0.65201014,0.0014820445,0.3336347,0.0005916049,0.00034427558,0.00038131786,0.0019992504,0.0003410243,0.0092157],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99831843,0.00048058172,0.000101886784,0.0005262338,0.0003245873,0.00024833015],"domain_scores_gemma":[0.983809,0.013388575,0.00081266003,0.0008629047,0.0005172783,0.0006095163],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023585842,0.0008184002,0.0014276467,0.00085260684,0.0012871872,0.0028288364,0.0031118176,0.0023927744,0.008719805],"category_scores_gemma":[0.013039163,0.00042578147,0.0015358076,0.0018290995,0.0018826006,0.005657102,0.0031069785,0.0036434657,0.00065896934],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007630689,0.00033349713,0.0034879893,0.0011716547,0.00020301758,0.00037860754,0.0007240931,0.5284105,0.003127046,0.34279028,0.012152978,0.10645727],"study_design_scores_gemma":[0.00014321285,0.00012888217,0.00109844,0.000071525516,0.000073211704,0.00048623892,0.00032693532,0.4925035,0.0036372042,0.49562904,0.0058572832,0.000044462184],"about_ca_topic_score_codex":0.0014069618,"about_ca_topic_score_gemma":0.0016019731,"teacher_disagreement_score":0.008719805,"about_ca_system_score_codex":0.0022383076,"about_ca_system_score_gemma":0.0014097595,"threshold_uncertainty_score":0.029170632},"labels":[],"label_agreement":null},{"id":"W2030006812","doi":"10.1186/1471-2105-10-99","title":"Markov clustering versus affinity propagation for the partitioning of protein interaction graphs","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":234,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto; Hospital for Sick Children","funders":"Hospital for Sick Children","keywords":"Cluster analysis; Computer science; Markov chain; Affinity propagation; Partition (number theory); Theoretical computer science; Data mining; Machine learning; Correlation clustering; Mathematics; Canopy clustering algorithm; Combinatorics","score_opus":0.02334492071945516,"score_gpt":0.26218292354744616,"score_spread":0.238838002827991,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030006812","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07637575,0.0005996625,0.91929376,0.00039799948,0.00004511953,0.0001711776,0.00033707113,0.001121869,0.0016575691],"genre_scores_gemma":[0.480282,0.00050901383,0.5152599,0.00021308333,0.000069215144,0.00028406398,0.0013681754,0.000221731,0.0017928262],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986553,0.00047157786,0.000068379544,0.00033216013,0.00035481754,0.00011786103],"domain_scores_gemma":[0.98831475,0.008483449,0.00093255175,0.0007916291,0.0011569601,0.00032068635],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026421454,0.000994583,0.0007449154,0.002456684,0.00090410555,0.0011923806,0.002070885,0.0018881876,0.001673291],"category_scores_gemma":[0.011981853,0.00053765136,0.0010531257,0.0016081487,0.0011023486,0.0019389191,0.0012975124,0.0016173118,0.00063233933],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023590545,0.00010143014,0.0035300024,0.00016644705,0.00010035586,0.00006396484,0.00016145484,0.9007372,0.003952,0.01345774,0.0013961251,0.07609734],"study_design_scores_gemma":[0.000009498036,0.000023504233,0.0004119472,0.000007061727,0.0000090908325,0.00002865449,0.000014711337,0.9891304,0.0013030508,0.008809067,0.00024408051,0.000008954452],"about_ca_topic_score_codex":0.010560818,"about_ca_topic_score_gemma":0.010634891,"teacher_disagreement_score":0.010560818,"about_ca_system_score_codex":0.0020167418,"about_ca_system_score_gemma":0.0014653591,"threshold_uncertainty_score":0.020998657},"labels":[],"label_agreement":null},{"id":"W2030393641","doi":"10.1186/1471-2105-12-s1-s55","title":"Closest string with outliers","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"University of Waterloo; Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"String (physics); Hamming distance; Outlier; Combinatorics; Integer (computer science); String metric; Edit distance; Bounded function; Hamming code; Set (abstract data type); Discrete mathematics; Algorithm; Mathematics; String searching algorithm; Computer science; Artificial intelligence; Pattern matching","score_opus":0.04317960402421332,"score_gpt":0.2097569128317822,"score_spread":0.16657730880756888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030393641","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.050822787,0.001690372,0.9345255,0.0034435296,0.00029849872,0.00029323908,0.0021652828,0.002485793,0.004275045],"genre_scores_gemma":[0.39466217,0.0014439012,0.58612734,0.0014970531,0.0005819199,0.0008622445,0.0060529173,0.00075999077,0.008012457],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99131155,0.0022144641,0.0009140801,0.0029368086,0.002150221,0.00047298908],"domain_scores_gemma":[0.96903676,0.019932328,0.0029231508,0.0057058553,0.0016436195,0.00075827737],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036673115,0.0015303966,0.0034442327,0.002618296,0.0017714688,0.0034351677,0.0052621826,0.0041617677,0.0063837003],"category_scores_gemma":[0.039534796,0.00086409063,0.002121172,0.0059620407,0.002741758,0.008788978,0.004778843,0.005034002,0.002577749],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016807896,0.00045940987,0.007939424,0.0014005787,0.0002362859,0.0010488058,0.0008290714,0.4882148,0.0059219967,0.18220085,0.031767927,0.27830008],"study_design_scores_gemma":[0.00007807604,0.00015564502,0.00045998246,0.000103380495,0.000032267057,0.0006345628,0.00014543188,0.69996405,0.0035606713,0.28743634,0.007382172,0.000047399248],"about_ca_topic_score_codex":0.0020611412,"about_ca_topic_score_gemma":0.0013922567,"teacher_disagreement_score":0.0063837003,"about_ca_system_score_codex":0.0021205884,"about_ca_system_score_gemma":0.0024675345,"threshold_uncertainty_score":0.02135557},"labels":[],"label_agreement":null},{"id":"W2030496326","doi":"10.1186/1471-2105-12-113","title":"A fully automatic gridding method for cDNA microarray images","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"DNA microarray; Computer science; Computational biology; Microarray; Complementary DNA; Artificial intelligence; Pattern recognition (psychology); Data mining; Bioinformatics; Biology; Genetics; Gene; Gene expression","score_opus":0.037787144706220105,"score_gpt":0.2927419322280458,"score_spread":0.25495478752182565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030496326","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037980543,0.000074252945,0.9941679,0.00003560691,0.00002650521,0.000043386393,0.000073120296,0.0014809298,0.00030021867],"genre_scores_gemma":[0.01988495,0.00008768318,0.9786769,0.000026551066,0.0000136388035,0.00009241154,0.00023359669,0.00021402538,0.0007701604],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992306,0.0001399115,0.00006246128,0.00017828164,0.00032691407,0.000061907864],"domain_scores_gemma":[0.9987575,0.00038329864,0.000115290895,0.00030565413,0.00038385246,0.000054498167],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008570796,0.0007518561,0.000809828,0.0013373903,0.00044626748,0.00095853384,0.0013626725,0.0007085236,0.003691748],"category_scores_gemma":[0.0024355485,0.00049966073,0.00093412696,0.0014052391,0.00057803554,0.000732524,0.00083484396,0.000831483,0.0024930786],"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":[0.00031268178,0.00005915969,0.0007838514,0.00028815377,0.000044720386,0.00013305359,0.00014912285,0.039333776,0.20755702,0.00535343,0.0041959225,0.74178904],"study_design_scores_gemma":[0.00005033493,0.000110017856,0.0017063209,0.000024887293,0.000025861298,0.00035132057,0.0000564448,0.8773648,0.10179924,0.0072961664,0.011152128,0.00006243677],"about_ca_topic_score_codex":0.0021766876,"about_ca_topic_score_gemma":0.002909301,"teacher_disagreement_score":0.003691748,"about_ca_system_score_codex":0.0006639314,"about_ca_system_score_gemma":0.0012790901,"threshold_uncertainty_score":0.012350202},"labels":[],"label_agreement":null},{"id":"W2030528974","doi":"10.1186/1471-2105-12-25","title":"Systematic error detection in experimental high-throughput screening","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University and Génome Québec Innovation Centre; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Computer science; Context (archaeology); Error detection and correction; Data mining; Systematic error; Statistical power; Type I and type II errors; Process (computing); Statistics; Algorithm; Reliability engineering; Mathematics; Biology","score_opus":0.06811592733085549,"score_gpt":0.29838761659394086,"score_spread":0.2302716892630854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030528974","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14296104,0.0030776882,0.84451765,0.00039274292,0.0005184783,0.00082374475,0.0012417742,0.0043540313,0.0021127642],"genre_scores_gemma":[0.66216713,0.0010814203,0.33117506,0.00046187773,0.00014016044,0.0016229112,0.0022395866,0.00046315382,0.0006486653],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.93674684,0.029826913,0.005256898,0.0057283696,0.02124684,0.0011941891],"domain_scores_gemma":[0.76528955,0.17260596,0.021440212,0.020320471,0.019271305,0.0010724845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.039073832,0.0017061497,0.0021312474,0.004132865,0.0010477573,0.002327511,0.0036789423,0.0023943174,0.0015536952],"category_scores_gemma":[0.13327208,0.0008444227,0.0019730988,0.004034612,0.0032520925,0.0017553262,0.0028479616,0.0019088153,0.00078365864],"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":[0.005726178,0.0013809007,0.18002081,0.012400824,0.0027728053,0.001955528,0.001980706,0.22055583,0.15021555,0.025574626,0.007267348,0.39014882],"study_design_scores_gemma":[0.00029718867,0.0026167561,0.057632692,0.00077930925,0.00048237058,0.0018180629,0.00034821438,0.5185632,0.37760723,0.028348345,0.011010345,0.0004963562],"about_ca_topic_score_codex":0.0010791344,"about_ca_topic_score_gemma":0.00093722844,"teacher_disagreement_score":0.039073832,"about_ca_system_score_codex":0.0018138965,"about_ca_system_score_gemma":0.002331951,"threshold_uncertainty_score":0.20664471},"labels":[],"label_agreement":null},{"id":"W2032345031","doi":"10.1186/1471-2105-13-174","title":"A novel hierarchical clustering algorithm for gene sequences","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Fractal and DNA sequence analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":94,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"National Natural Science Foundation of China","keywords":"Cluster analysis; Hierarchical clustering; DNA sequencing; Complete-linkage clustering; Single-linkage clustering; DNA microarray; Tuple; Similarity (geometry); Phylogenetic tree; Pattern recognition (psychology); Measure (data warehouse); Sequence (biology); Correlation clustering; Data mining; Computational biology; Computer science; Artificial intelligence; Biology; Gene; Mathematics; CURE data clustering algorithm; Genetics; Image (mathematics)","score_opus":0.02575875611595342,"score_gpt":0.2702451143211852,"score_spread":0.2444863582052318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032345031","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021497556,0.00022649595,0.995706,0.000067685105,0.00004939468,0.00007161329,0.00016925964,0.000882152,0.00067754823],"genre_scores_gemma":[0.018820504,0.00014042236,0.9787677,0.0000508289,0.00004247789,0.0001583644,0.00059162575,0.00015822778,0.0012697233],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99824166,0.00024296268,0.00013146411,0.0005035836,0.000779329,0.00010100971],"domain_scores_gemma":[0.9987047,0.00032737266,0.00013221918,0.00019481037,0.0005846898,0.000056231424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012378914,0.0009691502,0.001046119,0.0034658995,0.0012604101,0.0013034615,0.0020474615,0.0012305281,0.0035455732],"category_scores_gemma":[0.0036380605,0.00056859566,0.0015332913,0.0038166926,0.00071713154,0.0017134724,0.001189715,0.0012551049,0.0030437403],"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":[0.00013103016,0.000072315845,0.0016153732,0.00040926837,0.00018245023,0.0001261028,0.0004075107,0.10722465,0.021973751,0.027165959,0.013904467,0.82678723],"study_design_scores_gemma":[0.000054830347,0.00007790898,0.001299002,0.000055677443,0.000057680667,0.0003924201,0.000087113396,0.92398596,0.00987009,0.035849057,0.028206421,0.00006385435],"about_ca_topic_score_codex":0.0061246124,"about_ca_topic_score_gemma":0.0067206114,"teacher_disagreement_score":0.0061246124,"about_ca_system_score_codex":0.0015478956,"about_ca_system_score_gemma":0.0019564703,"threshold_uncertainty_score":0.012177944},"labels":[],"label_agreement":null},{"id":"W2033377371","doi":"10.1186/1471-2105-10-s14-s4","title":"Googling DNA sequences on the World Wide Web","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Ontario Genomics; Ontario Genomics Institute; Genome Canada","keywords":"DNA microarray; World Wide Web; Computational biology; Biology; The Internet; Computer science; Genetics; Bioinformatics; Data science; Gene; Gene expression","score_opus":0.020518604062589485,"score_gpt":0.24137362208411092,"score_spread":0.22085501802152144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2033377371","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09368417,0.003968899,0.71676046,0.0017800796,0.0008075706,0.001540794,0.05777157,0.07950623,0.04418025],"genre_scores_gemma":[0.08823661,0.002618211,0.8357464,0.00042066342,0.00017715574,0.0008476341,0.054330826,0.0036543882,0.013968128],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991596,0.00015575848,0.00011388092,0.00020250071,0.0003097184,0.000058583984],"domain_scores_gemma":[0.99843913,0.00061702635,0.00020473628,0.00025468037,0.00039015416,0.00009425394],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009496237,0.0009986821,0.00075742137,0.010174944,0.0008090706,0.0021571417,0.00072690897,0.00085976237,0.013879257],"category_scores_gemma":[0.0052010203,0.00034263052,0.00075803156,0.007684174,0.0004323835,0.0022760124,0.001130228,0.00070236146,0.012638532],"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":[0.00037604664,0.00018079836,0.0077429563,0.0019803664,0.00013402852,0.0008759496,0.0005591364,0.0034226966,0.03602089,0.013323025,0.055302024,0.880082],"study_design_scores_gemma":[0.00017359862,0.0003134179,0.02696108,0.0011601923,0.00015578858,0.0033186676,0.0013370386,0.093044505,0.110833034,0.075860575,0.68660605,0.00023600762],"about_ca_topic_score_codex":0.0029433346,"about_ca_topic_score_gemma":0.0031001153,"teacher_disagreement_score":0.013879257,"about_ca_system_score_codex":0.00053737726,"about_ca_system_score_gemma":0.0011536293,"threshold_uncertainty_score":0.046430767},"labels":[],"label_agreement":null},{"id":"W2034031757","doi":"10.1186/1471-2105-15-302","title":"SAGE: String-overlap Assembly of GEnomes","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"De Bruijn graph; Contig; String (physics); Sequence assembly; Computer science; Graph; Theoretical computer science; Genomics; Genome; Computation; Biology; Computational biology; Algorithm; Mathematics; Genetics; Gene","score_opus":0.01149497004112611,"score_gpt":0.2257135221193186,"score_spread":0.21421855207819251,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034031757","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013835822,0.00029531383,0.8833339,0.00020892374,0.00020555075,0.00024395954,0.008528044,0.089702085,0.0036463381],"genre_scores_gemma":[0.0445546,0.0002944774,0.9136259,0.00021911768,0.000072926225,0.0005989419,0.02389374,0.013896284,0.0028439919],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984428,0.0005198938,0.0001488825,0.00044672284,0.00035176732,0.00008999813],"domain_scores_gemma":[0.9975229,0.0011903092,0.00027114313,0.00050752243,0.00036183343,0.00014629167],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017461019,0.0018817954,0.000999226,0.0022080569,0.0011572338,0.001535271,0.0019622487,0.0007811092,0.012957171],"category_scores_gemma":[0.004628648,0.00095977745,0.0023555502,0.0019268879,0.0009851467,0.0014489555,0.002051795,0.002265695,0.007976286],"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":[0.002960701,0.0003417407,0.007447633,0.0045544924,0.0009622615,0.0013725623,0.001785132,0.06713989,0.2651131,0.06220172,0.22388008,0.36224076],"study_design_scores_gemma":[0.00060832786,0.000784283,0.0064128786,0.0004484183,0.00031661586,0.0019646036,0.0003719412,0.39325422,0.21495172,0.10648809,0.274,0.0003990021],"about_ca_topic_score_codex":0.0008536116,"about_ca_topic_score_gemma":0.001294826,"teacher_disagreement_score":0.012957171,"about_ca_system_score_codex":0.00054444,"about_ca_system_score_gemma":0.0012197456,"threshold_uncertainty_score":0.043346107},"labels":[],"label_agreement":null},{"id":"W2035486209","doi":"10.1186/1471-2105-9-243","title":"MD-SeeGH: a platform for integrative analysis of multi-dimensional genomic data","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomic variations and chromosomal abnormalities","field":"Biochemistry, Genetics and Molecular Biology","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; BC Cancer Agency; Canadian Centre for Applied Research in Cancer Control","funders":"National Institutes of Health; National Institute of Dental and Craniofacial Research; Canadian Breast Cancer Research Alliance; Genome Canada","keywords":"Computational biology; DNA microarray; Genomics; Computer science; DNA methylation; Copy-number variation; Biology; Software; Genome; Data mining; Bioinformatics; Genetics; Gene; Gene expression","score_opus":0.06515720872580286,"score_gpt":0.28112740047967566,"score_spread":0.2159701917538728,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2035486209","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008563262,0.00061028457,0.8709068,0.00053727836,0.00024866173,0.00056350854,0.01055436,0.10583876,0.0021771046],"genre_scores_gemma":[0.028922098,0.0002766732,0.9461539,0.0003379071,0.00010373761,0.002424566,0.014417996,0.005390878,0.001972203],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99750924,0.00061178306,0.00019148986,0.0004907503,0.0009939001,0.00020292246],"domain_scores_gemma":[0.99592906,0.0022094036,0.00038272963,0.0005785941,0.0005829506,0.0003172559],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004827057,0.0021201859,0.0018511051,0.00471806,0.0011322551,0.0021379692,0.002999244,0.0012281459,0.017040228],"category_scores_gemma":[0.008265221,0.0014934017,0.0016060278,0.0027428323,0.000917727,0.0020850196,0.0039479034,0.0027030872,0.0067207986],"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":[0.0035905798,0.00034564105,0.0062411088,0.0020370674,0.001005274,0.0014674686,0.0012658214,0.019452525,0.20287809,0.0126651935,0.17627832,0.5727729],"study_design_scores_gemma":[0.001556052,0.00064229,0.018497793,0.00030712888,0.0003628186,0.0027648099,0.00039527664,0.43020028,0.2351011,0.050120495,0.25918496,0.0008669935],"about_ca_topic_score_codex":0.0015784905,"about_ca_topic_score_gemma":0.0030880794,"teacher_disagreement_score":0.017040228,"about_ca_system_score_codex":0.0010491097,"about_ca_system_score_gemma":0.0015916434,"threshold_uncertainty_score":0.057005227},"labels":[],"label_agreement":null},{"id":"W2036298771","doi":"10.1186/1471-2105-12-s5-s8","title":"Promoting ranking diversity for genomics search with relevance-novelty combined model","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Information Retrieval and Search Behavior","field":"Computer Science","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":"York University","funders":"Beihang University; National Natural Science Foundation of China; State Key Laboratory of Software Development Environment; National Science Foundation","keywords":"Relevance (law); Novelty; Computer science; Information retrieval; Ranking (information retrieval); Term (time); Data science","score_opus":0.09916546799670223,"score_gpt":0.2562741648534256,"score_spread":0.15710869685672335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036298771","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13416065,0.0019173374,0.8553883,0.00097000855,0.00010475637,0.00021668835,0.00026698332,0.0011896269,0.0057857293],"genre_scores_gemma":[0.91413665,0.00046303586,0.08070549,0.00018613096,0.00015223096,0.00017138523,0.00029208514,0.000081970014,0.0038110241],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978302,0.0009117874,0.000093319475,0.00038090834,0.0005853073,0.00019834154],"domain_scores_gemma":[0.997575,0.0013701391,0.00028636723,0.00023152606,0.0003941581,0.00014290061],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023536147,0.000979339,0.0015489734,0.0023466172,0.0006350759,0.0012763554,0.0021929552,0.0018569786,0.0016840134],"category_scores_gemma":[0.0057691094,0.00051609986,0.0018127692,0.0018879916,0.0007789069,0.002969314,0.0014441705,0.0011728414,0.0006450112],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00076333625,0.0005936674,0.009987311,0.00041805618,0.00040933935,0.0005340016,0.00028022515,0.7256303,0.0118800355,0.027704341,0.004727549,0.2170719],"study_design_scores_gemma":[0.000031218045,0.00014488645,0.00062405335,0.000006315676,0.00005581498,0.00011861373,0.000015252579,0.99038893,0.0006943893,0.0073958603,0.00050401076,0.000020654854],"about_ca_topic_score_codex":0.0038320485,"about_ca_topic_score_gemma":0.004712989,"teacher_disagreement_score":0.0038320485,"about_ca_system_score_codex":0.0013139184,"about_ca_system_score_gemma":0.0010453156,"threshold_uncertainty_score":0.012447238},"labels":[],"label_agreement":null},{"id":"W2037567612","doi":"10.1186/1471-2105-10-s1-s60","title":"GAIA: a gram-based interaction analysis tool – an approach for identifying interacting domains in yeast","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Ontario Institute for Cancer Research","funders":"Michael Smith Health Research BC; Canadian Institutes of Health Research; Government of Ontario; Ontario Institute for Cancer Research","keywords":"Domain (mathematical analysis); Protein–protein interaction; Set (abstract data type); Computational biology; Computer science; Gram; Saccharomyces cerevisiae; Budding yeast; Identification (biology); Protein domain; Folding (DSP implementation); Data mining; Yeast; Biology; Genetics; Gene; Mathematics","score_opus":0.028505559512490307,"score_gpt":0.2980608545648929,"score_spread":0.2695552950524026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2037567612","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28270003,0.0015198715,0.6349266,0.00033082272,0.00009592884,0.00043644497,0.009110168,0.06767101,0.0032091364],"genre_scores_gemma":[0.3008997,0.0003152833,0.6893068,0.00013255383,0.000034260174,0.00024117771,0.007272473,0.0010445744,0.000753224],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995117,0.00010848426,0.000046778478,0.000111056994,0.0001662232,0.00005565974],"domain_scores_gemma":[0.99906343,0.00045471877,0.00019021587,0.00008009208,0.0001262537,0.0000852971],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060412294,0.0014604303,0.0006769145,0.004437547,0.0008365549,0.0009047234,0.0007651687,0.00065360963,0.0025892463],"category_scores_gemma":[0.0018251226,0.00026408245,0.0010972369,0.0019276214,0.00033039012,0.0007259491,0.0012966687,0.0007980711,0.0011404771],"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":[0.0024229516,0.00056795374,0.06235695,0.0015394196,0.0007349019,0.0031640779,0.0012008981,0.026152397,0.254376,0.006316136,0.028420871,0.61274755],"study_design_scores_gemma":[0.00016721609,0.0005505093,0.03612822,0.00013064835,0.00032733948,0.0040029273,0.0007699697,0.80642647,0.09604936,0.017933263,0.037297364,0.00021666875],"about_ca_topic_score_codex":0.0011436647,"about_ca_topic_score_gemma":0.0018230001,"teacher_disagreement_score":0.004437547,"about_ca_system_score_codex":0.00039066904,"about_ca_system_score_gemma":0.0006752522,"threshold_uncertainty_score":0.008661926},"labels":[],"label_agreement":null},{"id":"W2039740528","doi":"10.1186/1471-2105-10-193","title":"Filtering Genes for Cluster and Network Analysis","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; SickKids Foundation; Hospital for Sick Children; Ted Rogers Centre for Heart Research; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Genome Canada; Canadian Institutes of Health Research; Mitacs; Ontario Genomics; Ontario Genomics Institute","keywords":"Interpretability; Computer science; Similarity (geometry); Network analysis; Data mining; Set (abstract data type); Gene regulatory network; Cluster analysis; Filter (signal processing); Modular design; Cluster (spacecraft); Computational biology; Gene; Artificial intelligence; Biology; Genetics; Gene expression","score_opus":0.010698307085337215,"score_gpt":0.2370848833538894,"score_spread":0.22638657626855216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2039740528","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015299415,0.00012077,0.98192734,0.00017412935,0.000047246922,0.00014175192,0.0004801661,0.0013542533,0.00045496176],"genre_scores_gemma":[0.12811573,0.00013209473,0.8681512,0.000103840866,0.00006049341,0.0005077735,0.0015420907,0.00048456734,0.0009021886],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968997,0.0012485959,0.0001587911,0.0008238669,0.00071409065,0.00015497903],"domain_scores_gemma":[0.9871272,0.008009268,0.00085103087,0.0022366515,0.0015558527,0.00021999907],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0055372096,0.0010399399,0.0010273223,0.002632281,0.0010699369,0.001354759,0.0014700503,0.0012420826,0.0046639005],"category_scores_gemma":[0.028730607,0.0003913631,0.0018476336,0.0031424055,0.0009601937,0.0012998886,0.0010307059,0.0013673778,0.0012306776],"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":[0.0010253073,0.00029058033,0.02144255,0.0009652662,0.0009197456,0.00036005455,0.0007896808,0.17594208,0.037766807,0.07604253,0.018749034,0.66570646],"study_design_scores_gemma":[0.00009803556,0.00019755079,0.008839271,0.000078588295,0.00016918893,0.00026802774,0.00013561989,0.86158425,0.02856657,0.083734736,0.016240578,0.00008757832],"about_ca_topic_score_codex":0.004467258,"about_ca_topic_score_gemma":0.003884065,"teacher_disagreement_score":0.0055372096,"about_ca_system_score_codex":0.0015363364,"about_ca_system_score_gemma":0.0016585002,"threshold_uncertainty_score":0.02928394},"labels":[],"label_agreement":null},{"id":"W2041184037","doi":"10.1186/1471-2105-8-117","title":"Colony size measurement of the yeast gene deletion strains for functional genomics","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Fungal and yeast genetics research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":69,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; University of Waterloo; Carleton University; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Functional genomics; Yeast; Saccharomyces cerevisiae; DNA microarray; Biology; Computational biology; Genomics; Model organism; Genetics; Gene; Plasmid; Comparative genomics; Genome; Gene expression","score_opus":0.037444805723937255,"score_gpt":0.2591775465108114,"score_spread":0.2217327407868741,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2041184037","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24267946,0.0013839336,0.73912954,0.00027468379,0.0002954908,0.0010729289,0.0054225856,0.006475315,0.0032661345],"genre_scores_gemma":[0.18083817,0.00081066537,0.8052076,0.00012965451,0.000025007283,0.0017862102,0.007230103,0.0010303921,0.0029421542],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985934,0.00025440386,0.00017579373,0.00030748334,0.0005846664,0.00008429327],"domain_scores_gemma":[0.99753004,0.00087191124,0.0002866904,0.00046538774,0.000707694,0.00013833331],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016602016,0.0013877453,0.0009734065,0.0030652755,0.00041915994,0.00051440496,0.0015575687,0.0006811649,0.0040358785],"category_scores_gemma":[0.0023617337,0.00053215143,0.0009373123,0.0016238086,0.00043416506,0.0004431346,0.00073717383,0.0016575507,0.0029756804],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008246498,0.0000944951,0.001127426,0.00012748416,0.000017677216,0.000036628848,0.00005466913,0.00021087451,0.9841881,0.00018106734,0.0003835872,0.013495481],"study_design_scores_gemma":[0.00001665254,0.00017403274,0.0068650674,0.0000151263475,0.000034674154,0.00016919128,0.000026951002,0.006131654,0.98315954,0.00013998467,0.0032458203,0.00002137046],"about_ca_topic_score_codex":0.00093632564,"about_ca_topic_score_gemma":0.0015369386,"teacher_disagreement_score":0.0040358785,"about_ca_system_score_codex":0.0005809784,"about_ca_system_score_gemma":0.00036945843,"threshold_uncertainty_score":0.013501406},"labels":[],"label_agreement":null},{"id":"W2041435062","doi":"10.1186/1471-2105-15-52","title":"Comparison of genotype clustering tools with rare variants","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Montreal Heart Institute","funders":"Institut de Cardiologie de Montréal; Fondation Institut de Cardiologie de Montréal; Université de Montréal","keywords":"Concordance; Genotyping; Genotype; Minor allele frequency; Biology; Cluster analysis; Genetics; Gold standard (test); Allele; Allele frequency; Population; Computational biology; Computer science; Statistics; Medicine; Mathematics; Artificial intelligence; Gene","score_opus":0.03260006616483543,"score_gpt":0.2889988527256054,"score_spread":0.25639878656077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2041435062","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5626792,0.0055041783,0.3669331,0.0013819534,0.0009439209,0.0011523853,0.0094759455,0.042747036,0.009182375],"genre_scores_gemma":[0.5366759,0.0008759095,0.43679807,0.0004213017,0.00016363729,0.00081865716,0.018322065,0.0044176825,0.0015067853],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9698132,0.013907945,0.0027481418,0.0053258794,0.0072337626,0.0009710267],"domain_scores_gemma":[0.9080268,0.066868804,0.004491135,0.008481564,0.010708999,0.0014226328],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026182473,0.0022883194,0.0016992473,0.008921573,0.00141847,0.0041766614,0.0035256878,0.0024798515,0.0041606533],"category_scores_gemma":[0.08169583,0.0009685935,0.0029755204,0.004538947,0.0010633371,0.0021127497,0.004465816,0.0014880224,0.0023974914],"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":[0.014220887,0.0012300415,0.16101374,0.0038931854,0.012196712,0.00083978166,0.0022725519,0.15989748,0.015649473,0.008703136,0.039605517,0.5804776],"study_design_scores_gemma":[0.0016398655,0.0020616252,0.09691774,0.0006869663,0.002256366,0.0021658984,0.001064299,0.81735104,0.032172464,0.023516545,0.01929948,0.0008677548],"about_ca_topic_score_codex":0.005211513,"about_ca_topic_score_gemma":0.0051635336,"teacher_disagreement_score":0.026182473,"about_ca_system_score_codex":0.001738454,"about_ca_system_score_gemma":0.002396219,"threshold_uncertainty_score":0.13846779},"labels":[],"label_agreement":null},{"id":"W2042301222","doi":"10.1186/1471-2105-11-562","title":"An improved method for scoring protein-protein interactions using semantic similarity within the gene ontology","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":192,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Semantic similarity; Gene ontology; Computer science; Similarity (geometry); Graph; Protein function prediction; Cluster analysis; Ontology; Gene Annotation; Representation (politics); Computational biology; Data mining; Protein function; Information retrieval; Artificial intelligence; Gene; Theoretical computer science; Biology; Genetics; Genome; Gene expression","score_opus":0.024240405385633584,"score_gpt":0.3072557650958416,"score_spread":0.283015359710208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2042301222","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0727702,0.0005920045,0.9132202,0.00021314317,0.00011212955,0.00036740716,0.0018400148,0.008821721,0.0020631198],"genre_scores_gemma":[0.22667581,0.00021366062,0.76516247,0.00010097427,0.00006528784,0.0003310481,0.0049712085,0.00034011638,0.0021394885],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99790937,0.00020710728,0.00016295213,0.00041949467,0.0011650436,0.00013588321],"domain_scores_gemma":[0.9975426,0.0006968582,0.00024819322,0.00027692472,0.0011578186,0.00007767727],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013191478,0.0011823165,0.0011111478,0.007883264,0.00068810716,0.0010465572,0.0016288962,0.0012408138,0.0025409153],"category_scores_gemma":[0.004571275,0.00031291638,0.0015999447,0.0048615867,0.0006464247,0.0016545398,0.0009806345,0.0010174492,0.001430675],"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":[0.00065806374,0.00048026477,0.016584959,0.0006095848,0.0005747594,0.00034889794,0.00025050782,0.042144347,0.074399054,0.008208628,0.014670719,0.8410703],"study_design_scores_gemma":[0.00013352087,0.0002617879,0.0134119475,0.000035400466,0.00018895838,0.00088088907,0.00018494521,0.9148925,0.043881103,0.011302876,0.014738299,0.000087693144],"about_ca_topic_score_codex":0.008066691,"about_ca_topic_score_gemma":0.0109032225,"teacher_disagreement_score":0.008066691,"about_ca_system_score_codex":0.0012419418,"about_ca_system_score_gemma":0.001867071,"threshold_uncertainty_score":0.01603949},"labels":[],"label_agreement":null},{"id":"W2044267926","doi":"10.1186/1471-2105-8-136","title":"An adaptive bin framework search method for a beta-sheet protein homopolymer model","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Bin; Computer science; Context (archaeology); Set (abstract data type); Search algorithm; Exponential growth; Function (biology); Monte Carlo method; Algorithm; Mathematical optimization; Theoretical computer science; Mathematics","score_opus":0.02344821303907908,"score_gpt":0.32136390687974065,"score_spread":0.2979156938406616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2044267926","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.050955117,0.0007594489,0.94365054,0.00014622987,0.00004625622,0.000086812266,0.0001283116,0.0006436042,0.0035836252],"genre_scores_gemma":[0.53880906,0.00038187695,0.45602542,0.00020738722,0.000047888396,0.00033970704,0.00045246587,0.0003046671,0.0034316329],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999796,0.000070173955,0.000008093994,0.00002349789,0.00007158647,0.00003061962],"domain_scores_gemma":[0.99968123,0.00014014705,0.000029288356,0.000022585973,0.00008021303,0.000046520356],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007880845,0.0005050311,0.0010717476,0.0007411322,0.00046313414,0.0005740244,0.0015525218,0.0010215124,0.0032395197],"category_scores_gemma":[0.0010917739,0.00031049474,0.00048282513,0.0008110845,0.000423454,0.00069929915,0.00081319455,0.00074759615,0.00043129077],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000102693106,0.000049116552,0.00046975384,0.000055375745,0.00003572198,0.0000404169,0.000027318974,0.94396794,0.0011306864,0.008628004,0.00090616324,0.044586737],"study_design_scores_gemma":[0.0000038132557,0.000006474212,0.000022627562,0.0000017419106,0.0000016766927,0.0000039713873,0.000001883099,0.99916184,0.00007368234,0.0005977666,0.00012294446,0.0000015688765],"about_ca_topic_score_codex":0.009993264,"about_ca_topic_score_gemma":0.011495631,"teacher_disagreement_score":0.009993264,"about_ca_system_score_codex":0.0008176959,"about_ca_system_score_gemma":0.0013895716,"threshold_uncertainty_score":0.019870162},"labels":[],"label_agreement":null},{"id":"W2044833006","doi":"10.1186/1471-2105-12-s3-s1","title":"Building a biomedical tokenizer using the token lattice design pattern and the adapted Viterbi algorithm","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Lexical analysis; Computer science; Security token; Viterbi algorithm; Artificial intelligence; Domain (mathematical analysis); Classifier (UML); Natural language processing; Hidden Markov model","score_opus":0.060771486185793054,"score_gpt":0.2754870983270212,"score_spread":0.2147156121412281,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2044833006","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00686898,0.00007498647,0.9856205,0.00017852247,0.00007670069,0.00015342208,0.00018474003,0.0059080594,0.00093417807],"genre_scores_gemma":[0.0477733,0.000057906156,0.9484025,0.00014890626,0.000028059594,0.0002295472,0.0006339634,0.000627663,0.0020982162],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9972269,0.00079477753,0.00039708894,0.00075274333,0.00064591673,0.00018262354],"domain_scores_gemma":[0.99596304,0.0017759674,0.0003604054,0.00063787017,0.0011071416,0.00015557735],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003681378,0.0008568852,0.0010245513,0.0016570196,0.0009850726,0.0016866559,0.0025501312,0.0015303682,0.0069899303],"category_scores_gemma":[0.008888351,0.00074382656,0.00089253864,0.0017507826,0.0015229877,0.002720439,0.0017924603,0.0019719547,0.006255101],"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":[0.0012598726,0.00025608827,0.0041310987,0.00073083886,0.00012852561,0.00050842226,0.00064228073,0.065716594,0.05401304,0.049267992,0.018462995,0.8048822],"study_design_scores_gemma":[0.00021244201,0.00028620014,0.00046762364,0.000067395726,0.00008615672,0.0005892296,0.00015106043,0.80758506,0.122158475,0.037456412,0.030855313,0.00008475347],"about_ca_topic_score_codex":0.0029874314,"about_ca_topic_score_gemma":0.004175759,"teacher_disagreement_score":0.0069899303,"about_ca_system_score_codex":0.0013148217,"about_ca_system_score_gemma":0.004042481,"threshold_uncertainty_score":0.023383617},"labels":[],"label_agreement":null},{"id":"W2047165041","doi":"10.1186/1471-2105-9-55","title":"Designing multiple degenerate primers via consecutive pairwise alignments","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"University of Tehran","keywords":"Degenerate energy levels; Primer (cosmetics); Computation; Pairwise comparison; Computer science; Algorithm; Cover (algebra); Reduction (mathematics); Computational biology; Theoretical computer science; Biology; Mathematics; Engineering; Physics; Artificial intelligence","score_opus":0.026146798081331638,"score_gpt":0.2254022577459897,"score_spread":0.19925545966465807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047165041","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012164366,0.00048352373,0.9852505,0.00009058486,0.00003863082,0.00013997489,0.00013334885,0.00094603014,0.0007530148],"genre_scores_gemma":[0.026987208,0.000310341,0.97147477,0.00006609143,0.000016056021,0.00017095043,0.0004664163,0.0001406488,0.00036752826],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966097,0.0009226489,0.0003314054,0.0014350404,0.0005065967,0.00019468743],"domain_scores_gemma":[0.996944,0.001658388,0.00048021265,0.00043325257,0.0003695331,0.00011455083],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026634699,0.0018529458,0.0015318583,0.0014483125,0.00092343526,0.0010854143,0.0021663958,0.0014472874,0.003653988],"category_scores_gemma":[0.005505289,0.0013468497,0.0017383281,0.0014077654,0.0010077793,0.0013159435,0.0011929714,0.0024723632,0.0031863947],"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":[0.00057641097,0.0002743621,0.0020624783,0.0032634374,0.00020866995,0.0005982952,0.00054137205,0.020911813,0.6566863,0.018341484,0.0032802792,0.2932551],"study_design_scores_gemma":[0.00013117705,0.0006332546,0.0012856633,0.0002146347,0.00018143184,0.00266136,0.00016071794,0.12051968,0.81066954,0.024954403,0.03847907,0.00010910225],"about_ca_topic_score_codex":0.00018215511,"about_ca_topic_score_gemma":0.0002837897,"teacher_disagreement_score":0.003653988,"about_ca_system_score_codex":0.0005511832,"about_ca_system_score_gemma":0.00086616876,"threshold_uncertainty_score":0.014085889},"labels":[],"label_agreement":null},{"id":"W2047300262","doi":"10.1186/1471-2105-14-141","title":"An automated graphics tool for comparative genomics: the Coulson plot generator","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Alberta; Wellcome Trust","keywords":"Plot (graphics); Context (archaeology); Computer science; Comparative genomics; Genomics; Graphics; Representation (politics); File format; Software; Data mining; Computational biology; Genome; Biology; Genetics; Gene; Programming language; Computer graphics (images)","score_opus":0.026758218816336235,"score_gpt":0.2806950135405673,"score_spread":0.2539367947242311,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047300262","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020368365,0.0002933538,0.5795655,0.00033063986,0.00043478786,0.00044014677,0.031191621,0.37963143,0.006075743],"genre_scores_gemma":[0.013890393,0.00042514957,0.8577262,0.0004242779,0.00012102036,0.0026834453,0.031537704,0.08518038,0.008011441],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99838424,0.0004373369,0.00020941992,0.00032867887,0.00051512354,0.0001251477],"domain_scores_gemma":[0.9931632,0.004402029,0.00035751704,0.0005807121,0.0012035331,0.0002930823],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0045930985,0.0027289845,0.0014777594,0.0045088166,0.00068371015,0.0022502153,0.003983424,0.0012519319,0.17922507],"category_scores_gemma":[0.012542214,0.0012982287,0.0016587741,0.003832937,0.0005740791,0.0022360203,0.0021247428,0.0024951133,0.04050844],"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":[0.0011528372,0.00017723737,0.0027121056,0.0021405327,0.00022846102,0.00068441243,0.0005505614,0.00339397,0.017362569,0.012361828,0.6427242,0.31651124],"study_design_scores_gemma":[0.0012291194,0.00031877556,0.0067724497,0.0009276509,0.00021389304,0.0016337596,0.00031549906,0.108357206,0.068467416,0.027523598,0.783804,0.00043662838],"about_ca_topic_score_codex":0.0028358623,"about_ca_topic_score_gemma":0.0024015757,"teacher_disagreement_score":0.17922507,"about_ca_system_score_codex":0.0011184738,"about_ca_system_score_gemma":0.0018010658,"threshold_uncertainty_score":0.5995676},"labels":[],"label_agreement":null},{"id":"W2049268173","doi":"10.1186/1471-2105-8-444","title":"Insertions and the emergence of novel protein structure: a structure-based phylogenetic study of insertions","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":74,"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; Genome Atlantic","keywords":"Phylogenetic tree; Biology; Protein domain; Domain (mathematical analysis); Computational biology; Inference; Similarity (geometry); Variable (mathematics); Protein structure; Genetics; Evolutionary biology; Phylogenetics; Structural similarity; Insert (composites); Sequence alignment; Structural alignment; Computer science; Artificial intelligence; Gene; Peptide sequence; Mathematics","score_opus":0.010725812650330126,"score_gpt":0.24453967665412163,"score_spread":0.2338138640037915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2049268173","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94330406,0.0007547241,0.05485872,0.00012218615,0.0000061805317,0.00003784948,0.00021138003,0.00006735062,0.0006375021],"genre_scores_gemma":[0.9463252,0.00040378203,0.05236628,0.000033627504,0.0000103333105,0.000030101533,0.00066624326,0.000029170065,0.00013512782],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996069,0.0001319394,0.000031028892,0.00010951699,0.00007999195,0.000040691833],"domain_scores_gemma":[0.99883705,0.0005447318,0.0002853043,0.00010235695,0.0001318628,0.000098762095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011352396,0.00025596397,0.00034964853,0.0023349184,0.0006791652,0.00057116215,0.00047658331,0.00062213326,0.00051814516],"category_scores_gemma":[0.0028595726,0.00023870847,0.00058259343,0.0020675608,0.0006532018,0.0007564844,0.0006475319,0.0005798949,0.00016432595],"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":[0.0009307542,0.00043339957,0.46747184,0.0006490472,0.0004267198,0.0019396067,0.0029758466,0.16113079,0.19844793,0.017811025,0.000667901,0.14711511],"study_design_scores_gemma":[0.000040729068,0.0005297359,0.22778653,0.00013702438,0.00025294308,0.002544316,0.000870693,0.73059195,0.017882328,0.014387795,0.00488453,0.00009129585],"about_ca_topic_score_codex":0.0010871622,"about_ca_topic_score_gemma":0.00096159626,"teacher_disagreement_score":0.0023349184,"about_ca_system_score_codex":0.0005755731,"about_ca_system_score_gemma":0.0003801249,"threshold_uncertainty_score":0.006003797},"labels":[],"label_agreement":null},{"id":"W2050263604","doi":"10.1186/1471-2105-12-435","title":"PESCADOR, a web-based tool to assist text-mining of biointeractions extracted from PubMed queries","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":54,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Bundesministerium für Bildung und Forschung; Ottawa Hospital Research Institute","keywords":"Computer science; Relevance (law); Function (biology); Set (abstract data type); Resource (disambiguation); Mechanism (biology); Biological network; Web resource; Focus (optics); Information retrieval; Interaction network; Computational biology; World Wide Web; Bioinformatics; Biology; Gene","score_opus":0.03956506832173659,"score_gpt":0.25544508606942734,"score_spread":0.21588001774769075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2050263604","genre_codex":"dataset","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031851668,0.006715608,0.13701417,0.0016282506,0.00026317578,0.0025279915,0.59683174,0.20804729,0.015120069],"genre_scores_gemma":[0.06151467,0.0054515977,0.48027468,0.00071631,0.00015332086,0.003014268,0.43694007,0.006485788,0.005449313],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988814,0.00017748424,0.00034153316,0.00026380815,0.0002866865,0.000049111142],"domain_scores_gemma":[0.9927685,0.004818943,0.0010264898,0.00040826973,0.00071941415,0.0002583142],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027601584,0.0025831058,0.001502091,0.025494453,0.000977749,0.0024585861,0.0015103718,0.0009965108,0.026666094],"category_scores_gemma":[0.0138520235,0.0006853131,0.0014986115,0.014271244,0.0004886928,0.0037454332,0.002474182,0.0009290737,0.0075427564],"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":[0.0023106877,0.00038351293,0.013337559,0.044333026,0.001619598,0.005275517,0.003482505,0.004629803,0.043283127,0.014948886,0.34832916,0.5180666],"study_design_scores_gemma":[0.0010646009,0.0004841911,0.029880453,0.003468064,0.0013179942,0.00620949,0.0017125317,0.03884552,0.030408662,0.020427028,0.86575234,0.0004291598],"about_ca_topic_score_codex":0.0039185015,"about_ca_topic_score_gemma":0.008864876,"teacher_disagreement_score":0.026666094,"about_ca_system_score_codex":0.0012181399,"about_ca_system_score_gemma":0.0031009582,"threshold_uncertainty_score":0.08920699},"labels":[],"label_agreement":null},{"id":"W2050345155","doi":"10.1186/1471-2105-12-35","title":"VennDiagram: a package for the generation of highly-customizable Venn and Euler diagrams in R","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Data Analysis with R","field":"Computer Science","cited_by":3262,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"Canadian Institutes of Health Research; Government of Ontario; Ontario Institute for Cancer Research","keywords":"Venn diagram; Computer science; Visualization; Process (computing); Data mining; Engineering drawing; Theoretical computer science; Programming language; Mathematics","score_opus":0.07426646512308042,"score_gpt":0.24697291885229222,"score_spread":0.17270645372921178,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2050345155","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015585216,0.000521216,0.7922303,0.0002676489,0.00042794974,0.00037129078,0.023515107,0.1787196,0.0023883772],"genre_scores_gemma":[0.014251592,0.0004649534,0.87495834,0.00029597984,0.00013502028,0.0025495794,0.023163239,0.08185899,0.0023223816],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9939023,0.0026760707,0.0007728085,0.0012575566,0.0011424022,0.00024880693],"domain_scores_gemma":[0.9752855,0.017759072,0.0015238143,0.0028661333,0.002068957,0.00049657864],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01122103,0.0034640837,0.0029045055,0.006970113,0.0014343534,0.0034162025,0.0052431673,0.001344343,0.084762625],"category_scores_gemma":[0.045805775,0.0023636501,0.0033404247,0.0041221944,0.0012124503,0.0038409543,0.004033357,0.0050636176,0.026951231],"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":[0.0011381763,0.00015344638,0.004947765,0.008324218,0.0015757371,0.0010544279,0.0016706439,0.019694697,0.017468773,0.03621138,0.6473024,0.2604584],"study_design_scores_gemma":[0.0007537932,0.00023370405,0.005904801,0.0013664853,0.0006237754,0.0018425318,0.0002794941,0.1076371,0.03900562,0.11861886,0.72280943,0.0009244471],"about_ca_topic_score_codex":0.001802806,"about_ca_topic_score_gemma":0.0023760984,"teacher_disagreement_score":0.084762625,"about_ca_system_score_codex":0.0008609319,"about_ca_system_score_gemma":0.0030947968,"threshold_uncertainty_score":0.28355926},"labels":[],"label_agreement":null},{"id":"W2050870676","doi":"10.1186/1471-2105-10-410","title":"Refining gene signatures: a Bayesian approach","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","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":"Health Canada; Douglas Mental Health University Institute; Natural Sciences and Engineering Research Council of Canada","funders":"Canadian Institutes of Health Research","keywords":"Computer science; Bayesian probability; Context (archaeology); Data mining; Machine learning; DNA microarray; Artificial intelligence; Curse of dimensionality; Identification (biology); Microarray analysis techniques; Feature selection; Bayes' theorem; Pattern recognition (psychology); Gene; Biology; Genetics; Gene expression","score_opus":0.016360147667429287,"score_gpt":0.250817003064846,"score_spread":0.2344568553974167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2050870676","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0080145635,0.0001582925,0.9908235,0.00025488285,0.000009365189,0.00003226902,0.000068224595,0.000207292,0.00043156953],"genre_scores_gemma":[0.27677667,0.00043369568,0.71925914,0.0005206098,0.00013878685,0.0003581289,0.0005906161,0.00018659432,0.001735788],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975055,0.0010070807,0.00011074533,0.00047555377,0.0007657159,0.00013551433],"domain_scores_gemma":[0.9911874,0.0064057563,0.0005781467,0.00066892215,0.0009923103,0.00016754233],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005284556,0.00075335824,0.0016697611,0.0025429076,0.0006973472,0.001020303,0.002455198,0.0014730422,0.0014745144],"category_scores_gemma":[0.015514204,0.0008237954,0.001481927,0.001902293,0.0014618204,0.0014014803,0.0013385377,0.0018609388,0.0006251643],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040533798,0.0001823627,0.007367944,0.00025159598,0.00024313797,0.00017871255,0.0002912038,0.596279,0.011106152,0.052148517,0.0037188847,0.32782713],"study_design_scores_gemma":[0.00003827733,0.00004156673,0.0008405175,0.000029268338,0.000047657082,0.00007610178,0.000016308268,0.93846184,0.0019428314,0.056826763,0.0016510783,0.000027743547],"about_ca_topic_score_codex":0.003980222,"about_ca_topic_score_gemma":0.005761415,"teacher_disagreement_score":0.005284556,"about_ca_system_score_codex":0.0014957415,"about_ca_system_score_gemma":0.0018760802,"threshold_uncertainty_score":0.027947783},"labels":[],"label_agreement":null},{"id":"W2051873396","doi":"10.1186/1471-2105-8-227","title":"Relationship between insertion/deletion (indel) frequency of proteins and essentiality","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Canada's Michael Smith Genome Sciences Centre; Simon Fraser University; Michael Smith Health Research BC","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Genome British Columbia; Michael Smith Health Research BC; Genome Canada","keywords":"Indel; Biology; In silico; Proteome; Computational biology; Genetics; INDEL Mutation; DNA microarray; Saccharomyces cerevisiae; Gene; Genotype; Single-nucleotide polymorphism","score_opus":0.02498220279781606,"score_gpt":0.2616971265343822,"score_spread":0.23671492373656614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2051873396","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99032974,0.0007947355,0.007628555,0.00004411895,0.00000868366,0.000016005974,0.0004848618,0.00007418704,0.00061899057],"genre_scores_gemma":[0.9969451,0.00013456387,0.0023346276,0.000015080209,0.000005174067,0.000013630487,0.00041494987,0.000011397934,0.00012533048],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989504,0.00017199645,0.00014516935,0.00033330874,0.0003018534,0.00009729307],"domain_scores_gemma":[0.98422766,0.01016715,0.0036526227,0.0005876965,0.0008415983,0.00052329584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011360256,0.0002321747,0.00030659512,0.0014558419,0.00021569118,0.0005310114,0.00029806612,0.0004475163,0.001618653],"category_scores_gemma":[0.0048756353,0.00016192935,0.000254977,0.000828261,0.00046140238,0.00040796594,0.00038168195,0.0007366469,0.00028820967],"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":[0.0012197678,0.00019336164,0.6793514,0.00032797328,0.0006172261,0.0006862082,0.00017746739,0.0028732477,0.30095676,0.00036786954,0.00015873127,0.013070011],"study_design_scores_gemma":[0.00001588126,0.00074311695,0.8781167,0.000017829609,0.0002643592,0.0046346146,0.00022779715,0.010505431,0.10273851,0.0010557557,0.0016387738,0.000041248677],"about_ca_topic_score_codex":0.00023645461,"about_ca_topic_score_gemma":0.0002414012,"teacher_disagreement_score":0.001618653,"about_ca_system_score_codex":0.00021654984,"about_ca_system_score_gemma":0.00012731031,"threshold_uncertainty_score":0.00600791},"labels":[],"label_agreement":null},{"id":"W2052057394","doi":"10.1186/1471-2105-10-313","title":"Social tagging in the life sciences: characterizing a new metadata resource for bioinformatics","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; St. Paul's Hospital","funders":"Natural Sciences and Engineering Research Council of Canada; University of British Columbia","keywords":"Metadata; Computer science; World Wide Web; Information retrieval; Search engine indexing; Resource (disambiguation); Metadata repository; Annotation; Data science; Artificial intelligence","score_opus":0.07446472868360497,"score_gpt":0.32471233606516253,"score_spread":0.25024760738155755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052057394","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70475197,0.009307322,0.22360761,0.013401619,0.00041727594,0.0010080183,0.009739191,0.0014435044,0.036323458],"genre_scores_gemma":[0.84188306,0.0023995892,0.14588368,0.00080593856,0.00040470195,0.0006526232,0.00572562,0.00021493642,0.002029745],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98948765,0.0048763934,0.0013958694,0.0012225463,0.0025637795,0.00045380456],"domain_scores_gemma":[0.88303125,0.06537225,0.01872083,0.015511312,0.013251343,0.0041129473],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.017855853,0.00041081195,0.00069851923,0.015227906,0.0033695623,0.007909286,0.0013534158,0.0013971466,0.0018513262],"category_scores_gemma":[0.058259685,0.00030276782,0.000994349,0.02155015,0.0034699256,0.008719558,0.0051990543,0.0010335727,0.0009160915],"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":[0.0007758534,0.00034874637,0.4274249,0.003520155,0.0004625332,0.0007162201,0.02445316,0.0039918837,0.02158765,0.09505815,0.0128805395,0.40878022],"study_design_scores_gemma":[0.00011171478,0.0007960201,0.3668656,0.0025844176,0.00078529347,0.0034752022,0.03283023,0.042651188,0.03631346,0.25476158,0.25818235,0.0006430397],"about_ca_topic_score_codex":0.0040071346,"about_ca_topic_score_gemma":0.0075864797,"teacher_disagreement_score":0.9920907,"about_ca_system_score_codex":0.0036621387,"about_ca_system_score_gemma":0.004967451,"threshold_uncertainty_score":0.09443188},"labels":[],"label_agreement":null},{"id":"W2052656210","doi":"10.1186/1471-2105-14-s15-s19","title":"The dynamics of functional classes of plant genes in rediploidized ancient polyploids","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Chromosomal and Genetic Variations","field":"Agricultural and Biological Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Genome; Biology; Gene; Genetics; Gene family; Computational biology; Evolutionary dynamics; Evolutionary biology","score_opus":0.019255785105250056,"score_gpt":0.19619476762754154,"score_spread":0.17693898252229148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052656210","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9978382,0.00021347731,0.0009454276,0.000012504722,0.000001047402,0.0000023401865,0.00066963857,0.000027577096,0.00028972173],"genre_scores_gemma":[0.9966583,0.00009494364,0.0011750667,0.000018177914,0.000002063208,0.000009591685,0.0014007482,0.000018502302,0.00062259444],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99984217,0.000009521393,0.000011161401,0.000085013766,0.00003556713,0.00001658038],"domain_scores_gemma":[0.9993393,0.00018302174,0.0002296301,0.0000660548,0.00009976442,0.00008222715],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002054272,0.00010940671,0.00019130157,0.0010566969,0.00017827624,0.0003397438,0.00025156475,0.00023627859,0.0015661473],"category_scores_gemma":[0.000965491,0.00007720373,0.00017667605,0.0007022648,0.00022609028,0.00034730026,0.00029027762,0.0002580854,0.0003541918],"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":[0.0006445572,0.00003322796,0.23622178,0.00018179722,0.00008833099,0.00015785614,0.0006254968,0.0012442687,0.73825145,0.000579172,0.00013544002,0.021836627],"study_design_scores_gemma":[0.0000062036383,0.00009971182,0.94053274,0.0000071510153,0.000053504238,0.0007691965,0.00028603748,0.0037804658,0.05267528,0.00032650033,0.0014479918,0.00001514777],"about_ca_topic_score_codex":0.0013155093,"about_ca_topic_score_gemma":0.0013731499,"teacher_disagreement_score":0.0015661473,"about_ca_system_score_codex":0.00040718596,"about_ca_system_score_gemma":0.00010401001,"threshold_uncertainty_score":0.0052392483},"labels":[],"label_agreement":null},{"id":"W2053264599","doi":"10.1186/1471-2105-14-212","title":"Linear combination test for gene set analysis of a continuous phenotype","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Health Services; University of Calgary; University of Alberta","funders":"Canadian Institutes of Health Research; Department of Science and Technology, Ministry of Science and Technology, India; Department of Biotechnology, Ministry of Science and Technology, India","keywords":"Phenotype; Context (archaeology); Computational biology; Estimator; Computer science; Set (abstract data type); DNA microarray; Continuous variable; Gene expression profiling; Gene; Biology; Data mining; Genetics; Statistics; Gene expression; Mathematics","score_opus":0.01927340765702812,"score_gpt":0.26895499551251323,"score_spread":0.2496815878554851,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2053264599","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19324964,0.00079874205,0.7950858,0.0011079471,0.00041397207,0.0006730442,0.0026609516,0.0032660232,0.0027438474],"genre_scores_gemma":[0.7588715,0.00011038133,0.23581634,0.00039232828,0.00024426286,0.0011457588,0.0024225498,0.00020908538,0.0007877535],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9804488,0.012501876,0.0007920006,0.0031604436,0.0027435543,0.0003533338],"domain_scores_gemma":[0.89712703,0.09003267,0.0042371294,0.0043161237,0.0031774153,0.0011096785],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015962163,0.0010285582,0.0015895307,0.0031218922,0.0009927971,0.0013996157,0.0022089784,0.0013094903,0.006115238],"category_scores_gemma":[0.059660934,0.00034414232,0.0029410908,0.0028915985,0.00166242,0.001222879,0.001413834,0.0029419328,0.00096560456],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009610295,0.0012727985,0.25978768,0.0014252356,0.008562341,0.0017175745,0.00038706377,0.16474198,0.015596928,0.014396039,0.013721812,0.50878024],"study_design_scores_gemma":[0.0005184012,0.0030490716,0.049260493,0.00006534941,0.00086549716,0.001011959,0.00016995848,0.91002613,0.008102739,0.022984652,0.0037941386,0.00015161178],"about_ca_topic_score_codex":0.0010018436,"about_ca_topic_score_gemma":0.0011112579,"teacher_disagreement_score":0.015962163,"about_ca_system_score_codex":0.0011387803,"about_ca_system_score_gemma":0.0015179537,"threshold_uncertainty_score":0.084417045},"labels":[],"label_agreement":null},{"id":"W2054353156","doi":"10.1186/1471-2105-11-s12-s7","title":"SADI, SHARE, and the in silico scientific method","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Paul's Hospital","funders":"Natural Sciences and Engineering Research Council of Canada; Heart and Stroke Foundation of Canada; Genome Prairie; Canadian Institutes of Health Research; Genome Canada; Canarie; Microsoft Research","keywords":"Computer science; Workflow; Semantic Web; Social Semantic Web; Web service; World Wide Web; Set (abstract data type); Class (philosophy); Service (business); Data science; Semantic search; Artificial intelligence; Database","score_opus":0.10072184250704203,"score_gpt":0.387181686914727,"score_spread":0.28645984440768496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054353156","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014728694,0.0019010388,0.94440335,0.01690661,0.00026513636,0.00017011826,0.00035077456,0.0025404405,0.018733893],"genre_scores_gemma":[0.16069442,0.0018011986,0.8273095,0.0015689036,0.00017440935,0.0003309594,0.00068480964,0.00055740244,0.006878437],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98699933,0.005686004,0.0009945587,0.0013481033,0.0044699297,0.0005021361],"domain_scores_gemma":[0.9739473,0.014234887,0.0010428742,0.007134614,0.0027607013,0.0008796878],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024875363,0.0006473939,0.0010114233,0.0029005406,0.0019156329,0.007174409,0.0029171726,0.0023617,0.0042212848],"category_scores_gemma":[0.028247278,0.0007423964,0.0016478294,0.003319172,0.008755146,0.0095171975,0.007996202,0.003482481,0.0013367045],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018698341,0.00009711226,0.0028583591,0.00047622822,0.00009688922,0.00019494144,0.0020467532,0.005642825,0.0022093237,0.85618365,0.006514119,0.12349293],"study_design_scores_gemma":[0.000094058785,0.00008123978,0.0009794367,0.00019451608,0.000111294576,0.00058413314,0.00077880704,0.04664611,0.011419776,0.7824133,0.15661353,0.00008377481],"about_ca_topic_score_codex":0.003888235,"about_ca_topic_score_gemma":0.0039122826,"teacher_disagreement_score":0.024875363,"about_ca_system_score_codex":0.0037452444,"about_ca_system_score_gemma":0.008029845,"threshold_uncertainty_score":0.13155502},"labels":[],"label_agreement":null},{"id":"W2054958397","doi":"10.1186/1471-2105-9-25","title":"Using Generalized Procrustes Analysis (GPA) for normalization of cDNA microarray data","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Genomics; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; University of Ottawa","keywords":"Normalization (sociology); Quantile; Computer science; Data mining; Housekeeping gene; Statistics; Mathematics; Biology; Genetics; Gene expression","score_opus":0.14358390016491582,"score_gpt":0.3388302792023284,"score_spread":0.19524637903741257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054958397","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0075858007,0.00030694378,0.98623997,0.00016295398,0.0001341332,0.00019852039,0.00040456234,0.0044111665,0.00055603456],"genre_scores_gemma":[0.055398684,0.0004479505,0.93792,0.00016301642,0.000108707456,0.0014127289,0.0013517339,0.0023345188,0.0008626977],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9818918,0.007137748,0.001055952,0.0051883548,0.004322695,0.0004035634],"domain_scores_gemma":[0.9815014,0.009592664,0.0026547597,0.002724886,0.0033140206,0.00021224924],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01728167,0.0044945786,0.0022196285,0.003940369,0.0017655309,0.0031854862,0.0024524105,0.0017532494,0.0058700806],"category_scores_gemma":[0.039108276,0.0014221972,0.0050541423,0.006037152,0.002706736,0.0023725936,0.0026338813,0.005383927,0.0036611177],"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":[0.00080214185,0.0003185294,0.019690152,0.0025907918,0.0030543008,0.00059418223,0.0017706064,0.13776138,0.08729911,0.02512954,0.019907203,0.70108205],"study_design_scores_gemma":[0.00019659856,0.0010021216,0.029474063,0.0002819286,0.00076279684,0.0012888449,0.00043893664,0.7814263,0.07189419,0.057148147,0.055444177,0.00064182654],"about_ca_topic_score_codex":0.0022297364,"about_ca_topic_score_gemma":0.002983206,"teacher_disagreement_score":0.01728167,"about_ca_system_score_codex":0.0013400804,"about_ca_system_score_gemma":0.0035584252,"threshold_uncertainty_score":0.09139526},"labels":[],"label_agreement":null},{"id":"W2055029531","doi":"10.1186/1471-2105-13-s10-s17","title":"Gene network modular-based classification of microarray samples","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; Mount Sinai Hospital; York University","funders":"Canadian Institutes of Health Research","keywords":"Linear discriminant analysis; Modular design; DNA microarray; Discriminant; Computer science; Pattern recognition (psychology); Artificial intelligence; Computational biology; Data mining; Microarray analysis techniques; Biology; Gene; Genetics; Gene expression","score_opus":0.03825888650910341,"score_gpt":0.2668124748441448,"score_spread":0.22855358833504136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055029531","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6687032,0.00033933693,0.3270581,0.00022754924,0.00004865507,0.00018671615,0.0010659783,0.0010868023,0.0012836747],"genre_scores_gemma":[0.92102903,0.00009621273,0.07695675,0.000030207077,0.000031893684,0.00012803474,0.0012487866,0.000036635505,0.00044254668],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99946886,0.00016233874,0.000027667771,0.00014176893,0.00012868801,0.00007070558],"domain_scores_gemma":[0.99810094,0.00091873965,0.00030892203,0.00016968521,0.00042480024,0.00007700187],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012840519,0.00052530563,0.0005066659,0.0020574175,0.00021947993,0.000472653,0.00043178193,0.00033442394,0.0011463511],"category_scores_gemma":[0.003985125,0.000112819005,0.0005270917,0.0012008883,0.00039011336,0.00043831964,0.00044104937,0.00034955403,0.0002732651],"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":[0.0023198556,0.00045585228,0.11955388,0.00055530964,0.0003926916,0.00037166176,0.00030956577,0.22106855,0.15308726,0.0050684437,0.0033385933,0.4934783],"study_design_scores_gemma":[0.000028798817,0.0001492328,0.042578213,0.000013207839,0.000067659064,0.0001104357,0.000041688152,0.93499357,0.017290771,0.003997642,0.00070780056,0.000021028114],"about_ca_topic_score_codex":0.0011040769,"about_ca_topic_score_gemma":0.0011792093,"teacher_disagreement_score":0.0020574175,"about_ca_system_score_codex":0.00079787447,"about_ca_system_score_gemma":0.0004073855,"threshold_uncertainty_score":0.006790757},"labels":[],"label_agreement":null},{"id":"W2055553856","doi":"10.1186/1471-2105-8-190","title":"Can Clustal-style progressive pairwise alignment of multiple sequences be used in RNA secondary structure prediction?","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Multiple sequence alignment; Pairwise comparison; Protein secondary structure; Alignment-free sequence analysis; Structural alignment; Sequence alignment; Nucleic acid secondary structure; Nucleic acid structure; Sequence (biology); RNA; Computational biology; Conserved sequence; Computer science; Biology; Set (abstract data type); Consensus sequence; Phylogenetic tree; Bioinformatics; Genetics; Artificial intelligence; Peptide sequence; Gene; Biochemistry","score_opus":0.012431726598055248,"score_gpt":0.23945063842861142,"score_spread":0.22701891183055617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055553856","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05751927,0.0031989543,0.9242439,0.0015464876,0.00025056693,0.00017958073,0.0013645121,0.010465037,0.0012315743],"genre_scores_gemma":[0.20078282,0.001981736,0.7920892,0.0003698541,0.00011835727,0.0003865814,0.002522477,0.0012848963,0.0004641061],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99482024,0.0033896957,0.0002835771,0.00071394595,0.000643821,0.00014875384],"domain_scores_gemma":[0.9922001,0.0050407485,0.0008529467,0.00075886963,0.0009127546,0.0002346944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011282504,0.0015562375,0.0015861274,0.0031409767,0.00075017667,0.0011596346,0.0023336643,0.0019661253,0.00231545],"category_scores_gemma":[0.040596213,0.0009296874,0.0013667452,0.0069193654,0.0008825416,0.0024513437,0.0010084746,0.0016707781,0.0031951459],"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":[0.002708282,0.00051851274,0.02852898,0.0042196517,0.0023274636,0.00087815983,0.00086476293,0.09062172,0.08209718,0.020515876,0.026099285,0.7406201],"study_design_scores_gemma":[0.00044099728,0.00075342087,0.009310491,0.0006929,0.0005886797,0.0007823072,0.00030108378,0.83311325,0.050608322,0.07072129,0.03249333,0.00019393323],"about_ca_topic_score_codex":0.001455221,"about_ca_topic_score_gemma":0.0025158883,"teacher_disagreement_score":0.011282504,"about_ca_system_score_codex":0.000499451,"about_ca_system_score_gemma":0.0012064374,"threshold_uncertainty_score":0.059668303},"labels":[],"label_agreement":null},{"id":"W2056439952","doi":"10.1186/1471-2105-12-s9-s21","title":"Consistency-based detection of potential tumor-specific deletions in matched normal/tumor genomes","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"BC Cancer Agency; Natural Sciences and Engineering Research Council of Canada; Canada's Michael Smith Genome Sciences Centre","keywords":"Genome; Computational biology; Biology; Context (archaeology); Genetics; Cancer; Human genome; Consistency (knowledge bases); Computer science; Gene; Artificial intelligence","score_opus":0.015862311996866645,"score_gpt":0.20891035486141976,"score_spread":0.19304804286455313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056439952","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5988154,0.0006206924,0.39647534,0.00012754773,0.000030112045,0.000117380056,0.0011195084,0.0015814499,0.0011126008],"genre_scores_gemma":[0.75495875,0.00008861159,0.24119726,0.00008327656,0.000032500477,0.00012869078,0.0029043278,0.00023018186,0.00037647408],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9975369,0.0005311397,0.00022894722,0.0008391054,0.000684834,0.00017916216],"domain_scores_gemma":[0.9927125,0.004527938,0.0010477379,0.00065663445,0.00081000524,0.00024512663],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002764631,0.00065114134,0.0008633166,0.0018648001,0.00046670745,0.0009682715,0.001477096,0.0008790814,0.00069222896],"category_scores_gemma":[0.008402109,0.00037146173,0.000909698,0.0012395597,0.00073365396,0.000705085,0.0012341805,0.0007539507,0.00034801834],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0034690374,0.0005387512,0.22611794,0.00095900777,0.00079538964,0.0010172859,0.0006165028,0.20785587,0.33098823,0.0049916655,0.0018470671,0.22080329],"study_design_scores_gemma":[0.00006503757,0.00034808237,0.06940948,0.000032952586,0.00017430837,0.0010942129,0.00016905378,0.79389584,0.12775561,0.0048251776,0.002163496,0.00006677231],"about_ca_topic_score_codex":0.0011159452,"about_ca_topic_score_gemma":0.0018219869,"teacher_disagreement_score":0.002764631,"about_ca_system_score_codex":0.0005165792,"about_ca_system_score_gemma":0.0007943723,"threshold_uncertainty_score":0.0146209},"labels":[],"label_agreement":null},{"id":"W2057271915","doi":"10.1186/1471-2105-10-s8-s8","title":"Correlating protein function and stability through the analysis of single amino acid substitutions","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":122,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Structural Genomics Consortium","funders":"U.S. National Library of Medicine; National Institute of General Medical Sciences; National Institutes of Health","keywords":"Mutation; Function (biology); Stability (learning theory); Genetics; Protein structure; Computational biology; Biology; Amino acid; Protein stability; Gene; Biochemistry; Computer science","score_opus":0.015728237680591565,"score_gpt":0.23258057050350625,"score_spread":0.2168523328229147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2057271915","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91614664,0.0026691095,0.07145487,0.0001676458,0.000034688605,0.00005003321,0.00618383,0.0014775649,0.0018155508],"genre_scores_gemma":[0.9660868,0.00045128338,0.027917119,0.00003917951,0.000020775382,0.000035336612,0.0050275954,0.00008971316,0.0003321086],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993025,0.00016984898,0.00006565189,0.00024839505,0.0001693681,0.000044221975],"domain_scores_gemma":[0.9970264,0.0014549743,0.00082241645,0.00021019483,0.00038249526,0.000103558705],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012964205,0.00071562827,0.00066621834,0.003280475,0.00025633152,0.0007103298,0.0003979569,0.000595097,0.0010541661],"category_scores_gemma":[0.003906899,0.000158018,0.000593092,0.0022891925,0.0003174988,0.0005682302,0.00045141304,0.00040595903,0.0008115182],"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":[0.0016017356,0.0004004656,0.5360395,0.0015203317,0.0016236339,0.00059127324,0.00025030857,0.15686148,0.17529184,0.0019877674,0.003287476,0.12054432],"study_design_scores_gemma":[0.000020461006,0.00026005614,0.22049613,0.00005674714,0.0002772641,0.0006911451,0.00007349959,0.72123384,0.05032115,0.0033650827,0.0031442612,0.00006047434],"about_ca_topic_score_codex":0.0013813403,"about_ca_topic_score_gemma":0.0015704086,"teacher_disagreement_score":0.003280475,"about_ca_system_score_codex":0.00043714227,"about_ca_system_score_gemma":0.00027586002,"threshold_uncertainty_score":0.006856203},"labels":[],"label_agreement":null},{"id":"W2057279785","doi":"10.1186/1471-2105-9-s6-s12","title":"Genetic weighted k-means algorithm for clustering large-scale gene expression data","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":60,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Crossover; Computer science; Algorithm; Genetic algorithm; DNA microarray; Maxima and minima; Expression (computer science); Data mining; Gene; Computational biology; Gene expression; Mathematics; Artificial intelligence; Biology; Genetics; Machine learning","score_opus":0.03591019692004375,"score_gpt":0.27260320421340745,"score_spread":0.2366930072933637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2057279785","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00761951,0.00022817137,0.9910884,0.00009344134,0.000031926684,0.00006307133,0.00003657537,0.0005241317,0.00031474108],"genre_scores_gemma":[0.075463936,0.00017429602,0.92281824,0.00008160416,0.000032308624,0.00038955847,0.00022558635,0.00008094286,0.00073345896],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986743,0.00039818557,0.000093917544,0.00032752822,0.0004400771,0.00006602659],"domain_scores_gemma":[0.99881846,0.0005159564,0.00015544017,0.00011266079,0.0003541297,0.000043411914],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015930209,0.0010556902,0.001180323,0.0018159238,0.0009603981,0.0007470709,0.0018534855,0.001502051,0.0009836719],"category_scores_gemma":[0.0039504226,0.00037397954,0.0011996323,0.0023033922,0.0009180453,0.0008356594,0.00073949195,0.0012171493,0.00046373956],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015368445,0.000112527836,0.0016739103,0.00021164569,0.00025470444,0.00010733632,0.00020028371,0.6796166,0.007997345,0.009079662,0.0023427792,0.29824954],"study_design_scores_gemma":[0.00002811623,0.000035477056,0.00045181514,0.00001341044,0.000028300048,0.000055525867,0.000024326122,0.9869507,0.0021490648,0.008845465,0.0013959216,0.000021893875],"about_ca_topic_score_codex":0.007684011,"about_ca_topic_score_gemma":0.006630853,"teacher_disagreement_score":0.007684011,"about_ca_system_score_codex":0.0013293675,"about_ca_system_score_gemma":0.0021021974,"threshold_uncertainty_score":0.015278578},"labels":[],"label_agreement":null},{"id":"W2060064237","doi":"10.1186/1471-2105-12-139","title":"PeakRanger: A cloud-enabled peak caller for ChIP-seq data","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":168,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"National Science Foundation","keywords":"Computer science; Cloud computing; Chromatin immunoprecipitation; Massively parallel; Software; Chip; Parallel computing; Multi-core processor; Data mining; Biology; Operating system","score_opus":0.05121050092748334,"score_gpt":0.2519177744359786,"score_spread":0.2007072735084953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2060064237","genre_codex":"software","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01375821,0.0010591337,0.3303536,0.0004698564,0.00039198544,0.00072936824,0.057202313,0.5906298,0.0054057557],"genre_scores_gemma":[0.07791672,0.0006241211,0.7509269,0.0018151472,0.0002520653,0.002423921,0.09783971,0.0636522,0.0045492137],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961133,0.00041671688,0.000277362,0.0011769199,0.001707293,0.00030836594],"domain_scores_gemma":[0.9946576,0.0022733859,0.0005946857,0.0008802428,0.0012378646,0.0003562501],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005245787,0.0025578241,0.0016976027,0.00302675,0.0013362037,0.0022282337,0.0052794656,0.0016144771,0.02074265],"category_scores_gemma":[0.0094935885,0.0015098958,0.0020066719,0.0026664687,0.0008220103,0.001851513,0.0021277608,0.002978721,0.015063166],"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":[0.0054847533,0.0005855516,0.018363755,0.003564708,0.0012319465,0.000942956,0.00092192006,0.03627029,0.13259378,0.0076504787,0.54105616,0.25133368],"study_design_scores_gemma":[0.001718452,0.00049041124,0.018186398,0.00036542377,0.000381819,0.0011762199,0.00022767244,0.51841223,0.23667525,0.01824094,0.2030505,0.0010746549],"about_ca_topic_score_codex":0.004605203,"about_ca_topic_score_gemma":0.0059258677,"teacher_disagreement_score":0.02074265,"about_ca_system_score_codex":0.0013959489,"about_ca_system_score_gemma":0.0024707478,"threshold_uncertainty_score":0.06939107},"labels":[],"label_agreement":null},{"id":"W2062584460","doi":"10.1186/s12859-014-0396-9","title":"Pathomx: an interactive workflow-based tool for the analysis of metabolomic data","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; National Research Council Canada; National Institute for Health and Care Research; Wellcome Trust","keywords":"Workflow; Computer science; Toolbox; Visualization; Scripting language; Plug-in; Software; Data visualization; Python (programming language); Software engineering; Metabolomics; Data integration; Data mining; Database; Data science; Bioinformatics; Programming language","score_opus":0.031130060562930013,"score_gpt":0.2978217137669514,"score_spread":0.2666916532040214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2062584460","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0050633424,0.00043984014,0.47851804,0.0006093277,0.00034073566,0.0007743664,0.030878844,0.47775638,0.0056191427],"genre_scores_gemma":[0.03959158,0.0013941779,0.77877533,0.0014514672,0.00023924657,0.0053625726,0.08011751,0.07820843,0.014859672],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990878,0.0001497517,0.00011349696,0.00021804313,0.00033198975,0.000098902936],"domain_scores_gemma":[0.9978975,0.0012367719,0.0001714742,0.00020605122,0.00027781137,0.00021046637],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003088821,0.0028482096,0.0010585847,0.0029989833,0.00064435706,0.002063036,0.0029733274,0.001391368,0.05179779],"category_scores_gemma":[0.0051283785,0.0011419876,0.0017227557,0.0014357693,0.0007129292,0.0028143614,0.0037664156,0.002235932,0.014407361],"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":[0.0027952073,0.0002767113,0.0031364663,0.00463286,0.00033135808,0.0028411134,0.0012196193,0.010409268,0.068546705,0.013234641,0.5525488,0.3400272],"study_design_scores_gemma":[0.0013913352,0.000452451,0.009739232,0.0016424889,0.00022332808,0.0030817438,0.00027434062,0.13439907,0.08636478,0.043993227,0.71780807,0.00062996696],"about_ca_topic_score_codex":0.0014748668,"about_ca_topic_score_gemma":0.0013248092,"teacher_disagreement_score":0.05179779,"about_ca_system_score_codex":0.0007734995,"about_ca_system_score_gemma":0.0019823397,"threshold_uncertainty_score":0.1732809},"labels":[],"label_agreement":null},{"id":"W2063430651","doi":"10.1186/1471-2105-8-270","title":"Recognizing protein–protein interfaces with empirical potentials and reduced amino acid alphabets","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children","funders":"European Commission","keywords":"Decoy; Statistical potential; Parameterized complexity; Computer science; Protein structure; Computational biology; Protein structure prediction; Amino acid; Hierarchy; Biological system; Theoretical computer science; Bioinformatics; Algorithm; Biology; Biochemistry","score_opus":0.015598047749565039,"score_gpt":0.2640748466565687,"score_spread":0.2484767989070037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2063430651","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7439709,0.00061250874,0.25075388,0.00031762596,0.000022581327,0.00007667784,0.00020956268,0.0011514007,0.002884813],"genre_scores_gemma":[0.9419408,0.00014764721,0.056603916,0.00008597053,0.000019165795,0.00008861785,0.00044644697,0.00010981819,0.000557643],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99951446,0.00019755516,0.000031785,0.00007242801,0.00012975854,0.00005396883],"domain_scores_gemma":[0.99638283,0.0026219622,0.00027997833,0.0002946421,0.00027240042,0.00014819548],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001645455,0.00054162584,0.00075680093,0.0015360013,0.00038224453,0.00095546065,0.0009674555,0.00081225584,0.0012599209],"category_scores_gemma":[0.005567913,0.00026156288,0.0007459057,0.0006608174,0.00071470876,0.001409918,0.0009810097,0.0009818096,0.00035590588],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047126206,0.00025854647,0.008902559,0.00014389152,0.0000735804,0.00014807735,0.0001342107,0.8947168,0.009574402,0.012541683,0.00087055453,0.0721644],"study_design_scores_gemma":[0.000011768982,0.000029459085,0.00044950983,0.000004523953,0.0000036378967,0.00002298472,0.000014708354,0.9923924,0.000788316,0.0061816247,0.00009543842,0.000005523376],"about_ca_topic_score_codex":0.0022041604,"about_ca_topic_score_gemma":0.0013317284,"teacher_disagreement_score":0.0022041604,"about_ca_system_score_codex":0.0009897343,"about_ca_system_score_gemma":0.000763428,"threshold_uncertainty_score":0.008702159},"labels":[],"label_agreement":null},{"id":"W2064299963","doi":"10.1186/1471-2105-8-s10-s2","title":"Prediction of tissue-specific cis-regulatory modules using Bayesian networks and regression trees","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Transcription factor; Gene regulatory network; Computational biology; Regression; Bayesian network; Biology; DNA binding site; DNA microarray; Bayesian probability; Gene expression; Gene; Computer science; Tree (set theory); Data mining; Artificial intelligence; Genetics; Mathematics; Promoter; Statistics","score_opus":0.01523708875916004,"score_gpt":0.2288783935614113,"score_spread":0.21364130480225124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064299963","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06010357,0.00026192446,0.9380499,0.00011303262,0.000007215191,0.000037801223,0.00032943356,0.0005784116,0.00051864755],"genre_scores_gemma":[0.6404403,0.00037519334,0.35483077,0.00011013436,0.00004529761,0.00022346035,0.0023390085,0.00017933875,0.001456565],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99906677,0.00044957033,0.000041138617,0.00024846676,0.00013082917,0.00006337507],"domain_scores_gemma":[0.9952814,0.0037112606,0.00043107208,0.00012341715,0.0003438418,0.00010903539],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022548952,0.001021988,0.0010095186,0.0020498147,0.00036877012,0.0006548876,0.0009205114,0.00089016143,0.0012601742],"category_scores_gemma":[0.0072483933,0.00065529154,0.0010175306,0.00088843156,0.0003864795,0.00074254215,0.00055205385,0.001081384,0.00052541477],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017800483,0.00007362979,0.008211882,0.00006595564,0.00011601656,0.000083563435,0.000044479526,0.92514664,0.003851549,0.0027883544,0.00069819175,0.05874178],"study_design_scores_gemma":[0.0000058853393,0.000007749588,0.0005759164,0.0000043994364,0.000009670185,0.000013342412,0.0000020821997,0.99595034,0.00043518885,0.002891103,0.00010006466,0.0000041510234],"about_ca_topic_score_codex":0.0059077437,"about_ca_topic_score_gemma":0.006831234,"teacher_disagreement_score":0.0059077437,"about_ca_system_score_codex":0.0009061572,"about_ca_system_score_gemma":0.0008132794,"threshold_uncertainty_score":0.011925161},"labels":[],"label_agreement":null},{"id":"W2064828432","doi":"10.1186/1471-2105-15-260","title":"Gene set enrichment analysis for multiple continuous phenotypes","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Department of Science and Technology, Ministry of Science and Technology, India; Department of Biotechnology, Ministry of Science and Technology, India","keywords":"Phenotype; Categorical variable; Gene; DNA microarray; Computational biology; Set (abstract data type); Genetics; Biology; Microarray; Continuous variable; Microarray analysis techniques; Computer science; Gene expression; Mathematics; Statistics; Machine learning","score_opus":0.01972766746154005,"score_gpt":0.2610992394118885,"score_spread":0.24137157195034845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064828432","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43707547,0.0009481527,0.55241615,0.00110524,0.00010101482,0.00024702723,0.003747076,0.0016661384,0.0026937348],"genre_scores_gemma":[0.89162135,0.00012691504,0.105388656,0.00016425939,0.000049124003,0.000322798,0.0016428389,0.000098710974,0.0005854043],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964972,0.001658225,0.00015541975,0.0007044767,0.0008022128,0.00018251219],"domain_scores_gemma":[0.9764168,0.019939201,0.0012313465,0.0012824385,0.00078489573,0.00034524134],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004874289,0.000671251,0.00083122874,0.0024911333,0.0005794275,0.0008853117,0.0011996747,0.00047752395,0.0038124726],"category_scores_gemma":[0.013325662,0.00017003577,0.0018465539,0.0021236057,0.0010618228,0.000502764,0.0010453331,0.0012490215,0.00033598533],"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":[0.0036450133,0.000995415,0.4786175,0.0016017813,0.0041542435,0.0019808952,0.00034582528,0.16408618,0.049829237,0.017394936,0.005723811,0.27162516],"study_design_scores_gemma":[0.00029101942,0.0011398789,0.1810976,0.000072481234,0.0011547974,0.0014261231,0.0002651142,0.72398484,0.023278907,0.06165487,0.005529954,0.00010448362],"about_ca_topic_score_codex":0.0015307808,"about_ca_topic_score_gemma":0.0020304788,"teacher_disagreement_score":0.004874289,"about_ca_system_score_codex":0.0007743646,"about_ca_system_score_gemma":0.001254668,"threshold_uncertainty_score":0.025777996},"labels":[],"label_agreement":null},{"id":"W2065925372","doi":"10.1186/1471-2105-15-170","title":"Ensemble analyses improve signatures of tumour hypoxia and reveal inter-platform differences","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Cancer, Hypoxia, and Metabolism","field":"Biochemistry, Genetics and Molecular Biology","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research","funders":"Center for Translational Molecular Medicine; Government of Ontario","keywords":"DNA microarray; Biomarker discovery; Computer science; Limiting; Biomarker; Transcriptome; Computational biology; Data mining; Bioinformatics; Artificial intelligence; Pattern recognition (psychology); Machine learning; Biology; Proteomics; Gene; Gene expression; Genetics","score_opus":0.02264884552033729,"score_gpt":0.2699888478312685,"score_spread":0.24734000231093117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2065925372","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7524234,0.0035211886,0.23776697,0.0006015033,0.00019543605,0.0001114598,0.0019742954,0.0016511136,0.0017546639],"genre_scores_gemma":[0.9042413,0.0008306789,0.09064826,0.00019688871,0.0001305432,0.000103684804,0.002713497,0.00027300042,0.0008621638],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99864584,0.00038977375,0.00010013331,0.0004631793,0.00026642057,0.00013466687],"domain_scores_gemma":[0.9951546,0.002723885,0.00062044483,0.0007314316,0.000615117,0.00015451666],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032499414,0.0010515022,0.0010940603,0.001567432,0.00036281967,0.001297662,0.00037407494,0.0005513127,0.0011618354],"category_scores_gemma":[0.0064870464,0.00021517128,0.0012962575,0.001214214,0.00030239136,0.0009924207,0.00093570544,0.0011669374,0.0005386519],"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":[0.0017586217,0.00039314036,0.17605884,0.0007669994,0.0020969175,0.0002338164,0.00043363596,0.049125284,0.3327618,0.00090371637,0.0036646163,0.43180275],"study_design_scores_gemma":[0.00008520519,0.0020081028,0.3743825,0.00018479364,0.0023681214,0.0010035092,0.00040842165,0.3541568,0.24245943,0.012259251,0.010474042,0.00020987487],"about_ca_topic_score_codex":0.0005383262,"about_ca_topic_score_gemma":0.0010575973,"teacher_disagreement_score":0.0032499414,"about_ca_system_score_codex":0.0003050725,"about_ca_system_score_gemma":0.0004185215,"threshold_uncertainty_score":0.017187536},"labels":[],"label_agreement":null},{"id":"W2065928355","doi":"10.1186/1471-2105-15-278","title":"Equivalent input produces different output in the UniFrac significance test","year":2014,"lang":"en","type":"letter","venue":"BMC Bioinformatics","topic":"Microbial Community Ecology and Physiology","field":"Environmental Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Contango Strategies (Canada); University of Saskatchewan","funders":"Western Economic Diversification Canada; Genome Prairie","keywords":"UniFrac; Consistency (knowledge bases); Tree (set theory); Computer science; Statistical hypothesis testing; Statistics; Biology; Mathematics; Artificial intelligence; Genetics","score_opus":0.03544347977958179,"score_gpt":0.2396278816646724,"score_spread":0.2041844018850906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2065928355","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03696837,0.0035278413,0.5577637,0.30055007,0.032382984,0.00046479524,0.0040068445,0.022453327,0.041882068],"genre_scores_gemma":[0.28243035,0.002469455,0.44224697,0.22473064,0.014331779,0.0013978598,0.0036567894,0.00769643,0.021039737],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.95846176,0.020975303,0.004230829,0.002949637,0.012080105,0.001302283],"domain_scores_gemma":[0.73678553,0.21775459,0.0069332146,0.016826164,0.02025846,0.001442018],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.028466513,0.00095507654,0.0010851295,0.0014325673,0.001384111,0.0033087016,0.002060443,0.007699693,0.014446059],"category_scores_gemma":[0.21616322,0.0006199902,0.0014011473,0.002157507,0.0034006955,0.0024955191,0.0018369587,0.0071321786,0.011056189],"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":[0.0017526334,0.00026509096,0.018564388,0.0012581426,0.00019217627,0.008620813,0.002643514,0.0033942778,0.010534233,0.08405831,0.5124152,0.35630134],"study_design_scores_gemma":[0.00042143022,0.00055156474,0.010523766,0.0012149658,0.00021726124,0.029560689,0.0010963277,0.039878134,0.044476636,0.18217602,0.6894564,0.000426703],"about_ca_topic_score_codex":0.0009918195,"about_ca_topic_score_gemma":0.001218541,"teacher_disagreement_score":0.028466513,"about_ca_system_score_codex":0.0025578763,"about_ca_system_score_gemma":0.0013943625,"threshold_uncertainty_score":0.15054709},"labels":[],"label_agreement":null},{"id":"W2066656905","doi":"10.1186/1471-2105-14-202","title":"MetaPathways: a modular pipeline for constructing pathway/genome databases from environmental sequence information","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Microbial Metabolic Engineering and Bioproduction","field":"Biochemistry, Genetics and Molecular Biology","cited_by":104,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Genome British Columbia; University of Alberta; Genome Canada; Tula Foundation; Western Canada Research Grid; Canadian Institute for Advanced Research","keywords":"KEGG; GenBank; Pipeline (software); Computer science; Annotation; Modular design; Computational biology; Database; Biology; Artificial intelligence; Genetics; Gene; Transcriptome; Programming language","score_opus":0.019750814503093676,"score_gpt":0.21109957472463892,"score_spread":0.19134876022154523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2066656905","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008477509,0.0005403372,0.43414277,0.00031658213,0.000115798975,0.00057577976,0.12279996,0.42901507,0.0040162187],"genre_scores_gemma":[0.052233987,0.0009313041,0.65177023,0.00033192805,0.00006894208,0.0015388004,0.25003982,0.040140774,0.0029442287],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99865997,0.00018836203,0.0001386753,0.0005326254,0.00036828656,0.0001119875],"domain_scores_gemma":[0.9979656,0.00084721233,0.0002952064,0.00044655125,0.0002665442,0.00017903878],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003201923,0.0033882617,0.0012706618,0.005458017,0.0012673772,0.003216093,0.0042324835,0.0010270503,0.026525306],"category_scores_gemma":[0.0053387214,0.0021633953,0.0025749956,0.0037649092,0.00067802245,0.003591568,0.0039577805,0.0027570794,0.012713075],"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":[0.0041688024,0.00049300684,0.017088983,0.006844331,0.0015666978,0.0019138361,0.0017984846,0.029020935,0.089103006,0.02229321,0.35787022,0.4678385],"study_design_scores_gemma":[0.0009960495,0.0005321462,0.013034056,0.000886583,0.0006133651,0.001740647,0.00091298186,0.19787809,0.13806538,0.07032018,0.57433444,0.000685974],"about_ca_topic_score_codex":0.003099943,"about_ca_topic_score_gemma":0.0042948565,"teacher_disagreement_score":0.026525306,"about_ca_system_score_codex":0.001206869,"about_ca_system_score_gemma":0.0038385342,"threshold_uncertainty_score":0.08873606},"labels":[],"label_agreement":null},{"id":"W2067516565","doi":"10.1186/1471-2105-11-25","title":"Calibur: a tool for clustering large numbers of protein decoys","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":78,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Decoy; Cluster analysis; Bottleneck; Engineering; Artificial intelligence; Data mining; Computer science","score_opus":0.0061356032309906995,"score_gpt":0.24359543162986375,"score_spread":0.23745982839887306,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2067516565","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01030598,0.0007626,0.5334925,0.00034509497,0.00016965804,0.0009784969,0.0073255594,0.44265234,0.0039678244],"genre_scores_gemma":[0.071969576,0.00067907484,0.85862076,0.0006003409,0.00007865309,0.0036399756,0.030727647,0.028529227,0.0051547983],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99602854,0.00077093864,0.0003472779,0.00065747247,0.0018475136,0.0003482827],"domain_scores_gemma":[0.9955173,0.0015254708,0.0005076728,0.0008440739,0.001209133,0.00039627514],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043354584,0.0041413833,0.0029803242,0.006208052,0.002168999,0.0025547468,0.009447934,0.0019374929,0.026014391],"category_scores_gemma":[0.011652972,0.0017158116,0.0019960448,0.0044013076,0.0012407068,0.0023973556,0.0045253676,0.0040919133,0.011873501],"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":[0.0030561748,0.0008146905,0.004973098,0.0024015612,0.0007978502,0.0006176723,0.0009260129,0.034363113,0.036602262,0.015560478,0.44714823,0.45273885],"study_design_scores_gemma":[0.0012424553,0.00059287145,0.0041938387,0.00023387882,0.00017252908,0.0005823918,0.0003094272,0.7643546,0.08838406,0.020480191,0.119029135,0.00042471383],"about_ca_topic_score_codex":0.012564475,"about_ca_topic_score_gemma":0.012575477,"teacher_disagreement_score":0.026014391,"about_ca_system_score_codex":0.0025404596,"about_ca_system_score_gemma":0.0036454466,"threshold_uncertainty_score":0.087026775},"labels":[],"label_agreement":null},{"id":"W2068856084","doi":"10.1186/1471-2105-11-s1-s40","title":"New decoding algorithms for Hidden Markov Models using distance measures on labellings","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"DNA and Biological Computing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Decoding methods; Markov chain; Markov model; Hidden Markov model; Algorithm; Theoretical computer science; Artificial intelligence; Machine learning","score_opus":0.060008494598102875,"score_gpt":0.29085506612591827,"score_spread":0.2308465715278154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2068856084","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025496853,0.00013006688,0.9953335,0.00011498247,0.0000312332,0.000036730245,0.0001351834,0.0009970447,0.0006716309],"genre_scores_gemma":[0.06261233,0.00029998875,0.9309995,0.00019507113,0.00010168024,0.00026936995,0.0014314489,0.0011572841,0.0029333383],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971847,0.00081574364,0.00029960516,0.00063631375,0.00087150215,0.00019218338],"domain_scores_gemma":[0.9860788,0.010230559,0.0006253633,0.0012704699,0.0015195981,0.0002752643],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032020968,0.0016370299,0.0016052519,0.0022262428,0.0009825793,0.002552829,0.0031223986,0.0029098946,0.0062401476],"category_scores_gemma":[0.023425387,0.0011134658,0.0017471544,0.002513611,0.0013019801,0.00496116,0.00387582,0.0043018647,0.0033807084],"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":[0.00018884597,0.00013816201,0.0012540601,0.00033150832,0.0000916264,0.00014403286,0.0003645514,0.41457295,0.0038300364,0.14734626,0.007655732,0.42408234],"study_design_scores_gemma":[0.000024057477,0.000015235702,0.00007510556,0.00002691713,0.000011182732,0.000048892354,0.000022543856,0.87795424,0.0014208696,0.1186524,0.0017295979,0.00001891373],"about_ca_topic_score_codex":0.0039593955,"about_ca_topic_score_gemma":0.0049246927,"teacher_disagreement_score":0.0062401476,"about_ca_system_score_codex":0.0027612755,"about_ca_system_score_gemma":0.0026231732,"threshold_uncertainty_score":0.020875394},"labels":[],"label_agreement":null},{"id":"W2068916031","doi":"10.1186/1471-2105-14-s3-s15","title":"Characterizing the state of the art in the computational assignment of gene function: lessons from the first critical assessment of functional annotation (CAFA)","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":68,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"National Institute of General Medical Sciences; National Institutes of Health; Michael Smith Health Research BC","keywords":"Annotation; Function (biology); Task (project management); Computer science; Similarity (geometry); Gene ontology; Field (mathematics); Sequence (biology); Gene Annotation; Computational biology; Artificial intelligence; Gene; Biology; Genetics; Genome; Image (mathematics); Mathematics","score_opus":0.0205252854573285,"score_gpt":0.25658317216549725,"score_spread":0.23605788670816874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2068916031","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.075086534,0.09498866,0.7498824,0.06511036,0.001199926,0.00010949259,0.0013305438,0.0020329952,0.010259137],"genre_scores_gemma":[0.4783123,0.044444393,0.46352002,0.0059749503,0.0019124199,0.0002622226,0.0024987797,0.0011940604,0.0018807678],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.97759366,0.00914151,0.0014359767,0.0055534597,0.005501036,0.00077432423],"domain_scores_gemma":[0.7829915,0.16996264,0.0040402827,0.022435851,0.018296093,0.0022735826],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07451264,0.0021064568,0.003674193,0.0068820277,0.0022000805,0.013828158,0.0062096994,0.005468499,0.0019052386],"category_scores_gemma":[0.14427856,0.0012096172,0.0020147266,0.0057348046,0.013751649,0.022262447,0.005675002,0.012462974,0.0022308049],"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":[0.0008774497,0.00038769707,0.020052617,0.003917523,0.0005146507,0.00015976484,0.0026561304,0.06576563,0.012366444,0.2248471,0.02042938,0.6480256],"study_design_scores_gemma":[0.000055560395,0.00050985406,0.009584338,0.0021953273,0.00016892838,0.00042541279,0.0021647057,0.225495,0.017571643,0.68723595,0.05418915,0.00040420087],"about_ca_topic_score_codex":0.004928372,"about_ca_topic_score_gemma":0.003022199,"teacher_disagreement_score":0.92548734,"about_ca_system_score_codex":0.0051396643,"about_ca_system_score_gemma":0.004175876,"threshold_uncertainty_score":0.3940652},"labels":[],"label_agreement":null},{"id":"W2069716529","doi":"10.1186/1471-2105-14-s16-s6","title":"Random forests on Hadoop for genome-wide association studies of multivariate neuroimaging phenotypes","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Aging; University of California, San Diego; Genentech; National Institutes of Health; Canadian Institutes of Health Research; University of California, Los Angeles; Servier; Imperial College London; Northern California Institute for Research and Education; Synarc; Engineering and Physical Sciences Research Council; Bayer HealthCare; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; National University of Singapore; Medpace; Pfizer; Biogen; AstraZeneca; Bristol-Myers Squibb; Eli Lilly and Company; Novartis Pharmaceuticals Corporation; F. Hoffmann-La Roche; Amorfix Life Sciences; Alzheimer's Drug Discovery Foundation; Foundation for the National Institutes of Health","keywords":"Multivariate statistics; Random forest; Computer science; Artificial intelligence; Neuroimaging; Genome-wide association study; Machine learning; Genetic architecture; Genetic association; Quantitative trait locus; Population; Data mining; Computational biology; Biology; Single-nucleotide polymorphism; Genetics; Gene; Genotype","score_opus":0.02956429377384484,"score_gpt":0.29190146679685874,"score_spread":0.2623371730230139,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2069716529","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03415701,0.0030458188,0.75204474,0.0014718451,0.001300735,0.0012237609,0.022433707,0.17925969,0.005062559],"genre_scores_gemma":[0.1901419,0.00075567595,0.7756919,0.00074981706,0.0002567287,0.0016121594,0.025509978,0.0031765846,0.0021052405],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99552685,0.0015055977,0.0003981286,0.0010091052,0.0009904376,0.0005698192],"domain_scores_gemma":[0.9930849,0.0030042336,0.00046279837,0.0015043811,0.0013076498,0.00063604565],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006947295,0.0026976604,0.002213399,0.0019889665,0.0016357313,0.0021166066,0.0050828285,0.0011746679,0.0068227337],"category_scores_gemma":[0.015087409,0.0017016189,0.003877584,0.003267069,0.001087375,0.0025342,0.0031203139,0.0028630663,0.004842348],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0052675116,0.0010373617,0.013770208,0.0023591989,0.002343844,0.002205206,0.0007467871,0.4398549,0.008576111,0.023913609,0.19879867,0.30112666],"study_design_scores_gemma":[0.00084776786,0.00014250228,0.0024006108,0.000098348086,0.00014339233,0.00020657596,0.00015482659,0.9157842,0.0024473283,0.06084456,0.016799284,0.00013069437],"about_ca_topic_score_codex":0.021785047,"about_ca_topic_score_gemma":0.030088047,"teacher_disagreement_score":0.021785047,"about_ca_system_score_codex":0.0011123822,"about_ca_system_score_gemma":0.0036658377,"threshold_uncertainty_score":0.043316483},"labels":[],"label_agreement":null},{"id":"W2070040136","doi":"10.1186/1471-2105-12-436","title":"clusterMaker: a multi-algorithm clustering plugin for Cytoscape","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":669,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Center for Research Resources; National Institute of General Medical Sciences; National Institutes of Health","keywords":"Cluster analysis; Computer science; Interactome; Plug-in; Hierarchical clustering; Computational biology; Visualization; Dendrogram; Data mining; Bioinformatics; Biology; Machine learning; Genetics","score_opus":0.03728483425002162,"score_gpt":0.24980731058751915,"score_spread":0.21252247633749755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070040136","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002357919,0.0006602238,0.31821766,0.00050419144,0.00051058637,0.0005648569,0.033135645,0.63890785,0.0051410096],"genre_scores_gemma":[0.03342263,0.0011517662,0.7388601,0.0015406029,0.00030133972,0.0063769286,0.058853596,0.14717998,0.012313094],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981692,0.0003166468,0.00013512827,0.00046368001,0.00075852626,0.00015671266],"domain_scores_gemma":[0.9963129,0.002113836,0.0002207185,0.00046582308,0.0005908947,0.00029592353],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027923377,0.0032162,0.0018900314,0.0047734412,0.0019436936,0.0026689959,0.0071166563,0.002878002,0.066871464],"category_scores_gemma":[0.009217148,0.002318028,0.0021750894,0.0026587043,0.0007771382,0.0033688964,0.0032614851,0.005041406,0.028777184],"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":[0.001020228,0.00025122822,0.0017174934,0.0044353786,0.000994061,0.0006283902,0.00075275695,0.015460149,0.017891485,0.014736144,0.7748127,0.1673],"study_design_scores_gemma":[0.00085616385,0.00016531163,0.003379519,0.0006956886,0.00027681424,0.00072024344,0.00019058342,0.18323207,0.05756226,0.07015693,0.68199193,0.0007724399],"about_ca_topic_score_codex":0.007032656,"about_ca_topic_score_gemma":0.010300281,"teacher_disagreement_score":0.066871464,"about_ca_system_score_codex":0.0013019076,"about_ca_system_score_gemma":0.0047412897,"threshold_uncertainty_score":0.22370732},"labels":[],"label_agreement":null},{"id":"W2070739680","doi":"10.1186/1471-2105-8-s10-s1","title":"NIPS workshop on New Problems and Methods in Computational Biology","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Artificial intelligence; Computer science; Computational genomics; Presentation (obstetrics); Data science; Session (web analytics); Computational model; Modelling biological systems; Inference; Field (mathematics); Annotation; Systems biology; Machine learning; Computational biology; Biology; Genomics; Genome; Gene; World Wide Web; Mathematics","score_opus":0.05067414694382884,"score_gpt":0.37165532817481045,"score_spread":0.3209811812309816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070739680","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032249384,0.14858127,0.6036174,0.083367035,0.075446256,0.0006750706,0.003908675,0.0020958865,0.079083435],"genre_scores_gemma":[0.036661975,0.1251875,0.56802356,0.016536402,0.100777954,0.002257196,0.0090137245,0.0027335747,0.13880824],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9923292,0.0025199319,0.0007120091,0.0011873287,0.0028900367,0.00036148375],"domain_scores_gemma":[0.98282284,0.010138501,0.0005083128,0.0016989696,0.0033577112,0.0014736176],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015238737,0.0021431402,0.003087506,0.0027660236,0.0011485651,0.006271192,0.0043559726,0.0046143136,0.026671985],"category_scores_gemma":[0.02569967,0.0010657782,0.0031172184,0.0026190868,0.002383348,0.00551997,0.0041495548,0.010856935,0.01403122],"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":[0.00020060553,0.00013395216,0.00063744735,0.0015191071,0.0004448555,0.0002889374,0.00021216979,0.011135613,0.0013310692,0.1459281,0.55159247,0.2865758],"study_design_scores_gemma":[0.00008649703,0.000094250485,0.0009073832,0.00086477597,0.0000949189,0.0003740449,0.000075555436,0.04120912,0.0009771639,0.20185865,0.7533593,0.00009824643],"about_ca_topic_score_codex":0.0015110242,"about_ca_topic_score_gemma":0.0014924983,"teacher_disagreement_score":0.026671985,"about_ca_system_score_codex":0.0022526917,"about_ca_system_score_gemma":0.0041614575,"threshold_uncertainty_score":0.08922666},"labels":[],"label_agreement":null},{"id":"W2070791418","doi":"10.1186/1471-2105-13-206","title":"CaPSID: A bioinformatics platform for computational pathogen sequence identification in human genomes and transcriptomes","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; McGill University; University of Toronto; Ontario Institute for Cancer Research","funders":"Canadian Institutes of Health Research; Government of Ontario; Terry Fox Research Institute; Ontario Institute for Cancer Research","keywords":"Genome; Capsid; Biology; Computational biology; Transcriptome; DNA sequencing; Proteome; Reference genome; Identification (biology); Gene; Genetics; Gene expression","score_opus":0.0399281561811749,"score_gpt":0.28162911583535716,"score_spread":0.24170095965418226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070791418","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027037742,0.0010343319,0.6706049,0.0007769176,0.00021914531,0.0005545622,0.036875363,0.26030815,0.0025888784],"genre_scores_gemma":[0.1683159,0.0013153802,0.7441847,0.00062450266,0.00011826527,0.0017559932,0.06489387,0.01663393,0.00215743],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99904984,0.00028850816,0.00010403661,0.00026802204,0.00022809274,0.00006147539],"domain_scores_gemma":[0.99726605,0.0016373027,0.00025517226,0.00035530256,0.00024090066,0.00024542015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033044459,0.0017296433,0.00132414,0.0018184789,0.00078748097,0.0020833048,0.0023482498,0.0010681786,0.009459223],"category_scores_gemma":[0.0075172307,0.0011212385,0.0017215203,0.0020020895,0.000659691,0.001635767,0.0027479487,0.0019028797,0.0039517437],"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":[0.00907805,0.00079765846,0.020854713,0.0060138186,0.0024135995,0.0031757315,0.002452119,0.19541708,0.106332354,0.042134587,0.29614723,0.31518298],"study_design_scores_gemma":[0.0015856336,0.0005749404,0.008881016,0.00031149364,0.00036073953,0.0011281208,0.00034106025,0.765907,0.035896502,0.04859281,0.13609543,0.00032526415],"about_ca_topic_score_codex":0.0027578138,"about_ca_topic_score_gemma":0.0037316955,"teacher_disagreement_score":0.009459223,"about_ca_system_score_codex":0.00071248534,"about_ca_system_score_gemma":0.001949751,"threshold_uncertainty_score":0.031644285},"labels":[],"label_agreement":null},{"id":"W2071286514","doi":"10.1186/1471-2105-8-208","title":"Seahawk: moving beyond HTML in Web-based bioinformatics analysis","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Genome Alberta; Dalhousie University; Genome Canada","keywords":"Computer science; World Wide Web; Web service; Data Web; Web modeling; Semantic Web; XML; XSLT; Web standards; Information retrieval","score_opus":0.07830484163187579,"score_gpt":0.35560889294768033,"score_spread":0.27730405131580455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2071286514","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06521362,0.0008006302,0.77477485,0.0027031142,0.00018581854,0.0005434279,0.0017784835,0.13294652,0.02105355],"genre_scores_gemma":[0.089753486,0.00065726315,0.8798792,0.0012462224,0.000058477905,0.00032432642,0.0030736756,0.018251063,0.0067563173],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981919,0.00034179736,0.00013394658,0.00053285854,0.0006670518,0.00013237797],"domain_scores_gemma":[0.99579924,0.0018715597,0.00035393308,0.00085535285,0.00064665923,0.000473201],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003350532,0.0007403409,0.00043229217,0.0011168938,0.00084271503,0.0024096773,0.002095165,0.0011418446,0.0053494684],"category_scores_gemma":[0.005577301,0.0009870201,0.0009106715,0.0011158457,0.0022626861,0.004826525,0.0036946377,0.0020494715,0.004436528],"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":[0.0013884392,0.00054957764,0.022813167,0.0013103328,0.00026178893,0.0014702202,0.006908546,0.011650355,0.10171831,0.042334102,0.14212592,0.66746926],"study_design_scores_gemma":[0.00033284543,0.0005153825,0.025789114,0.0013503298,0.00026341694,0.0032323666,0.0018120473,0.14653167,0.119816415,0.11161379,0.5881699,0.0005727283],"about_ca_topic_score_codex":0.00258053,"about_ca_topic_score_gemma":0.0032274888,"teacher_disagreement_score":0.0053494684,"about_ca_system_score_codex":0.0009603817,"about_ca_system_score_gemma":0.0017357797,"threshold_uncertainty_score":0.017895699},"labels":[],"label_agreement":null},{"id":"W2074131187","doi":"10.1186/1471-2105-15-78","title":"ShatterProof: operational detection and quantification of chromothripsis","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomic variations and chromosomal abnormalities","field":"Biochemistry, Genetics and Molecular Biology","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Domtar (Canada); University Health Network; University of British Columbia; University of Toronto; Ontario Institute for Cancer Research","funders":"Prostate Cancer Canada; Government of Ontario; Ontario Institute for Cancer Research; Movember Foundation","keywords":"Chromothripsis; Computer science; Computational biology; Biology; Genetics; Genome instability","score_opus":0.009942496063046542,"score_gpt":0.2124061246202045,"score_spread":0.20246362855715797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2074131187","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07254558,0.0013405122,0.6332148,0.00047293454,0.0002468521,0.00036019593,0.020379657,0.26677474,0.004664744],"genre_scores_gemma":[0.23747928,0.0006626615,0.70658493,0.0006390677,0.0000954091,0.0013162621,0.028616263,0.020153709,0.0044523813],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975157,0.00031390987,0.00019679117,0.0009335963,0.0008428365,0.00019719922],"domain_scores_gemma":[0.99579275,0.0020899856,0.0009069739,0.0005156768,0.00048829964,0.00020645247],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036111034,0.0020468603,0.0013265458,0.0032751176,0.00086099864,0.0022275057,0.0017169963,0.0014100388,0.007874479],"category_scores_gemma":[0.011565316,0.0010937237,0.0013864995,0.001761925,0.00088406244,0.0014128542,0.0018374764,0.0013823168,0.004429585],"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":[0.0036577343,0.00039701242,0.06733275,0.0033901066,0.001069394,0.00084356853,0.0015933091,0.0366745,0.24233086,0.0121447025,0.13351916,0.49704692],"study_design_scores_gemma":[0.00044676126,0.00083024165,0.048142243,0.00036130974,0.00033605137,0.0021687301,0.00028565523,0.43903434,0.38730758,0.023241065,0.09720721,0.0006389023],"about_ca_topic_score_codex":0.0029972757,"about_ca_topic_score_gemma":0.004073562,"teacher_disagreement_score":0.007874479,"about_ca_system_score_codex":0.0010131578,"about_ca_system_score_gemma":0.0017751143,"threshold_uncertainty_score":0.02634281},"labels":[],"label_agreement":null},{"id":"W2074656136","doi":"10.1186/1471-2105-7-s4-s13","title":"Determination of the minimum number of microarray experiments for discovery of gene expression patterns","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"DNA microarray; Cluster analysis; Expression (computer science); False discovery rate; Data mining; Microarray analysis techniques; Function (biology); Set (abstract data type); Similarity (geometry); Gene chip analysis; Computational biology; Interval (graph theory); Gene expression profiling; Microarray; Computer science; Hierarchical clustering; Microarray databases; Gene expression; Biology; Gene; Artificial intelligence; Mathematics; Genetics","score_opus":0.015086703780507608,"score_gpt":0.27456269834544395,"score_spread":0.25947599456493636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2074656136","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051583033,0.00060786697,0.94571024,0.00025310565,0.00005248731,0.00031336542,0.00037039432,0.0005305663,0.00057893596],"genre_scores_gemma":[0.09908362,0.00021358042,0.8990192,0.00007211135,0.00003721282,0.0007655148,0.0005150298,0.00009821603,0.00019551936],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99444264,0.0019427931,0.0008806907,0.0010665742,0.0014436668,0.00022367873],"domain_scores_gemma":[0.9453871,0.038763314,0.003595759,0.0058952305,0.0054113623,0.0009471833],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008490801,0.00070368435,0.0015240425,0.0015575651,0.00078071444,0.00096580514,0.0018130178,0.0015760318,0.001186536],"category_scores_gemma":[0.038296886,0.00073337293,0.0012567574,0.001094119,0.00083824893,0.0013966544,0.0008302468,0.0019324907,0.00067824154],"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":[0.002274105,0.0008278447,0.02329334,0.0020421233,0.00031815094,0.0004455253,0.00034972013,0.05714022,0.6700056,0.010127207,0.0021111309,0.23106496],"study_design_scores_gemma":[0.0003481587,0.001478092,0.036266476,0.00031120385,0.00038231083,0.0013777642,0.0002479572,0.5131915,0.40233877,0.034053776,0.009817098,0.00018699004],"about_ca_topic_score_codex":0.00037739606,"about_ca_topic_score_gemma":0.0009595376,"teacher_disagreement_score":0.008490801,"about_ca_system_score_codex":0.0009020619,"about_ca_system_score_gemma":0.0017742105,"threshold_uncertainty_score":0.044904172},"labels":[],"label_agreement":null},{"id":"W2074909362","doi":"10.1186/1471-2105-12-303","title":"Prototype semantic infrastructure for automated small molecule classification and annotation in lipidomics","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick; Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; New Brunswick Innovation Foundation; Canarie","keywords":"Ontology; Computer science; Annotation; Service (business); Information retrieval; Semantic Web; Web service; World Wide Web; Lipidomics; Bioinformatics; Artificial intelligence; Biology","score_opus":0.04138146981705494,"score_gpt":0.2698668574848378,"score_spread":0.22848538766778287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2074909362","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012488677,0.00024505684,0.8577705,0.00078514195,0.00007694563,0.0006887194,0.0034730393,0.11736262,0.007109197],"genre_scores_gemma":[0.1186737,0.0006348386,0.8414647,0.00088442647,0.00007335053,0.0010295813,0.02720618,0.0044147945,0.0056183757],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99811447,0.00025948932,0.00020553231,0.00049904553,0.0007186717,0.00020291144],"domain_scores_gemma":[0.99729615,0.0007683888,0.00028932033,0.0007479028,0.00063398725,0.0002641504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039990055,0.0011813146,0.0009374723,0.003567716,0.0014989653,0.0034718125,0.0038637305,0.0019301956,0.005435299],"category_scores_gemma":[0.005438249,0.00072933617,0.0016877531,0.002675865,0.0015161219,0.0062379004,0.0047356137,0.0016189744,0.0046771653],"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":[0.0027701175,0.0023865597,0.016133301,0.0027220207,0.0005533328,0.0034937775,0.0025468243,0.037045,0.13747945,0.16056708,0.12886849,0.50543404],"study_design_scores_gemma":[0.000307979,0.00031747573,0.005115752,0.00045874694,0.00025185043,0.0015910557,0.0008651116,0.52727664,0.09275392,0.10558329,0.2652159,0.00026226332],"about_ca_topic_score_codex":0.006989971,"about_ca_topic_score_gemma":0.006957787,"teacher_disagreement_score":0.006989971,"about_ca_system_score_codex":0.0025496387,"about_ca_system_score_gemma":0.0038272187,"threshold_uncertainty_score":0.02114904},"labels":[],"label_agreement":null},{"id":"W2075326868","doi":"10.1186/1471-2105-8-197","title":"MASPECTRAS: a platform for management and analysis of proteomics LC-MS/MS data","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medizinische Universität Graz; Bundesministerium für Bildung, Wissenschaft und Kultur; Karl-Franzens-Universität Graz; University of Toronto; Österreichischen Akademie der Wissenschaften","keywords":"Computer science; Proteomics; Software; UniProt; Cluster analysis; Mascot; Data management; Proteome; Data mining; Database; Data science; Bioinformatics; Artificial intelligence; Biology","score_opus":0.03817860811772101,"score_gpt":0.3073214138576116,"score_spread":0.2691428057398906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2075326868","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014063589,0.0006684397,0.5963939,0.0006475198,0.00036479547,0.0017080305,0.03982275,0.3411464,0.0051845936],"genre_scores_gemma":[0.038839474,0.0010088094,0.8171471,0.0009696288,0.0003213598,0.0033102531,0.10923024,0.022363013,0.0068101096],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99802774,0.00020424889,0.00030520567,0.0004459807,0.00085982576,0.00015706748],"domain_scores_gemma":[0.99712783,0.00069628423,0.000498843,0.0006674544,0.0006880581,0.00032157177],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035278914,0.0024236676,0.0012813237,0.0030093417,0.001041188,0.002828367,0.0034538354,0.0011259554,0.019455167],"category_scores_gemma":[0.0052966466,0.0010312181,0.001185897,0.002329934,0.00071135,0.0027500468,0.0028265628,0.0022446604,0.015758313],"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":[0.0034517911,0.00051826175,0.006071492,0.0023742826,0.00093876227,0.0027112018,0.00061560655,0.007895594,0.29635262,0.012224936,0.32906997,0.33777547],"study_design_scores_gemma":[0.0013192986,0.00076239055,0.010958597,0.00044329357,0.00035309023,0.005357038,0.00017832108,0.13241528,0.3409479,0.02610049,0.48036608,0.0007982237],"about_ca_topic_score_codex":0.0011422782,"about_ca_topic_score_gemma":0.0010671432,"teacher_disagreement_score":0.019455167,"about_ca_system_score_codex":0.0006642839,"about_ca_system_score_gemma":0.002227178,"threshold_uncertainty_score":0.06508398},"labels":[],"label_agreement":null},{"id":"W2075694192","doi":"10.1186/1471-2105-13-s1-s2","title":"SPARQL Assist language-neutral query composer","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","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":"St. Paul's Hospital; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Canarie; Microsoft Research","keywords":"SPARQL; Computer science; Named graph; Semantics (computer science); World Wide Web; Identifier; Information retrieval; Semantic Web; Query language; Context (archaeology); Task (project management); RDF query language; SPARK (programming language); RDF; Web search query; Web query classification; Programming language; Search engine","score_opus":0.022859403368950572,"score_gpt":0.28317180680258563,"score_spread":0.26031240343363504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2075694192","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012118191,0.00020773511,0.67740697,0.000780641,0.0001632945,0.0007055208,0.003930005,0.29044345,0.01424413],"genre_scores_gemma":[0.28100333,0.00058900216,0.6183768,0.0035002453,0.0003633308,0.0012383761,0.022661438,0.04674813,0.025519464],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99496955,0.0011674246,0.0006684251,0.0011629253,0.0017078457,0.0003238031],"domain_scores_gemma":[0.991935,0.0032086428,0.0003642478,0.0024267156,0.0017503063,0.0003151635],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00797061,0.0015548436,0.0010362456,0.0010848835,0.00087732525,0.002866116,0.0026150928,0.0012498195,0.025165204],"category_scores_gemma":[0.011081667,0.00079178915,0.0012929554,0.000994721,0.0011785907,0.0041059265,0.0038647566,0.0018578281,0.010411817],"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":[0.0049361815,0.0007104271,0.010558556,0.0027122276,0.00045227964,0.0027818286,0.0046655824,0.012112077,0.10306396,0.10502899,0.34059748,0.41238034],"study_design_scores_gemma":[0.00048426207,0.00030873384,0.0024581112,0.00027232963,0.00019934583,0.002141246,0.00086890836,0.19841826,0.16812646,0.06158101,0.5648383,0.00030309928],"about_ca_topic_score_codex":0.001698491,"about_ca_topic_score_gemma":0.0012987118,"teacher_disagreement_score":0.025165204,"about_ca_system_score_codex":0.0010003686,"about_ca_system_score_gemma":0.0014426317,"threshold_uncertainty_score":0.08418596},"labels":[],"label_agreement":null},{"id":"W2076017572","doi":"10.1186/1471-2105-12-247","title":"Dissecting protein loops with a statistical scalpel suggests a functional implication of some structural motifs","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Illinois Program for Research in the Humanities, University of Illinois at Urbana-Champaign; Institute of Pharmacy, Nirma University; Institute of Mountain Hazards and Environment; Institut de recherche en santé mentale; Centre for Earth Observation Instrumentation; Institut Pierre-Gilles de Gennes; Jinggangshan University; Institute for Global Prominent Research, Chiba University; Joint Fire Science Program; Critical Ecosystem Partnership Fund; Iran Polymer and Petrochemical Institute; International Pediatric Research Foundation; Josiah Macy Jr. Foundation; Institut de Physique du Globe de Paris; Japan Foundation Endowment Committee; Coalition for Epidemic Preparedness Innovations; James N. Kirby Foundation; Japan Health Sciences Foundation; ITP Foundation","keywords":"Structural motif; Computational biology; Biology; Structural Classification of Proteins database; Structural alignment; Sequence motif; Protein family; Protein function prediction; Hidden Markov model; Protein structure; Sequence alignment; Genetics; Protein function; Peptide sequence; Computer science; Gene; Artificial intelligence; Biochemistry","score_opus":0.01275364778276367,"score_gpt":0.2278553035764588,"score_spread":0.21510165579369514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2076017572","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30386677,0.0003449487,0.69078165,0.00010312708,0.000024803829,0.000059250895,0.0005684314,0.0017632265,0.0024877482],"genre_scores_gemma":[0.7295095,0.0002830941,0.26696092,0.00004050793,0.00003624368,0.000064060194,0.0011798041,0.00031630832,0.0016095527],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998692,0.00001554983,0.0000061126507,0.000046549165,0.00003782212,0.00002474047],"domain_scores_gemma":[0.99928856,0.00039036194,0.000094592135,0.00006931367,0.000113821014,0.00004333388],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003220878,0.00030738738,0.0002124445,0.0010702999,0.00019233293,0.00036392317,0.00037281108,0.0002620866,0.0046124742],"category_scores_gemma":[0.0011156736,0.00014811107,0.0005072583,0.0007747222,0.00037344624,0.0004257405,0.00024868728,0.000354686,0.00075147854],"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":[0.00067665096,0.00010907327,0.027308246,0.0007384389,0.00011767512,0.0009235404,0.00037694752,0.04416258,0.49224737,0.010543407,0.0026203885,0.42017564],"study_design_scores_gemma":[0.00006898703,0.0004996915,0.04867932,0.00007369743,0.0001609037,0.0019442936,0.00028684703,0.7794179,0.13603319,0.020137472,0.012638405,0.000059352056],"about_ca_topic_score_codex":0.0012886445,"about_ca_topic_score_gemma":0.0018913661,"teacher_disagreement_score":0.0046124742,"about_ca_system_score_codex":0.00018745447,"about_ca_system_score_gemma":0.00039369956,"threshold_uncertainty_score":0.015430272},"labels":[],"label_agreement":null},{"id":"W2076426906","doi":"10.1186/1471-2105-15-114","title":"Biological relevance of CNV calling methods using familial relatedness including monozygotic twins","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomic variations and chromosomal abnormalities","field":"Biochemistry, Genetics and Molecular Biology","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Canadian Institutes of Health Research","keywords":"Copy-number variation; SNP array; Copy number analysis; SNP genotyping; Genotyping; Genetics; Biology; SNP; Computational biology; Computer science; Genomics; Single-nucleotide polymorphism; Genome; Gene; Genotype","score_opus":0.06364412042526461,"score_gpt":0.31840111189524806,"score_spread":0.25475699146998343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2076426906","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8073811,0.0018660984,0.18281887,0.0005599451,0.00027171907,0.00033866393,0.0007492965,0.0013086346,0.0047056316],"genre_scores_gemma":[0.860863,0.00037598234,0.13636786,0.00017770017,0.000054862943,0.0002050975,0.0009782257,0.00040587527,0.0005712806],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9896796,0.0044997507,0.000721616,0.0027997734,0.0019632513,0.0003361263],"domain_scores_gemma":[0.97642773,0.016072351,0.0013631046,0.0029703146,0.002636069,0.0005303368],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015169874,0.00070196326,0.0006430038,0.0017027347,0.0013035255,0.001275732,0.0008956272,0.0007853474,0.0017550355],"category_scores_gemma":[0.039367598,0.00036431488,0.0009783141,0.0011087023,0.00066084345,0.0005514893,0.0012653563,0.0009719205,0.0005898954],"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":[0.0012309037,0.0002860537,0.7122713,0.0005883942,0.0016145289,0.0014332349,0.0028080945,0.006754409,0.060162038,0.0035829998,0.0031182417,0.20614983],"study_design_scores_gemma":[0.00016812792,0.0007627507,0.74200886,0.00041912598,0.0020840943,0.010324713,0.0012132955,0.11346789,0.100889206,0.014421517,0.01397162,0.00026884835],"about_ca_topic_score_codex":0.003499788,"about_ca_topic_score_gemma":0.004803375,"teacher_disagreement_score":0.015169874,"about_ca_system_score_codex":0.0006300444,"about_ca_system_score_gemma":0.00096497784,"threshold_uncertainty_score":0.0802269},"labels":[],"label_agreement":null},{"id":"W2076460489","doi":"10.1186/1471-2105-10-414","title":"Modular prediction of protein structural classes from sequences of twilight-zone identity with predicting sequences","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":96,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Benchmark (surveying); Artificial intelligence; Support vector machine; Modular design; Similarity (geometry); Feature selection; Feature (linguistics); Pattern recognition (psychology); Class (philosophy); Sequence (biology); Contrast (vision); Data mining; Machine learning; Biology; Image (mathematics)","score_opus":0.01020080503328411,"score_gpt":0.24509219230986357,"score_spread":0.23489138727657946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2076460489","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79488647,0.0008885558,0.19471556,0.00026592964,0.00006936587,0.00017990799,0.0024710412,0.0038187506,0.0027043691],"genre_scores_gemma":[0.88776636,0.00021188709,0.103472844,0.000099118355,0.000056097928,0.00013055479,0.006867981,0.00008492981,0.0013102834],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99963033,0.000046401365,0.00002503166,0.00012235268,0.00012697343,0.00004883596],"domain_scores_gemma":[0.99897826,0.00030087086,0.00022620546,0.00011343225,0.00029769642,0.00008356666],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006842242,0.00071775576,0.00043842322,0.0013373608,0.00027107913,0.0005562503,0.0006225752,0.00045781466,0.0014151946],"category_scores_gemma":[0.0015890896,0.000121788886,0.00066097674,0.0007612478,0.00020714823,0.0005808901,0.00050530024,0.0007411414,0.0009402703],"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":[0.0012257874,0.0006638173,0.15541808,0.00036968847,0.00022123498,0.00025479877,0.00013405252,0.089862645,0.098246396,0.0013591774,0.011524064,0.64072025],"study_design_scores_gemma":[0.00004179334,0.00039630034,0.035973612,0.000042361506,0.00006981428,0.00029999742,0.00008138883,0.9179043,0.03967698,0.0021175402,0.003369877,0.000026154254],"about_ca_topic_score_codex":0.0017948245,"about_ca_topic_score_gemma":0.0028324558,"teacher_disagreement_score":0.0017948245,"about_ca_system_score_codex":0.00034080035,"about_ca_system_score_gemma":0.0007477426,"threshold_uncertainty_score":0.0047342777},"labels":[],"label_agreement":null},{"id":"W2077350268","doi":"10.1186/1471-2105-15-s6-i1","title":"Knowledge Discovery and interactive Data Mining in Bioinformatics - State-of-the-Art, future challenges and research directions","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":223,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; Discovery Centre; University Health Network","funders":"","keywords":"Data science; State (computer science); Computer science; World Wide Web; Bioinformatics; Biology","score_opus":0.06287523198941182,"score_gpt":0.34551861865405353,"score_spread":0.2826433866646417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077350268","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006498812,0.6616751,0.19022812,0.13348961,0.0021239114,0.00018593429,0.00047661547,0.0013414427,0.003980405],"genre_scores_gemma":[0.061037954,0.6039002,0.30849504,0.0100062145,0.011484211,0.00041083238,0.0012419702,0.00035338572,0.0030702085],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98347855,0.009558967,0.0011686648,0.0014748623,0.003621529,0.0006974039],"domain_scores_gemma":[0.9071623,0.08071096,0.0015286959,0.0031194142,0.0050225095,0.002456072],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04148045,0.0013972378,0.0029252672,0.0037220304,0.0020426773,0.011776411,0.0071209697,0.007434176,0.0047665667],"category_scores_gemma":[0.03216751,0.0013618233,0.0016398606,0.009374736,0.009313778,0.029784076,0.005089097,0.0075349216,0.0023137487],"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":[0.0006199392,0.00055339106,0.0031335386,0.008073018,0.00019661606,0.00021497332,0.00101824,0.0068877293,0.002067341,0.10134235,0.04732186,0.82857096],"study_design_scores_gemma":[0.00013413344,0.0004194904,0.002142064,0.005754825,0.00021931219,0.00068180007,0.0016767585,0.066703275,0.0038375107,0.6695781,0.24855745,0.00029537347],"about_ca_topic_score_codex":0.0033105782,"about_ca_topic_score_gemma":0.002709518,"teacher_disagreement_score":0.04148045,"about_ca_system_score_codex":0.002647214,"about_ca_system_score_gemma":0.0066117616,"threshold_uncertainty_score":0.21937221},"labels":[],"label_agreement":null},{"id":"W2079137604","doi":"10.1186/1471-2105-11-s6-s14","title":"Discovering gene functional relationships using FAUN (Feature Annotation Using Nonnegative matrix factorization)","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institutes of Health; University of British Columbia; Oak Ridge National Laboratory; Eunice Kennedy Shriver National Institute of Child Health and Human Development; University of Memphis","keywords":"Annotation; Non-negative matrix factorization; Computer science; Gene Annotation; Software; Feature (linguistics); Set (abstract data type); Genome; Field (mathematics); Data mining; Information retrieval; Computational biology; Gene; Matrix decomposition; Biology; Artificial intelligence; Genetics; Mathematics","score_opus":0.05097628625394497,"score_gpt":0.2947423372471521,"score_spread":0.24376605099320714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2079137604","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016022775,0.00026894495,0.97571564,0.00013907325,0.000030722516,0.00009145985,0.001131991,0.0059174774,0.00068196224],"genre_scores_gemma":[0.064533204,0.00012271313,0.932885,0.00006451633,0.000019963749,0.00015090719,0.0017289119,0.00013522847,0.0003594827],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993144,0.00015826299,0.00006865036,0.00022571711,0.00018363977,0.00004930037],"domain_scores_gemma":[0.99757653,0.0014916065,0.00032727708,0.00019244068,0.00034989865,0.00006235414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018430094,0.0010103378,0.00070076925,0.0036301163,0.00078188226,0.00089841685,0.0006985852,0.00065373455,0.0031728428],"category_scores_gemma":[0.006362335,0.00031976646,0.001455424,0.0018935936,0.0004784678,0.0013064239,0.0008626156,0.0006479245,0.0008726494],"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":[0.0005289541,0.00021486286,0.010701301,0.0007370821,0.00017211975,0.0005471943,0.00068461476,0.041038066,0.052266054,0.010637117,0.0127900755,0.86968243],"study_design_scores_gemma":[0.0000711433,0.00017245578,0.0068348236,0.00009476167,0.00009070395,0.0010511206,0.00016730632,0.9070336,0.022195706,0.045188654,0.016993802,0.000105928935],"about_ca_topic_score_codex":0.0039244615,"about_ca_topic_score_gemma":0.004940661,"teacher_disagreement_score":0.0039244615,"about_ca_system_score_codex":0.0005483718,"about_ca_system_score_gemma":0.00083734526,"threshold_uncertainty_score":0.010614216},"labels":[],"label_agreement":null},{"id":"W2080569293","doi":"10.1186/1471-2105-10-442","title":"G+C content dominates intrinsic nucleosome occupancy","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":281,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Canadian Institutes of Health Research; Genome Canada; Ontario Genomics; Ontario Genomics Institute; Canadian Institute for Advanced Research; Howard Hughes Medical Institute","keywords":"Nucleosome; Chromatin; Linker DNA; Biology; DNA; Genome; Genetics; Histone; DNA sequencing; GC-content; Computational biology; DNA microarray; Sequence (biology); Biophysics; Biological system; Gene","score_opus":0.01536453061776141,"score_gpt":0.22552557151633804,"score_spread":0.21016104089857662,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2080569293","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.950204,0.0008694571,0.044681013,0.00014753609,0.000029683222,0.000022502994,0.0011013374,0.0008256837,0.0021187179],"genre_scores_gemma":[0.9943586,0.00020372034,0.0043224855,0.00006040396,0.000010581776,0.000009816248,0.0007050136,0.000075057105,0.0002543992],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99970335,0.000046395155,0.000013002224,0.0001423652,0.000055559776,0.000039349492],"domain_scores_gemma":[0.99915385,0.00041909833,0.00018812747,0.00008586883,0.00008283306,0.0000703753],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041213658,0.0005599673,0.0006499701,0.00036226565,0.00031340632,0.0005760204,0.00048669474,0.0005784803,0.0015733608],"category_scores_gemma":[0.0017558777,0.00029948214,0.00055120996,0.00047229967,0.00037242548,0.00046753656,0.0002999316,0.00032817601,0.00051060726],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011206124,0.00010687754,0.27295887,0.0013789764,0.0005699426,0.0005848785,0.00021890711,0.26891884,0.40520018,0.0065129297,0.002324195,0.040104803],"study_design_scores_gemma":[0.000058041394,0.00024319284,0.1405708,0.000056337954,0.00038386628,0.00075119565,0.000086938795,0.7782287,0.06348582,0.012861969,0.0031875207,0.000085645974],"about_ca_topic_score_codex":0.0070612975,"about_ca_topic_score_gemma":0.0070891883,"teacher_disagreement_score":0.0070612975,"about_ca_system_score_codex":0.00076317735,"about_ca_system_score_gemma":0.0005893096,"threshold_uncertainty_score":0.0140404105},"labels":[],"label_agreement":null},{"id":"W2080867027","doi":"10.1186/1471-2105-12-s9-s9","title":"Detecting genomic regions associated with a disease using variability functions and Adjusted Rand Index","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computational biology; Biology; Identification (biology); Functional genomics; DNA microarray; Genetics; Function (biology); Genomics; Bioinformatics; Genome; Gene","score_opus":0.03697424106330998,"score_gpt":0.2178551642141747,"score_spread":0.1808809231508647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2080867027","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25375187,0.0008671032,0.7418501,0.00030557858,0.000032998505,0.00013275248,0.0004672172,0.0013638028,0.0012285287],"genre_scores_gemma":[0.63095516,0.00017655536,0.36680716,0.00010235963,0.000042474636,0.00019543793,0.0009515337,0.00018739079,0.0005819422],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981597,0.0006443106,0.00015110301,0.00056947663,0.00035601322,0.00011933856],"domain_scores_gemma":[0.986419,0.00984245,0.0018341274,0.0007459064,0.0008322437,0.00032621232],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00500901,0.0010908834,0.0010577943,0.0037348114,0.00063434214,0.0012137786,0.0011992679,0.0014722337,0.0015012937],"category_scores_gemma":[0.013829141,0.00027508446,0.0015389359,0.0015343664,0.0009875849,0.0010940436,0.0010003691,0.0010952814,0.0003634274],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010021566,0.00025187404,0.08059192,0.00029384304,0.0003960083,0.00028873645,0.00023162027,0.642626,0.012980849,0.00587199,0.0019439934,0.25352105],"study_design_scores_gemma":[0.000025433514,0.00016808948,0.009651096,0.000022979018,0.000049636623,0.00019610838,0.00003004312,0.98001343,0.0038780114,0.0054298234,0.0004927776,0.00004250969],"about_ca_topic_score_codex":0.0023887167,"about_ca_topic_score_gemma":0.0015102244,"teacher_disagreement_score":0.00500901,"about_ca_system_score_codex":0.0009587352,"about_ca_system_score_gemma":0.0007684939,"threshold_uncertainty_score":0.02649051},"labels":[],"label_agreement":null},{"id":"W2082220672","doi":"10.1186/1471-2105-8-358","title":"Combining classifiers to predict gene function in Arabidopsis thaliana using large-scale gene expression measurements","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto; Ontario Genomics; Ontario Genomics Institute; Genome Canada","keywords":"Arabidopsis thaliana; DNA microarray; Computational biology; Gene expression; Biology; Gene; Genetics; Function (biology); Arabidopsis; Scale (ratio); Mutant; Geography; Cartography","score_opus":0.04853023466139118,"score_gpt":0.28517308430739813,"score_spread":0.23664284964600696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082220672","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6855242,0.0007931001,0.30988804,0.00013011292,0.000051501585,0.000109702734,0.0007549015,0.001925691,0.0008226913],"genre_scores_gemma":[0.8655185,0.00014550629,0.13210194,0.00006538953,0.000026770502,0.00013622646,0.0015502477,0.00005437671,0.0004011107],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99921536,0.00021971531,0.000065020795,0.00027950338,0.00015654259,0.00006387017],"domain_scores_gemma":[0.99698347,0.0020766852,0.00023484195,0.00017321047,0.0004710608,0.00006070433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024840909,0.0011607009,0.00060800405,0.0013377538,0.00029786414,0.00061138516,0.0005803555,0.0007659828,0.00034200412],"category_scores_gemma":[0.0030945837,0.00025318775,0.0007818398,0.00063565845,0.00025030223,0.0005270256,0.00039023167,0.0006717626,0.0003206686],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00073306187,0.0006310668,0.075406596,0.00032542224,0.00075353036,0.00025631458,0.00014286619,0.46023473,0.12909654,0.0005295841,0.0013283622,0.33056197],"study_design_scores_gemma":[0.000012702826,0.0001467752,0.012613292,0.0000129221135,0.00007477644,0.000062834486,0.000032497068,0.9582588,0.027470084,0.0009588671,0.0003351802,0.000021273636],"about_ca_topic_score_codex":0.0017879315,"about_ca_topic_score_gemma":0.001951227,"teacher_disagreement_score":0.0024840909,"about_ca_system_score_codex":0.0007446706,"about_ca_system_score_gemma":0.00040952157,"threshold_uncertainty_score":0.013137341},"labels":[],"label_agreement":null},{"id":"W2082395827","doi":"10.1186/1471-2105-8-308","title":"Analysis of the role of retrotransposition in gene evolution in vertebrates","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Chromosomal and Genetic Variations","field":"Agricultural and Biological Sciences","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Retrotransposon; Biology; Pseudogene; Gene; Genetics; Genome; Genome evolution; Human genome; Negative selection; Evolutionary biology; Transposable element","score_opus":0.008255408423635808,"score_gpt":0.19695447435050886,"score_spread":0.18869906592687305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082395827","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99455476,0.00049182895,0.004178738,0.000013646626,0.0000019207268,0.000007871293,0.00028741529,0.000030414583,0.000433452],"genre_scores_gemma":[0.99515766,0.00016301626,0.003842093,0.000006702841,0.000004722325,0.000010198821,0.000592022,0.000013044888,0.00021047221],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99979573,0.00003923022,0.000022731641,0.00007456212,0.000045952074,0.000021738044],"domain_scores_gemma":[0.9991836,0.00042571328,0.00021169684,0.00003713622,0.000069541566,0.00007235614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050718675,0.00021590044,0.00019720627,0.0009386708,0.00018321436,0.00036143168,0.00021446566,0.00022533555,0.0011227385],"category_scores_gemma":[0.00088911754,0.000080586426,0.00038383206,0.0008847737,0.00021904446,0.00020648939,0.00019757403,0.0002630662,0.0002969135],"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":[0.00081747904,0.000056504767,0.6134132,0.00032666462,0.00031390743,0.00029601483,0.00026567894,0.0056588543,0.34356675,0.0009416967,0.00008897895,0.034254223],"study_design_scores_gemma":[0.000013230018,0.00039499463,0.9207185,0.000034559453,0.0002214193,0.0012905084,0.00020994646,0.022555456,0.051628783,0.00090722356,0.0020074877,0.000017860126],"about_ca_topic_score_codex":0.0006341771,"about_ca_topic_score_gemma":0.00068136683,"teacher_disagreement_score":0.0011227385,"about_ca_system_score_codex":0.00022862741,"about_ca_system_score_gemma":0.00015195606,"threshold_uncertainty_score":0.003755927},"labels":[],"label_agreement":null},{"id":"W2082852695","doi":"10.1186/1471-2105-12-414","title":"Three-dimensional modeling of chromatin structure from interaction frequency data using Markov chain Monte Carlo sampling","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":182,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University Health Centre; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Cancer Society Research Institute; Canadian Institutes of Health Research","keywords":"Chromatin; Markov chain Monte Carlo; Chromosome conformation capture; Computational biology; Chromosome; Computer science; Monte Carlo method; Biology; Algorithm; Enhancer; Genetics; Artificial intelligence; DNA; Bayesian probability; Transcription factor; Gene; Mathematics; Statistics","score_opus":0.06652223994272753,"score_gpt":0.26597249007886103,"score_spread":0.1994502501361335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082852695","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18183808,0.0003923479,0.8115792,0.00058663404,0.000053007647,0.0002113718,0.0011698798,0.0012528473,0.0029166515],"genre_scores_gemma":[0.7778251,0.0003469102,0.21549137,0.00024520123,0.00008272074,0.00076642743,0.0026875068,0.00031597924,0.0022387914],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995492,0.00019392384,0.000020594505,0.00008837442,0.000096521704,0.000051363586],"domain_scores_gemma":[0.99472976,0.004297158,0.00027790654,0.00021866098,0.00030515745,0.00017130373],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017905682,0.00068973476,0.000851971,0.00124127,0.00093370286,0.0012126518,0.0019707754,0.0017915699,0.0024514091],"category_scores_gemma":[0.0061259684,0.0009832652,0.001597653,0.0010204123,0.0014038052,0.0008440486,0.00082041346,0.0016478302,0.0004941148],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002486399,0.000014751924,0.0012275731,0.000017413306,0.00002169135,0.00003296316,0.000025241743,0.9934232,0.0003300454,0.0030745885,0.00017862779,0.0016290846],"study_design_scores_gemma":[0.000003905696,0.0000017790152,0.00009374753,0.0000018983194,0.0000014069306,0.000003944209,0.0000016421632,0.9984505,0.000055119577,0.0013241409,0.000059457347,0.0000023520745],"about_ca_topic_score_codex":0.03258531,"about_ca_topic_score_gemma":0.030411655,"teacher_disagreement_score":0.03258531,"about_ca_system_score_codex":0.002285633,"about_ca_system_score_gemma":0.0019416654,"threshold_uncertainty_score":0.06479132},"labels":[],"label_agreement":null},{"id":"W2083274478","doi":"10.1186/1471-2105-14-354","title":"Balony:a software package for analysis of data generated by synthetic genetic array experiments","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Fungal and yeast genetics research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":78,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto; Michael Smith Health Research BC; Canadian Institutes of Health Research; Tula Foundation","keywords":"Software package; Software; DNA microarray; R package; Computer science; Computational biology; Biology; Bioinformatics; Genetics; Programming language; Gene expression; Gene","score_opus":0.04914811403431144,"score_gpt":0.31499361420303784,"score_spread":0.2658455001687264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2083274478","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030543238,0.00060705416,0.48755744,0.00032509497,0.00042169166,0.00093077286,0.08196233,0.42199105,0.003150368],"genre_scores_gemma":[0.013055821,0.00088174467,0.78033596,0.0010050689,0.0001554705,0.009001466,0.089774065,0.099473506,0.0063168216],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9945819,0.0016717449,0.0007845928,0.0009686086,0.0016100219,0.00038326572],"domain_scores_gemma":[0.9908406,0.0059350925,0.00085591426,0.0009831059,0.0010817784,0.00030351742],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009880802,0.0043784915,0.004256711,0.004777924,0.0013451965,0.0032541892,0.004598052,0.001712392,0.102168575],"category_scores_gemma":[0.013566801,0.0031279528,0.0031806598,0.003040219,0.001234344,0.0024391413,0.0032054712,0.005415184,0.051805798],"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":[0.0029089155,0.0005007054,0.0050190277,0.012087598,0.0021825947,0.0014389281,0.0013800444,0.008411985,0.065145954,0.011885687,0.6872509,0.20178773],"study_design_scores_gemma":[0.0020301526,0.0010235318,0.020892253,0.0018030334,0.0011707118,0.0023192808,0.00044509495,0.112383574,0.08077877,0.049751583,0.7264258,0.00097617164],"about_ca_topic_score_codex":0.0018475078,"about_ca_topic_score_gemma":0.002794843,"teacher_disagreement_score":0.102168575,"about_ca_system_score_codex":0.0010909599,"about_ca_system_score_gemma":0.0033755472,"threshold_uncertainty_score":0.34178793},"labels":[],"label_agreement":null},{"id":"W2083366092","doi":"10.1186/1471-2105-10-222","title":"PCI-SS: MISO dynamic nonlinear protein secondary structure prediction","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Protein secondary structure; Conventional PCI; Interface (matter); Nonlinear system; Machine learning; Artificial intelligence; Data mining; Biology; Parallel computing; Physics","score_opus":0.0038572218742912727,"score_gpt":0.21592785593539401,"score_spread":0.21207063406110274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2083366092","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10456729,0.001356522,0.68708134,0.0006372535,0.00047884643,0.00068709895,0.021110578,0.17081796,0.013263129],"genre_scores_gemma":[0.23897,0.000491428,0.6983253,0.00041289828,0.00015170945,0.00086573156,0.046023775,0.0033287217,0.011430457],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999622,0.000043969707,0.000019349669,0.0001214866,0.00015688268,0.000036270634],"domain_scores_gemma":[0.9996294,0.00009847247,0.00005674711,0.00005930395,0.00010372327,0.000052481395],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007913117,0.0014123793,0.0007368901,0.0008773044,0.00042118906,0.00075739104,0.0012825185,0.00079026684,0.00905428],"category_scores_gemma":[0.0013322801,0.0003477706,0.000879934,0.00074944145,0.0002834147,0.0006890518,0.0008363553,0.0010085386,0.004449199],"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":[0.0025331548,0.00061754667,0.024213858,0.0009057969,0.00043261502,0.00064511655,0.00017645558,0.13136737,0.069102496,0.0155322375,0.30665994,0.4478134],"study_design_scores_gemma":[0.0001094425,0.00015977684,0.0026824488,0.00001684699,0.000029947607,0.00014303919,0.000016909573,0.9460664,0.023973215,0.0053201844,0.021452656,0.00002911865],"about_ca_topic_score_codex":0.0025311692,"about_ca_topic_score_gemma":0.003278882,"teacher_disagreement_score":0.00905428,"about_ca_system_score_codex":0.00074742833,"about_ca_system_score_gemma":0.0013073238,"threshold_uncertainty_score":0.03028959},"labels":[],"label_agreement":null},{"id":"W2084063783","doi":"10.1186/1471-2105-8-368","title":"Assessment of algorithms for high throughput detection of genomic copy number variation in oligonucleotide microarray data","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomic variations and chromosomal abnormalities","field":"Biochemistry, Genetics and Molecular Biology","cited_by":55,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; BC Children's Hospital; BC Cancer Agency","funders":"BC Cancer Agency; Michael Smith Health Research BC; Genome British Columbia; Canada's Michael Smith Genome Sciences Centre; Genome Canada","keywords":"Copy-number variation; SNP genotyping; SNP array; Biology; DNA microarray; Genotyping; Single-nucleotide polymorphism; Computational biology; Copy number analysis; Genetics; SNP; Loss of heterozygosity; Genomics; Genome; Genotype; Gene; Allele","score_opus":0.022774831259624703,"score_gpt":0.29166617376329534,"score_spread":0.26889134250367064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084063783","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031863045,0.000219469,0.95655626,0.00017600218,0.00003627659,0.00024923397,0.0004632607,0.010102331,0.0003341512],"genre_scores_gemma":[0.07864432,0.00011550911,0.91838,0.00009244316,0.000021946162,0.000832741,0.0011960575,0.00044897242,0.00026795425],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9906308,0.0044448054,0.0011009158,0.0011735355,0.002375843,0.00027410212],"domain_scores_gemma":[0.93118614,0.0579889,0.0019470715,0.002805075,0.0057489467,0.0003239915],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017084405,0.001967048,0.001717594,0.0036076838,0.00087141094,0.0025148164,0.002705384,0.002364336,0.0020143432],"category_scores_gemma":[0.07377697,0.0007897998,0.0015990387,0.0034541816,0.0007803411,0.0026106914,0.0013727001,0.0018200307,0.0011460722],"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":[0.0017042528,0.0005349677,0.018321257,0.0008694271,0.0008265814,0.0003288861,0.00048127427,0.3428057,0.034969956,0.009471895,0.008317446,0.5813684],"study_design_scores_gemma":[0.000051187057,0.000072855626,0.0018468166,0.000015065997,0.000029198818,0.000109832385,0.000035696346,0.9872335,0.0068247267,0.0031276492,0.0006352632,0.000018252751],"about_ca_topic_score_codex":0.0024499786,"about_ca_topic_score_gemma":0.0019809024,"teacher_disagreement_score":0.017084405,"about_ca_system_score_codex":0.0016787923,"about_ca_system_score_gemma":0.001740393,"threshold_uncertainty_score":0.09035206},"labels":[],"label_agreement":null},{"id":"W2084339286","doi":"10.1186/s12859-015-0540-1","title":"OpenMS-Simulator: an open-source software for theoretical tandem mass spectrum prediction","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","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":"National Key Research and Development Program of China; University of Waterloo; National Natural Science Foundation of China","keywords":"Computer science; Computation; Software; Tandem mass spectrometry; Similarity (geometry); Simulation; Data mining; Artificial intelligence; Mass spectrometry; Algorithm; Chemistry","score_opus":0.03403832030887243,"score_gpt":0.3039335129003802,"score_spread":0.26989519259150774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084339286","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011854324,0.0004897409,0.5423822,0.00026315777,0.00027393596,0.00032061042,0.009454238,0.4321415,0.0028204033],"genre_scores_gemma":[0.1619899,0.00153652,0.66061854,0.0010303973,0.00020494858,0.0024196184,0.05953091,0.1040959,0.008573327],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991385,0.00014508748,0.000110246176,0.00020315313,0.00031206833,0.000090857524],"domain_scores_gemma":[0.9978167,0.0011724893,0.0002044998,0.00025109758,0.00037473594,0.00018056476],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020261768,0.002747485,0.0013740977,0.0017038276,0.00077193737,0.0014076091,0.006204746,0.0019305302,0.020664973],"category_scores_gemma":[0.006269965,0.001587584,0.002275537,0.0010644884,0.00078283245,0.002385047,0.0024579861,0.003683085,0.008436427],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002792916,0.0011328491,0.015096807,0.0043501635,0.0013912506,0.0019840735,0.001255206,0.33641487,0.049108174,0.031621817,0.30391154,0.25094035],"study_design_scores_gemma":[0.00031259184,0.00011512022,0.0011208158,0.000108633336,0.00008415534,0.00027338043,0.000055184795,0.9102906,0.02072266,0.01021475,0.05655701,0.00014520425],"about_ca_topic_score_codex":0.0035602415,"about_ca_topic_score_gemma":0.0030755233,"teacher_disagreement_score":0.020664973,"about_ca_system_score_codex":0.0008489431,"about_ca_system_score_gemma":0.0028009443,"threshold_uncertainty_score":0.069131196},"labels":[],"label_agreement":null},{"id":"W2084455604","doi":"10.1186/1471-2105-10-115","title":"Most parsimonious haplotype allele sharing determination","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Agricultural Research Institute","keywords":"Haplotype; Genetics; Pedigree chart; Single-nucleotide polymorphism; Biology; Allele; Haplotype estimation; Genetic association; Linkage disequilibrium; Genotype; Computational biology; Gene","score_opus":0.01855987131325696,"score_gpt":0.26849910023989476,"score_spread":0.2499392289266378,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084455604","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.060407665,0.0005421294,0.92986596,0.00040865078,0.00009753621,0.0004025789,0.0022159037,0.0020336467,0.00402607],"genre_scores_gemma":[0.31246787,0.00022230473,0.6771674,0.0002069294,0.00011475518,0.00071600446,0.004707029,0.0003993554,0.00399826],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99861836,0.0007175173,0.00008715187,0.00032348593,0.00015980809,0.0000937327],"domain_scores_gemma":[0.9932319,0.0050794813,0.00022809116,0.0010307543,0.0002860929,0.00014372652],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030307367,0.00092443795,0.0012202023,0.0022126797,0.0010761674,0.0008255545,0.0022942098,0.0012554617,0.014310734],"category_scores_gemma":[0.01725567,0.0005962742,0.001260993,0.0023149797,0.00051033136,0.001091804,0.001358938,0.0012107735,0.0028963443],"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":[0.0016228575,0.00045209719,0.013170018,0.0005339671,0.00038454507,0.0007910971,0.0005776425,0.3373079,0.0030968955,0.0184767,0.015519671,0.6080667],"study_design_scores_gemma":[0.00037434007,0.00013877728,0.0025484671,0.00006577624,0.00017411701,0.00061386003,0.00007953425,0.931204,0.0013973241,0.058103997,0.005249874,0.000049869992],"about_ca_topic_score_codex":0.0028864737,"about_ca_topic_score_gemma":0.0052397707,"teacher_disagreement_score":0.014310734,"about_ca_system_score_codex":0.0004924137,"about_ca_system_score_gemma":0.0018880607,"threshold_uncertainty_score":0.047874212},"labels":[],"label_agreement":null},{"id":"W2084771278","doi":"10.1186/1471-2105-9-255","title":"Protein contact order prediction from primary sequences","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Protein Data Bank (RCSB PDB); Protein secondary structure; Protein structure prediction; Sequence (biology); Contact order; Protein structure; Protein folding; Matthews correlation coefficient; Protein Data Bank; Protein sequencing; Similarity (geometry); Computer science; Folding (DSP implementation); Order (exchange); Peptide sequence; Bioinformatics; Biology; Artificial intelligence; Genetics; Engineering; Biochemistry","score_opus":0.010084148967345701,"score_gpt":0.2092890452395811,"score_spread":0.19920489627223542,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084771278","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6823909,0.0044086413,0.27961472,0.00032672397,0.000100800054,0.00028489763,0.019949587,0.006624008,0.006299682],"genre_scores_gemma":[0.8447548,0.0011375089,0.12285756,0.00006549133,0.00008910882,0.00020356364,0.029123636,0.0002736452,0.0014946562],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99941146,0.000086122105,0.000050626353,0.00015586165,0.00024817607,0.000047753485],"domain_scores_gemma":[0.9967843,0.0013416094,0.00064713234,0.00021001877,0.000811312,0.00020556008],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005574429,0.0008991782,0.0008674262,0.0034387494,0.00036160005,0.00049686007,0.00045212943,0.0005259116,0.003517788],"category_scores_gemma":[0.0036481337,0.00020973025,0.0006793947,0.0019938443,0.00033022606,0.00055664405,0.0003355703,0.00045459642,0.0034030653],"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":[0.0028056914,0.0005975126,0.18212435,0.0041979784,0.00039835233,0.002304571,0.00035849027,0.06815626,0.45554945,0.003951093,0.015393425,0.2641628],"study_design_scores_gemma":[0.00015282935,0.00089081295,0.13875753,0.000262795,0.00029871525,0.0036733164,0.00018337127,0.61096287,0.2133444,0.011252162,0.020126848,0.0000943701],"about_ca_topic_score_codex":0.0011079726,"about_ca_topic_score_gemma":0.001225903,"teacher_disagreement_score":0.003517788,"about_ca_system_score_codex":0.0005117852,"about_ca_system_score_gemma":0.0007451086,"threshold_uncertainty_score":0.011768162},"labels":[],"label_agreement":null},{"id":"W2087450928","doi":"10.1186/1471-2105-10-184","title":"FuGEFlow: data model and markup language for flow cytometry","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; BC Cancer Agency","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institute of Allergy and Infectious Diseases; National Institutes of Health; Michael Smith Health Research BC","keywords":"Markup language; Computer science; Metadata; Data flow diagram; Database; World Wide Web; XML","score_opus":0.03626515090075776,"score_gpt":0.2830928028498879,"score_spread":0.24682765194913014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087450928","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00092720677,0.00023898955,0.9187573,0.0003278991,0.00011688849,0.00044167094,0.0070817056,0.06935873,0.0027495585],"genre_scores_gemma":[0.018692322,0.000754207,0.90743345,0.00088636397,0.0000953421,0.0025786203,0.04094967,0.02283931,0.0057706055],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99491656,0.0010353897,0.0012638278,0.0008264134,0.0016438892,0.00031399168],"domain_scores_gemma":[0.99227107,0.004061743,0.0006115014,0.0014586765,0.001322609,0.0002743963],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008522219,0.0029313136,0.0012541554,0.00418584,0.0012933299,0.0062583676,0.0061095026,0.003739669,0.016391136],"category_scores_gemma":[0.016341845,0.0024841712,0.0033437663,0.0021486671,0.0018925023,0.005983253,0.0038199103,0.005339598,0.012076331],"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":[0.0012352235,0.00040113291,0.00359911,0.0050723944,0.00028774337,0.0026323441,0.004066025,0.05371901,0.044372838,0.3415358,0.21741484,0.3256636],"study_design_scores_gemma":[0.00018173577,0.00012452362,0.000613947,0.0008698204,0.00008976364,0.0010884852,0.00013914617,0.0638762,0.026995385,0.07690275,0.82885706,0.0002611189],"about_ca_topic_score_codex":0.007304624,"about_ca_topic_score_gemma":0.004624733,"teacher_disagreement_score":0.016391136,"about_ca_system_score_codex":0.0024399047,"about_ca_system_score_gemma":0.004352686,"threshold_uncertainty_score":0.05483377},"labels":[],"label_agreement":null},{"id":"W2087932775","doi":"10.1186/1471-2105-11-403","title":"Data reduction for spectral clustering to analyze high throughput flow cytometry data","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":166,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"National Institute of Biomedical Imaging and Bioengineering; Mitacs; National Institutes of Health; Michael Smith Health Research BC","keywords":"Throughput; Computer science; Cluster analysis; Reduction (mathematics); Flow cytometry; Data reduction; Data mining; Computational biology; Biology; Mathematics; Artificial intelligence; Molecular biology; Telecommunications","score_opus":0.054617542012774634,"score_gpt":0.3018674232321299,"score_spread":0.24724988121935526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087932775","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0061383313,0.000059519716,0.98800886,0.00012171956,0.000041907395,0.00016070892,0.00031759517,0.0048793387,0.00027194075],"genre_scores_gemma":[0.023331799,0.000053451804,0.9741027,0.00005083129,0.000024107461,0.0004719672,0.001115049,0.00049047905,0.0003597104],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99813676,0.0004710899,0.0001655323,0.0003460692,0.0007646879,0.000115790725],"domain_scores_gemma":[0.99609154,0.0014263793,0.00027320677,0.00077761407,0.0013000832,0.00013103729],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002898488,0.0015865709,0.0011077615,0.0036213412,0.0015127267,0.0015123088,0.0020787022,0.0011201239,0.004738255],"category_scores_gemma":[0.010870124,0.0005593837,0.0029385483,0.0035814818,0.0007850493,0.0010519054,0.0017833853,0.002204062,0.004586887],"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":[0.0005499668,0.00060242834,0.004400041,0.000751551,0.0005211311,0.00026767008,0.0006478852,0.07984522,0.09912996,0.014587559,0.020807656,0.77788883],"study_design_scores_gemma":[0.000058486163,0.00011053155,0.0049309977,0.00003170901,0.000063776075,0.00030598097,0.00017131121,0.9156349,0.044688474,0.019094266,0.014812403,0.00009723967],"about_ca_topic_score_codex":0.0035716475,"about_ca_topic_score_gemma":0.004137075,"teacher_disagreement_score":0.004738255,"about_ca_system_score_codex":0.0011370134,"about_ca_system_score_gemma":0.0020027412,"threshold_uncertainty_score":0.01585102},"labels":[],"label_agreement":null},{"id":"W2087937056","doi":"10.1186/1471-2105-10-287","title":"Epitopia: a web-server for predicting B-cell epitopes","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"vaccines and immunoinformatics approaches","field":"Biochemistry, Genetics and Molecular Biology","cited_by":232,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Tel Aviv University; Killam Trusts","keywords":"Epitope; Computer science; Web server; Web application; Interface (matter); Sequence (biology); Computational biology; Graphical user interface; Data mining; Bioinformatics; Antigen; Biology; The Internet; Operating system; Immunology; Genetics","score_opus":0.015221118561711447,"score_gpt":0.2332089179338898,"score_spread":0.21798779937217833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087937056","genre_codex":"software","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07762764,0.0058054626,0.30531225,0.0011814709,0.00057160866,0.001112919,0.17026041,0.4052571,0.032871097],"genre_scores_gemma":[0.18699212,0.002664834,0.37839198,0.00061464234,0.00025863087,0.0014015074,0.37947786,0.017706677,0.03249175],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997129,0.000051938558,0.000031136085,0.000059888305,0.000105569765,0.000038601287],"domain_scores_gemma":[0.9993061,0.00027889953,0.00006650505,0.00007652984,0.00015748222,0.00011447684],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007680455,0.0014519478,0.0009198183,0.0013583454,0.00053416664,0.000967026,0.0020137979,0.0010819276,0.03162585],"category_scores_gemma":[0.0027085044,0.00064112706,0.0006786961,0.0010999071,0.0002674336,0.0018932257,0.0010812408,0.0011004233,0.01898587],"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":[0.0064865495,0.00042992475,0.0077889124,0.002918826,0.00036577473,0.0019287607,0.00030430153,0.018299222,0.07846796,0.0074034957,0.5919305,0.28367576],"study_design_scores_gemma":[0.0022908514,0.00081859966,0.02578714,0.00064419786,0.0003378753,0.0038920434,0.0002702353,0.3863706,0.10685634,0.019156363,0.4530917,0.00048401175],"about_ca_topic_score_codex":0.0028378966,"about_ca_topic_score_gemma":0.0024945757,"teacher_disagreement_score":0.03162585,"about_ca_system_score_codex":0.0004885852,"about_ca_system_score_gemma":0.0010631254,"threshold_uncertainty_score":0.10579896},"labels":[],"label_agreement":null},{"id":"W2090242275","doi":"10.1186/1471-2105-9-450","title":"Bluejay 1.0: genome browsing and comparison with rich customization provision and dynamic resource linking","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children; University of Calgary","funders":"Genome Canada; Genome Alberta; University of Calgary","keywords":"Personalization; Resource (disambiguation); Computer science; World Wide Web; Genome; DNA microarray; Computational biology; Biology; Data science; Genetics; Gene","score_opus":0.015214036059689802,"score_gpt":0.24463081578491097,"score_spread":0.22941677972522118,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2090242275","genre_codex":"software","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30663013,0.001344306,0.092535295,0.0010812739,0.00050044246,0.000839961,0.20153952,0.35975984,0.035769243],"genre_scores_gemma":[0.25733298,0.0005949535,0.2687895,0.00063607394,0.00006183349,0.0007489352,0.41336143,0.0502222,0.008252103],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99892056,0.000153776,0.0000665933,0.00031835973,0.00036323507,0.00017753892],"domain_scores_gemma":[0.99857974,0.00042169017,0.00008239338,0.0003901773,0.00034070824,0.00018530311],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018298642,0.0010644053,0.0005903055,0.0026290282,0.0010581793,0.0018449366,0.0021700684,0.00090608513,0.013708968],"category_scores_gemma":[0.003027521,0.0006893086,0.0010816591,0.0027312448,0.00043283342,0.0020311312,0.0022034706,0.0012576621,0.006035421],"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":[0.0074799997,0.0018123443,0.034583807,0.0027291423,0.00073068513,0.0017138455,0.0033694208,0.018136956,0.11936879,0.007981828,0.5822759,0.21981724],"study_design_scores_gemma":[0.0016474961,0.0009576742,0.100705266,0.00047956032,0.0003136718,0.0023529257,0.0018789982,0.1353995,0.113390446,0.0076605934,0.63443726,0.0007766621],"about_ca_topic_score_codex":0.02404372,"about_ca_topic_score_gemma":0.021892633,"teacher_disagreement_score":0.02404372,"about_ca_system_score_codex":0.00074475957,"about_ca_system_score_gemma":0.0013224857,"threshold_uncertainty_score":0.047807515},"labels":[],"label_agreement":null},{"id":"W2091244202","doi":"10.1186/1471-2105-13-199","title":"Normalization of ChIP-seq data with control","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":122,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Cancer Institute; National Human Genome Research Institute; National Institutes of Health","keywords":"Normalization (sociology); Chip; Computer science; False discovery rate; DNA microarray; Data mining; Computational biology; Biology; Genetics; Gene","score_opus":0.012600498616690542,"score_gpt":0.2263756072074164,"score_spread":0.21377510859072585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2091244202","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009815662,0.00041197494,0.98282856,0.00009834678,0.00032385197,0.00042287653,0.0011799384,0.004078644,0.0008400586],"genre_scores_gemma":[0.120904386,0.000552274,0.8623014,0.0004583752,0.00017518453,0.0045242347,0.006152527,0.0027997186,0.002131887],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98313016,0.004012739,0.0013415762,0.0056690234,0.005306953,0.00053957355],"domain_scores_gemma":[0.9681424,0.014571861,0.0017625296,0.0101715475,0.005097627,0.00025409745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018961051,0.002272015,0.002008122,0.002141496,0.0011105668,0.0019083467,0.003532187,0.0017198191,0.0069039334],"category_scores_gemma":[0.05725237,0.0011053229,0.0018813718,0.0039732247,0.0024749541,0.0013590177,0.0021084694,0.0032592148,0.0028556772],"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":[0.0032329618,0.00082740304,0.03230825,0.003483375,0.001550423,0.0005662591,0.0010634206,0.13490516,0.35574788,0.03577091,0.018984942,0.41155908],"study_design_scores_gemma":[0.00028032486,0.00042052363,0.025670908,0.00023213479,0.0003768489,0.0006335198,0.00012073215,0.5153519,0.37669685,0.03137278,0.04850886,0.000334615],"about_ca_topic_score_codex":0.0019199791,"about_ca_topic_score_gemma":0.0018794817,"teacher_disagreement_score":0.018961051,"about_ca_system_score_codex":0.00184049,"about_ca_system_score_gemma":0.002096577,"threshold_uncertainty_score":0.10027683},"labels":[],"label_agreement":null},{"id":"W2091723965","doi":"10.1186/1471-2105-11-229","title":"GOAL: A software tool for assessing biological significance of genes groups","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"National Research Council Canada","keywords":"DNA microarray; Computational biology; Software; Biology; Gene; Genetics; Bioinformatics; Computer science; Gene expression; Programming language","score_opus":0.01928520424911289,"score_gpt":0.26124994545107205,"score_spread":0.24196474120195915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2091723965","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0070441198,0.00030274715,0.57792443,0.00033445156,0.00013701788,0.0005021757,0.013095361,0.39777467,0.0028850164],"genre_scores_gemma":[0.058891505,0.00048853987,0.8593725,0.0007693434,0.00010202623,0.0026521448,0.03836487,0.03574564,0.0036133393],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99746513,0.0005971762,0.00033674107,0.0005499462,0.0008856729,0.00016541994],"domain_scores_gemma":[0.99212235,0.005215754,0.00069278956,0.0006389189,0.0010155606,0.0003144846],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0056499047,0.0035587312,0.0015599204,0.006939821,0.0010487854,0.0026985186,0.0040275534,0.0015879128,0.017346151],"category_scores_gemma":[0.014019062,0.0014106997,0.0024555332,0.0032075606,0.0012334272,0.0028571142,0.0032705937,0.0021272504,0.0078551425],"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":[0.0030760877,0.0005934522,0.021314766,0.005651307,0.0011925995,0.002308829,0.0017637209,0.034347683,0.054262403,0.03265927,0.38626134,0.45656854],"study_design_scores_gemma":[0.0019100797,0.0008873132,0.018482864,0.001343039,0.0009227513,0.0024317869,0.0005530413,0.48824677,0.08207394,0.12285157,0.279671,0.0006258175],"about_ca_topic_score_codex":0.0023922042,"about_ca_topic_score_gemma":0.002044985,"teacher_disagreement_score":0.017346151,"about_ca_system_score_codex":0.0012496547,"about_ca_system_score_gemma":0.0023684022,"threshold_uncertainty_score":0.05802864},"labels":[],"label_agreement":null},{"id":"W2091810468","doi":"10.1186/1471-2105-9-s3-s1","title":"The Second International Symposium on Languages in Biology and Medicine (LBM) 2007","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computational biology; Biology; Data science; Computer science","score_opus":0.01740688202851943,"score_gpt":0.30610580208425237,"score_spread":0.28869892005573294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2091810468","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0108692655,0.19621114,0.12829727,0.17165798,0.28933758,0.0011485154,0.00461393,0.0062799873,0.19158436],"genre_scores_gemma":[0.033844534,0.078254096,0.08283763,0.019477114,0.05606778,0.0012626888,0.008036711,0.0051677227,0.71505165],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9911209,0.0035050274,0.0007173768,0.0012092039,0.0025095234,0.0009379881],"domain_scores_gemma":[0.987795,0.0031029787,0.0005428674,0.0010826743,0.0044209706,0.003055546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013124551,0.0020329268,0.0023808696,0.004958771,0.0020698553,0.012725313,0.0029364675,0.004229848,0.094103895],"category_scores_gemma":[0.01733918,0.0007503247,0.0023809727,0.0022615886,0.0025128268,0.00951257,0.0075120064,0.006457448,0.047818456],"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":[0.00021582769,0.00007452427,0.0002511944,0.0006086495,0.000040323786,0.00014550111,0.0007335385,0.00023552924,0.0021049627,0.020028817,0.77180505,0.20375597],"study_design_scores_gemma":[0.000010896858,0.000046971978,0.00032681192,0.00042511596,0.000013878932,0.00023865375,0.0003073269,0.00037447596,0.00076579204,0.00564968,0.9918133,0.000027107628],"about_ca_topic_score_codex":0.0022875671,"about_ca_topic_score_gemma":0.00355269,"teacher_disagreement_score":0.094103895,"about_ca_system_score_codex":0.005488884,"about_ca_system_score_gemma":0.008080996,"threshold_uncertainty_score":0.3148089},"labels":[],"label_agreement":null},{"id":"W2092793778","doi":"10.1186/1471-2105-14-11","title":"An improved method to detect correct protein folds using partial clustering","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athabasca University; University of Alberta","funders":"Alberta Prion Research Institute; Alberta Innovates","keywords":"Decoy; Cluster analysis; Data mining; Computer science; Selection (genetic algorithm); Protein structure prediction; Pattern recognition (psychology); Artificial intelligence; Algorithm; Protein structure","score_opus":0.012986935295008595,"score_gpt":0.27881630737906493,"score_spread":0.2658293720840563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2092793778","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040138684,0.00035243374,0.95301026,0.00010734996,0.000059120946,0.00011560337,0.00036326345,0.004897514,0.00095560664],"genre_scores_gemma":[0.18046223,0.00017380934,0.8150649,0.00011048321,0.00003657271,0.00014862577,0.0014366538,0.0004233397,0.0021433493],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989648,0.0001545644,0.00006968791,0.0002552269,0.00043589683,0.00011989381],"domain_scores_gemma":[0.99790895,0.00044951247,0.00017077393,0.0003838326,0.0009892477,0.00009759661],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014317054,0.001028863,0.0010342761,0.0024493379,0.0009984628,0.0007265443,0.001325872,0.00087001006,0.002914939],"category_scores_gemma":[0.0027574007,0.00039157397,0.0012095217,0.0016304029,0.0005307012,0.0011121136,0.0008294632,0.0007204452,0.0017003752],"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":[0.00047258582,0.00015538103,0.009610659,0.0003501629,0.00016963319,0.00017326653,0.00021428804,0.04342065,0.082011774,0.004666813,0.010829127,0.84792554],"study_design_scores_gemma":[0.000051646857,0.00012320884,0.0040120305,0.000032074167,0.000067823865,0.0006130035,0.00005239403,0.94818896,0.03718324,0.004373694,0.0052437223,0.00005822433],"about_ca_topic_score_codex":0.0044206255,"about_ca_topic_score_gemma":0.0052224463,"teacher_disagreement_score":0.0044206255,"about_ca_system_score_codex":0.0005196101,"about_ca_system_score_gemma":0.0016158911,"threshold_uncertainty_score":0.009751439},"labels":[],"label_agreement":null},{"id":"W2094867507","doi":"10.1186/1471-2105-14-27","title":"Predicting PDZ domain mediated protein interactions from structure","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Hippo pathway signaling and YAP/TAZ","field":"Biochemistry, Genetics and Molecular Biology","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Institute of General Medical Sciences; Canadian Institutes of Health Research","keywords":"PDZ domain; Computational biology; Peptide; Peptide sequence; Domain (mathematical analysis); Sequence (biology); Biology; Protein sequencing; Protein domain; Computer science; Bioinformatics; Biochemistry; Gene; Mathematics","score_opus":0.00867511211621647,"score_gpt":0.21604297905403494,"score_spread":0.20736786693781847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2094867507","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9430559,0.0003004477,0.052650392,0.00009423185,0.000008446626,0.000050565966,0.001895942,0.0011902694,0.00075380196],"genre_scores_gemma":[0.9693656,0.000101834026,0.026758607,0.000028306618,0.0000075978714,0.000050696046,0.0033397037,0.00003219902,0.00031539417],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99986756,0.000021197664,0.000009270603,0.000045408287,0.000039949802,0.000016638443],"domain_scores_gemma":[0.9994629,0.0002996003,0.00007927035,0.000025251727,0.00009865251,0.000034391083],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033068415,0.00060494227,0.00043625495,0.00083067134,0.0002350652,0.00035860398,0.0003103669,0.00041559082,0.0013571925],"category_scores_gemma":[0.0008684856,0.00017548887,0.00047656152,0.00044781482,0.0001531074,0.00032472302,0.0002901971,0.0005098816,0.00050839246],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015753753,0.000737607,0.2338463,0.0005573798,0.0004589958,0.000652846,0.00008033062,0.4517172,0.14106591,0.0012075539,0.004862441,0.16323802],"study_design_scores_gemma":[0.000024702182,0.0001444355,0.017101688,0.000006909604,0.000040279596,0.00017277536,0.00001513213,0.9593911,0.022107707,0.0004855421,0.0005006184,0.00000914033],"about_ca_topic_score_codex":0.0014051648,"about_ca_topic_score_gemma":0.0016713693,"teacher_disagreement_score":0.0014051648,"about_ca_system_score_codex":0.00044377186,"about_ca_system_score_gemma":0.000484401,"threshold_uncertainty_score":0.0045402646},"labels":[],"label_agreement":null},{"id":"W2095632020","doi":"10.1186/1471-2105-7-333","title":"A methodology for global validation of microarray experiments","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":72,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University and Génome Québec Innovation Centre","funders":"Génome Québec; Genome Canada","keywords":"DNA microarray; Replicate; Microarray; Computer science; Data mining; Concordance; Concordance correlation coefficient; Correlation; Microarray analysis techniques; Computational biology; Bioinformatics; Biology; Gene; Statistics; Genetics; Mathematics; Gene expression","score_opus":0.060875881693568064,"score_gpt":0.3393195170226023,"score_spread":0.27844363532903427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2095632020","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011386003,0.000095469026,0.997542,0.000041311272,0.000043901782,0.00029769455,0.00009621963,0.0004682167,0.0002766007],"genre_scores_gemma":[0.018516669,0.000110177665,0.97766954,0.00017244164,0.000057055342,0.002378399,0.00050912605,0.00022509514,0.00036159973],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.92418295,0.046125796,0.0052015535,0.0074142925,0.016209567,0.00086582336],"domain_scores_gemma":[0.85002863,0.07202912,0.0074640857,0.040562186,0.029057529,0.0008584467],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06346203,0.002243695,0.00243384,0.0042607184,0.0017606701,0.0024637417,0.0034150714,0.0022987013,0.0025791961],"category_scores_gemma":[0.10950864,0.0012351131,0.0035348278,0.0032111562,0.0032556,0.0015898765,0.0036351453,0.0046603316,0.001918168],"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":[0.0009801284,0.00049050985,0.019145943,0.0026772013,0.001520059,0.0007331682,0.0014081119,0.06925902,0.1308467,0.105703786,0.013699813,0.6535356],"study_design_scores_gemma":[0.00043010619,0.002334778,0.021017013,0.00090462575,0.0011180043,0.002785944,0.0005088137,0.49141487,0.20770736,0.17253743,0.09877856,0.0004625301],"about_ca_topic_score_codex":0.0008166089,"about_ca_topic_score_gemma":0.0008766192,"teacher_disagreement_score":0.06346203,"about_ca_system_score_codex":0.0019175083,"about_ca_system_score_gemma":0.0038235337,"threshold_uncertainty_score":0.33562332},"labels":[],"label_agreement":null},{"id":"W2095857517","doi":"10.1186/1471-2105-11-65","title":"Haplotype allelic classes for detecting ongoing positive selection","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Digestive system and related health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier Universitaire Sainte-Justine; Université de Montréal","funders":"Canadian Institutes of Health Research; Genome Canada","keywords":"Biology; Haplotype; Genetics; Allele frequency; Locus (genetics); International HapMap Project; Linkage disequilibrium; Natural selection; Allele; Selection (genetic algorithm); Evolutionary biology; Computer science; Gene; Artificial intelligence","score_opus":0.012740858546409061,"score_gpt":0.27290535632370805,"score_spread":0.260164497777299,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2095857517","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.682851,0.00039454797,0.31174296,0.00014686794,0.00005835722,0.00016053388,0.0016997107,0.00086580764,0.002080264],"genre_scores_gemma":[0.93886065,0.00004259844,0.060136713,0.0000352247,0.000035452114,0.000071915754,0.00063572294,0.00003721772,0.00014455988],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997532,0.0013069417,0.00021070754,0.00050158374,0.00036011956,0.00008862101],"domain_scores_gemma":[0.9706906,0.02337435,0.002588793,0.0017766486,0.0009509134,0.0006186623],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0053427387,0.0002613054,0.0004238672,0.0021924358,0.00032609116,0.0008830177,0.00063469895,0.00059195684,0.0022225513],"category_scores_gemma":[0.022474552,0.00012612087,0.0004458608,0.0013807347,0.00076700473,0.0008164276,0.0007074957,0.0006375579,0.0002574739],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020514824,0.00030190867,0.6495154,0.00038574034,0.0007918249,0.00035261473,0.00047328716,0.046544746,0.027099969,0.016021105,0.002641931,0.25381997],"study_design_scores_gemma":[0.00025450753,0.0013458332,0.22549792,0.00006506361,0.00034670904,0.0020650835,0.0003967861,0.70553994,0.02015531,0.039639894,0.0045227683,0.00017017777],"about_ca_topic_score_codex":0.0007408762,"about_ca_topic_score_gemma":0.00053634867,"teacher_disagreement_score":0.0053427387,"about_ca_system_score_codex":0.00033352766,"about_ca_system_score_gemma":0.00036999397,"threshold_uncertainty_score":0.028255403},"labels":[],"label_agreement":null},{"id":"W2096548036","doi":"10.1186/1471-2105-5-3","title":"VKCDB: Voltage-gated potassium channel database","year":2004,"lang":"en","type":"review","venue":"BMC Bioinformatics","topic":"Ion channel regulation and function","field":"Biochemistry, Genetics and Molecular Biology","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Canadian Institutes of Health Research","keywords":"Potassium channel; Voltage-gated potassium channel; Ion channel; Voltage-gated ion channel; Inward-rectifier potassium ion channel; Biology; Database; Channel (broadcasting); GenBank; Potassium; Chemistry; Computer science; Biophysics; Biochemistry","score_opus":0.04418633462436138,"score_gpt":0.2961691965879071,"score_spread":0.2519828619635457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096548036","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029023835,0.0032168166,0.011363295,0.00038853186,0.00022282204,0.00022239427,0.9499861,0.020257989,0.01143968],"genre_scores_gemma":[0.005254643,0.0011496696,0.010496856,0.00019845752,0.000023874012,0.00023330306,0.9785472,0.0015449859,0.0025510364],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993587,0.000058794485,0.00012914345,0.00018397535,0.00018386976,0.00008557281],"domain_scores_gemma":[0.9993025,0.00012933978,0.00009692935,0.00010217735,0.0002166061,0.00015237786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067411986,0.0012848605,0.0019467811,0.0036778166,0.0009632637,0.0025300388,0.0030952133,0.001837062,0.072222024],"category_scores_gemma":[0.0030466574,0.0004942455,0.00069798087,0.00545531,0.000358349,0.0020235674,0.0020518778,0.0012998843,0.07664584],"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":[0.0010983241,0.00010151522,0.0020459513,0.0064395545,0.00013761218,0.00046777257,0.00012821327,0.0013671034,0.0130689,0.0061214515,0.9226054,0.046418216],"study_design_scores_gemma":[0.0004138336,0.000051594572,0.0038983661,0.00063717965,0.00011039988,0.000674344,0.000064810934,0.0029419046,0.0058215754,0.0058716456,0.9794312,0.000083176834],"about_ca_topic_score_codex":0.0031117524,"about_ca_topic_score_gemma":0.0031099839,"teacher_disagreement_score":0.072222024,"about_ca_system_score_codex":0.00090956804,"about_ca_system_score_gemma":0.0028786287,"threshold_uncertainty_score":0.24160671},"labels":[],"label_agreement":null},{"id":"W2097593311","doi":"10.1186/1471-2105-11-243","title":"MOTIPS: Automated Motif Analysis for Predicting Targets of Modular Protein Domains","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Institute of General Medical Sciences; National Institute on Drug Abuse; National Institutes of Health","keywords":"Computational biology; Motif (music); Modular design; DNA microarray; Computer science; Bioinformatics; Biology; Genetics; Programming language; Gene; Gene expression","score_opus":0.008454412933677317,"score_gpt":0.23456004819857065,"score_spread":0.22610563526489333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2097593311","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4606278,0.0016077958,0.50150615,0.0002807037,0.000062215244,0.0003074216,0.010264821,0.023628037,0.0017150631],"genre_scores_gemma":[0.6149503,0.0002963848,0.37378713,0.0000717256,0.0000390244,0.00027833137,0.009331374,0.00030617503,0.0009394947],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997008,0.000097743134,0.000022894079,0.00007521686,0.00007390138,0.000029565525],"domain_scores_gemma":[0.99926835,0.00044723274,0.00009751032,0.00005484924,0.00008123489,0.00005076583],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006939341,0.00086749106,0.0006667449,0.0020684807,0.00033885555,0.0005229122,0.0008164471,0.0007101623,0.0018940892],"category_scores_gemma":[0.002195442,0.000282083,0.0006025473,0.0008985702,0.00019235439,0.00074446975,0.0005801973,0.00044880004,0.000678236],"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":[0.0033791764,0.0005347947,0.06174677,0.0013415817,0.00070566783,0.0008751828,0.00022761854,0.19524369,0.14674623,0.0060398676,0.020663708,0.5624957],"study_design_scores_gemma":[0.00011015872,0.00018745798,0.0044307513,0.000015763151,0.00004672762,0.00035166257,0.00003696127,0.97230047,0.016056318,0.004498978,0.0019441834,0.000020472566],"about_ca_topic_score_codex":0.0014208312,"about_ca_topic_score_gemma":0.0023103433,"teacher_disagreement_score":0.0020684807,"about_ca_system_score_codex":0.00031590307,"about_ca_system_score_gemma":0.0004571795,"threshold_uncertainty_score":0.0063363314},"labels":[],"label_agreement":null},{"id":"W2098478473","doi":"10.1186/1471-2105-7-534","title":"iHOPerator: user-scripting a personalized bioinformatics Web, starting with the iHOP website","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Paul's Hospital; University of British Columbia; Providence Health Care","funders":"Natural Sciences and Engineering Research Council of Canada; Genome British Columbia; Genome Alberta; Michael Smith Health Research BC; Genome Canada","keywords":"World Wide Web; Computer science; Scripting language; Web page; Web navigation; Client-side scripting; Web development; Dynamic web page; Context (archaeology); User interface; Web design; Web service; Static web page","score_opus":0.0658434519539109,"score_gpt":0.3047877373377604,"score_spread":0.2389442853838495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098478473","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028393293,0.00024175421,0.39825034,0.0005113468,0.00039214786,0.0010217197,0.0064036166,0.5284318,0.036353976],"genre_scores_gemma":[0.22686757,0.0005677742,0.5275081,0.0026902445,0.0004892982,0.0024865537,0.018652836,0.15276583,0.06797174],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994242,0.00012994917,0.00005599699,0.00011879484,0.00016640722,0.00010462851],"domain_scores_gemma":[0.99696726,0.0013527295,0.00018161893,0.00066314073,0.00036948005,0.00046578393],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017225196,0.00095573417,0.0003815877,0.0005780435,0.00039938895,0.0012089498,0.0013435365,0.0006837001,0.030528931],"category_scores_gemma":[0.0041761356,0.00057807274,0.0007949728,0.00029309522,0.00073226605,0.0015114595,0.0019772311,0.0015947311,0.014998861],"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":[0.0042655845,0.000866103,0.013117889,0.0017828773,0.00018845624,0.0032140017,0.0038569213,0.0046696286,0.13031329,0.017655445,0.44272363,0.37734616],"study_design_scores_gemma":[0.00039156206,0.00052460295,0.012761253,0.00045066624,0.00011426763,0.0017783106,0.00045344993,0.047347058,0.24674378,0.014651085,0.6743579,0.00042609748],"about_ca_topic_score_codex":0.0006814789,"about_ca_topic_score_gemma":0.0009051955,"teacher_disagreement_score":0.030528931,"about_ca_system_score_codex":0.00038307553,"about_ca_system_score_gemma":0.00071505836,"threshold_uncertainty_score":0.10212946},"labels":[],"label_agreement":null},{"id":"W2098927868","doi":"10.1186/1471-2105-13-s6-s11","title":"Challenges in estimating percent inclusion of alternatively spliced junctions from RNA-seq data","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA Research and Splicing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":82,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research; National Science Foundation","keywords":"Computer science; Alternative splicing; Probabilistic logic; Computational biology; Exon; RNA-Seq; Focus (optics); Metric (unit); Artificial intelligence; Data mining; Machine learning; Biology; Genetics; Transcriptome; Gene; Gene expression; Physics","score_opus":0.13135979292320452,"score_gpt":0.3494587628119391,"score_spread":0.2180989698887346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098927868","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03119224,0.0018945816,0.9633867,0.00079541875,0.000091541355,0.00009244516,0.0006363095,0.0013247709,0.0005859387],"genre_scores_gemma":[0.30473122,0.0026461785,0.68655187,0.0011526787,0.00022353965,0.0004644301,0.002524043,0.0008739871,0.0008320442],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98551106,0.005613917,0.0012985367,0.0034828829,0.0036305592,0.00046309122],"domain_scores_gemma":[0.90718776,0.075259045,0.0052185357,0.0067276224,0.005124877,0.00048213374],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0378723,0.0018649553,0.0024422584,0.002509615,0.0013369591,0.004514083,0.0045861467,0.0030200563,0.0004183765],"category_scores_gemma":[0.097964354,0.001721991,0.0025298875,0.0031894054,0.0026331665,0.0051580374,0.0028661187,0.0041399226,0.0007554585],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035549438,0.00015988952,0.086597666,0.0017252578,0.0010584013,0.00048162468,0.0013973908,0.6203728,0.0328873,0.021025024,0.0033445505,0.2305947],"study_design_scores_gemma":[0.00002111022,0.00009377503,0.017725982,0.0002294958,0.00011720001,0.00050569576,0.0002567294,0.88784856,0.018741775,0.068730615,0.0055671595,0.00016186702],"about_ca_topic_score_codex":0.0073046307,"about_ca_topic_score_gemma":0.0066153244,"teacher_disagreement_score":0.0378723,"about_ca_system_score_codex":0.0016246933,"about_ca_system_score_gemma":0.0023817022,"threshold_uncertainty_score":0.20029026},"labels":[],"label_agreement":null},{"id":"W2099003362","doi":"10.1186/s12859-015-0497-0","title":"GeneDig: a web application for accessing genomic and bioinformatics knowledge","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","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":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre; Montreal General Hospital","funders":"McGill University Health Centre; McGill University","keywords":"Computer science; World Wide Web; Genomic information; Usability; Genomics; Data science; Genome; Bioinformatics; Computational biology; Biology; Human–computer interaction; Gene; Genetics","score_opus":0.046363336134565385,"score_gpt":0.3213206243563992,"score_spread":0.2749572882218338,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099003362","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026901549,0.0010818947,0.31762147,0.0007657175,0.00018684125,0.0007124561,0.020855654,0.61189824,0.019976139],"genre_scores_gemma":[0.21235633,0.0020215784,0.61081094,0.0028090477,0.00020371217,0.00251394,0.07834744,0.038783748,0.05215329],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9996406,0.000063314474,0.000035648853,0.00008082945,0.0001441628,0.00003540788],"domain_scores_gemma":[0.99882716,0.00068403955,0.000073788084,0.00010414762,0.00015858188,0.00015227591],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010008881,0.001070337,0.00046549275,0.0021133972,0.00037777924,0.0012065822,0.0015303254,0.00095949136,0.019201588],"category_scores_gemma":[0.0023218035,0.00041386136,0.00051100506,0.001300639,0.00039124617,0.0017132955,0.0023293023,0.00069979083,0.010618798],"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":[0.0017564597,0.0005417606,0.008069734,0.0023631928,0.00019301877,0.0020322194,0.0011993332,0.0037140944,0.06134552,0.007002707,0.37254366,0.5392383],"study_design_scores_gemma":[0.00059345586,0.00040222512,0.015996864,0.00063221686,0.00019538328,0.0038036199,0.000529168,0.08290848,0.10355578,0.016784934,0.77413577,0.00046203338],"about_ca_topic_score_codex":0.0013321217,"about_ca_topic_score_gemma":0.0014683483,"teacher_disagreement_score":0.019201588,"about_ca_system_score_codex":0.00053666654,"about_ca_system_score_gemma":0.0006978229,"threshold_uncertainty_score":0.06423569},"labels":[],"label_agreement":null},{"id":"W2099753867","doi":"10.1186/1471-2105-12-491","title":"MAKER2: an annotation pipeline and genome-database management tool for second-generation genome projects","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2312,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"Division of Integrative Organismal Systems; National Institute of General Medical Sciences; National Human Genome Research Institute; University of Utah; Agricultural Research Service; San Francisco State University; Michigan State University; College of Engineering, Michigan State University; U.S. Department of Agriculture; National Institutes of Health; National Science Foundation","keywords":"Annotation; Genome; Genome project; Gene Annotation; Computer science; DNA sequencing; Pipeline (software); Genome browser; Computational biology; Genomics; Database; Data mining; Biology; Gene; Genetics; Artificial intelligence","score_opus":0.04623520706017015,"score_gpt":0.24603221744344678,"score_spread":0.19979701038327663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099753867","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005469632,0.0007947944,0.4306002,0.0012808037,0.0007997465,0.0011026991,0.104808286,0.4494049,0.005738907],"genre_scores_gemma":[0.027318243,0.0008500857,0.63046235,0.0013035287,0.00033265413,0.0051320544,0.2519807,0.07469785,0.007922563],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9952631,0.00070363516,0.0004977278,0.0014482833,0.0017296381,0.000357697],"domain_scores_gemma":[0.992574,0.002794777,0.001132449,0.0013816771,0.0011897642,0.00092729036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009493947,0.0052520186,0.0025732499,0.0072644553,0.0032611939,0.0068932446,0.008182982,0.0032109532,0.028581645],"category_scores_gemma":[0.019630922,0.004022828,0.0034218878,0.008139729,0.0011650088,0.00572265,0.0071750134,0.0060503227,0.022540832],"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":[0.0030770598,0.00032986433,0.0047867782,0.0037691146,0.0006788102,0.0015749767,0.0014464837,0.0066306945,0.044466075,0.012291536,0.7771792,0.14376941],"study_design_scores_gemma":[0.0012233981,0.00032161668,0.006387158,0.0004456725,0.00039291973,0.0014252871,0.00041105246,0.049209002,0.085497156,0.031021766,0.822902,0.00076304236],"about_ca_topic_score_codex":0.0017690405,"about_ca_topic_score_gemma":0.0017876975,"teacher_disagreement_score":0.028581645,"about_ca_system_score_codex":0.0018608778,"about_ca_system_score_gemma":0.0041409843,"threshold_uncertainty_score":0.09561515},"labels":[],"label_agreement":null},{"id":"W2099950456","doi":"10.1186/1471-2105-5-101","title":"Structural characterization of genomes by large scale sequence-structure threading: application of reliability analysis in structural genomics","year":2004,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; BC Centre for Disease Control; Simon Fraser University; University of British Columbia","funders":"Genome Prairie; Canadian Institutes of Health Research; Genome British Columbia; Michael Smith Health Research BC","keywords":"Weibull distribution; Maintainability; Reliability (semiconductor); Structural genomics; Genome; Threading (protein sequence); Computational biology; Biology; Computer science; Reliability engineering; Genomics; Genetics; Data mining; Power (physics); Gene; Protein structure; Statistics; Engineering; Mathematics; Physics","score_opus":0.00539309504578688,"score_gpt":0.23219419528709262,"score_spread":0.22680110024130573,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099950456","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43359146,0.00091305183,0.5629333,0.00021893877,0.00002518001,0.000057094803,0.00039911777,0.0009991295,0.00086270255],"genre_scores_gemma":[0.84430665,0.00035155893,0.15403822,0.000033095093,0.000020197582,0.00007045959,0.0008192814,0.00016900686,0.00019152429],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997118,0.00010386031,0.000024319696,0.00008105769,0.00005871993,0.000020174411],"domain_scores_gemma":[0.9971438,0.001592552,0.0005489329,0.00033958975,0.00027237064,0.00010282431],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018264889,0.00043828698,0.0005422346,0.0013082089,0.00049053744,0.00061348267,0.0005337717,0.00046899347,0.0007033558],"category_scores_gemma":[0.0065836883,0.0002471737,0.00085728866,0.0011983281,0.0004796162,0.0012174237,0.00039506814,0.00071588025,0.000210232],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00054391864,0.00029978613,0.09110039,0.0009989617,0.00037473108,0.00043298854,0.001158701,0.41410363,0.2615655,0.03821724,0.0011586519,0.19004558],"study_design_scores_gemma":[0.000019501509,0.0001260076,0.016068067,0.000028111806,0.000067056746,0.00019643921,0.000080648475,0.93777925,0.016754717,0.02737262,0.0014784286,0.000029195548],"about_ca_topic_score_codex":0.0017764837,"about_ca_topic_score_gemma":0.0012712023,"teacher_disagreement_score":0.0018264889,"about_ca_system_score_codex":0.0007004778,"about_ca_system_score_gemma":0.0004907346,"threshold_uncertainty_score":0.009659529},"labels":[],"label_agreement":null},{"id":"W2100258314","doi":"10.1186/1471-2105-5-96","title":"Base-By-Base: Single nucleotide-level analysis of whole viral genome alignments","year":2004,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Poxvirus research and outbreaks","field":"Immunology and Microbiology","cited_by":80,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"National Institute of Allergy and Infectious Diseases; Natural Sciences and Engineering Research Council of Canada; Defense Advanced Research Projects Agency","keywords":"Genome; Annotation; Biology; Computational biology; Java; Gene; Genome browser; Genetics; DNA microarray; Computer science; Software; Genomics; Programming language","score_opus":0.03318109257616441,"score_gpt":0.2569063753054517,"score_spread":0.22372528272928727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100258314","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033748277,0.00096912164,0.49915695,0.00037288805,0.000693616,0.00057897985,0.0710332,0.38819125,0.0052557862],"genre_scores_gemma":[0.077319555,0.0005158957,0.7702422,0.00022092453,0.0001771424,0.0011524359,0.0968245,0.05155588,0.0019914804],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977913,0.00044029436,0.00023310313,0.0006467814,0.0007539545,0.00013455446],"domain_scores_gemma":[0.9950648,0.0021720452,0.00081552466,0.00075950765,0.00089604553,0.00029205548],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043581715,0.003007497,0.0024257277,0.006604678,0.0012962556,0.0028753963,0.0029272984,0.0015189615,0.027933741],"category_scores_gemma":[0.013069855,0.0012636977,0.0019369592,0.006637902,0.0005342117,0.0027302606,0.0016887833,0.0024561384,0.016930215],"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":[0.0049073095,0.0012920725,0.024865966,0.0052984087,0.0025521165,0.0017051502,0.0018205474,0.010513841,0.14240006,0.008168875,0.4094854,0.38699025],"study_design_scores_gemma":[0.0011874209,0.0014560326,0.057782844,0.00083011703,0.0012784416,0.004894084,0.0006031414,0.38941056,0.16233753,0.031336244,0.34786698,0.0010166472],"about_ca_topic_score_codex":0.0014419457,"about_ca_topic_score_gemma":0.0016820504,"teacher_disagreement_score":0.027933741,"about_ca_system_score_codex":0.0006121618,"about_ca_system_score_gemma":0.0014545773,"threshold_uncertainty_score":0.093447685},"labels":[],"label_agreement":null},{"id":"W2100284033","doi":"10.1186/1471-2105-15-344","title":"CIG-P: Circular Interaction Graph for Proteomics","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","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":"Trinity Western University; Western University","funders":"Trinity Western University","keywords":"Visualization; Proteomics; Computer science; AKA; Computational biology; Graph; Data mining; Biology; Biochemistry; Theoretical computer science","score_opus":0.01974616961840828,"score_gpt":0.2766336423122025,"score_spread":0.2568874726937942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100284033","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031187702,0.00039705372,0.8787996,0.0005274444,0.0001443007,0.00026207996,0.014467194,0.09853895,0.0037446343],"genre_scores_gemma":[0.06394805,0.0014570694,0.84932876,0.00076672697,0.000104240105,0.0016679696,0.057256997,0.01996545,0.0055047097],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992812,0.00015302426,0.000053422253,0.00018982183,0.00026815952,0.000054485885],"domain_scores_gemma":[0.99818027,0.001083617,0.000150625,0.00026816162,0.00020975305,0.00010758125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011725293,0.0024580504,0.0008391365,0.003455206,0.00073315913,0.0018467366,0.0019752383,0.0013245776,0.024736425],"category_scores_gemma":[0.0045425394,0.0010094172,0.002231767,0.002366224,0.00065611175,0.0018163248,0.002359983,0.0016918466,0.006197344],"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":[0.00077073695,0.00028040927,0.0047019157,0.004067644,0.00040489103,0.0015310564,0.00090029085,0.07903213,0.026804663,0.13810967,0.334677,0.40871963],"study_design_scores_gemma":[0.00028231367,0.00015958042,0.0017285944,0.000403663,0.00013456498,0.0012679327,0.0001253351,0.32029012,0.019859105,0.24907112,0.4064831,0.00019457002],"about_ca_topic_score_codex":0.0027743818,"about_ca_topic_score_gemma":0.0023738975,"teacher_disagreement_score":0.024736425,"about_ca_system_score_codex":0.0010237717,"about_ca_system_score_gemma":0.001378016,"threshold_uncertainty_score":0.08275163},"labels":[],"label_agreement":null},{"id":"W2100744247","doi":"10.1186/1471-2105-11-484","title":"Protein network prediction and topological analysis in Leishmania major as a tool for drug target selection","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Research on Leishmaniasis Studies","field":"Medicine","cited_by":95,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Center for Research Resources; National Institutes of Health; Universidad de Antioquia; McMaster University; Departamento Administrativo de Ciencia, Tecnología e Innovación (COLCIENCIAS)","keywords":"Tropical disease; Computational biology; Betweenness centrality; Proteome; Interaction network; Drug discovery; Biology; Centrality; Drug; Leishmania; Computer science; Disease; Bioinformatics; Genetics; Medicine; Gene; Parasite hosting; Pharmacology; Mathematics","score_opus":0.016249164020894335,"score_gpt":0.28605494756141575,"score_spread":0.2698057835405214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100744247","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67072165,0.001677538,0.31618887,0.000537658,0.000026892785,0.00024144686,0.0033661476,0.0038049966,0.003434949],"genre_scores_gemma":[0.920527,0.00045497145,0.07625201,0.000031238327,0.00001246135,0.00011939706,0.002294794,0.000050403487,0.00025764474],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998549,0.00006713386,0.000009345031,0.00001935283,0.000037668487,0.000011607164],"domain_scores_gemma":[0.9989931,0.00061042554,0.0001665151,0.000043836066,0.000135593,0.00005047478],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046104647,0.0004486578,0.00034711705,0.002955207,0.00020006059,0.0004408905,0.00028559635,0.00026937563,0.0013202897],"category_scores_gemma":[0.0024517775,0.00012930208,0.00046931795,0.0012010415,0.00014683438,0.00042847672,0.0003553444,0.00026458144,0.00024285211],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010634754,0.00039979338,0.09884842,0.0011900039,0.00052533654,0.00063409936,0.00020874653,0.6001756,0.071255006,0.00980536,0.004227642,0.21166658],"study_design_scores_gemma":[0.000023016815,0.00014004656,0.011263967,0.000022652193,0.000073571944,0.00024781396,0.000029053557,0.97733593,0.0059399237,0.003293173,0.0016142628,0.000016651673],"about_ca_topic_score_codex":0.0014286375,"about_ca_topic_score_gemma":0.0012596383,"teacher_disagreement_score":0.002955207,"about_ca_system_score_codex":0.0004284089,"about_ca_system_score_gemma":0.0004245749,"threshold_uncertainty_score":0.0044168234},"labels":[],"label_agreement":null},{"id":"W2101212866","doi":"10.1186/1471-2105-10-45","title":"Comparison of small n statistical tests of differential expression applied to microarrays","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":82,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University and Génome Québec Innovation Centre","funders":"","keywords":"DNA microarray; Bayes' theorem; Statistical hypothesis testing; Statistical power; Normalization (sociology); Statistics; False discovery rate; Sample size determination; Multiple comparisons problem; Computer science; Statistic; Data mining; Mathematics; Biology; Bayesian probability; Genetics; Gene expression; Gene","score_opus":0.029347025360879755,"score_gpt":0.3093103171116424,"score_spread":0.2799632917507627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2101212866","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24241687,0.0013579649,0.750667,0.00029881072,0.00031925694,0.0008309465,0.00038573475,0.0011321103,0.002591251],"genre_scores_gemma":[0.6054112,0.00035858864,0.39088953,0.00019074965,0.00010303517,0.0016651744,0.0005573288,0.00039764645,0.00042678267],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9424775,0.04446906,0.0027360932,0.0030770146,0.006821543,0.00041867213],"domain_scores_gemma":[0.609504,0.36686796,0.007587189,0.008654973,0.0065400484,0.0008457904],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.047304418,0.0009991622,0.0013870662,0.002438285,0.0006544546,0.0013530982,0.0016065218,0.0014613924,0.001818323],"category_scores_gemma":[0.21345025,0.0004642035,0.0015549102,0.0019095015,0.002709607,0.0018402043,0.0014523378,0.0015099044,0.0002816415],"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":[0.013581091,0.0016985959,0.10978434,0.004507216,0.0053994344,0.001229235,0.0020906988,0.17877753,0.09733824,0.041904997,0.005638315,0.53805035],"study_design_scores_gemma":[0.00094248424,0.012870419,0.08961374,0.0006098184,0.0011390669,0.0017040935,0.0009261679,0.7206881,0.10369681,0.058925413,0.008429136,0.00045473795],"about_ca_topic_score_codex":0.00055763446,"about_ca_topic_score_gemma":0.0006674258,"teacher_disagreement_score":0.047304418,"about_ca_system_score_codex":0.0011231005,"about_ca_system_score_gemma":0.0013280844,"threshold_uncertainty_score":0.25017267},"labels":[],"label_agreement":null},{"id":"W2101348989","doi":"10.1186/1471-2105-11-s4-i1","title":"Proceedings of the ninth annual UT-ORNL-KBRIN Bioinformatics Summit 2010","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Oak Ridge National Laboratory; Vanderbilt University; University of British Columbia; National Institutes of Health; University of Memphis; University of Louisville","keywords":"Summit; Library science; Session (web analytics); Political science; Oak Ridge National Laboratory; Medical education; Informatics; Medicine; World Wide Web; Computer science; Geography","score_opus":0.014106414844126076,"score_gpt":0.2563653818904353,"score_spread":0.2422589670463092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2101348989","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055558644,0.019740248,0.031988125,0.40325564,0.1495794,0.0024701762,0.056887355,0.0070050796,0.27351522],"genre_scores_gemma":[0.06800884,0.011661544,0.037603438,0.030057134,0.015302397,0.0021995632,0.13786922,0.0023592694,0.69493866],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973355,0.0007419399,0.00009964825,0.0003239364,0.00091118057,0.00058776693],"domain_scores_gemma":[0.9921531,0.0008400666,0.00019547134,0.0003318759,0.002059943,0.0044194325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008978884,0.0009209982,0.0009898008,0.0012735284,0.0034691226,0.004766356,0.0018267323,0.0014592195,0.06860617],"category_scores_gemma":[0.0085029695,0.00034856304,0.00045510023,0.0009057205,0.00089153775,0.0020300217,0.006911509,0.0035616122,0.0393411],"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":[0.00018164353,0.000084834166,0.0007886906,0.00009024532,0.000009923875,0.00009225653,0.00019380936,0.00010994849,0.00070782227,0.0003574497,0.96778864,0.029594775],"study_design_scores_gemma":[0.000051382478,0.000059281472,0.0050548445,0.0001240104,0.000019093883,0.000056138993,0.0006539197,0.0007299535,0.00096589397,0.0012353789,0.99101675,0.000033339504],"about_ca_topic_score_codex":0.016391028,"about_ca_topic_score_gemma":0.10761815,"teacher_disagreement_score":0.06860617,"about_ca_system_score_codex":0.0041831713,"about_ca_system_score_gemma":0.00726188,"threshold_uncertainty_score":0.22951049},"labels":[],"label_agreement":null},{"id":"W2102858485","doi":"10.1186/1471-2105-10-357","title":"AIR: A batch-oriented web program package for construction of supermatrices ready for phylogenomic analyses","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":211,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Norges Forskningsråd; Universitetet i Oslo","keywords":"Phylogenetic tree; Sequence (biology); Biology; Computational biology; Tree (set theory); Phylogenomics; DNA microarray; Evolutionary biology; Phylogenetics; R package; Computer science; Gene; Data mining; Bioinformatics; Genetics; Clade; Programming language","score_opus":0.0384095315106722,"score_gpt":0.3222790566447174,"score_spread":0.2838695251340452,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102858485","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035020215,0.00023657555,0.63237685,0.000109314504,0.00019211238,0.00037424,0.021483324,0.33950076,0.0022247606],"genre_scores_gemma":[0.01561399,0.00035664992,0.78291494,0.00029696987,0.0001292799,0.0027475872,0.06116423,0.13176131,0.0050150454],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987778,0.0002663798,0.00012895248,0.00036617185,0.00031186792,0.00014891879],"domain_scores_gemma":[0.9975109,0.0014191305,0.00022827194,0.0003617204,0.00030966414,0.00017027413],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031401957,0.0036913115,0.0018398146,0.002262415,0.0011243653,0.0019888235,0.0037346906,0.0012525986,0.06338245],"category_scores_gemma":[0.0048327227,0.0021375245,0.0035345089,0.0017097399,0.0008332561,0.0021949199,0.003011367,0.003929869,0.04156023],"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":[0.0042085513,0.0005947413,0.0064111687,0.005406051,0.0014967261,0.0014282179,0.0013318957,0.013917118,0.10426202,0.01364699,0.5198617,0.32743484],"study_design_scores_gemma":[0.0014839183,0.00055078225,0.010910764,0.00053205655,0.00062734465,0.0014738421,0.00021973033,0.17644572,0.13055412,0.03000637,0.64664775,0.00054775405],"about_ca_topic_score_codex":0.0015488209,"about_ca_topic_score_gemma":0.0017354493,"teacher_disagreement_score":0.06338245,"about_ca_system_score_codex":0.0005302949,"about_ca_system_score_gemma":0.0016928093,"threshold_uncertainty_score":0.21203542},"labels":[],"label_agreement":null},{"id":"W2103183338","doi":"10.1186/1471-2105-13-s19-s2","title":"Exploiting ancestral mammalian genomes for the prediction of human transcription factor binding sites","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Centre National de la Recherche Scientifique","keywords":"DNA binding site; Genome; Genomics; Biology; Computational biology; Comparative genomics; Transcription factor; Evolutionary biology; Genetics; Genome evolution; Gene; Promoter","score_opus":0.04655835942742874,"score_gpt":0.262063859411683,"score_spread":0.21550549998425422,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103183338","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40839928,0.003947839,0.5137221,0.0009691707,0.00008570346,0.00017964216,0.046670616,0.021590514,0.004435125],"genre_scores_gemma":[0.46998936,0.001122919,0.46767417,0.00021715986,0.00003450018,0.00016093686,0.058788892,0.0011686598,0.0008433265],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997156,0.000068915564,0.000012963776,0.0001141012,0.000060894614,0.00002738933],"domain_scores_gemma":[0.9992101,0.00048802677,0.0000838596,0.00008633531,0.000080011836,0.00005162781],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078409037,0.0007987817,0.00061075354,0.0019501194,0.00065571227,0.00061299937,0.00089435995,0.000947982,0.003599522],"category_scores_gemma":[0.0037139603,0.00055525126,0.0008709756,0.0019492194,0.00028021203,0.0006379663,0.0007951114,0.000799317,0.0013661823],"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":[0.002140395,0.00037628086,0.11750436,0.0028392987,0.0008831852,0.0015024417,0.0011722338,0.31855556,0.12317907,0.017804252,0.031033887,0.38300905],"study_design_scores_gemma":[0.00013145574,0.00013956448,0.027945431,0.00014811009,0.00021926778,0.0007505457,0.0001691125,0.91079336,0.021941649,0.015534298,0.022159828,0.00006736282],"about_ca_topic_score_codex":0.007145671,"about_ca_topic_score_gemma":0.0127311265,"teacher_disagreement_score":0.007145671,"about_ca_system_score_codex":0.00066376623,"about_ca_system_score_gemma":0.0010038476,"threshold_uncertainty_score":0.014208138},"labels":[],"label_agreement":null},{"id":"W2103592640","doi":"10.1186/1471-2105-15-229","title":"SnowyOwl: accurate prediction of fungal genes by using RNA-Seq and homology information to select among ab initio models","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; Concordia University","funders":"Genome Alberta; Genome Canada; McGill University","keywords":"Gene prediction; Genome; Computational biology; Gene; Biology; Genetics; Homology (biology); Gene Annotation; RNA-Seq; Genomics; DNA microarray; Transcriptome; Gene expression","score_opus":0.020085814343212993,"score_gpt":0.2237495654642957,"score_spread":0.2036637511210827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103592640","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26779166,0.0008130862,0.56209666,0.00042447465,0.00022206218,0.00050356105,0.024238074,0.13960272,0.0043076957],"genre_scores_gemma":[0.42207465,0.000530599,0.51354104,0.00035709515,0.00006574882,0.0008492441,0.048814498,0.010107811,0.0036592146],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99965274,0.00005553673,0.000017782526,0.00013537829,0.00009398822,0.00004454669],"domain_scores_gemma":[0.9992348,0.0004613609,0.00008697129,0.00008394337,0.00007852266,0.000054457225],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010123786,0.0018791105,0.00085208786,0.0008048943,0.00066468795,0.001214262,0.0016519947,0.00085383566,0.0058394214],"category_scores_gemma":[0.0019778493,0.0010157407,0.0018456648,0.0005505623,0.0004857724,0.0011482385,0.0011269217,0.0011295343,0.0021188941],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0035889926,0.00063420244,0.03736796,0.0024790834,0.0012334281,0.0013343375,0.00086467963,0.34563333,0.22107343,0.0073265983,0.09121015,0.28725383],"study_design_scores_gemma":[0.00015358829,0.00013463396,0.0023239448,0.00003876926,0.000053925254,0.00007469272,0.000051558156,0.96042925,0.02905594,0.0024147602,0.0052212593,0.000047720347],"about_ca_topic_score_codex":0.0052216756,"about_ca_topic_score_gemma":0.009092707,"teacher_disagreement_score":0.0058394214,"about_ca_system_score_codex":0.0008548607,"about_ca_system_score_gemma":0.0012708397,"threshold_uncertainty_score":0.019534767},"labels":[],"label_agreement":null},{"id":"W2104239076","doi":"10.1186/1471-2105-10-241","title":"Multi-level learning: improving the prediction of protein, domain and residue interactions by allowing information flow between levels","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Institutes of Health; Yale University","keywords":"Computer science; Computational biology; Domain (mathematical analysis); DNA microarray; Bioinformatics; Chemistry; Biology; Biochemistry; Mathematics; Gene expression; Gene","score_opus":0.017120454248524975,"score_gpt":0.24037328422694504,"score_spread":0.22325282997842005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104239076","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.060082205,0.00026017826,0.9370976,0.00033154953,0.000016875692,0.00005653164,0.00008427094,0.0013283335,0.00074246153],"genre_scores_gemma":[0.6599649,0.00011880409,0.33770534,0.00031597976,0.00004407614,0.00012041206,0.00036335955,0.00014091378,0.0012263005],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99877757,0.0003554383,0.000070785834,0.00033697003,0.00029106537,0.00016806897],"domain_scores_gemma":[0.9961061,0.002297302,0.0004290726,0.00048350767,0.0004516438,0.00023246501],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025753484,0.0010430987,0.001356088,0.0012888396,0.0006855064,0.0016101119,0.0029277923,0.0021208439,0.0019290377],"category_scores_gemma":[0.0073750494,0.00064293755,0.0014926909,0.0009642467,0.0013015933,0.0032999387,0.0033142255,0.0024219241,0.00057626015],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002236004,0.00027345362,0.006860189,0.00009996538,0.000117279575,0.00012578686,0.00014790222,0.79830056,0.0060307547,0.0067234216,0.0014950664,0.1796019],"study_design_scores_gemma":[0.000005323367,0.000018506984,0.00016652921,0.000003620312,0.000005091853,0.000007403235,0.0000040987375,0.9964619,0.00086334336,0.0023738458,0.00008699636,0.0000034183],"about_ca_topic_score_codex":0.004969943,"about_ca_topic_score_gemma":0.0041335733,"teacher_disagreement_score":0.004969943,"about_ca_system_score_codex":0.0013726562,"about_ca_system_score_gemma":0.0013925306,"threshold_uncertainty_score":0.013619959},"labels":[],"label_agreement":null},{"id":"W2105074464","doi":"10.1186/1471-2105-15-s7-s8","title":"Population substructure in Cache County, Utah: the Cache County study","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Forensic and Genetic Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Neurological Disorders and Stroke; National Human Genome Research Institute; National Institute on Aging; University of California, San Diego; Genentech; National Institutes of Health; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; University of California, Los Angeles; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; Alzheimer's Association; Amorfix Life Sciences; F. Hoffmann-La Roche; Medpace; Bristol-Myers Squibb; Eli Lilly and Company; AstraZeneca; Novartis Pharmaceuticals Corporation; Synarc; Dana Foundation; Bayer HealthCare; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Foundation for the National Institutes of Health","keywords":"International HapMap Project; Population; Cache; Population stratification; Geography; Demography; Computer science; Biology; Genetics; Genotype; Genotyping; Sociology","score_opus":0.015173799726650868,"score_gpt":0.27276204595015485,"score_spread":0.25758824622350396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105074464","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9970483,0.00023964656,0.00018732254,0.00015593905,0.0000074506825,0.00002691867,0.0015614143,0.000007623262,0.00076536165],"genre_scores_gemma":[0.997726,0.00010604997,0.00034031842,0.00010905893,0.000008480256,0.000055953788,0.0013380836,0.0000051173492,0.00031085633],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9993575,0.0001711646,0.000041423453,0.0002067021,0.00015740219,0.00006579088],"domain_scores_gemma":[0.99860424,0.00018926479,0.0003876139,0.00016197107,0.00048833987,0.00016864699],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080669875,0.00014682641,0.0002565352,0.0010990378,0.0020490258,0.00072075013,0.00063081103,0.000482858,0.00085409445],"category_scores_gemma":[0.0032080882,0.0001128926,0.00016185711,0.0024365007,0.00043934403,0.00026815844,0.00070505176,0.00037282298,0.000090474736],"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":[0.000080783895,0.000029868017,0.99418133,0.000012507216,0.00007081382,0.00009099241,0.00066436507,0.000107709435,0.00018975083,0.00014042763,0.0020945536,0.0023368562],"study_design_scores_gemma":[0.000008364561,0.000024629657,0.99775827,0.00001646055,0.000040908213,0.000100613324,0.00052187894,0.00023901054,0.000049450955,0.000094600706,0.0011412231,0.000004478435],"about_ca_topic_score_codex":0.34606704,"about_ca_topic_score_gemma":0.59825265,"teacher_disagreement_score":0.34606704,"about_ca_system_score_codex":0.0014825482,"about_ca_system_score_gemma":0.0021597955,"threshold_uncertainty_score":0.6881054},"labels":[],"label_agreement":null},{"id":"W2105612251","doi":"10.1186/1471-2105-12-s8-s12","title":"A linear classifier based on entity recognition tools and a statistical approach to method extraction in the protein-protein interaction literature","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","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":"Queen's University","funders":"Fundação Luso-Americana para o Desenvolvimento; Natural Sciences and Engineering Research Council of Canada; Queen's University","keywords":"Computer science; Classifier (UML); Artificial intelligence; Pattern recognition (psychology); Relationship extraction; Machine learning; Ranking (information retrieval); Natural language processing; Data mining; Information extraction","score_opus":0.09354681556915123,"score_gpt":0.32892828978095134,"score_spread":0.2353814742118001,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105612251","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08532628,0.006431932,0.8770525,0.00242873,0.00054750725,0.00085131516,0.0059535587,0.01530377,0.006104458],"genre_scores_gemma":[0.34361187,0.0019528433,0.63113034,0.00068021147,0.0004916651,0.00092913397,0.015938036,0.00035214578,0.004913682],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99241877,0.0018954229,0.0012920042,0.0017479016,0.0022808718,0.0003650338],"domain_scores_gemma":[0.977759,0.013434252,0.0015045175,0.0015068746,0.0052967654,0.00049857824],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007917657,0.0010038897,0.0010986651,0.013215482,0.0011116564,0.0046059266,0.0020599274,0.0018105032,0.003487555],"category_scores_gemma":[0.023058822,0.00036751124,0.0017524685,0.009767845,0.00087934016,0.0051343082,0.00187229,0.0017673547,0.0052465554],"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":[0.0006613724,0.000389346,0.02637365,0.0012143718,0.00029817683,0.0005608738,0.00028600852,0.011517146,0.016001819,0.0071920613,0.024893265,0.9106118],"study_design_scores_gemma":[0.0002204977,0.0011702435,0.024389643,0.0004227853,0.0006184949,0.0019579881,0.00074815156,0.8553806,0.044294897,0.02463037,0.04595951,0.00020678435],"about_ca_topic_score_codex":0.004968896,"about_ca_topic_score_gemma":0.007414908,"teacher_disagreement_score":0.013215482,"about_ca_system_score_codex":0.0016782569,"about_ca_system_score_gemma":0.003477925,"threshold_uncertainty_score":0.041873097},"labels":[],"label_agreement":null},{"id":"W2105896055","doi":"10.1186/1471-2105-6-186","title":"Nonparametric tests for differential gene expression and interaction effects in multi-factorial microarray experiments","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Nonparametric statistics; Outlier; DNA microarray; Parametric statistics; Covariate; Microarray analysis techniques; Robustness (evolution); Statistical hypothesis testing; Gene expression profiling; Computational biology; Computer science; Data mining; Biology; Statistics; Gene expression; Mathematics; Genetics; Gene","score_opus":0.03083952188263326,"score_gpt":0.31633714419032416,"score_spread":0.2854976223076909,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105896055","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058153357,0.0011104097,0.9339788,0.00045204826,0.0001900257,0.0006067999,0.001228716,0.0016149011,0.002664925],"genre_scores_gemma":[0.62417305,0.0004535233,0.36821786,0.00042025512,0.00023690786,0.0035252154,0.0015452274,0.00030618007,0.0011217666],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95940274,0.027560527,0.0016278974,0.0036135276,0.0069219726,0.0008732232],"domain_scores_gemma":[0.833997,0.14171351,0.008349136,0.010877889,0.00413505,0.000927362],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.031206453,0.0012898657,0.0023301234,0.003063322,0.00086924236,0.0016884772,0.0027896585,0.0021322332,0.0049296487],"category_scores_gemma":[0.11480788,0.00043424597,0.0023477392,0.0033772783,0.005178526,0.0025060961,0.001673005,0.0032624232,0.0008266049],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0070925285,0.0010581688,0.07218098,0.0044663264,0.002867404,0.0019272112,0.0014010661,0.09660896,0.049738508,0.13472244,0.011527982,0.61640835],"study_design_scores_gemma":[0.0012450487,0.0065104687,0.11094668,0.0005097393,0.0009383613,0.0029668475,0.0008679429,0.48827174,0.046524372,0.3193905,0.021278093,0.0005501575],"about_ca_topic_score_codex":0.0004914393,"about_ca_topic_score_gemma":0.00037528813,"teacher_disagreement_score":0.031206453,"about_ca_system_score_codex":0.0012005572,"about_ca_system_score_gemma":0.0021605282,"threshold_uncertainty_score":0.16503751},"labels":[],"label_agreement":null},{"id":"W2106017862","doi":"10.1186/1471-2105-9-375","title":"Critical assessment of alignment procedures for LC-MS proteomics and metabolomics measurements","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":191,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IONICS Mass Spectrometry (Canada)","funders":"Cancer Research UK","keywords":"Proteomics; Metabolomics; Computational biology; DNA microarray; Computer science; Bioinformatics; Data science; Biology; Genetics","score_opus":0.042791251933404335,"score_gpt":0.310214925530109,"score_spread":0.26742367359670466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106017862","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11446034,0.0038767492,0.870358,0.00057804945,0.0005473371,0.0011986935,0.0014385387,0.00561491,0.0019273423],"genre_scores_gemma":[0.1539935,0.0008853994,0.8394327,0.0001387589,0.000090765854,0.00093580165,0.0027654422,0.0014271993,0.0003303877],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9686067,0.011101412,0.003915503,0.0030108765,0.012714717,0.0006506936],"domain_scores_gemma":[0.84872544,0.075644895,0.013509665,0.011726748,0.04908594,0.0013073279],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04408759,0.0022578451,0.0011942174,0.005203695,0.0019886883,0.0036569505,0.0023886915,0.0017999515,0.002809723],"category_scores_gemma":[0.14476758,0.00081024645,0.0018998076,0.0046188976,0.0015888014,0.0033230756,0.0025340032,0.0018192615,0.0015772998],"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":[0.004249907,0.0008181108,0.033377696,0.0053778966,0.00096302875,0.0006211478,0.0023466456,0.04344959,0.18825643,0.011459281,0.0110946465,0.69798553],"study_design_scores_gemma":[0.00026967248,0.0026225732,0.051671024,0.0011203067,0.0008549292,0.0017105018,0.0015334302,0.31240135,0.57225704,0.016253646,0.038619537,0.00068595854],"about_ca_topic_score_codex":0.0013903036,"about_ca_topic_score_gemma":0.0010137323,"teacher_disagreement_score":0.04408759,"about_ca_system_score_codex":0.0015966637,"about_ca_system_score_gemma":0.0030998958,"threshold_uncertainty_score":0.23316026},"labels":[],"label_agreement":null},{"id":"W2106606545","doi":"10.1186/1471-2105-5-201","title":"A novel Mixture Model Method for identification of differentially expressed genes from DNA microarray data","year":2004,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Repeatability; Nonparametric statistics; Set (abstract data type); Sensitivity (control systems); Computer science; Data set; Data mining; DNA microarray; Microarray analysis techniques; Algorithm; Pattern recognition (psychology); Statistics; Mathematics; Gene; Biology; Artificial intelligence; Genetics; Gene expression","score_opus":0.04615492341010959,"score_gpt":0.3068764359789374,"score_spread":0.2607215125688278,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106606545","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010128077,0.00011477096,0.99806947,0.000040174637,0.000018743689,0.00002533792,0.00006678532,0.0005866801,0.00006534196],"genre_scores_gemma":[0.04092143,0.00031304077,0.9546678,0.00017465798,0.000100040386,0.0005869266,0.0013672635,0.0003563111,0.0015124085],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99681854,0.0011205275,0.00019391671,0.00080989266,0.00090174057,0.00015535293],"domain_scores_gemma":[0.9967482,0.0021910835,0.00019719863,0.00024727834,0.000532625,0.000083481005],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0052161133,0.0018071333,0.0020614776,0.0027647926,0.0007341981,0.00155627,0.002720707,0.002045649,0.002134111],"category_scores_gemma":[0.008587421,0.0008651484,0.0029603408,0.0024237297,0.0007284227,0.0015119086,0.0014665318,0.0026934324,0.0024603407],"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":[0.0007076321,0.00024936564,0.0041818796,0.00046820403,0.00064775563,0.00021889646,0.00020914793,0.1844885,0.03225212,0.01292688,0.006420816,0.7572288],"study_design_scores_gemma":[0.00003343955,0.000065132925,0.00078531785,0.0000181336,0.000059215417,0.00014614935,0.000015236043,0.9841808,0.003931481,0.007006735,0.0037132706,0.000045057866],"about_ca_topic_score_codex":0.0028312195,"about_ca_topic_score_gemma":0.0029039849,"teacher_disagreement_score":0.0052161133,"about_ca_system_score_codex":0.0008990844,"about_ca_system_score_gemma":0.0016177833,"threshold_uncertainty_score":0.027585745},"labels":[],"label_agreement":null},{"id":"W2107815233","doi":"10.1186/1471-2105-9-101","title":"Prediction of mucin-type O-glycosylation sites in mammalian proteins using the composition of k-spaced amino acid pairs","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Glycosylation and Glycoproteins Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":153,"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":"Program for New Century Excellent Talents in University; China Agricultural University; University of Alberta","keywords":"Glycosylation; Threonine; Computational biology; Serine; Encoding (memory); Binary classification; Support vector machine; Mucin; Computer science; Amino acid; Biology; Bioinformatics; Artificial intelligence; Biochemistry; Phosphorylation","score_opus":0.05543503999968876,"score_gpt":0.2762255201344427,"score_spread":0.2207904801347539,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107815233","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94487673,0.0008895042,0.05138383,0.00008120889,0.00003404496,0.000047180045,0.0011831272,0.0008208416,0.0006836157],"genre_scores_gemma":[0.9178797,0.00054396485,0.0776354,0.00004275772,0.000015499634,0.00003697543,0.0033691698,0.00003862595,0.00043787618],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998528,0.000024832985,0.00001601298,0.0000457197,0.000043964512,0.000016651977],"domain_scores_gemma":[0.99967766,0.0000692926,0.00009074415,0.00002415213,0.00010242395,0.000035812034],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047766033,0.000503995,0.00038488235,0.0007312232,0.00018407253,0.00033104027,0.00027227815,0.00036248603,0.00048591947],"category_scores_gemma":[0.00075304165,0.000118791824,0.0006037114,0.0006265912,0.00013312949,0.0004169269,0.00027488492,0.00048016332,0.00034754205],"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":[0.0024205642,0.00067694,0.23496662,0.00073704537,0.00044672607,0.0006520445,0.00012096976,0.08993766,0.44628227,0.00075208925,0.0050169057,0.21799015],"study_design_scores_gemma":[0.000049620794,0.00038773756,0.052173305,0.00003831777,0.00011198707,0.0004295725,0.00006542298,0.8791041,0.06528798,0.0005656427,0.0017530427,0.000033401342],"about_ca_topic_score_codex":0.0013064881,"about_ca_topic_score_gemma":0.0014546786,"teacher_disagreement_score":0.0013064881,"about_ca_system_score_codex":0.00023997293,"about_ca_system_score_gemma":0.0004361568,"threshold_uncertainty_score":0.0025977492},"labels":[],"label_agreement":null},{"id":"W2109203567","doi":"10.1186/s12859-015-0805-8","title":"Revisiting operons: an analysis of the landscape of transcriptional units in E. coli","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Andlinger Center for Energy and the Environment, Princeton University; U.S. Department of Energy; Canadian Association for the Study of the Liver; National Science Foundation","keywords":"Operon; Computational biology; DNA microarray; Biology; Genetics; Escherichia coli; Gene; Gene expression","score_opus":0.04254395801968929,"score_gpt":0.26151269206273164,"score_spread":0.21896873404304235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109203567","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98741686,0.00032994783,0.010735575,0.00010558416,0.0000046111504,0.00001362976,0.00055188243,0.00020080138,0.0006410706],"genre_scores_gemma":[0.9848262,0.00023882608,0.013095615,0.00003308123,0.000006059626,0.00003067905,0.0014904888,0.000070268725,0.00020869813],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998653,0.000027844111,0.0000075728967,0.000042081825,0.000028271399,0.000028898483],"domain_scores_gemma":[0.99960726,0.0002408427,0.000037564423,0.00003351408,0.000043151736,0.00003774887],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025258955,0.0003002961,0.0004995829,0.0008671609,0.00037634664,0.00080124324,0.000538816,0.0004228137,0.001077146],"category_scores_gemma":[0.0011655344,0.00019602932,0.0007053962,0.001247877,0.0003825661,0.0004844107,0.00046488902,0.00039855143,0.00015835013],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005645979,0.0002570193,0.09450872,0.00044752224,0.00022871632,0.00056046224,0.00044217895,0.802547,0.046480067,0.0053512407,0.0015067247,0.04710579],"study_design_scores_gemma":[0.000024256165,0.000078890946,0.030861808,0.000013812537,0.000057738715,0.00013711082,0.00018871804,0.9588105,0.0039329655,0.00446521,0.0014120472,0.000016900105],"about_ca_topic_score_codex":0.0074176886,"about_ca_topic_score_gemma":0.00547509,"teacher_disagreement_score":0.0074176886,"about_ca_system_score_codex":0.00069471815,"about_ca_system_score_gemma":0.0005810917,"threshold_uncertainty_score":0.014748991},"labels":[],"label_agreement":null},{"id":"W2109327803","doi":"10.1186/1471-2105-3-35","title":"FunSpec: a web-based cluster interpreter for yeast","year":2002,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":409,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Canadian Institutes of Health Research; University of Toronto; Genome Canada","keywords":"Cluster analysis; Categorical variable; Interpreter; Gene; Computational biology; Computer science; Exposition (narrative); Interpretation (philosophy); DNA microarray; Biology; Genetics; Artificial intelligence; Gene expression; Machine learning","score_opus":0.01484499009857399,"score_gpt":0.22456440291573057,"score_spread":0.2097194128171566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109327803","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010501699,0.00027342277,0.5753296,0.0001881445,0.000115253526,0.00020778504,0.017889788,0.3901116,0.005382687],"genre_scores_gemma":[0.12576014,0.0006443444,0.71867126,0.0004885258,0.00009129226,0.0014226108,0.047064543,0.09593019,0.00992703],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.999579,0.000059149817,0.00007600777,0.00011450046,0.00012866588,0.000042622833],"domain_scores_gemma":[0.9984725,0.0008035605,0.0001228368,0.0002354281,0.00027223962,0.00009339407],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016878053,0.0014907009,0.0007903557,0.0019542556,0.00091481366,0.0018954166,0.0027089177,0.0009362382,0.023952635],"category_scores_gemma":[0.004196754,0.0010087168,0.0016601637,0.0013859351,0.00073267584,0.0022781119,0.0021071124,0.0013224832,0.0076468443],"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":[0.0048672003,0.00033753226,0.01481949,0.0041790823,0.00062673347,0.0030230775,0.004022485,0.049329013,0.04486599,0.07786445,0.34691024,0.4491547],"study_design_scores_gemma":[0.000772538,0.0002143741,0.005669589,0.00063695805,0.00018754895,0.0017517481,0.00082079147,0.342535,0.08274246,0.12015574,0.4440616,0.00045168746],"about_ca_topic_score_codex":0.003400894,"about_ca_topic_score_gemma":0.0042189183,"teacher_disagreement_score":0.023952635,"about_ca_system_score_codex":0.0010388468,"about_ca_system_score_gemma":0.0013010392,"threshold_uncertainty_score":0.080129564},"labels":[],"label_agreement":null},{"id":"W2109429447","doi":"10.1186/1471-2105-12-486","title":"Constructing a semantic predication gold standard from the biomedical literature","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":66,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"U.S. National Library of Medicine; National Institutes of Health","keywords":"Unified Medical Language System; Computer science; Information retrieval; Annotation; Terminology; Natural language processing; Biomedical text mining; Ontology; Task (project management); Semantic similarity; Controlled vocabulary; Artificial intelligence; Text mining; Linguistics","score_opus":0.023971190296094843,"score_gpt":0.24545670248368603,"score_spread":0.2214855121875912,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109429447","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39241973,0.007573518,0.5524862,0.0029189938,0.00097527495,0.0026049728,0.010811068,0.004138265,0.026071975],"genre_scores_gemma":[0.55591816,0.0012768056,0.41516066,0.0005459473,0.00023748311,0.0036922528,0.020997494,0.0008516093,0.0013195588],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9089855,0.03444411,0.018497694,0.013586818,0.02311136,0.0013745527],"domain_scores_gemma":[0.62771255,0.22673105,0.019229854,0.036286756,0.088023774,0.0020160328],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.10395984,0.0013044638,0.0016064391,0.032314185,0.005148577,0.005814632,0.0031005915,0.0026264763,0.003257273],"category_scores_gemma":[0.25596792,0.0006486081,0.002040533,0.01437126,0.003850662,0.0066217887,0.0100791715,0.0021021303,0.0020031712],"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":[0.0016499958,0.0008509285,0.15301399,0.016171446,0.0021491863,0.001959697,0.031692017,0.013988637,0.07400356,0.057698056,0.03459436,0.6122282],"study_design_scores_gemma":[0.0004357977,0.001015791,0.26123166,0.008776964,0.002800792,0.002983322,0.023733873,0.15527298,0.18070926,0.14711143,0.21511935,0.00080886047],"about_ca_topic_score_codex":0.0028117222,"about_ca_topic_score_gemma":0.004137385,"teacher_disagreement_score":0.10395984,"about_ca_system_score_codex":0.0032495542,"about_ca_system_score_gemma":0.006815845,"threshold_uncertainty_score":0.5497988},"labels":[],"label_agreement":null},{"id":"W2110845345","doi":"10.1186/1471-2105-7-244","title":"Identification of consensus RNA secondary structures using suffix arrays","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Nucleic acid secondary structure; Protein secondary structure; Computational biology; Suffix array; Conserved sequence; Suffix; Structural motif; DNA microarray; Computer science; Sequence alignment; RNA; Data structure; Biology; Genetics; DNA; Gene; Base sequence; Peptide sequence","score_opus":0.014567914469078996,"score_gpt":0.2406418170439644,"score_spread":0.2260739025748854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110845345","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23774457,0.00038120055,0.75235426,0.0000951199,0.000016921826,0.00021104961,0.0015704193,0.005742978,0.0018834971],"genre_scores_gemma":[0.23702681,0.00016915696,0.75778127,0.000036586876,0.000013633564,0.00024630767,0.0036578714,0.0002701685,0.00079823285],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999297,0.00019418134,0.00010344887,0.00018748881,0.0001793717,0.000038523973],"domain_scores_gemma":[0.9957041,0.0026203087,0.0006380529,0.00025011448,0.0006746757,0.00011274747],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014657743,0.0008122238,0.00077655265,0.0014732329,0.00043812097,0.00089396635,0.0007823186,0.0007339701,0.0029854437],"category_scores_gemma":[0.004507528,0.00028260282,0.0007613313,0.001069306,0.0003512423,0.0011317396,0.00053785613,0.00046931015,0.0013809543],"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":[0.0020923582,0.00045084022,0.026935752,0.0014072744,0.000247899,0.0003621496,0.00032142253,0.17157893,0.2279744,0.0102669485,0.0043256627,0.5540364],"study_design_scores_gemma":[0.00008995045,0.00046133998,0.0031223984,0.000058209564,0.000058545058,0.0004012356,0.000093640425,0.8523555,0.12987614,0.009580539,0.003857383,0.000045098128],"about_ca_topic_score_codex":0.0003963276,"about_ca_topic_score_gemma":0.0005845404,"teacher_disagreement_score":0.0029854437,"about_ca_system_score_codex":0.0004373061,"about_ca_system_score_gemma":0.0006853199,"threshold_uncertainty_score":0.009987295},"labels":[],"label_agreement":null},{"id":"W2111112354","doi":"10.1186/1471-2105-14-s12-s1","title":"Using context-specific effect of miRNAs to identify functional associations between miRNAs and gene signatures","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"MicroRNA in disease regulation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":56,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates","keywords":"microRNA; Biology; Context (archaeology); Computational biology; Gene regulatory network; Gene; Regulation of gene expression; DNA microarray; Genetics; Gene expression","score_opus":0.03031355083459365,"score_gpt":0.2895462607782136,"score_spread":0.25923270994361997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111112354","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48218536,0.0006283305,0.51295274,0.0001381172,0.00003359271,0.00009326424,0.0010601905,0.0011598563,0.0017485637],"genre_scores_gemma":[0.9127206,0.00027999916,0.084040664,0.000067172565,0.000022015953,0.000112856505,0.0014620682,0.00012321719,0.0011715165],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9996191,0.00008776184,0.000021444026,0.00016084003,0.00007714716,0.00003364709],"domain_scores_gemma":[0.9992506,0.00040690272,0.0001508636,0.00007674637,0.00008676407,0.000028196764],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008548391,0.00067055173,0.00041739672,0.0008786153,0.00021914096,0.00044300812,0.00038243225,0.00033289485,0.0011797987],"category_scores_gemma":[0.0021002886,0.00024284612,0.0010675238,0.00063829956,0.0003145177,0.00048268383,0.0005415079,0.00064281694,0.00033464303],"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":[0.0010638171,0.00023363743,0.051516518,0.00035244957,0.0004846415,0.00047479293,0.00010370991,0.72544193,0.12565222,0.0049787946,0.0006604734,0.08903704],"study_design_scores_gemma":[0.000012447128,0.00012354535,0.009991082,0.000010327017,0.000099908095,0.0001405233,0.000015588124,0.9653359,0.019660478,0.0036726072,0.00091908,0.000018395453],"about_ca_topic_score_codex":0.0012425333,"about_ca_topic_score_gemma":0.0017168501,"teacher_disagreement_score":0.0012425333,"about_ca_system_score_codex":0.00041142193,"about_ca_system_score_gemma":0.00047634786,"threshold_uncertainty_score":0.0045208335},"labels":[],"label_agreement":null},{"id":"W2111492198","doi":"10.1186/1471-2105-7-423","title":"Detection of prokaryotic promoters from the genomic distribution of hexanucleotide pairs","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bacterial Genetics and Biotechnology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies; Université de Sherbrooke","keywords":"Promoter; Biology; Genetics; Computational biology; Bacterial genome size; Genome; Gene; Intergenic region; Transcription (linguistics); DNA sequencing; Regulatory sequence; DNA microarray; Transcription factor; Gene expression","score_opus":0.0061610793041830285,"score_gpt":0.18525158885705942,"score_spread":0.1790905095528764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111492198","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6821431,0.0015240952,0.3107707,0.00010903731,0.00003043653,0.000087730834,0.0017383327,0.0020392507,0.0015573556],"genre_scores_gemma":[0.7580731,0.0005882339,0.23629065,0.00006117764,0.000018407281,0.000093586576,0.003934337,0.00014328299,0.0007972448],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99981505,0.00003182541,0.000009746941,0.00007254127,0.000052746367,0.000018000897],"domain_scores_gemma":[0.9992888,0.0003431553,0.0001393602,0.000036613073,0.00013180726,0.000060318027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038930055,0.00043486612,0.00038505963,0.0011299626,0.00018953915,0.00035268062,0.0003746277,0.00036667238,0.00076893857],"category_scores_gemma":[0.0015398337,0.00020668776,0.0002880484,0.00088920817,0.00022794983,0.00028267852,0.0003463391,0.0004435936,0.0005508812],"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":[0.0010663846,0.0001029567,0.040565163,0.0007082703,0.000067752604,0.0002488063,0.00017621618,0.008489268,0.8364257,0.0009695727,0.00049736444,0.11068255],"study_design_scores_gemma":[0.000096343174,0.00031275384,0.06731661,0.000083549836,0.000112273774,0.0013669414,0.00018896244,0.26994348,0.6495908,0.005794431,0.0051356526,0.000058297443],"about_ca_topic_score_codex":0.0006998979,"about_ca_topic_score_gemma":0.0011014867,"teacher_disagreement_score":0.0011299626,"about_ca_system_score_codex":0.000268648,"about_ca_system_score_gemma":0.00039462885,"threshold_uncertainty_score":0.002572298},"labels":[],"label_agreement":null},{"id":"W2111607030","doi":"10.1186/1471-2105-10-202","title":"NLStradamus: a simple Hidden Markov Model for nuclear localization signal prediction","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Nuclear Structure and Function","field":"Biochemistry, Genetics and Molecular Biology","cited_by":719,"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":"Nuclear localization sequence; NLS; Hidden Markov model; Nuclear transport; Markov chain; Computational biology; Simple (philosophy); Computer science; Set (abstract data type); Markov model; Artificial intelligence; Biology; Machine learning; Genetics; Cell nucleus; Gene","score_opus":0.010340648857877142,"score_gpt":0.2196102180540038,"score_spread":0.20926956919612666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111607030","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0322669,0.0006957483,0.9469694,0.0006440379,0.0001307801,0.00015213252,0.0030484581,0.014875173,0.0012174045],"genre_scores_gemma":[0.41927764,0.0006554696,0.56559587,0.00048972305,0.00013058489,0.0008295349,0.008260283,0.0009035837,0.0038573113],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99964213,0.00016537138,0.000023879395,0.000073553434,0.00006387819,0.000031221953],"domain_scores_gemma":[0.9986162,0.0011221592,0.000057073004,0.000053667514,0.00009166298,0.00005920668],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012401869,0.00074030703,0.0008809349,0.00067825837,0.00058355206,0.0007821274,0.0017632666,0.0013101539,0.0052235485],"category_scores_gemma":[0.003728669,0.00073250197,0.0011002729,0.0005958867,0.00036253096,0.0008259699,0.00078429887,0.0015302371,0.0016502355],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00063471304,0.00011774941,0.0025073672,0.00021399544,0.00018003011,0.00019156706,0.000078264595,0.89413476,0.0018538105,0.005627616,0.008078866,0.0863813],"study_design_scores_gemma":[0.000017334518,0.000008084204,0.00006196935,0.0000035303867,0.0000052595083,0.000008905992,0.0000019180145,0.9976271,0.00021468702,0.0016903875,0.00035681465,0.00000392372],"about_ca_topic_score_codex":0.01612737,"about_ca_topic_score_gemma":0.018633042,"teacher_disagreement_score":0.01612737,"about_ca_system_score_codex":0.0010432354,"about_ca_system_score_gemma":0.0015279076,"threshold_uncertainty_score":0.032067},"labels":[],"label_agreement":null},{"id":"W2111931353","doi":"10.1186/1471-2105-10-s12-i1","title":"Trends in modeling Biomedical Complex Systems","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Ministero dell’Istruzione, dell’Università e della Ricerca; World Anti-Doping Agency","keywords":"Computer science; Data science; Multidisciplinary approach; Inference; Informatics; Management science; Complex system; Health informatics; Artificial intelligence; Engineering; Medicine","score_opus":0.028375283573716284,"score_gpt":0.2678424997625228,"score_spread":0.2394672161888065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111931353","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0042187427,0.20661296,0.7141233,0.051568553,0.0031369622,0.00013333882,0.0005746582,0.0008286194,0.018802807],"genre_scores_gemma":[0.1105433,0.4060943,0.44333258,0.009631842,0.014415186,0.0009780761,0.0019052662,0.00050395366,0.012595508],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973826,0.001220022,0.00015925667,0.00045388468,0.0007146822,0.00006963316],"domain_scores_gemma":[0.991091,0.0063591986,0.0003424643,0.00075846835,0.0011988839,0.0002499837],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00602748,0.001346093,0.0016384404,0.0022655074,0.0004894485,0.0040300577,0.002585751,0.0027778007,0.0053894348],"category_scores_gemma":[0.01177443,0.0006637625,0.0011575177,0.0038533625,0.0027571332,0.0071319896,0.0022595935,0.0046852496,0.0024586304],"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":[0.000060176968,0.00009400893,0.0015022607,0.0019049824,0.00013673224,0.00010613881,0.00029531124,0.035250865,0.00084112625,0.73067003,0.026871055,0.20226733],"study_design_scores_gemma":[0.000030418094,0.00007432302,0.00061866577,0.0006628165,0.000055916396,0.0001555482,0.00017040053,0.14447989,0.00044931436,0.61530226,0.2379484,0.000052112653],"about_ca_topic_score_codex":0.0022358499,"about_ca_topic_score_gemma":0.0015086706,"teacher_disagreement_score":0.00602748,"about_ca_system_score_codex":0.0019667512,"about_ca_system_score_gemma":0.0019797846,"threshold_uncertainty_score":0.031876743},"labels":[],"label_agreement":null},{"id":"W2114857957","doi":"10.1186/1471-2105-4-16","title":"Domain fusion analysis by applying relational algebra to protein sequence and domain databases","year":2003,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Cancer Institute; Canadian Institutes of Health Research","keywords":"Computer science; Domain (mathematical analysis); UniProt; Protein domain; Sequence database; Hidden Markov model; Computational biology; Relational database; Database; Protein structure database; Sequence (biology); Protein sequencing; Data mining; Artificial intelligence; Biology; Peptide sequence; Gene; Genetics; Mathematics","score_opus":0.018481855168488638,"score_gpt":0.24497772610081245,"score_spread":0.22649587093232382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114857957","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0048007513,0.00011066174,0.9906308,0.00011450339,0.0000137598345,0.000091786875,0.0003747196,0.0030165743,0.00084646384],"genre_scores_gemma":[0.06972768,0.00027862669,0.92723227,0.000069101356,0.000032187254,0.00015791366,0.0017901986,0.00021519104,0.0004969256],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952355,0.0013195941,0.00074465113,0.0008100386,0.0017305717,0.00015962559],"domain_scores_gemma":[0.9937796,0.0033689027,0.00046744844,0.0014369022,0.00080154825,0.00014560197],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0057404,0.00074009964,0.00084999774,0.0038884657,0.0010574985,0.0038755399,0.0020709136,0.00048472686,0.0033876384],"category_scores_gemma":[0.013284378,0.0005330591,0.0024164324,0.0039181216,0.0011320652,0.005087101,0.0028892583,0.0012056074,0.0016276195],"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":[0.0005790573,0.00032009778,0.008022186,0.0008363432,0.0005353013,0.000930018,0.0010193547,0.10479411,0.019346716,0.35784614,0.009947794,0.49582288],"study_design_scores_gemma":[0.00010718185,0.00016727656,0.0010105941,0.00013001126,0.00023519984,0.00076031475,0.00045383238,0.6403333,0.0270406,0.29746825,0.032197967,0.00009554959],"about_ca_topic_score_codex":0.004718405,"about_ca_topic_score_gemma":0.003838231,"teacher_disagreement_score":0.0057404,"about_ca_system_score_codex":0.0011787966,"about_ca_system_score_gemma":0.0020240713,"threshold_uncertainty_score":0.030358493},"labels":[],"label_agreement":null},{"id":"W2114864966","doi":"10.1186/s12859-015-0469-4","title":"An evidence-based approach to identify aging-related genes in Caenorhabditis elegans","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetics, Aging, and Longevity in Model Organisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Comisión Nacional de Investigación Científica y Tecnológica; Instituto Milenio en Inmunología e Inmunoterapia; Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Caenorhabditis elegans; Model organism; Gene; Organism; Biology; Computational biology; Knowledge base; DNA microarray; Genetics; Computer science; World Wide Web","score_opus":0.04925741564619464,"score_gpt":0.2981212473397274,"score_spread":0.24886383169353277,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114864966","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.108289994,0.0061844173,0.83023214,0.0042119073,0.00018272221,0.0017258866,0.033892304,0.0064458284,0.008834787],"genre_scores_gemma":[0.26310998,0.00132924,0.7173822,0.00068814284,0.00006124284,0.00064584153,0.015757512,0.00013782454,0.0008880212],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99760485,0.000565057,0.00034368702,0.00055174384,0.0008468794,0.000087745095],"domain_scores_gemma":[0.99091434,0.0065676756,0.00058220956,0.00043049385,0.0012798647,0.0002253228],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004017001,0.0010490847,0.00096448464,0.01192776,0.00088273466,0.0022219433,0.0021344125,0.0018514239,0.003937649],"category_scores_gemma":[0.017529635,0.0005039609,0.0024315848,0.004081967,0.000786319,0.001909656,0.0020710998,0.0009876518,0.00045512753],"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":[0.0013399286,0.0011828573,0.062219467,0.007534738,0.0030402709,0.0058010696,0.0012807008,0.22715631,0.037618384,0.0667423,0.023866994,0.56221694],"study_design_scores_gemma":[0.0004043177,0.00045255836,0.018837739,0.0012757492,0.0022391002,0.0015673519,0.0009853563,0.75967973,0.020660043,0.14490975,0.048823755,0.00016441944],"about_ca_topic_score_codex":0.008235015,"about_ca_topic_score_gemma":0.018193154,"teacher_disagreement_score":0.01192776,"about_ca_system_score_codex":0.0019094523,"about_ca_system_score_gemma":0.003099579,"threshold_uncertainty_score":0.021244168},"labels":[],"label_agreement":null},{"id":"W2115044025","doi":"10.1186/1471-2105-14-s9-s4","title":"Classification and assessment tools for structural motif discovery algorithms","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"King Saud University; University of Ottawa","keywords":"Motif (music); Computer science; Structural motif; Benchmark (surveying); Sequence motif; DNA microarray; Data mining; Computational biology; Drug discovery; Machine learning; Algorithm; Artificial intelligence; Bioinformatics; Biology; DNA; Genetics; Gene","score_opus":0.021244962799292395,"score_gpt":0.26984898610286223,"score_spread":0.24860402330356984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115044025","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.086444564,0.012854148,0.7552235,0.0031555558,0.0014053324,0.0025813887,0.04119141,0.0797452,0.017398804],"genre_scores_gemma":[0.22225818,0.0018707218,0.7120502,0.0007660327,0.0004384082,0.0030170232,0.055052493,0.0023119925,0.0022349705],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98133355,0.0033996063,0.0032590374,0.002501696,0.008506302,0.0009997761],"domain_scores_gemma":[0.9367322,0.035759732,0.0062292307,0.0062366403,0.013737557,0.0013046883],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010072104,0.0030332822,0.0017150996,0.016333185,0.001283468,0.004074315,0.0051051,0.0037674732,0.0068276497],"category_scores_gemma":[0.07927176,0.0005860969,0.002832383,0.010796859,0.0008468469,0.005898395,0.0026432425,0.0033237354,0.0041607856],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013638233,0.0014208234,0.034671433,0.003507378,0.00050603173,0.0003229449,0.00032036388,0.061380364,0.0048379246,0.032430295,0.124006175,0.7352324],"study_design_scores_gemma":[0.00035425765,0.0007592859,0.008816237,0.0006994272,0.0001985938,0.0009935232,0.00028652116,0.8390247,0.01579218,0.056205943,0.076712884,0.00015648516],"about_ca_topic_score_codex":0.0026058287,"about_ca_topic_score_gemma":0.0029888833,"teacher_disagreement_score":0.016333185,"about_ca_system_score_codex":0.0029270295,"about_ca_system_score_gemma":0.002936582,"threshold_uncertainty_score":0.053267002},"labels":[],"label_agreement":null},{"id":"W2115059509","doi":"10.1186/1471-2105-15-47","title":"PSEUDOMARKER 2.0: efficient computation of likelihoods using NOMAD","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal; Group for Research in Decision Analysis","funders":"FP7 Health; Air Force Office of Scientific Research; National Institute of Mental Health; National Institute on Aging; National Institutes of Health; Academy of Finland; European Commission","keywords":"Computation; Computer science; Computational biology; DNA microarray; Biology; Algorithm; Genetics; Gene expression; Gene","score_opus":0.017862716838259705,"score_gpt":0.2715878407092353,"score_spread":0.2537251238709756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115059509","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003995353,0.00034431255,0.9411601,0.00020089396,0.0001332171,0.00013828666,0.0024397562,0.048850946,0.002737058],"genre_scores_gemma":[0.029359274,0.00023040394,0.94925886,0.00026685072,0.00006964119,0.00068564614,0.0045286105,0.0128610395,0.0027398001],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977603,0.0009767188,0.0002010221,0.00035570073,0.00054943364,0.00015688738],"domain_scores_gemma":[0.9935272,0.004515706,0.00032789967,0.00063936366,0.0008133316,0.00017655746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00597029,0.0021765532,0.0025774045,0.0023221006,0.001830609,0.0039713737,0.0057987757,0.0022080159,0.056021858],"category_scores_gemma":[0.021134447,0.0026570053,0.002991526,0.0022033355,0.0009776629,0.003561575,0.0038686488,0.003690161,0.01851582],"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":[0.001647402,0.00039271644,0.008603633,0.002598407,0.00078618905,0.00069083035,0.0010126285,0.1827392,0.007063458,0.07017613,0.17796138,0.546328],"study_design_scores_gemma":[0.00031300538,0.00006819771,0.0011230907,0.0001184785,0.00008028377,0.00037613697,0.000112447175,0.87199104,0.0065011065,0.058180135,0.060974497,0.0001615736],"about_ca_topic_score_codex":0.0041018045,"about_ca_topic_score_gemma":0.00916123,"teacher_disagreement_score":0.056021858,"about_ca_system_score_codex":0.0013430491,"about_ca_system_score_gemma":0.003880473,"threshold_uncertainty_score":0.18741179},"labels":[],"label_agreement":null},{"id":"W2115427074","doi":"10.1186/1471-2105-14-186","title":"MITE Digger, an efficient and accurate algorithm for genome wide discovery of miniature inverted repeat transposable elements","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Chromosomal and Genetic Variations","field":"Agricultural and Biological Sciences","cited_by":62,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"General Electric (Canada); University of Toronto","funders":"University of Toronto","keywords":"Transposable element; Mite; Genome; Inverted repeat; Computational biology; Computer science; Algorithm; Biology; Genetics; Gene; Ecology","score_opus":0.017332050745270177,"score_gpt":0.215296391470711,"score_spread":0.19796434072544083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115427074","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.078162506,0.001027047,0.8491204,0.00026434194,0.00010455758,0.00023636347,0.0032994892,0.06557802,0.0022073116],"genre_scores_gemma":[0.12168254,0.0002178855,0.86907756,0.00019905754,0.000023375782,0.00032908315,0.005453802,0.0013775694,0.0016390587],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996506,0.000060959555,0.00002879696,0.00012763172,0.000099826335,0.000032050906],"domain_scores_gemma":[0.99961936,0.00021104579,0.000040429804,0.000044218366,0.000059138783,0.00002585014],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00075868773,0.0009975467,0.0007347913,0.0015156332,0.00065676076,0.00088034704,0.0012040811,0.0008782428,0.0033303162],"category_scores_gemma":[0.0019460011,0.0006208174,0.0007295551,0.0011806221,0.00025262687,0.0009302798,0.0009932574,0.00086542586,0.0016189828],"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":[0.002004585,0.00040939322,0.015334719,0.00091791776,0.00059880764,0.0008820612,0.00049829873,0.036285523,0.1580286,0.0054167663,0.051113978,0.72850925],"study_design_scores_gemma":[0.0006430263,0.00047461336,0.0081892,0.000051450665,0.00015265658,0.0012580141,0.00020295467,0.89390266,0.048503347,0.010007711,0.03651485,0.0000995022],"about_ca_topic_score_codex":0.001453534,"about_ca_topic_score_gemma":0.0032745108,"teacher_disagreement_score":0.0033303162,"about_ca_system_score_codex":0.0004250898,"about_ca_system_score_gemma":0.0008058068,"threshold_uncertainty_score":0.011141002},"labels":[],"label_agreement":null},{"id":"W2116096983","doi":"10.1186/1471-2105-13-102","title":"Workflows for microarray data processing in the Kepler environment","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Canadian Institutes of Health Research; National Science Foundation","keywords":"Workflow; Computer science; Python (programming language); Graphical user interface; Pipeline (software); Java; Software engineering; Database; Programming language","score_opus":0.07304841262008531,"score_gpt":0.30161588278825785,"score_spread":0.22856747016817253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116096983","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004699021,0.0008466615,0.854067,0.00056995073,0.00026568645,0.0013820507,0.016187696,0.11540858,0.0065733073],"genre_scores_gemma":[0.024758192,0.0013209401,0.90623707,0.00043245358,0.00010465417,0.0036917594,0.048739366,0.01189117,0.0028244196],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99394965,0.0013219693,0.0013068671,0.001298549,0.0016561924,0.00046671007],"domain_scores_gemma":[0.9931585,0.001967263,0.0005626668,0.001801633,0.0017842138,0.0007256891],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008339563,0.0029076005,0.0014080355,0.003315593,0.001873069,0.004212614,0.0034421498,0.0014530226,0.011318064],"category_scores_gemma":[0.01156301,0.0014520835,0.0030588575,0.0034471357,0.0012177523,0.002322505,0.004017417,0.0029606745,0.01871565],"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":[0.004595252,0.0006405796,0.007216128,0.007590017,0.0008911149,0.0024286523,0.0028530068,0.086293384,0.16248049,0.0763351,0.25354546,0.3951308],"study_design_scores_gemma":[0.000582471,0.00031828159,0.0053278957,0.00089438667,0.00025343153,0.0012155848,0.00031194647,0.11712434,0.12250644,0.119980365,0.63070154,0.00078329083],"about_ca_topic_score_codex":0.0029529792,"about_ca_topic_score_gemma":0.0018712512,"teacher_disagreement_score":0.011318064,"about_ca_system_score_codex":0.0017389505,"about_ca_system_score_gemma":0.0047542723,"threshold_uncertainty_score":0.044104397},"labels":[],"label_agreement":null},{"id":"W2116128456","doi":"10.1186/1471-2105-15-s3-a1","title":"Highlights from the ISCB Student Council Symposium 2013","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Oxford; Genome Canada; National Science Foundation","keywords":"Library science; Computational biology; Computer science; Data science; Biology","score_opus":0.026457790260734238,"score_gpt":0.26145885002145786,"score_spread":0.2350010597607236,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116128456","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026566416,0.040838696,0.002249364,0.34311718,0.52598006,0.00049603096,0.0046798517,0.000510734,0.07947141],"genre_scores_gemma":[0.028718852,0.08401203,0.005912535,0.09121557,0.28570044,0.0011671677,0.01622752,0.0015024121,0.48554346],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99241805,0.0008836399,0.00033934554,0.0005961377,0.0041035935,0.0016593304],"domain_scores_gemma":[0.98055035,0.00052950036,0.0006261556,0.00027346978,0.008159329,0.00986123],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016326375,0.0021634654,0.0013098146,0.0029431807,0.004500682,0.012116036,0.0025573568,0.005713314,0.04952975],"category_scores_gemma":[0.009086458,0.0006977172,0.001747315,0.0037729032,0.0009993608,0.0026535566,0.006644596,0.009524744,0.031189092],"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":[0.00008591671,0.00006407112,0.00014557253,0.00017811357,0.00000734578,0.000039799972,0.000055041626,0.00006042817,0.00019502621,0.0007644583,0.9800029,0.018401299],"study_design_scores_gemma":[0.000020595113,0.000047280864,0.0012507745,0.00023769519,0.000013417814,0.000020682051,0.00020325117,0.00004678603,0.00021971202,0.00051263877,0.99741143,0.000015836576],"about_ca_topic_score_codex":0.01586283,"about_ca_topic_score_gemma":0.035681672,"teacher_disagreement_score":0.04952975,"about_ca_system_score_codex":0.006882399,"about_ca_system_score_gemma":0.02677345,"threshold_uncertainty_score":0.16569352},"labels":[],"label_agreement":null},{"id":"W2116676712","doi":"10.1186/1471-2105-7-480","title":"RiboSubstrates: a web application addressing the cleavage specificities of ribozymes in designated genomes","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Atlantic Cancer Research Institute; Université de Moncton; Université de Sherbrooke","funders":"Canadian Institutes of Health Research; Atlantic Canada Opportunities Agency; Université de Sherbrooke","keywords":"Ribozyme; Computational biology; Mammalian CPEB3 ribozyme; Biology; Ligase ribozyme; RNA; Gene silencing; Functional genomics; DNA microarray; Hammerhead ribozyme; Computer science; Genome; Gene; Genomics; Genetics; Gene expression","score_opus":0.03215291938696927,"score_gpt":0.24609796270677625,"score_spread":0.213945043319807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116676712","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032417677,0.0027682476,0.22677846,0.0003913655,0.0002590858,0.0006124293,0.03684137,0.6891937,0.010737712],"genre_scores_gemma":[0.21546678,0.0062128804,0.44324437,0.002078784,0.00026967915,0.0031263225,0.17573014,0.11805334,0.03581772],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9996506,0.000049626266,0.00003838696,0.00008102321,0.000120224555,0.000060092647],"domain_scores_gemma":[0.9995536,0.00022273856,0.000085679254,0.0000477754,0.000033146116,0.000057040674],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00074328907,0.0028007047,0.0011824989,0.0017003622,0.000436975,0.0012108266,0.0014485877,0.001472695,0.030907588],"category_scores_gemma":[0.0011383047,0.00086073537,0.0012223445,0.00074079813,0.00034131587,0.0010297735,0.0017794135,0.0013474572,0.021250663],"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":[0.004862101,0.00096764753,0.008947698,0.00620506,0.0006911647,0.0034085955,0.00066942663,0.007637147,0.39713943,0.0071184463,0.21913797,0.34321526],"study_design_scores_gemma":[0.0015580992,0.0010434617,0.015696473,0.0007232451,0.00037976826,0.004570302,0.00019689072,0.07077369,0.5008832,0.012715704,0.3908737,0.000585463],"about_ca_topic_score_codex":0.00039326653,"about_ca_topic_score_gemma":0.000565123,"teacher_disagreement_score":0.030907588,"about_ca_system_score_codex":0.00047714403,"about_ca_system_score_gemma":0.0004697738,"threshold_uncertainty_score":0.10339624},"labels":[],"label_agreement":null},{"id":"W2117044793","doi":"10.1186/1471-2105-6-128","title":"Integrative analysis of multiple gene expression profiles with quality-adjusted effect size models","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":56,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto; SickKids Foundation; Hospital for Sick Children","funders":"","keywords":"Weighting; Data mining; Computer science; Consistency (knowledge bases); DNA microarray; R package; Data quality; Statistical power; Computational biology; Gene; Biology; Statistics; Gene expression; Mathematics; Artificial intelligence; Genetics; Metric (unit)","score_opus":0.023493328889068035,"score_gpt":0.2824609765342343,"score_spread":0.2589676476451663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117044793","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01976239,0.00040650135,0.9786244,0.00017252975,0.000026751852,0.00021636652,0.00019830195,0.00040456027,0.0001881301],"genre_scores_gemma":[0.39465266,0.0006436472,0.5995446,0.0003044046,0.00013045868,0.002048043,0.0015011973,0.00038319608,0.0007917999],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.96688956,0.023966365,0.001165318,0.0048986673,0.0025403434,0.0005397666],"domain_scores_gemma":[0.8685,0.11307842,0.005968133,0.007923437,0.0038679882,0.0006619194],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07380764,0.0021721707,0.0030842081,0.004059989,0.0005347107,0.002397927,0.004054251,0.0019196147,0.0017777111],"category_scores_gemma":[0.10358509,0.0012000512,0.005651215,0.0035455294,0.002304828,0.0023979442,0.0025144673,0.0027515157,0.00040857017],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014379006,0.00039483616,0.043018788,0.0010529883,0.009042166,0.0007702039,0.0011007081,0.6867785,0.017068611,0.044687636,0.001884064,0.1927636],"study_design_scores_gemma":[0.00016950567,0.00032630583,0.009000834,0.00004364073,0.001123431,0.00013453912,0.000052419044,0.93348914,0.0021786403,0.052132376,0.0012767322,0.00007242325],"about_ca_topic_score_codex":0.0030021786,"about_ca_topic_score_gemma":0.002747528,"teacher_disagreement_score":0.07380764,"about_ca_system_score_codex":0.0017366764,"about_ca_system_score_gemma":0.0014943101,"threshold_uncertainty_score":0.3903368},"labels":[],"label_agreement":null},{"id":"W2117463702","doi":"10.1186/1471-2105-9-279","title":"Identifying a few foot-and-mouth disease virus signature nucleotide strings for computational genotyping","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Animal Disease Management and Epidemiology","field":"Agricultural and Biological Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; University of Alberta","keywords":"Genotyping; Foot-and-mouth disease virus; Computational biology; Biology; Signature (topology); DNA microarray; Genetics; Genotype; Virus; Gene; Mathematics","score_opus":0.06867020602029669,"score_gpt":0.25867838621071254,"score_spread":0.19000818019041585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117463702","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46243444,0.00020012181,0.5306108,0.00025459428,0.000031424934,0.000180569,0.0009950631,0.004351912,0.0009410463],"genre_scores_gemma":[0.5540529,0.000068588655,0.44266206,0.00010773298,0.000013180267,0.00018749254,0.00230728,0.00009555304,0.00050524814],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999411,0.00021855114,0.00007013409,0.00014513037,0.00011168069,0.000043511587],"domain_scores_gemma":[0.9978528,0.0012956964,0.00020497621,0.000227982,0.00033398718,0.000084575266],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011955217,0.00052641006,0.000819786,0.0011081917,0.00044386048,0.0006698706,0.00082967937,0.00078624155,0.0013134523],"category_scores_gemma":[0.0055773435,0.00025092348,0.0004667544,0.0008875004,0.00025398514,0.0008111274,0.000435522,0.0005344391,0.00083546917],"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":[0.0016047185,0.0009981061,0.059308685,0.0004804336,0.0002266064,0.00032579797,0.00025321453,0.16434047,0.08538834,0.0025471253,0.005006684,0.6795199],"study_design_scores_gemma":[0.000044600765,0.0001647523,0.00523807,0.000019188661,0.000033413926,0.00017847044,0.000051221417,0.97294307,0.016979005,0.0032232828,0.001104769,0.000020142941],"about_ca_topic_score_codex":0.0012118783,"about_ca_topic_score_gemma":0.0018011112,"teacher_disagreement_score":0.0013134523,"about_ca_system_score_codex":0.000347015,"about_ca_system_score_gemma":0.0008535669,"threshold_uncertainty_score":0.0063225627},"labels":[],"label_agreement":null},{"id":"W2117980752","doi":"10.1186/1471-2105-13-s19-s11","title":"Linearization of ancestral multichromosomal genomes","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Genome; Row; Combinatorics; Linearization; Mathematics; Biology; Genetics; Computer science; Gene; Physics; Nonlinear system","score_opus":0.021088227291032657,"score_gpt":0.25444365989167667,"score_spread":0.233355432600644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117980752","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23085354,0.0004451554,0.75800085,0.00070489047,0.00003076874,0.00014822898,0.0013482888,0.0016593016,0.0068090074],"genre_scores_gemma":[0.66925997,0.00040856077,0.319968,0.00026459896,0.000046224595,0.0001232315,0.004665072,0.00039999417,0.00486436],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999468,0.00013325774,0.000025233705,0.00019868225,0.00009855127,0.000076207405],"domain_scores_gemma":[0.99786264,0.0013414568,0.00024643197,0.00031313836,0.0001375348,0.0000987857],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058900024,0.0005062852,0.00060909335,0.00069206406,0.00057483005,0.0010201081,0.0010178811,0.0007460642,0.007759527],"category_scores_gemma":[0.0042327773,0.0005889629,0.0012795421,0.0007055982,0.000822968,0.0018764071,0.001590277,0.001539213,0.0011814298],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00074053614,0.00027780578,0.0073841936,0.0010151819,0.00015838341,0.00085651723,0.0010485555,0.6641191,0.040173486,0.12487734,0.00849467,0.15085422],"study_design_scores_gemma":[0.000070496986,0.0002047753,0.0021269738,0.000101731384,0.00006165862,0.0005399058,0.0003809839,0.7879854,0.025698192,0.17295772,0.0098249735,0.000047245736],"about_ca_topic_score_codex":0.0023626855,"about_ca_topic_score_gemma":0.0022499303,"teacher_disagreement_score":0.007759527,"about_ca_system_score_codex":0.0009708154,"about_ca_system_score_gemma":0.00066359644,"threshold_uncertainty_score":0.02595824},"labels":[],"label_agreement":null},{"id":"W2119722989","doi":"10.1186/1471-2105-7-391","title":"Probe-level linear model fitting and mixture modeling results in high accuracy detection of differential gene expression","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","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":"Université de Montréal; Institute for Research in Immunology and Cancer","funders":"Natural Sciences and Engineering Research Council of Canada; Université de Montréal","keywords":"Replicate; False positive paradox; Computer science; DNA microarray; Linear model; Replication (statistics); Set (abstract data type); Mixture model; Data set; Expression (computer science); Pattern recognition (psychology); Data mining; Gaussian; Computational biology; Artificial intelligence; Mathematics; Statistics; Gene expression; Gene; Biology; Genetics; Machine learning","score_opus":0.025785161643324863,"score_gpt":0.25112015716946995,"score_spread":0.22533499552614508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119722989","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003665617,0.00009469103,0.9938198,0.00006725674,0.000014407509,0.000028196162,0.000096597054,0.002076143,0.00013735195],"genre_scores_gemma":[0.09499893,0.00019559884,0.8999732,0.00021757351,0.000055562396,0.0004790963,0.0013091009,0.0011973383,0.0015735496],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9863708,0.0068515833,0.00049082655,0.003519009,0.0023964052,0.00037146226],"domain_scores_gemma":[0.9785084,0.015755203,0.000987741,0.003038394,0.0015459189,0.00016426515],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013055963,0.0029029178,0.002664537,0.0028306271,0.0007535546,0.0024291754,0.0023908755,0.003333485,0.0021916202],"category_scores_gemma":[0.04220974,0.001449344,0.0032132568,0.0032895084,0.0013139654,0.0027098777,0.0021956833,0.0039338167,0.004947296],"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":[0.0015009547,0.00044955048,0.00965637,0.0007719152,0.0010796658,0.00025717492,0.0005959028,0.2741415,0.086980976,0.011214804,0.007836144,0.60551506],"study_design_scores_gemma":[0.00005731243,0.00011398154,0.002563387,0.000026986816,0.00010522556,0.00021908859,0.000029437802,0.9620324,0.019922314,0.01119627,0.0036420221,0.00009153881],"about_ca_topic_score_codex":0.0022169645,"about_ca_topic_score_gemma":0.0029578747,"teacher_disagreement_score":0.013055963,"about_ca_system_score_codex":0.0010601358,"about_ca_system_score_gemma":0.0014643379,"threshold_uncertainty_score":0.06904739},"labels":[],"label_agreement":null},{"id":"W2119886845","doi":"10.1186/1471-2105-5-13","title":"SeeGH – A software tool for visualization of whole genome array comparative genomic hybridization data","year":2004,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomic variations and chromosomal abnormalities","field":"Biochemistry, Genetics and Molecular Biology","cited_by":89,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency","funders":"","keywords":"Genome browser; Computer science; Context (archaeology); Genome; Visualization; Chromosome; DNA microarray; Reference genome; Human genome; Comparative genomic hybridization; Software; Genome project; Copy number analysis; Annotation; Computational biology; Biology; Genetics; Data mining; Genomics; Copy-number variation; Gene","score_opus":0.03524230117997183,"score_gpt":0.278305355110992,"score_spread":0.24306305393102018,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119886845","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026244286,0.00042661553,0.4849775,0.0002895597,0.00029363815,0.00037462823,0.021831911,0.48518848,0.0039932216],"genre_scores_gemma":[0.026262913,0.0009242321,0.7832634,0.0010398717,0.00020514148,0.003232382,0.07309039,0.09609008,0.015891545],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981186,0.00036400522,0.00021647598,0.00033807312,0.00080204237,0.000160748],"domain_scores_gemma":[0.9966606,0.001796807,0.0002474562,0.0003467572,0.00076103193,0.00018733383],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002963202,0.002587268,0.0016007676,0.0046835425,0.0007525693,0.0018052333,0.0029864714,0.0014255084,0.09156621],"category_scores_gemma":[0.005822107,0.0015604121,0.0015206287,0.0022195217,0.0005934383,0.002256988,0.0025219603,0.0026346846,0.035229463],"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":[0.0013484211,0.00020786544,0.0023121403,0.002581478,0.0003047321,0.0013206905,0.0009202218,0.0047870344,0.075043075,0.006506208,0.59667957,0.3079886],"study_design_scores_gemma":[0.00081630156,0.00032072098,0.008652905,0.0006260517,0.00019036426,0.0027503842,0.00028202406,0.088257596,0.13243154,0.023202734,0.7418787,0.000590633],"about_ca_topic_score_codex":0.0017736406,"about_ca_topic_score_gemma":0.0017212214,"teacher_disagreement_score":0.09156621,"about_ca_system_score_codex":0.00069811125,"about_ca_system_score_gemma":0.0010897586,"threshold_uncertainty_score":0.30631948},"labels":[],"label_agreement":null},{"id":"W2119894516","doi":"10.1186/1471-2105-8-286","title":"CLUSS: Clustering of protein sequences based on a new similarity measure","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Université de Sherbrooke","keywords":"Cluster analysis; Similarity (geometry); Phylogenetic tree; Biological data; Similarity measure; Computer science; Matching (statistics); Protein sequencing; Measure (data warehouse); Data mining; Protein family; Computational biology; Artificial intelligence; Bioinformatics; Biology; Genetics; Peptide sequence; Mathematics; Gene","score_opus":0.018123837303283746,"score_gpt":0.26742335716123616,"score_spread":0.24929951985795243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119894516","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03803408,0.0010951862,0.9485748,0.00033106882,0.00027639064,0.0004702397,0.00175949,0.0074336524,0.0020251027],"genre_scores_gemma":[0.121409334,0.00049352634,0.86989236,0.0001332208,0.00016744024,0.00063802017,0.0050708074,0.0007482748,0.001447046],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99664235,0.00057424715,0.00039229964,0.0006878562,0.0015404127,0.00016283404],"domain_scores_gemma":[0.99737537,0.00060978474,0.0005150596,0.00043824577,0.0008488234,0.00021277275],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017485389,0.0016574229,0.0018503123,0.0081659015,0.0015031992,0.0017937092,0.0023086064,0.0014821499,0.0029211626],"category_scores_gemma":[0.006044791,0.00058888656,0.0019480101,0.006287765,0.0015526119,0.0029281264,0.0026284144,0.0013420283,0.0022314016],"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":[0.001505477,0.00050707854,0.019046718,0.0022064638,0.0012215478,0.0006455495,0.0011585804,0.12367601,0.07126323,0.035066724,0.035478756,0.7082238],"study_design_scores_gemma":[0.00023680663,0.00045283718,0.005945177,0.00014450596,0.00018170904,0.0010045166,0.00039192446,0.87480634,0.036806982,0.039366625,0.04050222,0.00016044485],"about_ca_topic_score_codex":0.0017343665,"about_ca_topic_score_gemma":0.001598451,"teacher_disagreement_score":0.0081659015,"about_ca_system_score_codex":0.0013511556,"about_ca_system_score_gemma":0.0016682063,"threshold_uncertainty_score":0.009803414},"labels":[],"label_agreement":null},{"id":"W2120027330","doi":"10.1186/1471-2105-10-306","title":"A methodology for the analysis of differential coexpression across the human lifespan","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institute of General Medical Sciences; Canadian Institutes of Health Research; National Institutes of Health","keywords":"Biology; DNA microarray; Similarity (geometry); Differential (mechanical device); Computational biology; Gene; Microarray analysis techniques; Gene expression; Genetics; Computer science; Artificial intelligence","score_opus":0.04775446544068047,"score_gpt":0.34034123617324125,"score_spread":0.2925867707325608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120027330","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024570439,0.00010159674,0.99649566,0.000039833427,0.000026921225,0.00004722106,0.00020690856,0.0003860926,0.00023871627],"genre_scores_gemma":[0.029649464,0.00014919804,0.9684775,0.00006157296,0.00003982895,0.00042709467,0.00053309626,0.00012794413,0.0005343703],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99801207,0.00058891886,0.00020006976,0.00046889254,0.0006560454,0.00007400041],"domain_scores_gemma":[0.9945427,0.0028390128,0.00066892954,0.00077885593,0.0010364468,0.00013407074],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040350007,0.000662891,0.000558939,0.004024462,0.00056330103,0.0010059845,0.001003982,0.0008874371,0.002694309],"category_scores_gemma":[0.0107627865,0.0003863226,0.0015647396,0.0029814623,0.00075251475,0.00067094556,0.0011306081,0.001524155,0.0011613966],"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":[0.00024755087,0.00023866112,0.017415203,0.00083767745,0.0005529475,0.0006745541,0.0009782221,0.043676216,0.08757819,0.07820324,0.009994199,0.7596033],"study_design_scores_gemma":[0.00007180848,0.00042686408,0.039683804,0.00018537242,0.00026268256,0.0029108755,0.00049222226,0.7046286,0.03838547,0.14067918,0.07205134,0.00022174117],"about_ca_topic_score_codex":0.0017851935,"about_ca_topic_score_gemma":0.0017097335,"teacher_disagreement_score":0.0040350007,"about_ca_system_score_codex":0.0006114446,"about_ca_system_score_gemma":0.0012248772,"threshold_uncertainty_score":0.021339357},"labels":[],"label_agreement":null},{"id":"W2120865704","doi":"10.1186/1471-2105-10-s13-o5","title":"Functionally informative tag SNP selection using a pareto-optimal approach: playing the game of life","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Single-nucleotide polymorphism; SNP; SNP genotyping; Genotyping; Selection (genetic algorithm); Tag SNP; Computational biology; Biology; DNA microarray; Genomics; Genetics; Computer science; Genome; Genotype; Gene; Artificial intelligence","score_opus":0.035381251315872116,"score_gpt":0.24991471195998424,"score_spread":0.21453346064411213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120865704","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028752647,0.00041850714,0.9645018,0.0012199288,0.00005665504,0.000101522324,0.00003195937,0.000095630065,0.004821246],"genre_scores_gemma":[0.37545863,0.0006063032,0.6172421,0.0006942026,0.00008481228,0.00034480664,0.00011417442,0.00010753286,0.0053474037],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982936,0.0010992192,0.000049030314,0.00013445553,0.0002742422,0.00014958715],"domain_scores_gemma":[0.9974017,0.0019923723,0.0001122166,0.000096451375,0.00023467175,0.0001625409],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006269546,0.001367368,0.0017674168,0.0011247848,0.0010635351,0.0016968845,0.0016301412,0.0017994908,0.0025862555],"category_scores_gemma":[0.0053467443,0.00062109734,0.0012302651,0.00077807007,0.0021735004,0.0015187943,0.00184801,0.0015939979,0.00038030196],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013707319,0.00015449784,0.00095897284,0.00011771524,0.00012981988,0.00014818474,0.00017308103,0.88289946,0.0016598294,0.06463928,0.001447702,0.047534313],"study_design_scores_gemma":[0.000033639695,0.00006495932,0.000115585804,0.000015607937,0.00002323368,0.000019519397,0.00004094027,0.9637905,0.00035482823,0.034794718,0.0007312594,0.000015247399],"about_ca_topic_score_codex":0.002943357,"about_ca_topic_score_gemma":0.002458455,"teacher_disagreement_score":0.006269546,"about_ca_system_score_codex":0.0015962328,"about_ca_system_score_gemma":0.0024457066,"threshold_uncertainty_score":0.03315693},"labels":[],"label_agreement":null},{"id":"W2120895683","doi":"10.1186/1471-2105-12-8","title":"Flexible taxonomic assignment of ambiguous sequencing reads","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Genetics","keywords":"Metagenomics; Computer science; Set (abstract data type); False positive paradox; Data mining; Computational biology; Matching (statistics); Phylogenetic tree; Biology; Information retrieval; Artificial intelligence; Statistics; Genetics; Mathematics; Gene","score_opus":0.062467156920103004,"score_gpt":0.23166582566858296,"score_spread":0.16919866874847994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120895683","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14323744,0.0004330844,0.85167646,0.000114417184,0.0000750722,0.00022695604,0.00052797276,0.002825962,0.0008826702],"genre_scores_gemma":[0.31711268,0.00012644682,0.67876035,0.00023206968,0.00005463612,0.0002677894,0.00229344,0.00049726095,0.00065528625],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9947365,0.0012050765,0.00046779792,0.0018427746,0.0014992408,0.0002485756],"domain_scores_gemma":[0.9848993,0.0059446967,0.0023294515,0.0032001976,0.003180934,0.0004454082],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0057610907,0.0013004174,0.0010764884,0.0021483123,0.0011756747,0.0015072526,0.0020666253,0.0015883929,0.001438523],"category_scores_gemma":[0.021488044,0.0005175457,0.0010107398,0.0020173648,0.0011643054,0.001379831,0.0023646622,0.0017266102,0.0011984697],"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":[0.0017235775,0.00053073594,0.048132155,0.0012880556,0.0003197872,0.0008150429,0.0015612339,0.12930189,0.2903928,0.007897065,0.004497025,0.5135407],"study_design_scores_gemma":[0.00018986502,0.0004809322,0.021307211,0.00022869704,0.0001476706,0.001247141,0.00046567514,0.7553355,0.1800579,0.028144414,0.012252396,0.00014257726],"about_ca_topic_score_codex":0.0010574431,"about_ca_topic_score_gemma":0.0013076295,"teacher_disagreement_score":0.0057610907,"about_ca_system_score_codex":0.00071781594,"about_ca_system_score_gemma":0.0012355931,"threshold_uncertainty_score":0.030467927},"labels":[],"label_agreement":null},{"id":"W2121109569","doi":"10.1186/1471-2105-9-261","title":"Probe-specific mixed-model approach to detect copy number differences using multiplex ligation-dependent probe amplification (MLPA)","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomic variations and chromosomal abnormalities","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Instituto de Salud Carlos III; Generalitat de Catalunya; European Commission","keywords":"Multiplex ligation-dependent probe amplification; Normalization (sociology); Mixed model; Multiplex; Computer science; Copy-number variation; Bivariate analysis; Statistics; Algorithm; Mathematics; Biology; Machine learning; Bioinformatics; Genetics; Genome","score_opus":0.0513519044060402,"score_gpt":0.24780123376166083,"score_spread":0.19644932935562062,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121109569","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0046463176,0.00009772812,0.99429625,0.00007389235,0.000029938117,0.00009372107,0.00010335356,0.0005190487,0.00013966596],"genre_scores_gemma":[0.2114617,0.00025579977,0.7821403,0.0002912541,0.0000930011,0.0018665426,0.000756001,0.00023412069,0.0029013995],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9949517,0.0030914922,0.00018144496,0.0010083616,0.00057499495,0.00019195172],"domain_scores_gemma":[0.9907312,0.0076288646,0.0004768356,0.00042500359,0.0006009537,0.00013730967],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009639058,0.002241414,0.002384119,0.0016526805,0.0006803157,0.00156391,0.0037969942,0.0020164798,0.0033138648],"category_scores_gemma":[0.012545794,0.0011663178,0.003210918,0.0009554506,0.00093124993,0.0010445144,0.0013498855,0.0027159308,0.00091811526],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012300966,0.00043150235,0.00893454,0.0006298971,0.0025790192,0.0005954134,0.00042964632,0.7834575,0.015360134,0.036713444,0.0022887345,0.14735009],"study_design_scores_gemma":[0.00004698207,0.0001881207,0.00049085845,0.000009095356,0.000126165,0.00007254214,0.000013685922,0.9872528,0.0021810876,0.008756552,0.00082920224,0.00003287945],"about_ca_topic_score_codex":0.0035551602,"about_ca_topic_score_gemma":0.004441779,"teacher_disagreement_score":0.009639058,"about_ca_system_score_codex":0.0013606638,"about_ca_system_score_gemma":0.001480843,"threshold_uncertainty_score":0.050976813},"labels":[],"label_agreement":null},{"id":"W2121776973","doi":"10.1186/1471-2105-15-148","title":"Improvement of domain-level ortholog clustering by optimizing domain-specific sum-of-pairs score","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"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 for Basic Biology; National Bioscience Database Center; Institute of Genetics; Research Organization of Information and Systems","keywords":"Cluster analysis; Pipeline (software); Pairwise comparison; Domain (mathematical analysis); Computer science; DNA microarray; Data mining; Genome; Computational biology; Architecture domain; Biology; Pattern recognition (psychology); Artificial intelligence; Gene; Genetics; Software; Mathematics","score_opus":0.02150140156673435,"score_gpt":0.22381527533736278,"score_spread":0.20231387377062843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121776973","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21071084,0.0006215346,0.7720263,0.00020502917,0.00009005316,0.0002726259,0.0010496802,0.013457269,0.0015665656],"genre_scores_gemma":[0.24560921,0.00014440251,0.7488491,0.00007904279,0.000017249793,0.00018210267,0.0029758136,0.0016616118,0.00048150955],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99635774,0.0010866303,0.00032461662,0.00087881845,0.0011185786,0.00023350194],"domain_scores_gemma":[0.9942648,0.0017722739,0.00062676123,0.00096943864,0.002126326,0.00024042773],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007326044,0.0018464958,0.0019445765,0.0029149128,0.001281549,0.0012725415,0.0022221622,0.0011760052,0.002144653],"category_scores_gemma":[0.014822929,0.0005933823,0.0018831006,0.0020347182,0.00062950386,0.0018669963,0.0018897195,0.0018960536,0.0014853595],"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":[0.0014207194,0.00073812064,0.064691,0.0014519794,0.00085043657,0.00048837723,0.0011386841,0.20487674,0.20059614,0.0057348744,0.016182292,0.5018307],"study_design_scores_gemma":[0.0001490112,0.00027674227,0.012851664,0.00006395258,0.0001403469,0.0002891532,0.00024079377,0.87530535,0.09906547,0.004478313,0.006988066,0.00015110207],"about_ca_topic_score_codex":0.0029160385,"about_ca_topic_score_gemma":0.0036790716,"teacher_disagreement_score":0.007326044,"about_ca_system_score_codex":0.0008409654,"about_ca_system_score_gemma":0.0016796724,"threshold_uncertainty_score":0.03874433},"labels":[],"label_agreement":null},{"id":"W2121981832","doi":"10.1186/1471-2105-13-s9-s2","title":"Modeling and mining term association for improving biomedical information retrieval performance","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Information retrieval; Ranking (information retrieval); Term (time); Term Discrimination; Set (abstract data type); Index (typography); Sentence; Association rule learning; Data mining; Paragraph; Baseline (sea); Artificial intelligence; Search engine; Concept search; Web search query; World Wide Web","score_opus":0.01922306671104155,"score_gpt":0.25661114349442515,"score_spread":0.2373880767833836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121981832","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2823738,0.006230456,0.70120287,0.0006889895,0.00018141096,0.00034539137,0.0014954676,0.005190853,0.0022907464],"genre_scores_gemma":[0.72882843,0.0012786975,0.2641702,0.00015501284,0.00024902652,0.00025427932,0.0035089394,0.00020214575,0.001353249],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99760336,0.0007065035,0.00029978354,0.00066710694,0.00052730594,0.00019599669],"domain_scores_gemma":[0.99451435,0.0028951012,0.0007948313,0.0005432714,0.0011046133,0.00014789445],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029491463,0.0014076835,0.0016889755,0.0047716885,0.00067341287,0.0012455389,0.0012760704,0.0010275949,0.0008680302],"category_scores_gemma":[0.010563579,0.0003167765,0.0017758819,0.005065153,0.0004661964,0.0023683605,0.0006922557,0.0011017265,0.0011827636],"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":[0.0013362985,0.00104634,0.04938056,0.00078767847,0.00055360515,0.0003799863,0.00034916785,0.21372004,0.045995012,0.003292799,0.008934731,0.6742238],"study_design_scores_gemma":[0.000032470354,0.0002765025,0.005062254,0.000020861704,0.0001886033,0.00022242809,0.00005476627,0.9807407,0.009129659,0.0025100387,0.0017243141,0.000037399357],"about_ca_topic_score_codex":0.007986033,"about_ca_topic_score_gemma":0.008732699,"teacher_disagreement_score":0.007986033,"about_ca_system_score_codex":0.0009777248,"about_ca_system_score_gemma":0.001911672,"threshold_uncertainty_score":0.015879095},"labels":[],"label_agreement":null},{"id":"W2122545386","doi":"10.1186/1471-2105-14-s5-s3","title":"Joint genotype inference with germline and somatic mutations","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Centre Hospitalier Universitaire Sainte-Justine","funders":"Foreign Affairs and International Trade Canada; Canadian Institutes of Health Research; Terry Fox Research Institute; Government of Canada","keywords":"Genetics; Biology; Genome; 1000 Genomes Project; Germline; Germline mutation; Exome sequencing; Exome; Computational biology; DNA sequencing; Cancer genome sequencing; Genotype; Whole genome sequencing; Mutation; Gene; Single-nucleotide polymorphism","score_opus":0.012273740109208165,"score_gpt":0.22595126737810664,"score_spread":0.21367752726889847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122545386","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029903496,0.0001941632,0.9638811,0.00018784193,0.000034490244,0.00007176863,0.0027294098,0.002556533,0.00044113502],"genre_scores_gemma":[0.47738716,0.0003931236,0.50177455,0.0005271398,0.00012677998,0.00038700222,0.015065786,0.0011416936,0.0031967412],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99720997,0.0011840968,0.00016797107,0.000998314,0.00029044892,0.00014922085],"domain_scores_gemma":[0.9843126,0.012827856,0.0005460853,0.0018193005,0.00031084334,0.00018339287],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0062379832,0.00094118546,0.0013164242,0.0017292671,0.00073939573,0.0017676533,0.0023451329,0.0018838303,0.004698428],"category_scores_gemma":[0.026088089,0.0012609973,0.0029094866,0.0020927277,0.0009068876,0.0015827308,0.0020550527,0.0021741695,0.0012149608],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009122016,0.00025644578,0.06369409,0.00037143502,0.0010600577,0.0013319384,0.00040273505,0.7173271,0.0062994906,0.022373835,0.0072744745,0.17869623],"study_design_scores_gemma":[0.00007974403,0.00003742928,0.0039991518,0.000027950187,0.00010783771,0.00044745725,0.000037244015,0.93420523,0.0019813962,0.056877695,0.0021673823,0.000031490126],"about_ca_topic_score_codex":0.008780761,"about_ca_topic_score_gemma":0.013467915,"teacher_disagreement_score":0.008780761,"about_ca_system_score_codex":0.00076282147,"about_ca_system_score_gemma":0.0018047867,"threshold_uncertainty_score":0.03298998},"labels":[],"label_agreement":null},{"id":"W2122656565","doi":"10.1186/1471-2105-11-344","title":"Error, reproducibility and sensitivity: a pipeline for data processing of Agilent oligonucleotide expression arrays","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Infection and Immunity","funders":"Biotechnology and Biological Sciences Research Council; University College London Hospitals NHS Foundation Trust; National Institute for Health and Care Research; Wellcome Trust","keywords":"Pipeline (software); DNA microarray; Oligonucleotide; Sensitivity (control systems); Reproducibility; Computational biology; Computer science; Bioinformatics; Biology; Gene expression; Genetics; Engineering; Chemistry; DNA; Gene; Chromatography; Programming language; Electronic engineering","score_opus":0.04951004012177882,"score_gpt":0.31344069538670294,"score_spread":0.2639306552649241,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122656565","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0041736346,0.00025807365,0.8797019,0.00031533567,0.00010281136,0.00079709396,0.0044000275,0.10857675,0.0016743009],"genre_scores_gemma":[0.017112715,0.00025039693,0.96035445,0.00031736863,0.000064941916,0.0029970843,0.006826298,0.008980306,0.0030964375],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9887177,0.0017540451,0.0013783318,0.0024212126,0.005168942,0.00055982615],"domain_scores_gemma":[0.98741883,0.004037233,0.0014722847,0.002267903,0.0044711586,0.0003324889],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01524812,0.0043676603,0.002452041,0.0039454703,0.0014024135,0.004474236,0.0039435653,0.0016318797,0.013000418],"category_scores_gemma":[0.023433134,0.0022879362,0.003130391,0.0027495567,0.001332546,0.0023271977,0.0033498742,0.0038438218,0.014512578],"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":[0.0018768073,0.00045797386,0.013747988,0.0027851192,0.0009053164,0.00080381514,0.0018870624,0.015616287,0.2162526,0.009281094,0.08743943,0.64894646],"study_design_scores_gemma":[0.00034893988,0.0011440594,0.031499963,0.0006114835,0.00065059995,0.0013763616,0.00034114218,0.2706704,0.48590407,0.023832755,0.18256654,0.0010536669],"about_ca_topic_score_codex":0.0023951489,"about_ca_topic_score_gemma":0.002463539,"teacher_disagreement_score":0.01524812,"about_ca_system_score_codex":0.0018095529,"about_ca_system_score_gemma":0.0041907146,"threshold_uncertainty_score":0.08064073},"labels":[],"label_agreement":null},{"id":"W2123076448","doi":"10.1186/1471-2105-11-383","title":"The oligodeoxynucleotide sequences corresponding to never-expressed peptide motifs are mainly located in the non-coding strand","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computational biology; Genetics; Biology; DNA microarray; Coding region; Molecular biology; Gene; Gene expression","score_opus":0.013192514968809728,"score_gpt":0.24217249296437277,"score_spread":0.22897997799556305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123076448","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98964244,0.0009927545,0.0077861696,0.000026982265,0.000022570233,0.000028702727,0.00035281316,0.000027959752,0.0011196927],"genre_scores_gemma":[0.9751406,0.0008098392,0.021640988,0.00008876824,0.000011397486,0.000060203063,0.0010924018,0.000031836924,0.0011239859],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9998228,0.00002463465,0.000018066874,0.000069580274,0.000042276046,0.00002263424],"domain_scores_gemma":[0.9996271,0.00012030121,0.0001246243,0.000033552802,0.00004854285,0.00004589572],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001379099,0.0002713421,0.00021697393,0.00016480406,0.00011638542,0.00024788763,0.00017237569,0.0002582503,0.0015221983],"category_scores_gemma":[0.00030511786,0.0001170079,0.00017198283,0.00021904947,0.00025156283,0.00012592571,0.0001285133,0.00037969407,0.00065031805],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012090981,0.00001294546,0.001225338,0.000073889394,0.000008252424,0.00005348976,0.0000117228865,0.00012353134,0.9965995,0.00010145743,0.000011171323,0.0016578528],"study_design_scores_gemma":[0.000013606998,0.00043314544,0.0123414425,0.000019290097,0.00004974628,0.0007069338,0.000037682406,0.0013203181,0.98215044,0.000273956,0.0026425973,0.000010830448],"about_ca_topic_score_codex":0.00017108521,"about_ca_topic_score_gemma":0.00042488927,"teacher_disagreement_score":0.0015221983,"about_ca_system_score_codex":0.00015644172,"about_ca_system_score_gemma":0.00020827632,"threshold_uncertainty_score":0.005092323},"labels":[],"label_agreement":null},{"id":"W2123808880","doi":"10.1186/1471-2105-6-273","title":"Ancestral sequence alignment under optimal conditions","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Phylogenetic tree; Pairwise comparison; Multiple sequence alignment; Alignment-free sequence analysis; Maximum parsimony; Heuristic; Sequence (biology); Tree (set theory); Biology; Sequence alignment; Algorithm; Computational biology; Computer science; Artificial intelligence; Clade; Mathematics; Genetics; Combinatorics; Gene","score_opus":0.034718946190375424,"score_gpt":0.2832690485862361,"score_spread":0.24855010239586067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123808880","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08774897,0.0016773284,0.8798063,0.0019839911,0.00018526749,0.00020624488,0.0024605019,0.0012710796,0.024660293],"genre_scores_gemma":[0.5131378,0.0015337026,0.47256693,0.0006464902,0.00038623117,0.00061808835,0.006398276,0.00079297007,0.003919462],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995887,0.0016142817,0.0003295439,0.0010949752,0.0007045128,0.00036972843],"domain_scores_gemma":[0.9702206,0.023628112,0.0014055589,0.0025835745,0.0017021948,0.0004599234],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00564116,0.0010836542,0.0016474302,0.002117347,0.0016972554,0.0025865557,0.0016489209,0.0025856895,0.013403969],"category_scores_gemma":[0.04360734,0.00081395236,0.0013974879,0.0027936192,0.0028263815,0.0051711495,0.002991998,0.0032137565,0.0029043285],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00061724,0.00011845989,0.0066728317,0.0008096121,0.00015951181,0.00078184984,0.000683959,0.5644186,0.0033093595,0.35837334,0.011453139,0.05260212],"study_design_scores_gemma":[0.000078566125,0.000059318,0.00087794673,0.00013038672,0.00003830289,0.00047362372,0.0001224683,0.48235157,0.0022606403,0.5075123,0.0060593607,0.000035569647],"about_ca_topic_score_codex":0.001245864,"about_ca_topic_score_gemma":0.00086979824,"teacher_disagreement_score":0.013403969,"about_ca_system_score_codex":0.001773357,"about_ca_system_score_gemma":0.0024140554,"threshold_uncertainty_score":0.044840813},"labels":[],"label_agreement":null},{"id":"W2125076371","doi":"10.1186/1471-2105-15-61","title":"CDSbank: taxonomy-aware extraction, selection, renaming and formatting of protein-coding DNA or amino acid sequences","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"GenBank; Computer science; Disk formatting; Sequence database; Redundancy (engineering); Web server; Data mining; Information retrieval; Database; Computational biology; Biology; The Internet; Genetics; World Wide Web","score_opus":0.024829442139633295,"score_gpt":0.24259199304970877,"score_spread":0.2177625509100755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125076371","genre_codex":"dataset","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00719948,0.0014375327,0.14024848,0.0013440262,0.0013006682,0.0012767268,0.5995298,0.23651142,0.011151815],"genre_scores_gemma":[0.0058151446,0.00095788704,0.2181862,0.000570817,0.00013111424,0.0013775392,0.7501715,0.019076446,0.0037133254],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9963588,0.00060768414,0.00093866827,0.0010766713,0.00077026815,0.00024786207],"domain_scores_gemma":[0.99328095,0.0020340788,0.001028847,0.0013550506,0.0016290719,0.0006720012],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0072832005,0.0043425653,0.0026340995,0.007048734,0.0025951033,0.0050181584,0.004637651,0.002139788,0.04333566],"category_scores_gemma":[0.015777161,0.0028367862,0.0023568494,0.009542727,0.0010382774,0.0047741663,0.004365079,0.004327091,0.07261785],"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":[0.0015765383,0.00017438969,0.002806909,0.0053280457,0.00018260411,0.0006635788,0.0010052713,0.0010345879,0.035646517,0.0051230765,0.87385786,0.07260069],"study_design_scores_gemma":[0.00044504946,0.00018920402,0.0057040863,0.001234257,0.00016870222,0.0008572137,0.00048622667,0.005527087,0.039189413,0.008767234,0.93716586,0.0002657067],"about_ca_topic_score_codex":0.0035709587,"about_ca_topic_score_gemma":0.0035195115,"teacher_disagreement_score":0.04333566,"about_ca_system_score_codex":0.0021642735,"about_ca_system_score_gemma":0.0057016374,"threshold_uncertainty_score":0.1449722},"labels":[],"label_agreement":null},{"id":"W2125456570","doi":"10.1186/1471-2105-11-461","title":"Pan-genome sequence analysis using Panseq: an online tool for the rapid analysis of core and accessory genomic regions","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Escherichia coli research studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":306,"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; Public Health Agency of Canada","funders":"Public Health Agency; Public Health Agency of Canada; Canadian Food Inspection Agency","keywords":"Genome; Biology; Genetics; Multilocus sequence typing; Locus (genetics); Population; Phylogenetic tree; Bacterial genome size; Reference genome; Whole genome sequencing; Computational biology; Gene; Genotype","score_opus":0.11340474752202609,"score_gpt":0.35653608672141324,"score_spread":0.24313133919938715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125456570","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055784628,0.0021490075,0.7127163,0.0004849054,0.00045388768,0.0011366217,0.07007096,0.1514194,0.005784246],"genre_scores_gemma":[0.04882456,0.0008161161,0.8761697,0.0004369767,0.0001082443,0.0019987067,0.057913415,0.010004124,0.0037280768],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987282,0.0003378737,0.00013557503,0.00036544667,0.00034160324,0.00009132091],"domain_scores_gemma":[0.9982974,0.00062775734,0.0004092936,0.00020922183,0.00030232794,0.00015410068],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030162123,0.0023135606,0.001650714,0.0033139705,0.00078964356,0.001298799,0.0013831549,0.00087303866,0.01537657],"category_scores_gemma":[0.0034101026,0.0010380795,0.0013106801,0.0018127002,0.00043257148,0.0016048332,0.0013895737,0.0018428874,0.006255821],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0047667143,0.0007135103,0.02379265,0.004684595,0.0013939078,0.0017391352,0.0015568053,0.004438937,0.47308475,0.005074349,0.13995066,0.33880404],"study_design_scores_gemma":[0.0013630401,0.0018177674,0.06949263,0.00087245996,0.0008113653,0.0034370753,0.0006531489,0.17211604,0.39286682,0.010725374,0.34499,0.00085421425],"about_ca_topic_score_codex":0.00059501274,"about_ca_topic_score_gemma":0.0011412622,"teacher_disagreement_score":0.01537657,"about_ca_system_score_codex":0.00038380278,"about_ca_system_score_gemma":0.0010368861,"threshold_uncertainty_score":0.051439762},"labels":[],"label_agreement":null},{"id":"W2125816119","doi":"10.1186/1471-2105-6-34","title":"Atlas – a data warehouse for integrative bioinformatics","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":163,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of British Columbia Hospital","funders":"Canadian Institutes of Health Research","keywords":"Atlas (anatomy); Data warehouse; Bioinformatics; Computational biology; Data science; Computer science; Biology; Data mining","score_opus":0.030515866595186156,"score_gpt":0.27606820481453165,"score_spread":0.2455523382193455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125816119","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006984635,0.0021381879,0.5951705,0.0035640188,0.0008266193,0.0010807419,0.1526168,0.219586,0.018032517],"genre_scores_gemma":[0.035425197,0.0021049527,0.53644985,0.0021491167,0.00065854564,0.0016982512,0.4029065,0.013670353,0.004937225],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9931191,0.0012487094,0.0015492849,0.0011914733,0.0025303264,0.00036115258],"domain_scores_gemma":[0.9771994,0.0032381632,0.0017417097,0.0097349435,0.005397708,0.002688103],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0093965,0.0018857052,0.0020654672,0.008953859,0.0020783332,0.010801367,0.007324488,0.0017493464,0.011805775],"category_scores_gemma":[0.014435419,0.0018857815,0.003029377,0.01356264,0.001395226,0.011498455,0.008800458,0.004777734,0.015578616],"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":[0.001342863,0.00033138692,0.009533424,0.0025054226,0.0011678801,0.0011860933,0.0013659678,0.016214823,0.014051718,0.10924652,0.6234757,0.21957834],"study_design_scores_gemma":[0.00024048398,0.00013602502,0.0031753439,0.00045085885,0.00028709872,0.00085041503,0.00035953525,0.039949704,0.013030585,0.09342738,0.8477952,0.00029733666],"about_ca_topic_score_codex":0.0036267012,"about_ca_topic_score_gemma":0.0029465242,"teacher_disagreement_score":0.011805775,"about_ca_system_score_codex":0.0018630737,"about_ca_system_score_gemma":0.005823236,"threshold_uncertainty_score":0.049694},"labels":[],"label_agreement":null},{"id":"W2126698259","doi":"10.1186/1471-2105-15-s9-s12","title":"ARYANA: Aligning Reads by Yet Another Approach","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Institute for Research in Fundamental Sciences; Royan Institute; Sharif University of Technology; National Science Foundation","keywords":"Computer science; Search engine indexing; Hash function; Software; Hash table; Scalability; Theoretical computer science; Algorithm; Computer engineering; Information retrieval; Programming language; Database","score_opus":0.011428203836682409,"score_gpt":0.20909785854690072,"score_spread":0.1976696547102183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126698259","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002836914,0.0018234482,0.9420768,0.00037907637,0.0009050087,0.000197637,0.0012276787,0.045060504,0.0054929024],"genre_scores_gemma":[0.01601342,0.0007513843,0.96466744,0.0007275128,0.00024183207,0.00043363933,0.0035283824,0.008890577,0.0047459407],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99414635,0.0011648996,0.00063546665,0.0021875065,0.001619802,0.00024596203],"domain_scores_gemma":[0.99542975,0.0015524839,0.00042485856,0.0016652456,0.000731345,0.00019631897],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004073121,0.002275784,0.0017383313,0.002484339,0.0018028368,0.0037603588,0.004199186,0.0018959588,0.014032678],"category_scores_gemma":[0.01276183,0.0015626969,0.002391838,0.0030821299,0.0014938007,0.0045792297,0.0060275714,0.004883329,0.018952543],"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":[0.000919618,0.00013780213,0.0033113605,0.0027389277,0.000765027,0.0008169511,0.0013884684,0.012063136,0.07495171,0.057540063,0.08535932,0.7600077],"study_design_scores_gemma":[0.00025317527,0.00038869606,0.002013291,0.00068944687,0.0003852674,0.0031693592,0.0005525357,0.10428995,0.11637887,0.12869945,0.64280295,0.00037703654],"about_ca_topic_score_codex":0.0012365533,"about_ca_topic_score_gemma":0.001640975,"teacher_disagreement_score":0.014032678,"about_ca_system_score_codex":0.0007040067,"about_ca_system_score_gemma":0.0018134871,"threshold_uncertainty_score":0.046944022},"labels":[],"label_agreement":null},{"id":"W2126957930","doi":"10.1186/1471-2105-13-15","title":"The EnzymeTracker: an open-source laboratory information management system for sample tracking","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Espace pour la vie; Concordia University","funders":"","keywords":"Computer science; Data management; Interface (matter); Sample (material); Ajax; Data sharing; Tracking system; Data science; World Wide Web; Web application; Database; Filter (signal processing)","score_opus":0.02994307694206483,"score_gpt":0.2968691113282399,"score_spread":0.26692603438617507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126957930","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004714439,0.00048819324,0.44897828,0.00035958271,0.00017345998,0.00077927986,0.0085152155,0.53201026,0.0039812806],"genre_scores_gemma":[0.06971619,0.0015186734,0.7629096,0.0017396515,0.00051784836,0.0030913134,0.09027604,0.041721407,0.028509349],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9955552,0.000468899,0.00063834887,0.0010073753,0.0020916963,0.0002383657],"domain_scores_gemma":[0.9868435,0.0032812143,0.0022598,0.0033891087,0.0026819094,0.001544544],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006614058,0.0020810121,0.001660174,0.0049043954,0.0011374799,0.0040355874,0.0056136977,0.0021249794,0.019709447],"category_scores_gemma":[0.011678515,0.0014413279,0.001055296,0.0033554411,0.00083041814,0.0049240617,0.00414146,0.0026680338,0.023998696],"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":[0.0032304302,0.0012970716,0.01161509,0.0016681873,0.00039921142,0.0012445323,0.0010639933,0.0033595995,0.08648649,0.0067030285,0.2722152,0.61071724],"study_design_scores_gemma":[0.0011533324,0.0007525346,0.018424815,0.00069763977,0.00037573406,0.0022318787,0.0002204496,0.077328615,0.20786671,0.01187267,0.67817485,0.000900666],"about_ca_topic_score_codex":0.00132379,"about_ca_topic_score_gemma":0.00082540425,"teacher_disagreement_score":0.019709447,"about_ca_system_score_codex":0.0010165708,"about_ca_system_score_gemma":0.002865413,"threshold_uncertainty_score":0.06593466},"labels":[],"label_agreement":null},{"id":"W2127147859","doi":"10.1186/1471-2105-9-158","title":"Improving the prediction of mRNA extremities in the parasitic protozoan Leishmania","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA Research and Splicing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Wilfrid Laurier University; Centre hospitalier de l'Université Laval; Centre hospitalier universitaire de Québec","funders":"Canadian Institutes of Health Research; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Polyadenylation; RNA splicing; Biology; DNA microarray; Computational biology; splice; In silico; Genetics; Alternative splicing; Expressed sequence tag; Polypyrimidine tract; Untranslated region; Gene; Messenger RNA; RNA; Gene expression","score_opus":0.026698459540062093,"score_gpt":0.2490251544614015,"score_spread":0.2223266949213394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127147859","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85015166,0.0004385971,0.14576201,0.000048595964,0.000014405725,0.000055514898,0.00084891316,0.0021685057,0.0005117705],"genre_scores_gemma":[0.80688393,0.00022599485,0.18844844,0.000045034478,0.000014987953,0.000052236723,0.0035015708,0.00018417231,0.0006436969],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996954,0.00007003146,0.00002852682,0.00010192666,0.00008032907,0.000023872084],"domain_scores_gemma":[0.99906343,0.0005078851,0.00011605905,0.000042407373,0.00022131349,0.000048981023],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068793114,0.0007088569,0.0003340247,0.00080716546,0.00026547216,0.0005184435,0.0003288779,0.00059985253,0.0008612669],"category_scores_gemma":[0.0021004344,0.00021752992,0.00047712785,0.00052357104,0.00015220913,0.00033963853,0.00031980823,0.00051643344,0.0008890379],"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":[0.0014769634,0.00026934542,0.04759078,0.00072192296,0.00014337811,0.0007787764,0.0002199667,0.09025242,0.6943511,0.00071392884,0.0012100419,0.1622713],"study_design_scores_gemma":[0.00006914416,0.0006890688,0.029860351,0.00003800197,0.00012740708,0.0009001991,0.00010916511,0.7383552,0.22649084,0.0008605618,0.0024696926,0.000030351372],"about_ca_topic_score_codex":0.0009782219,"about_ca_topic_score_gemma":0.0013494974,"teacher_disagreement_score":0.0009782219,"about_ca_system_score_codex":0.00023318763,"about_ca_system_score_gemma":0.00036361226,"threshold_uncertainty_score":0.0036381483},"labels":[],"label_agreement":null},{"id":"W2127314261","doi":"10.1186/1471-2105-13-318","title":"On the contributions of topological features to transcriptional regulatory network robustness","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene Regulatory Network Analysis","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":"McGill University","funders":"Canadian Institutes of Health Research; Fonds Québécois de la Recherche sur la Nature et les Technologies; Compute Canada; Natural Sciences and Engineering Research Council of Canada; McGill University","keywords":"Robustness (evolution); Gene regulatory network; Computational biology; DNA microarray; Topology (electrical circuits); Computer science; Biology; Systems biology; Gene; Genetics; Gene expression; Mathematics; Combinatorics","score_opus":0.0145162027474679,"score_gpt":0.24526934500809067,"score_spread":0.23075314226062277,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127314261","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95923305,0.00031620907,0.03744769,0.00039182822,0.000011921093,0.00002549074,0.00012497112,0.00007468882,0.0023742667],"genre_scores_gemma":[0.99733007,0.00009779288,0.0024420351,0.000013055648,0.000007466703,0.000009663508,0.000034400728,0.000009270971,0.00005618081],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995258,0.0002433033,0.000025333497,0.000066752706,0.000088118024,0.000050589766],"domain_scores_gemma":[0.97866917,0.01885923,0.0012358074,0.0005348572,0.0004164719,0.00028439052],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019231527,0.00038679873,0.00028896052,0.0009606068,0.00042804822,0.0009046299,0.00039286615,0.00058450253,0.0010853186],"category_scores_gemma":[0.015424422,0.0002123222,0.0004649271,0.00050248805,0.001084417,0.0010945685,0.0006099322,0.0005488074,0.00007203316],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014018151,0.00005451262,0.017015453,0.00014155555,0.00008846618,0.00009003551,0.000064301064,0.95834833,0.007211794,0.00724155,0.00014963855,0.009454166],"study_design_scores_gemma":[0.000015817324,0.00012985447,0.006999484,0.00001645981,0.00006673965,0.000090616464,0.00004090458,0.97641456,0.003886463,0.012109264,0.00020823894,0.000021601458],"about_ca_topic_score_codex":0.0010166441,"about_ca_topic_score_gemma":0.0011653784,"teacher_disagreement_score":0.0019231527,"about_ca_system_score_codex":0.0007276939,"about_ca_system_score_gemma":0.00033358554,"threshold_uncertainty_score":0.010170758},"labels":[],"label_agreement":null},{"id":"W2127325366","doi":"10.1186/1471-2105-4-65","title":"Statistical extraction of Drosophila cis-regulatory modules using exhaustive assessment of local word frequency","year":2003,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of General Medical Sciences; National Institutes of Health; York University","keywords":"Genome; DNA microarray; Coding (social sciences); Computational biology; Gene; Locus (genetics); Biology; Coding region; Regulatory sequence; Cis-regulatory module; Genetics; Computer science; Regulation of gene expression; Gene expression; Statistics; Mathematics; Enhancer","score_opus":0.01464972971313742,"score_gpt":0.28023106684270627,"score_spread":0.26558133712956883,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127325366","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5727126,0.00039008752,0.4227223,0.00009969526,0.000012346175,0.00012069433,0.0012199192,0.002282746,0.00043969575],"genre_scores_gemma":[0.76333433,0.00014802799,0.23021503,0.000069013404,0.000028242534,0.0003049488,0.005235306,0.0002083146,0.0004567539],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99913114,0.00030356,0.00010712529,0.0002227387,0.00017198852,0.00006345571],"domain_scores_gemma":[0.98676646,0.010910312,0.00066527154,0.0006247943,0.0008673661,0.00016571245],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002126098,0.0006589715,0.0008739417,0.0035970923,0.00045595982,0.000692779,0.00071917137,0.0008451166,0.00094148365],"category_scores_gemma":[0.014089769,0.0003101607,0.000887544,0.0015516268,0.00044980829,0.0011438946,0.0008617743,0.0004943002,0.0005442343],"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":[0.0013577149,0.00044071866,0.10054434,0.00087893964,0.0007161754,0.0005904516,0.00071463216,0.22195056,0.09065416,0.0031599249,0.0027440132,0.5762483],"study_design_scores_gemma":[0.000049861002,0.00015401744,0.020934211,0.000027951623,0.00008786838,0.0003080985,0.0000911078,0.94953865,0.022995014,0.0050782887,0.00069084443,0.00004413735],"about_ca_topic_score_codex":0.0018976659,"about_ca_topic_score_gemma":0.002888824,"teacher_disagreement_score":0.0035970923,"about_ca_system_score_codex":0.00047540097,"about_ca_system_score_gemma":0.0008432693,"threshold_uncertainty_score":0.011243999},"labels":[],"label_agreement":null},{"id":"W2128104809","doi":"10.1186/1471-2105-11-s1-s64","title":"Predicting protein functions by relaxation labelling protein interaction network","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; University of Toronto","funders":"","keywords":"Labelling; Computational biology; Protein–protein interaction; DNA microarray; Computer science; Relaxation (psychology); Biology; Bioinformatics; Genetics; Neuroscience; Biochemistry; Gene expression; Gene","score_opus":0.008306784005993129,"score_gpt":0.21799601741548452,"score_spread":0.2096892334094914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128104809","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20713411,0.00027570926,0.7904735,0.00013630673,0.00001234351,0.0000578251,0.00031796543,0.00073767226,0.00085453066],"genre_scores_gemma":[0.74810815,0.00020521895,0.24912435,0.000041894116,0.000026858352,0.00012557195,0.0010536581,0.00007971273,0.0012344941],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996873,0.0001135511,0.000012248323,0.00008386926,0.000077482386,0.000025607602],"domain_scores_gemma":[0.99746037,0.0018196413,0.0003139772,0.00012671521,0.00020678717,0.00007247057],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00095701765,0.0005698465,0.0005837877,0.001344409,0.00029677709,0.00045875285,0.0007817772,0.0009404124,0.00096318667],"category_scores_gemma":[0.0031143867,0.00026253902,0.00065636565,0.00073358585,0.00040350502,0.0009159798,0.0004313341,0.0008214375,0.0004104072],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003302517,0.0001268804,0.009727353,0.00014192892,0.0000828552,0.0001086329,0.00007431372,0.88342035,0.016693678,0.0028003196,0.0008130663,0.08568043],"study_design_scores_gemma":[0.0000032018079,0.000012398677,0.0006361859,0.0000020459406,0.0000057101042,0.000013838294,0.0000027543722,0.9968364,0.001182269,0.0012045396,0.000096488046,0.0000041050903],"about_ca_topic_score_codex":0.0034068744,"about_ca_topic_score_gemma":0.003792111,"teacher_disagreement_score":0.0034068744,"about_ca_system_score_codex":0.0008050542,"about_ca_system_score_gemma":0.0004852393,"threshold_uncertainty_score":0.0067741275},"labels":[],"label_agreement":null},{"id":"W2128374023","doi":"10.1186/1471-2105-5-40","title":"Pegasys: software for executing and integrating analyses of biological sequences","year":2004,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":92,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of British Columbia Hospital","funders":"Canadian Institutes of Health Research; Michael Smith Health Research BC","keywords":"Computer science; Workflow; Database; Software; File format; Interface (matter); SQL; Disk formatting; Software framework; Sequence diagram; Source code; Programming language; Data mining; Software system; Operating system; Component-based software engineering; Unified Modeling Language","score_opus":0.06584168856376765,"score_gpt":0.31367912502923484,"score_spread":0.2478374364654672,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128374023","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005887807,0.00080028706,0.49943024,0.00041522543,0.00033410822,0.0006139942,0.020128991,0.46581516,0.0065741674],"genre_scores_gemma":[0.033976365,0.0016835962,0.75794035,0.0012054797,0.0001539289,0.0030378953,0.097351715,0.09169727,0.0129533755],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981951,0.00022048668,0.00025458145,0.0004266032,0.0007424187,0.00016089744],"domain_scores_gemma":[0.99839514,0.00046535692,0.00023776607,0.0003980029,0.0003201763,0.00018349604],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00346714,0.003344846,0.0016805097,0.002749971,0.0011237517,0.0028976141,0.0051197223,0.0015399212,0.022772597],"category_scores_gemma":[0.0051165344,0.0022554917,0.002275968,0.0018013315,0.0012760564,0.0040823175,0.004799511,0.00391686,0.029687086],"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":[0.002602597,0.00048001547,0.0035282904,0.0035365608,0.0006155035,0.0016888046,0.0010999778,0.010726193,0.10185809,0.016093675,0.4697195,0.38805085],"study_design_scores_gemma":[0.00074142194,0.00028370033,0.0048022866,0.00044325687,0.00021121961,0.0023435354,0.00015492528,0.058556046,0.104355566,0.029064104,0.7986127,0.00043124586],"about_ca_topic_score_codex":0.0023265546,"about_ca_topic_score_gemma":0.0012822596,"teacher_disagreement_score":0.022772597,"about_ca_system_score_codex":0.0010825832,"about_ca_system_score_gemma":0.0025854893,"threshold_uncertainty_score":0.07618195},"labels":[],"label_agreement":null},{"id":"W2129978006","doi":"10.1186/1471-2105-9-329","title":"Evaluation of genomic island predictors using a comparative genomics approach","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":284,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Canadian Institutes of Health Research; Genome Canada; Michael Smith Health Research BC; Cystic Fibrosis Foundation","keywords":"Genome; Identification (biology); Comparative genomics; Genomics; Computational biology; Precision and recall; Computer science; Sequence (biology); Data mining; Biology; Genetics; Artificial intelligence; Gene; Ecology","score_opus":0.10055274526987305,"score_gpt":0.2917008819532804,"score_spread":0.19114813668340735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129978006","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8952181,0.0028165118,0.076170005,0.00026538954,0.000095121846,0.00035389996,0.016767813,0.005530246,0.0027830189],"genre_scores_gemma":[0.8021508,0.0004432451,0.14911555,0.0001333867,0.000057296893,0.0003201273,0.04691589,0.00027305976,0.0005906391],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970708,0.0006620733,0.00023730897,0.001094773,0.00073895336,0.00019597894],"domain_scores_gemma":[0.9932696,0.0042043496,0.00040868268,0.0004237937,0.0014313279,0.00026212775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004061918,0.0016476514,0.0012853489,0.008217617,0.00086465024,0.0013701753,0.001652753,0.0012373903,0.0013707052],"category_scores_gemma":[0.008389838,0.00028847577,0.0015491231,0.0046664295,0.0006320661,0.0011411248,0.0011065356,0.00095643423,0.00071491656],"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":[0.0039170156,0.0013810983,0.2529938,0.0030071232,0.0029688992,0.0009948784,0.0005008436,0.24180464,0.117192365,0.0029927497,0.012655223,0.3595913],"study_design_scores_gemma":[0.00010923546,0.0012184103,0.06775353,0.00010370155,0.00039922615,0.0007512395,0.0004301939,0.8779494,0.043907892,0.0021292255,0.0051624896,0.0000853983],"about_ca_topic_score_codex":0.008481373,"about_ca_topic_score_gemma":0.008542989,"teacher_disagreement_score":0.008481373,"about_ca_system_score_codex":0.0014999092,"about_ca_system_score_gemma":0.001364026,"threshold_uncertainty_score":0.021481752},"labels":[],"label_agreement":null},{"id":"W2130138427","doi":"10.1186/s12859-015-0791-x","title":"The Gap Procedure: for the identification of phylogenetic clusters in HIV-1 sequence data","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"HIV Research and Treatment","field":"Immunology and Microbiology","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Jewish General Hospital; Centre Hospitalier de l’Université de Montréal; McGill University","funders":"Canadian Institutes of Health Research","keywords":"Phylogenetic tree; Computational biology; Identification (biology); Sequence (biology); Human immunodeficiency virus (HIV); Biology; DNA microarray; Evolutionary biology; Genetics; Virology; Gene","score_opus":0.13240220328288554,"score_gpt":0.3364065460040913,"score_spread":0.20400434272120577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130138427","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009546707,0.0002002436,0.98340607,0.0001135695,0.000048147638,0.00030927348,0.0007637005,0.005129121,0.00048329285],"genre_scores_gemma":[0.02630654,0.000073219504,0.9710192,0.000053200907,0.000021195243,0.0004379074,0.0011745796,0.00061528425,0.00029876592],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9953447,0.0023902818,0.00024218367,0.00074390945,0.0010854995,0.00019346166],"domain_scores_gemma":[0.9913936,0.0053309654,0.0007181668,0.0012824221,0.0009995288,0.000275276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007601649,0.0013705081,0.0012960773,0.0045106104,0.0015959311,0.0017598448,0.0021498594,0.0022034633,0.00646093],"category_scores_gemma":[0.033696163,0.000788483,0.0014926646,0.0036771356,0.0014307568,0.001921696,0.0026493515,0.0024730877,0.00393749],"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":[0.0011478653,0.0002941939,0.014589302,0.001639403,0.0008007589,0.00069921545,0.0016905295,0.05265365,0.018987412,0.04037075,0.02851587,0.83861107],"study_design_scores_gemma":[0.00030693677,0.00043091932,0.009427142,0.0002939994,0.00018106455,0.0016335986,0.00057531387,0.84782046,0.017472863,0.08478596,0.036915317,0.00015638047],"about_ca_topic_score_codex":0.0015284794,"about_ca_topic_score_gemma":0.0022174772,"teacher_disagreement_score":0.007601649,"about_ca_system_score_codex":0.00068713864,"about_ca_system_score_gemma":0.0026838342,"threshold_uncertainty_score":0.040201843},"labels":[],"label_agreement":null},{"id":"W2130948145","doi":"10.1186/1471-2105-7-448","title":"Gene function classification using Bayesian models with hierarchy-based priors","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Toronto Public Health","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Prior probability; Bayesian probability; Hierarchy; DNA microarray; Computational biology; Computer science; Function (biology); Artificial intelligence; Data mining; Biology; Gene; Genetics; Gene expression","score_opus":0.027646690329334797,"score_gpt":0.24136193798693564,"score_spread":0.21371524765760086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130948145","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.088430874,0.0007043128,0.9065581,0.0010149623,0.00004044059,0.00014654109,0.0006027657,0.0007804691,0.0017214172],"genre_scores_gemma":[0.72902423,0.0006699551,0.26433164,0.0004143071,0.00019895459,0.00047954844,0.0019085611,0.00013038878,0.0028423201],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975974,0.0012416511,0.000102864804,0.0004134255,0.00045252035,0.00019213022],"domain_scores_gemma":[0.9848899,0.012516986,0.00093638833,0.00054354867,0.00086729624,0.00024582935],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008705382,0.001200763,0.001418957,0.0023651347,0.0006969054,0.0018487085,0.0022737158,0.0019418288,0.0024310886],"category_scores_gemma":[0.020657249,0.0008414091,0.0018067756,0.0018848007,0.0010734008,0.0027566496,0.0012540933,0.0021902025,0.0012320757],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005641174,0.00020256486,0.010617249,0.00014156204,0.00016213242,0.00007650199,0.00022328613,0.86962366,0.0012677448,0.015953617,0.0024142172,0.09875336],"study_design_scores_gemma":[0.000023987483,0.00001833573,0.0005554065,0.000011997672,0.000012945188,0.000012449932,0.0000059457725,0.9881661,0.00015270547,0.010841428,0.00018891528,0.000009818733],"about_ca_topic_score_codex":0.021339476,"about_ca_topic_score_gemma":0.016678562,"teacher_disagreement_score":0.021339476,"about_ca_system_score_codex":0.0026877248,"about_ca_system_score_gemma":0.0015153217,"threshold_uncertainty_score":0.046038985},"labels":[],"label_agreement":null},{"id":"W2131414388","doi":"10.1186/1471-2105-10-s1-s5","title":"ComPhy: prokaryotic composite distance phylogenies inferred from whole-genome gene sets","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"University of Missouri; University of Maryland, Baltimore County; National Science Foundation","keywords":"Genome; Phylogenetic tree; Biology; Phylogenetics; Computational biology; Gene; Distance matrices in phylogeny; Bacterial genome size; Distance matrix; Genetics; Evolutionary biology; Bioinformatics; Computer science; Algorithm","score_opus":0.013734137712329139,"score_gpt":0.2341514672249999,"score_spread":0.22041732951267076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131414388","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08643736,0.0015029652,0.816574,0.0004477958,0.0002569602,0.0003323432,0.03305573,0.058060355,0.0033325222],"genre_scores_gemma":[0.18480724,0.00056878396,0.7505233,0.00019167512,0.00009156083,0.0007606639,0.05359188,0.008444301,0.0010205207],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986292,0.00037317147,0.0000907622,0.0004923332,0.0003115448,0.000103041435],"domain_scores_gemma":[0.9949944,0.0030870435,0.00060836144,0.00062226475,0.00045038914,0.0002375567],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025843226,0.001583903,0.0016730728,0.005166555,0.0016868309,0.0020377599,0.00227332,0.001406937,0.008045002],"category_scores_gemma":[0.010372395,0.0012810242,0.002359305,0.004428586,0.0008179379,0.002168963,0.0021434492,0.0028220653,0.0030787617],"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":[0.0049526785,0.00061434525,0.06737282,0.009188286,0.0047991974,0.0019697594,0.0027614352,0.12663944,0.16998778,0.05253372,0.14425907,0.41492146],"study_design_scores_gemma":[0.00070412835,0.0004916958,0.041516684,0.000625024,0.0007615883,0.0028326164,0.00048177651,0.70361465,0.051783696,0.07054643,0.12625067,0.0003910709],"about_ca_topic_score_codex":0.0019301396,"about_ca_topic_score_gemma":0.0023283926,"teacher_disagreement_score":0.008045002,"about_ca_system_score_codex":0.0009488599,"about_ca_system_score_gemma":0.001875134,"threshold_uncertainty_score":0.026913166},"labels":[],"label_agreement":null},{"id":"W2131619859","doi":"10.1186/1471-2105-7-29","title":"Recrafting the neighbor-joining method","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Phylogenetic tree; Implementation; Construct (python library); k-nearest neighbors algorithm; Algorithm; Running time; Data mining; Theoretical computer science; Artificial intelligence; Biology","score_opus":0.015895730640615214,"score_gpt":0.2535508975119469,"score_spread":0.2376551668713317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131619859","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038043226,0.000451743,0.98629075,0.00016100051,0.000124288,0.00017815661,0.00032554773,0.0028207672,0.0058434447],"genre_scores_gemma":[0.037081305,0.0004801328,0.9560233,0.000109391374,0.00007693019,0.00029213683,0.0012465093,0.0009075041,0.0037828381],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99495715,0.0016810311,0.0004088113,0.0010789155,0.0016065788,0.00026749767],"domain_scores_gemma":[0.99033993,0.0036014707,0.0006154067,0.0030021158,0.0021641047,0.00027697234],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038891751,0.0011696384,0.0010194193,0.002328489,0.0014157493,0.0023085854,0.0035999583,0.0012605541,0.016038943],"category_scores_gemma":[0.017545061,0.0007073514,0.0011512816,0.0033709318,0.0010316707,0.0026400678,0.0027479553,0.0023111096,0.014495138],"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":[0.00030431128,0.00021159489,0.004185626,0.00095787726,0.00019255906,0.00036377765,0.00069177983,0.043952435,0.009513987,0.08806539,0.029821629,0.821739],"study_design_scores_gemma":[0.00014798254,0.0002289722,0.001835548,0.000344921,0.00014225236,0.0026007066,0.0005954014,0.4114147,0.028557496,0.216633,0.3373597,0.00013928056],"about_ca_topic_score_codex":0.0017674967,"about_ca_topic_score_gemma":0.0020926162,"teacher_disagreement_score":0.016038943,"about_ca_system_score_codex":0.0006627786,"about_ca_system_score_gemma":0.00219362,"threshold_uncertainty_score":0.053655624},"labels":[],"label_agreement":null},{"id":"W2132548846","doi":"10.1186/1471-2105-13-31","title":"PANDAseq: paired-end assembler for illumina sequences","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Microbial Community Ecology and Physiology","field":"Environmental Science","cited_by":2221,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Ontario","keywords":"Amplicon; Computer science; Sequence (biology); Error detection and correction; k-mer; Amplicon sequencing; Sequence assembly; Computational biology; DNA sequencing; Biology; Genetics; Algorithm; DNA; 16S ribosomal RNA; Polymerase chain reaction; Gene","score_opus":0.039292586530235186,"score_gpt":0.2637107171785696,"score_spread":0.2244181306483344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132548846","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02318856,0.0013464127,0.74520713,0.00031854893,0.00052830897,0.0020014518,0.08074807,0.13093537,0.01572627],"genre_scores_gemma":[0.033251647,0.00064327184,0.79641736,0.0005432412,0.0000929447,0.0039817067,0.13417155,0.018578555,0.012319738],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980946,0.00042779258,0.0001924035,0.0006360273,0.00050455384,0.00014458095],"domain_scores_gemma":[0.99893314,0.00021845143,0.0001374361,0.00026565677,0.00035401067,0.00009127503],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022472441,0.0029899261,0.0016533139,0.0016273553,0.001542559,0.002216277,0.002871254,0.001073271,0.024659362],"category_scores_gemma":[0.0033310477,0.0017142694,0.0017554924,0.001443101,0.00054902374,0.0010931966,0.0019232094,0.0030022329,0.025384886],"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":[0.0028261847,0.00029864672,0.0033190202,0.0043657455,0.0010440657,0.0006557765,0.000609874,0.0059941364,0.63639224,0.0060727284,0.20394938,0.13447231],"study_design_scores_gemma":[0.0005004271,0.0009409166,0.0069362433,0.00025378814,0.0004329438,0.0014548033,0.00012016019,0.06717082,0.4222796,0.0093658585,0.49016717,0.00037737298],"about_ca_topic_score_codex":0.0012104264,"about_ca_topic_score_gemma":0.0021983907,"teacher_disagreement_score":0.024659362,"about_ca_system_score_codex":0.00068924594,"about_ca_system_score_gemma":0.0011649117,"threshold_uncertainty_score":0.08249378},"labels":[],"label_agreement":null},{"id":"W2132626965","doi":"10.1186/s12859-015-0720-z","title":"PROKARYO: an illustrative and interactive computational model of the lactose operon in the bacterium Escherichia coli","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bacterial Genetics and Biotechnology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Operon; Computational biology; Computer science; Biological system; Biology; Escherichia coli; Gene; Genetics","score_opus":0.031199008765802526,"score_gpt":0.2582938359164607,"score_spread":0.22709482715065818,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132626965","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61708486,0.0005976617,0.33069387,0.0019744951,0.000121842895,0.00029119538,0.0033146925,0.002423527,0.043497916],"genre_scores_gemma":[0.9068882,0.00039580237,0.08498035,0.00012973622,0.000019132478,0.00039724787,0.0010396447,0.00018039887,0.005969494],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999013,0.00003838787,0.0000048781203,0.000012451656,0.000030050547,0.000012940735],"domain_scores_gemma":[0.9997004,0.00018930096,0.000023951654,0.000017007542,0.00003315614,0.00003625515],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018387868,0.00048531077,0.0004043587,0.0003473604,0.0005322004,0.0007401807,0.00096412,0.0010900478,0.0061661946],"category_scores_gemma":[0.0006137102,0.00020755788,0.00054649473,0.00032360828,0.00068243133,0.00051233696,0.0009407569,0.00053902913,0.0003107355],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007725979,0.00005021961,0.0014383565,0.0000862049,0.000017773513,0.0003224169,0.00019065259,0.9755765,0.002783085,0.016589984,0.0006307092,0.00223684],"study_design_scores_gemma":[0.000038974085,0.00003364576,0.00030921336,0.000011250332,0.000008957127,0.00005944006,0.00004692272,0.99173087,0.0010278518,0.0034892429,0.0032337657,0.000009959213],"about_ca_topic_score_codex":0.011717794,"about_ca_topic_score_gemma":0.0070216004,"teacher_disagreement_score":0.011717794,"about_ca_system_score_codex":0.00092604244,"about_ca_system_score_gemma":0.0008998364,"threshold_uncertainty_score":0.023299158},"labels":[],"label_agreement":null},{"id":"W2133103440","doi":"10.1186/1471-2105-13-s19-s15","title":"Gene trees and species trees: irreconcilable differences","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; McGill University","funders":"","keywords":"Gene duplication; Biology; Tree (set theory); Gene; Inference; Phylogenetic tree; Tree rearrangement; Extant taxon; Function (biology); Phylogenomics; Phylogenetics; Evolutionary biology; Set (abstract data type); Computational biology; Genetics; Computer science; Mathematics; Combinatorics; Artificial intelligence","score_opus":0.023805937387694338,"score_gpt":0.2215970825356099,"score_spread":0.19779114514791554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133103440","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13431285,0.010785607,0.827883,0.00867598,0.0003993361,0.000067468405,0.00034682348,0.0004878464,0.017041102],"genre_scores_gemma":[0.80749696,0.0028518636,0.18614812,0.00068313844,0.0003258153,0.00010529153,0.000403707,0.0002665046,0.0017185189],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9957611,0.0023729873,0.0001629371,0.0006644534,0.00090618164,0.00013225674],"domain_scores_gemma":[0.96597576,0.026150484,0.0023121105,0.0037751852,0.0013027346,0.00048362568],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008143555,0.00047909352,0.0006099572,0.0020642173,0.0013891363,0.0029839636,0.0016624335,0.0021064167,0.0028305694],"category_scores_gemma":[0.044428986,0.00043169077,0.00061143265,0.0026029525,0.0066641252,0.007888864,0.003036901,0.003072656,0.0006178237],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015753758,0.000019075549,0.00478057,0.00026545237,0.00006781606,0.0003592293,0.0019701084,0.015267995,0.001685569,0.9088235,0.0017561587,0.06484701],"study_design_scores_gemma":[0.000008845739,0.000017237026,0.0014775838,0.00007163379,0.000017853843,0.0005153362,0.0002475339,0.025936736,0.0009359765,0.9625786,0.008173373,0.000019268484],"about_ca_topic_score_codex":0.00032200458,"about_ca_topic_score_gemma":0.00045322764,"teacher_disagreement_score":0.008143555,"about_ca_system_score_codex":0.0017677812,"about_ca_system_score_gemma":0.00062076654,"threshold_uncertainty_score":0.043067753},"labels":[],"label_agreement":null},{"id":"W2133554582","doi":"10.1186/1471-2105-13-326","title":"A computational pipeline for the development of multi-marker bio-signature panels and ensemble classifiers","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vancouver General Hospital; Institute of Infection and Immunity; St. Paul's Hospital; Simon Fraser University; University of British Columbia; Prevention of Organ Failure","funders":"Astellas Pharma; Genome British Columbia; St. Paul's Foundation; Novartis Pharma; Genome Canada","keywords":"Pipeline (software); Computer science; Ensemble learning; Artificial intelligence; Machine learning; Random subspace method; Biomarker discovery; DNA microarray; Biomarker; Data mining; Big data; Receiver operating characteristic; Pattern recognition (psychology); Support vector machine; Proteomics; Biology; Gene","score_opus":0.04168584868854552,"score_gpt":0.2975414227229967,"score_spread":0.2558555740344512,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133554582","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0049455385,0.00008118815,0.9910774,0.00018044942,0.00001764014,0.00016094306,0.00027310266,0.0026918212,0.00057179795],"genre_scores_gemma":[0.07598902,0.000103984814,0.92108685,0.000117718475,0.000025429772,0.00062951155,0.0010520053,0.00016728952,0.00082815345],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99896216,0.0003057748,0.000106602136,0.00022724768,0.00031352462,0.00008464532],"domain_scores_gemma":[0.9967314,0.0019780907,0.0001667125,0.0003621965,0.0006595525,0.00010205684],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00307755,0.0013046601,0.0013267075,0.0015996508,0.0009206342,0.0018488351,0.002108919,0.0011317477,0.0044226027],"category_scores_gemma":[0.008388014,0.00092294044,0.0017992167,0.0014256224,0.0004968951,0.0014464408,0.0018473751,0.0020238564,0.001483921],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022316794,0.0001994287,0.0034318601,0.00021190321,0.00028550532,0.00022735912,0.0001818821,0.6615179,0.005011594,0.013066726,0.0059519853,0.3096907],"study_design_scores_gemma":[0.000015846295,0.0000224269,0.00025575262,0.000008948309,0.000017895312,0.000022360675,0.00001215104,0.98837274,0.0011793732,0.008935855,0.0011463912,0.0000103113625],"about_ca_topic_score_codex":0.009265159,"about_ca_topic_score_gemma":0.010587623,"teacher_disagreement_score":0.009265159,"about_ca_system_score_codex":0.0013610265,"about_ca_system_score_gemma":0.002740706,"threshold_uncertainty_score":0.018422425},"labels":[],"label_agreement":null},{"id":"W2134425468","doi":"10.1186/1471-2105-13-s10-s9","title":"Gene order in rosid phylogeny, inferred from pairwise syntenies among extant genomes","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Extant taxon; Phylogenetics; Biology; Evolutionary biology; Genome; Pairwise comparison; DNA microarray; Computational biology; Gene; Genetics; Computer science; Gene expression; Artificial intelligence","score_opus":0.016163955662212754,"score_gpt":0.22764341752703593,"score_spread":0.21147946186482316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134425468","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9826836,0.00066454883,0.012361138,0.00003876621,0.0000048368947,0.000019168716,0.0032418303,0.00026295063,0.00072308595],"genre_scores_gemma":[0.94650704,0.0004472775,0.039417926,0.000024319714,0.000007333786,0.00002531181,0.013218788,0.00008385218,0.0002681837],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998267,0.000030741703,0.000014910909,0.00008279767,0.000026195154,0.000018691147],"domain_scores_gemma":[0.9994516,0.00026163572,0.00011642457,0.00007956338,0.00004627001,0.000044547327],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045142553,0.0004007656,0.00029363896,0.0023866347,0.0004705027,0.0005863774,0.00040678537,0.00037318072,0.0012959711],"category_scores_gemma":[0.0015769708,0.00020566866,0.00061129336,0.0013947715,0.00021517539,0.0004923818,0.00043388805,0.00045142442,0.0004896536],"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":[0.0014432601,0.00016266666,0.53223425,0.001604844,0.000633139,0.0011219741,0.0017698106,0.05847232,0.2896627,0.004817207,0.0014796377,0.10659825],"study_design_scores_gemma":[0.00010407413,0.0004306629,0.7086554,0.00028481957,0.00097334554,0.0018368424,0.001348296,0.21772793,0.040916704,0.0108905835,0.016759152,0.00007227591],"about_ca_topic_score_codex":0.0026404862,"about_ca_topic_score_gemma":0.004740138,"teacher_disagreement_score":0.0026404862,"about_ca_system_score_codex":0.0005029198,"about_ca_system_score_gemma":0.00045184657,"threshold_uncertainty_score":0.0052502155},"labels":[],"label_agreement":null},{"id":"W2134591904","doi":"10.1186/1471-2105-5-170","title":"PhyME: A probabilistic algorithm for finding motifs in sets of orthologous sequences","year":2004,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":204,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Human Genome Research Institute; W. M. Keck Foundation; National Institutes of Health; National Science Foundation","keywords":"Probabilistic logic; Phylogenetic tree; Motif (music); Expectation–maximization algorithm; Computer science; Computational biology; Biology; Data mining; Algorithm; Gene; Genetics; Artificial intelligence; Maximum likelihood; Mathematics","score_opus":0.0151012122346998,"score_gpt":0.2562718729200442,"score_spread":0.24117066068534443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134591904","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0072295,0.00016888218,0.98792434,0.00010402327,0.000026359307,0.00008428625,0.00045441606,0.0036043404,0.00040375843],"genre_scores_gemma":[0.04721661,0.0001225298,0.9497302,0.00011014476,0.00002810764,0.0003569594,0.0012504556,0.00043497863,0.0007499171],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985662,0.0004696471,0.00010610983,0.0003342518,0.00044866037,0.00007516381],"domain_scores_gemma":[0.99707794,0.002132814,0.00017251684,0.00027805986,0.0002555249,0.00008318749],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030287202,0.0011721496,0.0013419713,0.0026843166,0.00097577804,0.0014038472,0.0025273534,0.0019708234,0.0059665414],"category_scores_gemma":[0.012697678,0.0011333411,0.0017565599,0.0018912669,0.0010178331,0.0032540099,0.0033696252,0.0020342118,0.0018646616],"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":[0.001248614,0.00036381627,0.013152047,0.0012092494,0.0006534145,0.00054739136,0.0005286014,0.16783778,0.021069774,0.042125557,0.017527493,0.7337362],"study_design_scores_gemma":[0.00027058966,0.00015851945,0.0019239874,0.000079311336,0.000078166144,0.00072375505,0.00008228157,0.895408,0.007975809,0.0803318,0.012896437,0.000071409515],"about_ca_topic_score_codex":0.0011756177,"about_ca_topic_score_gemma":0.0022179699,"teacher_disagreement_score":0.0059665414,"about_ca_system_score_codex":0.0004983762,"about_ca_system_score_gemma":0.0014878091,"threshold_uncertainty_score":0.019960105},"labels":[],"label_agreement":null},{"id":"W2135398177","doi":"10.1186/1471-2105-14-s15-s5","title":"Gene tree correction guided by orthology","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université de Montréal","funders":"","keywords":"Tree (set theory); Synteny; Ensembl; Set (abstract data type); Gene; Clade; Biology; Phylogenetic tree; Computer science; Computational biology; Mathematics; Genetics; Combinatorics; Genomics; Genome; Programming language","score_opus":0.012322689451228852,"score_gpt":0.22914997419534575,"score_spread":0.2168272847441169,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135398177","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08455418,0.00044521134,0.8989801,0.000491676,0.00036827815,0.00020939577,0.0012559316,0.011464043,0.0022312214],"genre_scores_gemma":[0.19921002,0.00011225486,0.7930656,0.00016394346,0.000074197706,0.00015272616,0.0025565638,0.002745051,0.0019196313],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99715495,0.0007647314,0.00018753154,0.001069155,0.0006114433,0.00021211272],"domain_scores_gemma":[0.98933977,0.0043355487,0.0009922938,0.0032181796,0.00183458,0.00027962655],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0046499074,0.00094811525,0.00093445985,0.0023294352,0.0012154261,0.0014330606,0.002185363,0.0013341734,0.01107523],"category_scores_gemma":[0.029999394,0.00065233704,0.0013832129,0.0022843818,0.0012472698,0.001821777,0.002327398,0.0023109491,0.0035939936],"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":[0.0025942083,0.00024706646,0.03350505,0.0015240853,0.00048640597,0.0015156568,0.0014569771,0.041600473,0.17299153,0.05543047,0.02530464,0.6633433],"study_design_scores_gemma":[0.00029343963,0.00041432635,0.014788318,0.00020438543,0.00032796036,0.0027172877,0.00050179724,0.6632224,0.14359553,0.10898838,0.064808406,0.00013767811],"about_ca_topic_score_codex":0.0010055911,"about_ca_topic_score_gemma":0.0018701437,"teacher_disagreement_score":0.01107523,"about_ca_system_score_codex":0.0008343231,"about_ca_system_score_gemma":0.0016301785,"threshold_uncertainty_score":0.037050307},"labels":[],"label_agreement":null},{"id":"W2135526239","doi":"10.1186/1471-2105-8-262","title":"False positive reduction in protein-protein interaction predictions using gene ontology annotations","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":72,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Ranking (information retrieval); Gene ontology; Computer science; Protein–protein interaction; Data mining; Set (abstract data type); Measure (data warehouse); Reduction (mathematics); Protein function prediction; Function (biology); Ontology; Computational biology; Machine learning; Protein function; Artificial intelligence; Gene; Bioinformatics; Biology; Mathematics; Genetics; Gene expression","score_opus":0.017851863187489957,"score_gpt":0.27350107672319923,"score_spread":0.2556492135357093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135526239","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6666348,0.0027006867,0.3130344,0.00043417816,0.00025999162,0.00034861555,0.0054549784,0.0078042806,0.0033280642],"genre_scores_gemma":[0.8779077,0.0004173096,0.11378295,0.00015674472,0.00004064452,0.00014589884,0.006966757,0.00019256868,0.00038950465],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9913276,0.0018528498,0.0010247517,0.0019160534,0.0033935097,0.00048532698],"domain_scores_gemma":[0.97911465,0.014048902,0.0021891692,0.0018794884,0.0024905005,0.0002772696],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0072806873,0.0016866496,0.0011510388,0.0034092746,0.0007096478,0.0015317029,0.001379446,0.001117815,0.0007219586],"category_scores_gemma":[0.019867543,0.00027400628,0.0016005208,0.0017657947,0.000662596,0.0014248067,0.0015310344,0.0011682805,0.00067668816],"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":[0.0045322166,0.0009878734,0.281657,0.003646496,0.0018012194,0.0030524908,0.00083300885,0.0966008,0.15136172,0.002339782,0.009108384,0.44407895],"study_design_scores_gemma":[0.000082066326,0.00078840874,0.08625864,0.00029660517,0.0009579747,0.0028429527,0.00042351973,0.6442973,0.24967314,0.0070544262,0.007130686,0.00019422385],"about_ca_topic_score_codex":0.0014845895,"about_ca_topic_score_gemma":0.0017285782,"teacher_disagreement_score":0.0072806873,"about_ca_system_score_codex":0.0005739951,"about_ca_system_score_gemma":0.0010079772,"threshold_uncertainty_score":0.03850442},"labels":[],"label_agreement":null},{"id":"W2135842485","doi":"10.1186/1471-2105-9-507","title":"MetaboMiner – semi-automated identification of metabolites from 2D NMR spectra of complex biofluids","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":199,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Institute for Nanotechnology; University of Alberta","funders":"Genome Alberta; Ministry of Advanced Education, Government of Alberta","keywords":"Metabolomics; Heteronuclear single quantum coherence spectroscopy; NMR spectra database; Proton NMR; Two-dimensional nuclear magnetic resonance spectroscopy; Nuclear magnetic resonance spectroscopy; Chemistry; Heteronuclear molecule; Nuclear magnetic resonance; Spectral line; Biological system; Analytical Chemistry (journal); Chromatography; Stereochemistry; Biology; Physics","score_opus":0.025207410916275246,"score_gpt":0.2568409985779328,"score_spread":0.23163358766165756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135842485","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03171709,0.0011288594,0.6931795,0.00027706055,0.00019035193,0.00046486474,0.018381586,0.25256544,0.0020953265],"genre_scores_gemma":[0.034311213,0.0005471243,0.9371342,0.00020500614,0.00005457118,0.0009571072,0.015973495,0.008902395,0.0019149245],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991972,0.00012165289,0.0000830085,0.00032687787,0.0002174073,0.000053882795],"domain_scores_gemma":[0.99858224,0.0006358312,0.0002876628,0.00014173276,0.00025757862,0.00009491497],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002155606,0.003314043,0.0018542742,0.0039675995,0.0005468031,0.0015566376,0.0016604357,0.0011925396,0.013243968],"category_scores_gemma":[0.003031917,0.0010897274,0.0019307596,0.0014559543,0.00043354183,0.0017119284,0.0014599026,0.0011383865,0.004662303],"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":[0.0036170476,0.00038083614,0.008109656,0.004238835,0.00094205275,0.0014068043,0.000622606,0.011353064,0.4201349,0.0026080136,0.063571244,0.48301485],"study_design_scores_gemma":[0.00063938735,0.00074839365,0.021456582,0.00041043453,0.00038628117,0.0029805135,0.00026250625,0.3472596,0.50382376,0.007242338,0.11408688,0.00070322515],"about_ca_topic_score_codex":0.0011401919,"about_ca_topic_score_gemma":0.0016799881,"teacher_disagreement_score":0.013243968,"about_ca_system_score_codex":0.00047672624,"about_ca_system_score_gemma":0.00124594,"threshold_uncertainty_score":0.044305503},"labels":[],"label_agreement":null},{"id":"W2136671508","doi":"10.1186/1471-2105-11-507","title":"Proteome scanning to predict PDZ domain interactions using support vector machines","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Hippo pathway signaling and YAP/TAZ","field":"Biochemistry, Genetics and Molecular Biology","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"PDZ domain; Computational biology; Proteome; Protein–protein interaction; Support vector machine; DNA microarray; Domain (mathematical analysis); Computer science; Protein Array Analysis; Biology; Human proteome project; Proteomics; Bioinformatics; Artificial intelligence; Genetics; Gene; Gene expression; Mathematics","score_opus":0.017073109368465934,"score_gpt":0.27795528179319323,"score_spread":0.2608821724247273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136671508","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60303146,0.0007488178,0.3866761,0.00035191115,0.00007910084,0.00022515569,0.0017740547,0.005946971,0.0011664449],"genre_scores_gemma":[0.87572074,0.00013877606,0.12074018,0.00008696932,0.000029642468,0.00021671977,0.0023232861,0.00004504497,0.0006985906],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995951,0.00009228656,0.000044761597,0.00011174132,0.00009743017,0.000058557172],"domain_scores_gemma":[0.99874806,0.0007827433,0.00011624635,0.000047570204,0.00025427417,0.00005104784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00092059333,0.0009079008,0.00061187276,0.0009515356,0.00024140929,0.00045816196,0.0005784175,0.00076092867,0.0013362507],"category_scores_gemma":[0.0018562919,0.0002589093,0.00071636384,0.00061886973,0.00017183596,0.00038210736,0.00030811533,0.00085553864,0.00057222607],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012371494,0.00093271583,0.0421499,0.0004305708,0.00041087135,0.00040894395,0.00009570946,0.4963917,0.048399672,0.000993831,0.006228085,0.40232086],"study_design_scores_gemma":[0.000008655082,0.00006629354,0.0016622419,0.0000038347584,0.000010175863,0.00003703191,0.0000069658377,0.99321586,0.004495215,0.0002758843,0.00021336238,0.0000044907797],"about_ca_topic_score_codex":0.0019138213,"about_ca_topic_score_gemma":0.0011672304,"teacher_disagreement_score":0.0019138213,"about_ca_system_score_codex":0.00045256494,"about_ca_system_score_gemma":0.00052778696,"threshold_uncertainty_score":0.0048686266},"labels":[],"label_agreement":null},{"id":"W2136850043","doi":"10.1186/1471-2105-4-2","title":"An automated method for finding molecular complexes in large protein interaction networks","year":2003,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6293,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; University of Toronto; Mount Sinai Hospital","funders":"Canadian Institutes of Health Research","keywords":"Computer science; Tree traversal; Cluster analysis; Protein Interaction Networks; Protein–protein interaction; Interaction network; Data mining; False positive paradox; Computational biology; Theoretical computer science; Algorithm; Artificial intelligence; Biology; Genetics","score_opus":0.017041386901073357,"score_gpt":0.31358256104532667,"score_spread":0.2965411741442533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136850043","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033902088,0.00016389498,0.9921604,0.000086911,0.000029282532,0.00014381553,0.0003529775,0.0030062748,0.0006662793],"genre_scores_gemma":[0.024032325,0.00011955324,0.9733098,0.00004343364,0.00002114662,0.00024108418,0.0009262831,0.000210204,0.0010962569],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983436,0.00025852738,0.00009439225,0.00043600376,0.00078797166,0.00007953751],"domain_scores_gemma":[0.99762255,0.0011007624,0.00024001497,0.00031750364,0.0006254859,0.000093746734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010504818,0.0019191873,0.00101863,0.0064948876,0.0015516861,0.0022663008,0.0022933825,0.0015033259,0.004975339],"category_scores_gemma":[0.0064879986,0.0007598197,0.0012866398,0.0034996518,0.00083499204,0.0019007988,0.0016919619,0.0012624286,0.00247788],"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":[0.0001985323,0.00016532403,0.0041147387,0.00053026585,0.00022944105,0.00041002684,0.00026427122,0.07854603,0.026609654,0.027614247,0.017749753,0.8435677],"study_design_scores_gemma":[0.0000641532,0.00004162094,0.0012120663,0.000041099727,0.000053470685,0.0005785357,0.000076740034,0.9360606,0.01166092,0.029804941,0.02036384,0.00004201227],"about_ca_topic_score_codex":0.0044208225,"about_ca_topic_score_gemma":0.0059556435,"teacher_disagreement_score":0.0064948876,"about_ca_system_score_codex":0.0015145944,"about_ca_system_score_gemma":0.0022339032,"threshold_uncertainty_score":0.01664418},"labels":[],"label_agreement":null},{"id":"W2136961946","doi":"10.1186/1471-2105-11-441","title":"Relations as patterns: bridging the gap between OBO and OWL","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":66,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Ontology; Open Biomedical Ontologies; Web Ontology Language; Ontology components; Semantics (computer science); Ontology language; OWL-S; Description logic; Programming language; Software; Automated reasoning; Protégé; Natural language processing; Bridging (networking); Information retrieval; Semantic Web; Artificial intelligence; Semantic Web Stack","score_opus":0.02210392464390946,"score_gpt":0.2746213768207904,"score_spread":0.25251745217688093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136961946","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004686298,0.00046237215,0.9837969,0.0019654909,0.000122056124,0.00020625089,0.00032352188,0.0022202583,0.006216838],"genre_scores_gemma":[0.061391696,0.0011925237,0.92912185,0.0014386587,0.00013177654,0.00044766563,0.0013144318,0.0018160265,0.0031453401],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98904896,0.003561922,0.0017166854,0.0012008209,0.0037854302,0.0006861262],"domain_scores_gemma":[0.98257154,0.007905746,0.0015079526,0.005675954,0.0017297874,0.00060898124],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0109055415,0.000959811,0.001026063,0.002868053,0.0013848941,0.0060486803,0.0030519078,0.0018029219,0.0036620551],"category_scores_gemma":[0.022963013,0.001523819,0.00215761,0.0038683012,0.005359548,0.014903774,0.0070774877,0.0044196937,0.0015091562],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001878035,0.00013515449,0.0027557795,0.00096451805,0.00009246308,0.0005842083,0.004007187,0.0029410685,0.006007082,0.7302299,0.012202287,0.2398926],"study_design_scores_gemma":[0.00007425381,0.000113838854,0.0016899769,0.0010342924,0.000118699936,0.0012425139,0.0014212951,0.0400511,0.008250876,0.47270635,0.47317,0.00012675539],"about_ca_topic_score_codex":0.008431224,"about_ca_topic_score_gemma":0.00782435,"teacher_disagreement_score":0.0109055415,"about_ca_system_score_codex":0.0020888448,"about_ca_system_score_gemma":0.0042534177,"threshold_uncertainty_score":0.057674766},"labels":[],"label_agreement":null},{"id":"W2136992683","doi":"10.1186/1471-2105-7-41","title":"Discovering semantic features in the literature: a foundation for building functional associations","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":92,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Computer science; Context (archaeology); DNA microarray; Non-negative matrix factorization; Data mining; Semantic similarity; Interpretation (philosophy); Information retrieval; Computational biology; Natural language processing; Gene; Artificial intelligence; Biology; Matrix decomposition; Gene expression; Genetics","score_opus":0.016823192533370328,"score_gpt":0.2701781252555171,"score_spread":0.25335493272214676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136992683","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13231748,0.0053078183,0.8036925,0.006266258,0.00041899158,0.0016830812,0.026575888,0.004960177,0.01877782],"genre_scores_gemma":[0.26701462,0.001964879,0.7094691,0.00035235204,0.00035849985,0.0010506507,0.018530136,0.00025062,0.0010092201],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976655,0.0004730191,0.00044709272,0.0006937452,0.0005813321,0.00013928942],"domain_scores_gemma":[0.98825175,0.006090936,0.0014745492,0.0012407982,0.0024120337,0.0005300347],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030305667,0.0010934476,0.0008559096,0.03348627,0.0019977677,0.0039240182,0.0013904487,0.0013879593,0.0041987174],"category_scores_gemma":[0.018524738,0.00052943005,0.002111416,0.016204134,0.0015858707,0.008341298,0.0022459957,0.0011638979,0.0020170866],"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":[0.00052289997,0.00078331836,0.05005751,0.0032236017,0.0005296736,0.0017811096,0.004183557,0.007317566,0.015157989,0.12435585,0.018518703,0.7735682],"study_design_scores_gemma":[0.00016905193,0.00044231102,0.04330701,0.0028466368,0.0009504606,0.0035724784,0.00604994,0.14399542,0.010947515,0.6435935,0.1438259,0.00029977504],"about_ca_topic_score_codex":0.00260639,"about_ca_topic_score_gemma":0.0035172678,"teacher_disagreement_score":0.03348627,"about_ca_system_score_codex":0.0013264966,"about_ca_system_score_gemma":0.0029854379,"threshold_uncertainty_score":0.016027391},"labels":[],"label_agreement":null},{"id":"W2137751072","doi":"10.1186/1471-2105-8-s5-s1","title":"Articles selected from posters presented at the Tenth Annual International Conference on Research in Computational Biology – Preface","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Università degli Studi di Palermo; Università degli Studi di Udine; International Business Machines Corporation; Broad Institute; Università degli Studi di Padova; U.S. Department of Energy; National Science Foundation","keywords":"Library science; Convention; Operations research; History; Political science; Computer science; Law; Engineering","score_opus":0.06454478139956638,"score_gpt":0.36266369236069484,"score_spread":0.29811891096112847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137751072","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002989987,0.030457376,0.0058788247,0.03227857,0.49282947,0.0011361277,0.0060868724,0.0016797141,0.42666304],"genre_scores_gemma":[0.0048525,0.020141149,0.002845463,0.0058625117,0.15071596,0.00040190693,0.005403766,0.0011600242,0.8086167],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989403,0.000099651756,0.00007987345,0.00021038775,0.00056931487,0.000100487945],"domain_scores_gemma":[0.9957345,0.0006270858,0.00024216625,0.00016138614,0.0021757912,0.0010590721],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013467136,0.0019387392,0.0011973326,0.0038723478,0.001595796,0.00506634,0.0012034682,0.0016457606,0.43672442],"category_scores_gemma":[0.0045569614,0.00044135682,0.0011966092,0.002732835,0.0004463213,0.0026464174,0.0020420116,0.00221264,0.258359],"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":[0.00005511585,0.000027463488,0.000054712338,0.00018507145,0.000006084537,0.000050188864,0.000026300559,0.00003942361,0.00063088303,0.00041728298,0.9684239,0.030083511],"study_design_scores_gemma":[0.000020049758,0.00004177179,0.0006431097,0.00022342808,0.0000090998265,0.00008711802,0.00006174153,0.00008035697,0.00018961843,0.0007868487,0.9978459,0.000011072687],"about_ca_topic_score_codex":0.00060692517,"about_ca_topic_score_gemma":0.0017522633,"teacher_disagreement_score":0.43672442,"about_ca_system_score_codex":0.001175129,"about_ca_system_score_gemma":0.00090420985,"threshold_uncertainty_score":0.80344427},"labels":[],"label_agreement":null},{"id":"W2137820961","doi":"10.1186/1471-2105-8-340","title":"Impact of image segmentation on high-content screening data quality for SK-BR-3 cells","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Women's Health Research Institute","funders":"","keywords":"High-content screening; Computer science; Segmentation; Content (measure theory); Information retrieval; Data science; Computational biology; Artificial intelligence; Biology; Genetics; Mathematics","score_opus":0.07732888352285805,"score_gpt":0.3812900083304241,"score_spread":0.30396112480756604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137820961","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91696554,0.0013009105,0.07685558,0.0005529004,0.00011269964,0.00019055328,0.0011937354,0.0019248413,0.00090320257],"genre_scores_gemma":[0.9301999,0.00032149526,0.06591828,0.00027575786,0.00002085262,0.00013603063,0.0022653663,0.0004252829,0.00043705758],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99651885,0.00079332764,0.00051490497,0.0005611812,0.0014088384,0.0002029628],"domain_scores_gemma":[0.97777987,0.015035355,0.0015135745,0.0014831072,0.0038901775,0.00029800087],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0058994493,0.00061719096,0.0008524261,0.001397882,0.0006545232,0.0011932441,0.0005922455,0.0009723994,0.0009487407],"category_scores_gemma":[0.018649075,0.00030330173,0.000630202,0.00090218696,0.0008254828,0.00061638735,0.0006740126,0.0006360878,0.0003213241],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0030224235,0.00028856934,0.060808796,0.0010232369,0.0002958788,0.0005662229,0.00080211303,0.033405297,0.7425904,0.000409316,0.0022090634,0.15457864],"study_design_scores_gemma":[0.000034410103,0.00067193044,0.08952533,0.000076921686,0.00019191352,0.0009677718,0.00022596902,0.17970516,0.7250742,0.00071942434,0.002726376,0.00008061916],"about_ca_topic_score_codex":0.0033670464,"about_ca_topic_score_gemma":0.002948615,"teacher_disagreement_score":0.0058994493,"about_ca_system_score_codex":0.0011844423,"about_ca_system_score_gemma":0.00076303375,"threshold_uncertainty_score":0.031199634},"labels":[],"label_agreement":null},{"id":"W2139251761","doi":"10.1186/1471-2105-13-s19-s8","title":"A consolidation algorithm for genomes fractionated after higher order polyploidization","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Deutscher Akademischer Austauschdienst","keywords":"Genome; Algorithm; Gene duplication; Consolidation (business); Biology; Fractionation; Computer science; Computational biology; Gene; Genetics; Chemistry","score_opus":0.015573472473317742,"score_gpt":0.25466988657805234,"score_spread":0.2390964141047346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139251761","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.046846088,0.0002900934,0.94793195,0.00017294537,0.00004226237,0.00019323335,0.00016411203,0.0037474646,0.0006119849],"genre_scores_gemma":[0.11714923,0.00009639037,0.8799098,0.00013020329,0.00002980188,0.0002933765,0.0010762917,0.00036367617,0.00095122773],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992206,0.00015184331,0.000106545136,0.00024733535,0.00017634388,0.000097432785],"domain_scores_gemma":[0.995752,0.0020295337,0.00046656665,0.00072003907,0.00083641894,0.00019546827],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020051387,0.0008116288,0.0009589978,0.0015429307,0.00075512996,0.0012622715,0.0023010669,0.0012810627,0.0035437343],"category_scores_gemma":[0.0069608125,0.00055143854,0.0009467906,0.0020996241,0.0007143466,0.0018957683,0.0020335964,0.001278646,0.0012572112],"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":[0.000707857,0.00023139635,0.008157827,0.00021040706,0.00015766111,0.00014930656,0.0004291301,0.14071466,0.025832446,0.009997276,0.0055131516,0.8078989],"study_design_scores_gemma":[0.00012721728,0.00010654764,0.0013888946,0.000019475901,0.000040478193,0.00013470426,0.000067897956,0.976253,0.009634549,0.007957624,0.004251272,0.00001839761],"about_ca_topic_score_codex":0.004302104,"about_ca_topic_score_gemma":0.004195051,"teacher_disagreement_score":0.004302104,"about_ca_system_score_codex":0.0010697442,"about_ca_system_score_gemma":0.0022191668,"threshold_uncertainty_score":0.011854947},"labels":[],"label_agreement":null},{"id":"W2139259976","doi":"10.1186/1471-2105-4-11","title":"PreBIND and Textomy – mining the biomedical literature for protein-protein interactions using a support vector machine","year":2003,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":340,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; National Research Council Canada; Lunenfeld-Tanenbaum Research Institute","funders":"Canadian Institutes of Health Research; Directorate for Biological Sciences; Genome Canada","keywords":"Computer science; Support vector machine; Set (abstract data type); Task (project management); Interaction information; Precision and recall; Recall; Data curation; Interaction network; Artificial intelligence; Protein–protein interaction; Data mining; Machine learning; Database; Information retrieval; Biology","score_opus":0.027212083889263005,"score_gpt":0.29671629648987846,"score_spread":0.26950421260061547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139259976","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3048123,0.03055897,0.44912943,0.0064884583,0.0010801342,0.004479551,0.13948278,0.04922898,0.014739333],"genre_scores_gemma":[0.2728015,0.005532228,0.60241234,0.0007535659,0.00039767078,0.002010341,0.10734342,0.0005317177,0.00821724],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99782807,0.0004170439,0.0005289041,0.00053281244,0.0005994194,0.00009379743],"domain_scores_gemma":[0.9913651,0.004296163,0.0012208937,0.0006881528,0.0021459528,0.00028381593],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036640374,0.0011159106,0.0011307918,0.016906857,0.0006997165,0.0021747882,0.0013259301,0.000947494,0.008280493],"category_scores_gemma":[0.012391887,0.0003690659,0.0013028565,0.0070893094,0.00054024585,0.0021746496,0.0014353298,0.0008191144,0.0046075247],"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":[0.00094555103,0.00039896808,0.02033173,0.0066350196,0.0004595455,0.0010750735,0.0006788184,0.005066533,0.037361152,0.002692855,0.052853905,0.87150097],"study_design_scores_gemma":[0.000700597,0.002955172,0.092262544,0.0023017458,0.0013203892,0.0075510843,0.002627303,0.31728104,0.17062686,0.033459272,0.36847067,0.00044332398],"about_ca_topic_score_codex":0.0022097067,"about_ca_topic_score_gemma":0.0037471433,"teacher_disagreement_score":0.016906857,"about_ca_system_score_codex":0.00080825883,"about_ca_system_score_gemma":0.003111933,"threshold_uncertainty_score":0.02770096},"labels":[],"label_agreement":null},{"id":"W2140058398","doi":"10.1186/1471-2105-11-47","title":"BSSF: a fingerprint based ultrafast binding site similarity search and function analysis server","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Natural Science Foundation of China; McGill University","keywords":"Computer science; Similarity (geometry); Structural genomics; Information retrieval; Data mining; Fingerprint (computing); Genomics; Nearest neighbor search; Function (biology); Computational biology; Genome; Biology; Genetics; Artificial intelligence; Protein structure; Gene; Image (mathematics)","score_opus":0.0262463177668005,"score_gpt":0.2816497731573805,"score_spread":0.25540345539058,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140058398","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07399789,0.0019217686,0.5951756,0.0005035934,0.00024598485,0.00048291424,0.025596375,0.2988402,0.003235597],"genre_scores_gemma":[0.2544711,0.0008980105,0.65779203,0.00050017214,0.00011181885,0.0011503093,0.074709356,0.005455403,0.0049117906],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.998968,0.00014087193,0.000083746585,0.00023316267,0.00043596787,0.00013833246],"domain_scores_gemma":[0.9988022,0.00035333878,0.00014384475,0.0002632283,0.00027061612,0.00016682052],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018169051,0.0018309427,0.0017930118,0.0026318168,0.0009800508,0.0012284385,0.003497753,0.0020178775,0.00784209],"category_scores_gemma":[0.0035064046,0.0009182754,0.0014300634,0.0020305049,0.0004922567,0.0023688856,0.0016557691,0.0017120701,0.0065681315],"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":[0.0040278337,0.0010440218,0.014523869,0.0012442638,0.00055746245,0.00068984344,0.00057503546,0.03239656,0.1666481,0.009716817,0.19324973,0.5753265],"study_design_scores_gemma":[0.00080236007,0.0006054813,0.010272447,0.00008476223,0.00011037939,0.0011898702,0.00018442897,0.8388259,0.07492984,0.018640928,0.05397971,0.00037391647],"about_ca_topic_score_codex":0.005011237,"about_ca_topic_score_gemma":0.0044761547,"teacher_disagreement_score":0.00784209,"about_ca_system_score_codex":0.0011455078,"about_ca_system_score_gemma":0.0023003237,"threshold_uncertainty_score":0.026234388},"labels":[],"label_agreement":null},{"id":"W2140106205","doi":"10.1186/1471-2105-11-63","title":"Validation of differential gene expression algorithms: Application comparing fold-change estimation to hypothesis testing","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"University of Ottawa","keywords":"Computer science; Bayes' theorem; DNA microarray; Algorithm; Nonparametric statistics; Data mining; Replicate; Cross-validation; Statistical hypothesis testing; Machine learning; Bayesian probability; Artificial intelligence; Statistics; Mathematics; Biology; Gene; Gene expression; Genetics","score_opus":0.05775399429316948,"score_gpt":0.27967853765939465,"score_spread":0.2219245433662252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140106205","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028846705,0.0015156091,0.9654309,0.00056448823,0.00015830835,0.00029840937,0.0001873188,0.0011740936,0.001824194],"genre_scores_gemma":[0.4462786,0.00084791624,0.54906505,0.0006338715,0.00018255916,0.0013019757,0.0008943925,0.00043310478,0.00036243055],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9364377,0.04378777,0.0029291625,0.00613095,0.010019631,0.000694764],"domain_scores_gemma":[0.64990526,0.31720978,0.009866205,0.0119197415,0.010303731,0.0007953223],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.09738839,0.0021874874,0.0021096475,0.005533884,0.0010071866,0.0033705956,0.003497296,0.0031411033,0.0023906913],"category_scores_gemma":[0.25428045,0.0005968954,0.002412765,0.0039961403,0.0056484956,0.0029346338,0.0038987023,0.004577865,0.0008484004],"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":[0.0018931642,0.00081230624,0.054159522,0.0027529777,0.0023229744,0.0002685472,0.0010944272,0.3580115,0.013284442,0.08644658,0.0044757915,0.47447768],"study_design_scores_gemma":[0.00016666314,0.00062053633,0.009026091,0.00038672442,0.00019946072,0.00030762723,0.00017131768,0.8680229,0.018307425,0.09896334,0.0037162,0.0001116394],"about_ca_topic_score_codex":0.0012020996,"about_ca_topic_score_gemma":0.00048484353,"teacher_disagreement_score":0.9026116,"about_ca_system_score_codex":0.003106416,"about_ca_system_score_gemma":0.002765792,"threshold_uncertainty_score":0.51504517},"labels":[],"label_agreement":null},{"id":"W2140424919","doi":"10.1186/s12859-015-0622-0","title":"Using Gene Ontology to describe the role of the neurexin-neuroligin-SHANK complex in human, mouse and rat and its relevance to autism","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Autism Spectrum Disorder Research","field":"Neuroscience","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto; Centre for Addiction and Mental Health","funders":"National Human Genome Research Institute; University College London; British Heart Foundation; Parkinson's UK; National Institute for Health and Care Research","keywords":"Neuroligin; Neurexin; Autism; Gene ontology; Autism spectrum disorder; Annotation; Biology; Computational biology; Gene; Genetics; Psychology; Developmental psychology; Gene expression","score_opus":0.14624088114181524,"score_gpt":0.3374047741527832,"score_spread":0.19116389301096795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140424919","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34586713,0.00833749,0.49230856,0.0025552884,0.00078860635,0.0010561565,0.106365755,0.00929102,0.0334301],"genre_scores_gemma":[0.37344936,0.0055458746,0.54865986,0.0005408066,0.00010624064,0.0013201444,0.0608005,0.0013136045,0.008263652],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995714,0.000058849022,0.00006033773,0.00012327833,0.00013087118,0.000055400178],"domain_scores_gemma":[0.99932194,0.00023989587,0.00013600032,0.00010697993,0.00013073761,0.00006444167],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056655216,0.00087331154,0.00034421778,0.005298099,0.00070110324,0.0010711036,0.00071363244,0.0004863321,0.002647889],"category_scores_gemma":[0.0013924894,0.00018489471,0.001148796,0.0052538496,0.00052383984,0.0011899179,0.0010069079,0.00085834187,0.0007080569],"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":[0.0011495382,0.00054281234,0.07490926,0.006536832,0.001145501,0.0041921074,0.0060344934,0.011880243,0.3541041,0.10046587,0.03129338,0.40774578],"study_design_scores_gemma":[0.00015765244,0.0005746169,0.17565198,0.0021629964,0.0013148502,0.0075137364,0.0044923425,0.060930096,0.07855099,0.115867,0.5523988,0.00038498145],"about_ca_topic_score_codex":0.008685723,"about_ca_topic_score_gemma":0.012586318,"teacher_disagreement_score":0.008685723,"about_ca_system_score_codex":0.0009313307,"about_ca_system_score_gemma":0.0014048249,"threshold_uncertainty_score":0.017270327},"labels":[],"label_agreement":null},{"id":"W2140572608","doi":"10.1186/1471-2105-11-s1-s4","title":"Better score function for peptide identification with ETD MS/MS spectra","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; Bioinformatics Solutions (Canada); University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo","keywords":"Electron-transfer dissociation; Tandem mass spectrometry; Proteomics; Peptide; Mass spectrometry; Database search engine; Computer science; Computational biology; Tandem mass tag; Bioinformatics; Chemistry; Chromatography; Quantitative proteomics; Search engine; Biology; Information retrieval; Biochemistry","score_opus":0.015368112956873332,"score_gpt":0.25119998308449154,"score_spread":0.23583187012761822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140572608","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09914156,0.00021271546,0.8921155,0.0002454299,0.000094296265,0.00014179191,0.0005106013,0.0064699235,0.0010682931],"genre_scores_gemma":[0.3224028,0.00013656281,0.6717152,0.00016913122,0.00005550199,0.00027627245,0.0025863012,0.00079247943,0.0018656814],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9968976,0.0007025326,0.00040649233,0.00035707862,0.0014616658,0.0001745205],"domain_scores_gemma":[0.99184775,0.0025184236,0.00061372446,0.00066624145,0.004011535,0.00034219178],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005128999,0.0017374296,0.0011839094,0.003571892,0.0006951278,0.0016962958,0.0017612266,0.0017569436,0.0029328845],"category_scores_gemma":[0.012916521,0.0002751878,0.0010707342,0.0021224672,0.0005840075,0.0026486975,0.0013618725,0.0011479225,0.0015989861],"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":[0.0020618534,0.0011026459,0.040924,0.0005763105,0.0004680713,0.00078086316,0.00033249168,0.16394375,0.13758375,0.010199737,0.01353871,0.6284878],"study_design_scores_gemma":[0.00007999951,0.00024653244,0.006018678,0.000015827998,0.000056718087,0.00039768705,0.000037057835,0.92003405,0.0657472,0.0033801803,0.0038892964,0.00009682748],"about_ca_topic_score_codex":0.0018824745,"about_ca_topic_score_gemma":0.001255063,"teacher_disagreement_score":0.005128999,"about_ca_system_score_codex":0.001412388,"about_ca_system_score_gemma":0.00094129035,"threshold_uncertainty_score":0.02712506},"labels":[],"label_agreement":null},{"id":"W2140818786","doi":"10.1186/1471-2105-13-22","title":"Analysis of energy-based algorithms for RNA secondary structure prediction","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":55,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of British Columbia Hospital","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Leverage (statistics); Algorithm; Computer science; Harmonic mean; Function (biology); Data mining; Mathematics; Artificial intelligence; Statistics; Biology","score_opus":0.014537501140611066,"score_gpt":0.2395444029647138,"score_spread":0.22500690182410274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140818786","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27115896,0.0051565175,0.7135832,0.0009836787,0.00019550322,0.00023304089,0.0012580208,0.002863915,0.0045672012],"genre_scores_gemma":[0.6970421,0.00066883716,0.29447567,0.0003172418,0.00015665656,0.0004564321,0.005334897,0.0004280635,0.0011200988],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956321,0.0016869075,0.00032745354,0.00055594544,0.0015762743,0.0002212625],"domain_scores_gemma":[0.96680343,0.028078875,0.0010295827,0.0013352341,0.0025057772,0.0002471167],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0068456577,0.0011536248,0.0010131723,0.0033278326,0.00081854494,0.0012623209,0.0017445151,0.0018212274,0.0024351373],"category_scores_gemma":[0.03358617,0.00033305422,0.0012631712,0.0023729277,0.00080803054,0.0016251411,0.0012694425,0.0015853068,0.00066208007],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035017676,0.00025748822,0.010705434,0.0002755801,0.00022558484,0.000073708456,0.00007540849,0.86455536,0.0016280151,0.008345026,0.0027226186,0.11078553],"study_design_scores_gemma":[0.000012018925,0.000044968205,0.0010569233,0.000013364051,0.000010191986,0.000032883356,0.0000096737185,0.99156255,0.00063248404,0.006230837,0.00038888713,0.000005258477],"about_ca_topic_score_codex":0.002119841,"about_ca_topic_score_gemma":0.0017255865,"teacher_disagreement_score":0.0068456577,"about_ca_system_score_codex":0.001764265,"about_ca_system_score_gemma":0.0013493868,"threshold_uncertainty_score":0.036203682},"labels":[],"label_agreement":null},{"id":"W2142056356","doi":"10.1186/1471-2105-3-2","title":"The Comparative RNA Web (CRW) Site: an online database of comparative sequence and structure information for ribosomal, intron, and other RNAs","year":2002,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1643,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Dalhousie University","funders":"National Institute of General Medical Sciences; University of Texas at Austin; Welch Foundation; National Institutes of Health; National Science Foundation","keywords":"Intron; RNA; Biology; Phylogenetic tree; Nucleic acid structure; Computational biology; Ribosomal RNA; Genetics; Nucleic acid secondary structure; Sequence (biology); Database; Gene; Computer science","score_opus":0.06946269515937568,"score_gpt":0.2973266295758393,"score_spread":0.22786393441646358,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142056356","genre_codex":"dataset","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01535593,0.009564512,0.110606425,0.0017336702,0.0011197634,0.0007571627,0.7261166,0.061295245,0.07345076],"genre_scores_gemma":[0.022669509,0.004830377,0.15497476,0.00085326657,0.00048169075,0.0012162058,0.7867006,0.0067823385,0.021491285],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99893695,0.00022181305,0.000121945355,0.00024647528,0.0003741659,0.000098605575],"domain_scores_gemma":[0.99808913,0.00062616594,0.00033912584,0.0003041952,0.0002684687,0.0003730171],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00195745,0.0015223671,0.0014318827,0.0061300774,0.0011222295,0.0021854423,0.0023853206,0.0014181134,0.07778636],"category_scores_gemma":[0.0042684493,0.0007198783,0.0005131923,0.008343894,0.00054472836,0.002264224,0.001523338,0.0016844776,0.045031678],"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":[0.00083383534,0.0002654805,0.0029340987,0.0038908988,0.00018610635,0.0005270135,0.0004061414,0.0011074085,0.071026675,0.01996142,0.6361937,0.2626673],"study_design_scores_gemma":[0.00018262214,0.00020186052,0.00845998,0.00061114016,0.0001485923,0.00059792073,0.00014761166,0.0025855363,0.02125021,0.010241918,0.9554652,0.0001075398],"about_ca_topic_score_codex":0.0019882282,"about_ca_topic_score_gemma":0.0019313027,"teacher_disagreement_score":0.07778636,"about_ca_system_score_codex":0.0008319225,"about_ca_system_score_gemma":0.0023705359,"threshold_uncertainty_score":0.2602213},"labels":[],"label_agreement":null},{"id":"W2142664740","doi":"10.1186/1471-2105-13-s9-s3","title":"Inference of gene regulatory subnetworks from time course gene expression data","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"National Natural Science Foundation of China","keywords":"Inference; Gene regulatory network; Computer science; Identification (biology); Computational biology; Block (permutation group theory); Data mining; Set (abstract data type); DNA microarray; Scale (ratio); Gene; Artificial intelligence; Gene expression; Biology; Genetics; Mathematics","score_opus":0.02317497161639883,"score_gpt":0.2607738370857789,"score_spread":0.23759886546938006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142664740","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22609915,0.00027253016,0.77079594,0.00012650354,0.000010664899,0.00008038616,0.0010357922,0.0009601371,0.00061879185],"genre_scores_gemma":[0.682424,0.00022939673,0.3135005,0.000038117523,0.000017958251,0.0001281704,0.0030590096,0.00007625784,0.00052658474],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997234,0.000063686784,0.000011651105,0.0001213566,0.00005222749,0.00002770244],"domain_scores_gemma":[0.9987073,0.000828758,0.00018384948,0.00010406156,0.00011331792,0.000062739826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006910362,0.00043256427,0.0004204866,0.0019783785,0.00030515075,0.00033946455,0.00062833354,0.00044819296,0.00085918914],"category_scores_gemma":[0.0028777597,0.00022851257,0.0007136926,0.00114847,0.00034403373,0.00048547154,0.0003657814,0.0006444806,0.00019867765],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005082256,0.00030877194,0.053155012,0.00044091485,0.0003236649,0.0003510194,0.0002721724,0.63732195,0.1036737,0.008097961,0.0014208222,0.19412577],"study_design_scores_gemma":[0.000008997704,0.000017963333,0.00843145,0.0000070487185,0.000024277078,0.000048097503,0.000023586204,0.9799446,0.005664138,0.005360136,0.00046156632,0.000008114682],"about_ca_topic_score_codex":0.0073548723,"about_ca_topic_score_gemma":0.009616339,"teacher_disagreement_score":0.0073548723,"about_ca_system_score_codex":0.00075454015,"about_ca_system_score_gemma":0.00063071813,"threshold_uncertainty_score":0.014624178},"labels":[],"label_agreement":null},{"id":"W2143416770","doi":"10.1186/1471-2105-15-s13-s2","title":"RiboFSM: Frequent subgraph mining for the discovery of RNA structures and interactions","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University; Simon Fraser University; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Université de Montréal; King Saud University","keywords":"Computational biology; Graph; Computer science; Theoretical computer science; Biology; RNA; DNA microarray; Combinatorics; Genetics; Mathematics; Gene; Gene expression","score_opus":0.01668141282398036,"score_gpt":0.2508486031466072,"score_spread":0.2341671903226268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143416770","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043590557,0.0012835078,0.8610908,0.00044625698,0.00013542153,0.0006613614,0.030392705,0.05983138,0.0025679632],"genre_scores_gemma":[0.12682219,0.0005703132,0.8144744,0.00018155058,0.0000642926,0.0008268966,0.053940006,0.0016889331,0.0014314856],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984029,0.00041853162,0.0001709644,0.00050070253,0.0003880272,0.000118912925],"domain_scores_gemma":[0.99739033,0.0014548987,0.00034413583,0.00042917326,0.0002668859,0.00011463763],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020215607,0.0016917821,0.001545918,0.007514257,0.0012136139,0.001474779,0.0019732455,0.0013824254,0.0051034098],"category_scores_gemma":[0.008129509,0.00080958195,0.002953402,0.0050560483,0.0005688388,0.002010808,0.0014861418,0.0012106432,0.002514832],"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":[0.001311923,0.00077114743,0.031435102,0.00497317,0.0022368135,0.0018349787,0.0013433615,0.097357795,0.054141786,0.030470124,0.11430666,0.65981704],"study_design_scores_gemma":[0.00024818332,0.0003100916,0.010071526,0.00021042002,0.00029689237,0.0017239013,0.00034605787,0.8431854,0.01832808,0.07274846,0.052415192,0.00011575017],"about_ca_topic_score_codex":0.0031293614,"about_ca_topic_score_gemma":0.0064317826,"teacher_disagreement_score":0.007514257,"about_ca_system_score_codex":0.00078832934,"about_ca_system_score_gemma":0.0015046928,"threshold_uncertainty_score":0.017072618},"labels":[],"label_agreement":null},{"id":"W2144030303","doi":"10.1186/1471-2105-15-341","title":"FastMG: a simple, fast, and accurate maximum likelihood procedure to estimate amino acid replacement rate matrices from large data sets","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Inference; Phylogenetic tree; Sequence (biology); Matrix (chemical analysis); Algorithm; Sequence alignment; Computer science; Protein sequencing; Similarity (geometry); Distance matrix; Data mining; Peptide sequence; Biology; Genetics; Artificial intelligence; Gene","score_opus":0.018077665721101796,"score_gpt":0.28126252376126315,"score_spread":0.26318485804016134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144030303","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009792655,0.00063487544,0.9385309,0.0002531024,0.00019259127,0.00038305015,0.0065481495,0.04283484,0.00082991447],"genre_scores_gemma":[0.022347206,0.00030081728,0.9582295,0.00013908448,0.00009138135,0.0009624743,0.010821597,0.006466556,0.00064146356],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9944559,0.0022034503,0.0004977023,0.001056587,0.0015505308,0.0002359683],"domain_scores_gemma":[0.9870781,0.007656714,0.0014806605,0.0018238152,0.0015770354,0.0003838275],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011721582,0.0041286065,0.0030815073,0.0058380538,0.0023532887,0.0031515423,0.0068797497,0.0029323227,0.013357166],"category_scores_gemma":[0.034997195,0.0029426084,0.0033988436,0.003882809,0.0014058615,0.003944672,0.003279189,0.0048376443,0.010987948],"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":[0.002030999,0.0006068033,0.021694044,0.0042498894,0.0032907547,0.0018307524,0.0016865889,0.08993029,0.059885085,0.021877363,0.15352577,0.63939166],"study_design_scores_gemma":[0.001403774,0.00043623568,0.009293744,0.00053520175,0.00058016786,0.0029222849,0.000266781,0.75432634,0.04205986,0.052102797,0.13532037,0.0007524065],"about_ca_topic_score_codex":0.002992873,"about_ca_topic_score_gemma":0.0054020993,"teacher_disagreement_score":0.013357166,"about_ca_system_score_codex":0.0014217104,"about_ca_system_score_gemma":0.004085634,"threshold_uncertainty_score":0.06199038},"labels":[],"label_agreement":null},{"id":"W2144326360","doi":"10.1186/1471-2105-14-s6-s2","title":"Simulating the decentralized processes of the human immune system in a virtual anatomy model","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Artificial Immune Systems Applications","field":"Engineering","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 Calgary","funders":"","keywords":"Computer science; Replicate; Immune system; Distributed computing; Visualization; Human–computer interaction; Artificial intelligence; Biology","score_opus":0.016378069319878806,"score_gpt":0.23870325032892034,"score_spread":0.22232518100904153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144326360","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5104656,0.00023758657,0.46374056,0.0011261726,0.00015445906,0.00022164024,0.00034699423,0.00087570294,0.022831267],"genre_scores_gemma":[0.93677086,0.0001825101,0.054985315,0.00016357994,0.000032210217,0.00016234086,0.00013416573,0.000055872406,0.0075132106],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998559,0.000052436746,0.0000053899266,0.000024321786,0.000037851056,0.000024062028],"domain_scores_gemma":[0.99950314,0.0002806353,0.00005081249,0.000044057535,0.000042149462,0.000079256904],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034648474,0.00040207125,0.0003726132,0.00029450585,0.00044619114,0.0010382032,0.00080016284,0.0011067779,0.0040593627],"category_scores_gemma":[0.0011584625,0.00024256171,0.00065361714,0.00018868317,0.0009153778,0.0005516433,0.0012040255,0.0005471986,0.0003014728],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004955281,0.00004022365,0.0010300471,0.000021002441,0.0000122001775,0.00011320716,0.00013370074,0.9879579,0.0019993184,0.0059506292,0.00026130644,0.0024309412],"study_design_scores_gemma":[0.000024566782,0.000039738323,0.0002943004,0.0000056972945,0.000008014775,0.000042485543,0.000032533626,0.99565166,0.0005506423,0.002419693,0.0009237156,0.000007052739],"about_ca_topic_score_codex":0.006180946,"about_ca_topic_score_gemma":0.004110566,"teacher_disagreement_score":0.006180946,"about_ca_system_score_codex":0.000642586,"about_ca_system_score_gemma":0.0011857993,"threshold_uncertainty_score":0.013579965},"labels":[],"label_agreement":null},{"id":"W2144811782","doi":"10.1186/1471-2105-12-225","title":"Binding Site Prediction for Protein-Protein Interactions and Novel Motif Discovery using Re-occurring Polypeptide Sequences","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Binding site; Proteome; Computational biology; Protein–protein interaction; Plasma protein binding; Sequence motif; Protein Array Analysis; Binding domain; Biology; Sequence (biology); Bioinformatics; DNA microarray; Genetics; Biochemistry; Gene","score_opus":0.045870827510556725,"score_gpt":0.2596847144328296,"score_spread":0.21381388692227288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144811782","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.63048726,0.0040342016,0.32747123,0.00019778356,0.000087835426,0.0003307053,0.02082009,0.013737536,0.0028333392],"genre_scores_gemma":[0.6740135,0.000746237,0.28959784,0.000137204,0.000058056004,0.0002727243,0.033769526,0.00036041831,0.0010444516],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99916077,0.00013616083,0.000072217226,0.0003054636,0.00026718937,0.00005828308],"domain_scores_gemma":[0.99827385,0.0008432909,0.00035700423,0.00017456638,0.000249054,0.00010218788],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008818766,0.0009988182,0.0008828242,0.0029033746,0.00033119306,0.000507056,0.0008941887,0.00095566316,0.0020733124],"category_scores_gemma":[0.002462905,0.00033253516,0.0010802657,0.0018655652,0.00031094116,0.00063697994,0.0006039473,0.00077300624,0.0015130909],"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":[0.0031352867,0.00082139025,0.20394497,0.0038088537,0.0012764197,0.0019002579,0.00037837267,0.09137848,0.32172748,0.0027237048,0.022727562,0.34617728],"study_design_scores_gemma":[0.00017076697,0.0005302446,0.075919636,0.00012254222,0.00025169508,0.002500209,0.00016901441,0.7957172,0.10438829,0.0056832875,0.014440669,0.00010645434],"about_ca_topic_score_codex":0.0013246988,"about_ca_topic_score_gemma":0.0024833737,"teacher_disagreement_score":0.0029033746,"about_ca_system_score_codex":0.00031963023,"about_ca_system_score_gemma":0.000588829,"threshold_uncertainty_score":0.006935954},"labels":[],"label_agreement":null},{"id":"W2144847592","doi":"10.1186/1471-2105-15-35","title":"Inferring clonal evolution of tumors from single nucleotide somatic mutations","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":272,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sinai Health System; University of Toronto; Ontario Institute for Cancer Research","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Genetics; Biology; Somatic cell; DNA microarray; Somatic evolution in cancer; Computational biology; Mutation; Nucleotide; Gene; Gene expression","score_opus":0.010037905264403343,"score_gpt":0.21691627519172957,"score_spread":0.20687836992732622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144847592","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8076327,0.0005846326,0.18872827,0.00018270171,0.0000085921165,0.000033356107,0.0015905905,0.0005146735,0.0007244554],"genre_scores_gemma":[0.96582806,0.00019552412,0.03184812,0.000060463946,0.000013908988,0.000023483499,0.00181364,0.00005185796,0.00016484672],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999711,0.00006296161,0.00001912638,0.00010789172,0.00007209345,0.000026950302],"domain_scores_gemma":[0.9976605,0.0015256656,0.00041364806,0.00016302885,0.00014997766,0.00008712385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010770787,0.00025850083,0.0003186101,0.0014167562,0.00030178882,0.0006483757,0.00042627795,0.00045363716,0.0005077394],"category_scores_gemma":[0.0041163946,0.00022328093,0.00050453644,0.00068148767,0.000385704,0.00046510328,0.0005096632,0.0005317012,0.00015094575],"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":[0.000342306,0.00008807056,0.49401093,0.00025281063,0.00026617336,0.00041131448,0.00034528106,0.33633024,0.044897206,0.0063198176,0.0016480861,0.115087725],"study_design_scores_gemma":[0.000020632295,0.00003690814,0.058491945,0.000035096382,0.000057099547,0.00045366475,0.00008727625,0.9072059,0.014068112,0.017911091,0.001614356,0.000017875034],"about_ca_topic_score_codex":0.0031195472,"about_ca_topic_score_gemma":0.005293585,"teacher_disagreement_score":0.0031195472,"about_ca_system_score_codex":0.0006746215,"about_ca_system_score_gemma":0.00050537154,"threshold_uncertainty_score":0.006202817},"labels":[],"label_agreement":null},{"id":"W2145021813","doi":"10.1186/1471-2105-13-245","title":"An algorithm for chemical genomic profiling that minimizes batch effects: bucket evaluations","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Cluster analysis; DNA microarray; Profiling (computer programming); Normalization (sociology); Genomics; Gene expression profiling; Computational biology; Data mining; Drug discovery; Algorithm; Artificial intelligence; Bioinformatics; Gene; Biology; Gene expression; Genome; Genetics","score_opus":0.03323431744631187,"score_gpt":0.3219691730689637,"score_spread":0.28873485562265183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145021813","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012367363,0.00023865684,0.9803832,0.00030352362,0.000059611542,0.00039698055,0.00045836705,0.0048158793,0.00097629963],"genre_scores_gemma":[0.043873686,0.0000825856,0.95265734,0.00017294406,0.00003256388,0.00047377546,0.001098998,0.0004970679,0.0011110433],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997491,0.0006702395,0.00022827653,0.00053855334,0.0007102183,0.00036160898],"domain_scores_gemma":[0.99559623,0.0023881719,0.00033039408,0.0004449881,0.0010378417,0.00020225187],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039862683,0.0021636588,0.0022082785,0.0028646924,0.0009861558,0.002362146,0.0033527855,0.0020674013,0.0062973453],"category_scores_gemma":[0.012084133,0.0009806368,0.0014914895,0.0028804825,0.0010088317,0.0027776079,0.0030533515,0.0026605104,0.0027622774],"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":[0.0012149378,0.00031391712,0.0046093417,0.00034800766,0.00015468254,0.00012887592,0.00017954905,0.19389597,0.013475217,0.0093181785,0.01338618,0.76297516],"study_design_scores_gemma":[0.00021034852,0.00017456326,0.00061798224,0.000029035195,0.000041128995,0.000081259546,0.00007392284,0.9730153,0.007551168,0.013810336,0.0043621175,0.00003278789],"about_ca_topic_score_codex":0.0042432533,"about_ca_topic_score_gemma":0.00515723,"teacher_disagreement_score":0.0062973453,"about_ca_system_score_codex":0.00211119,"about_ca_system_score_gemma":0.004073533,"threshold_uncertainty_score":0.021081686},"labels":[],"label_agreement":null},{"id":"W2145063082","doi":"10.1186/1471-2105-10-118","title":"ACID: annotation of cassette and integron data","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Antibiotic Resistance in Bacteria","field":"Biochemistry, Genetics and Molecular Biology","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"National Health and Medical Research Council; Medical Research Council; Australian Research Council; Canadian Institutes of Health Research; Macquarie University","keywords":"Integron; Annotation; Integrase; Gene cassette; Computer science; Computational biology; Genome; Genetic genealogy; Biology; Gene; Genetics; Plasmid; Population","score_opus":0.025123547859322238,"score_gpt":0.28154666715376697,"score_spread":0.2564231192944447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145063082","genre_codex":"dataset","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07561187,0.0033304892,0.37332624,0.0010418439,0.00051909743,0.0012594422,0.4204544,0.109688096,0.014768517],"genre_scores_gemma":[0.078023486,0.0014966349,0.2743258,0.00028155782,0.000113452326,0.00064177485,0.63340676,0.0068555484,0.0048549506],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984555,0.00027962582,0.00033790086,0.00034480743,0.0004856581,0.000096452226],"domain_scores_gemma":[0.99588275,0.0013477162,0.00053555815,0.0007241922,0.0011264479,0.0003834083],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002682558,0.001816394,0.0011036294,0.0048626177,0.0011080243,0.0020595088,0.0017147437,0.0011868621,0.014060183],"category_scores_gemma":[0.00900605,0.0006491022,0.000879119,0.0057177222,0.00050015945,0.0026094005,0.0022730788,0.0013476092,0.009822632],"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":[0.007860239,0.00046355894,0.022477446,0.015855912,0.00048266788,0.004128739,0.0045694006,0.008481115,0.2651614,0.016637271,0.2713671,0.3825152],"study_design_scores_gemma":[0.00029889535,0.0004291944,0.022457585,0.0012964386,0.0003117959,0.0029606759,0.00086958916,0.026952827,0.09511705,0.014005811,0.8349359,0.00036415842],"about_ca_topic_score_codex":0.0022094965,"about_ca_topic_score_gemma":0.0019952736,"teacher_disagreement_score":0.014060183,"about_ca_system_score_codex":0.0007321157,"about_ca_system_score_gemma":0.0019086956,"threshold_uncertainty_score":0.047035933},"labels":[],"label_agreement":null},{"id":"W2145428772","doi":"10.1186/1471-2105-12-481","title":"U-Compare bio-event meta-service: compatible BioNLP event extraction services","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Brain Injury Research Center; U.S. National Library of Medicine; National Institute of General Medical Sciences; Precursory Research for Embryonic Science and Technology; National Institute on Drug Abuse; Directorate for Biological Sciences; National Institutes of Health; Fonds Wetenschappelijk Onderzoek; China Scholarship Council; Joint Information Systems Committee; Vlaamse regering; Biotechnology and Biological Sciences Research Council; University of Tokyo; Korea Institute of Science and Technology Information; University of Massachusetts Amherst; Korea Institute of Science and Technology; Norges Teknisk-Naturvitenskapelige Universitet; Japan Society for the Promotion of Science; Academy of Finland; Ministry of Education, Culture, Sports, Science and Technology; National Institute of Advanced Industrial Science and Technology","keywords":"Computer science; Event (particle physics); Biomedical text mining; Interoperability; Service (business); Task (project management); Data mining; Extraction (chemistry); Information extraction; Information retrieval; Text mining; World Wide Web; Systems engineering; Engineering","score_opus":0.0833120254126558,"score_gpt":0.30913784916280196,"score_spread":0.22582582375014615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145428772","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017534753,0.00054818945,0.49286693,0.0015731998,0.0002571987,0.00075311674,0.03239492,0.4424699,0.011601807],"genre_scores_gemma":[0.247581,0.0007525967,0.606661,0.0024990253,0.00035123332,0.0014433253,0.100085795,0.031303458,0.00932248],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99669206,0.00070465886,0.00053471443,0.00062404317,0.001202534,0.00024202354],"domain_scores_gemma":[0.9882627,0.0051478073,0.001112488,0.0031914972,0.0016582046,0.0006273083],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008919743,0.0015320437,0.0015260144,0.004514329,0.0011532744,0.0039085676,0.0032789025,0.0022579762,0.017189924],"category_scores_gemma":[0.021053838,0.00092192984,0.00173875,0.004234874,0.0006558629,0.0062543266,0.0036950447,0.0014388751,0.0067285546],"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":[0.009973699,0.0011831885,0.035828177,0.0035299477,0.0011867981,0.0026917937,0.0024424267,0.016226195,0.044383127,0.04815237,0.39895228,0.43545],"study_design_scores_gemma":[0.0011633626,0.00040588796,0.016145602,0.0005142892,0.00046923532,0.002359299,0.0011153934,0.2965636,0.15967642,0.055354375,0.46563148,0.0006010712],"about_ca_topic_score_codex":0.004294055,"about_ca_topic_score_gemma":0.003399448,"teacher_disagreement_score":0.017189924,"about_ca_system_score_codex":0.0016712148,"about_ca_system_score_gemma":0.0027302487,"threshold_uncertainty_score":0.057506025},"labels":[],"label_agreement":null},{"id":"W2145664842","doi":"10.1186/1471-2105-13-s3-s4","title":"Combining automated peak tracking in SAR by NMR with structure-based backbone assignment from 15N-NOESY","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Two-dimensional nuclear magnetic resonance spectroscopy; Biological system; Computer science; Drug discovery; Chemistry; Algorithm; Stereochemistry; Biology","score_opus":0.007970372992195376,"score_gpt":0.2326558932292477,"score_spread":0.22468552023705232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145664842","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03488652,0.00035318575,0.9461618,0.00018909205,0.00006171264,0.00009218319,0.00022425191,0.017209733,0.0008216535],"genre_scores_gemma":[0.07723912,0.00019306225,0.9200527,0.00013079826,0.000035204142,0.00009925226,0.00056605897,0.0010791959,0.00060461817],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988288,0.00028911632,0.00006809594,0.00041444186,0.00030096187,0.00009850036],"domain_scores_gemma":[0.997505,0.0012101984,0.0003392451,0.0004058523,0.0004014688,0.0001383119],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042396463,0.002025104,0.0016983835,0.0017453764,0.0007314859,0.0014686729,0.0021323094,0.0015900861,0.0021525915],"category_scores_gemma":[0.0050233463,0.0010006059,0.001118705,0.0012724373,0.00072272413,0.0025346724,0.001721182,0.0019504172,0.0015524745],"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":[0.0012262738,0.00067759067,0.004274291,0.0006535513,0.00040840742,0.00025560238,0.00025118265,0.17978422,0.15240328,0.0030068806,0.0083431,0.6487156],"study_design_scores_gemma":[0.000066904766,0.0001578096,0.0008214541,0.000017403172,0.00004634791,0.00012309836,0.00004101039,0.92872673,0.0633374,0.0041640624,0.0024223493,0.00007539786],"about_ca_topic_score_codex":0.0020014255,"about_ca_topic_score_gemma":0.0032894413,"teacher_disagreement_score":0.0042396463,"about_ca_system_score_codex":0.0008148017,"about_ca_system_score_gemma":0.0021335313,"threshold_uncertainty_score":0.022421658},"labels":[],"label_agreement":null},{"id":"W2145683333","doi":"10.1186/1471-2105-8-324","title":"Mining and state-space modeling and verification of sub-networks from large-scale biomolecular networks","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Computer science; Component (thermodynamics); Context (archaeology); Cluster analysis; Biological network; Function (biology); Network model; Distributed computing; Gene regulatory network; DNA microarray; Systems biology; Data mining; Artificial intelligence; Bioinformatics; Biology","score_opus":0.008122024849831223,"score_gpt":0.21986943049142804,"score_spread":0.21174740564159683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145683333","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06375957,0.000057490455,0.9344269,0.00013042265,0.000007682078,0.00008459524,0.00027008378,0.0006604007,0.00060283934],"genre_scores_gemma":[0.7111645,0.00013960192,0.28603026,0.000039470113,0.0000150292035,0.00034862215,0.0013770546,0.000105344516,0.0007800932],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991653,0.00027093972,0.00005330822,0.00018346446,0.0002787536,0.000048271882],"domain_scores_gemma":[0.9926991,0.005296124,0.00065577455,0.0006316405,0.00060248317,0.00011500714],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014999248,0.0008108465,0.0005790562,0.0011685115,0.0005827903,0.0008715089,0.0012840574,0.00086384197,0.0013393818],"category_scores_gemma":[0.009142197,0.0004637555,0.0013712262,0.0006787834,0.0009750498,0.0011822128,0.0008303461,0.00093223,0.00022379203],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021656051,0.000027338556,0.0016613458,0.000036207963,0.000023900138,0.000066172965,0.00004734905,0.982734,0.0012128473,0.0062167966,0.00012194216,0.007830353],"study_design_scores_gemma":[0.0000014870262,0.000002458456,0.00009338556,9.845389e-7,0.0000016653586,0.0000044913604,0.0000029084508,0.9967614,0.00034702025,0.002736306,0.000046984354,9.036938e-7],"about_ca_topic_score_codex":0.008711495,"about_ca_topic_score_gemma":0.0074939257,"teacher_disagreement_score":0.008711495,"about_ca_system_score_codex":0.0012954811,"about_ca_system_score_gemma":0.0016864481,"threshold_uncertainty_score":0.017321587},"labels":[],"label_agreement":null},{"id":"W2145757848","doi":"10.1186/1471-2105-10-s1-s2","title":"Genome aliquoting with double cut and join","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Royal Society; Royal Society of Canada","keywords":"Genome; Sign (mathematics); Heuristic; Combinatorics; Genetics; Biology; Gene; Human genome; Computational biology; Mathematics; Computer science; Artificial intelligence","score_opus":0.012803395977688994,"score_gpt":0.2268005749068623,"score_spread":0.2139971789291733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145757848","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048512515,0.00034475402,0.9455979,0.00026973124,0.000043270986,0.00022166822,0.00027874578,0.0014794486,0.0032519822],"genre_scores_gemma":[0.17793712,0.00014380881,0.817453,0.00010971282,0.000036925267,0.00025394332,0.00094344286,0.00033571786,0.0027862596],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986143,0.00032902465,0.000086477594,0.00041914594,0.00042172047,0.00012932693],"domain_scores_gemma":[0.9953892,0.0029196213,0.00039940415,0.00078808685,0.00030225673,0.00020138998],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002199779,0.000978049,0.0012628459,0.0011152124,0.0010528404,0.0014223116,0.003097639,0.0016578252,0.007674374],"category_scores_gemma":[0.005850224,0.00052429514,0.0012764813,0.0016505521,0.0014405485,0.0023702201,0.0027521031,0.0018811811,0.0011534046],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010300694,0.00034572798,0.003037727,0.00056697306,0.000117039446,0.00032804933,0.00065336004,0.5532245,0.020477505,0.07046112,0.005618352,0.34413964],"study_design_scores_gemma":[0.00015420369,0.00031511293,0.0005368114,0.000043071384,0.000063229134,0.00029077748,0.0001882792,0.8811033,0.019937372,0.08840463,0.008926275,0.00003695266],"about_ca_topic_score_codex":0.001558985,"about_ca_topic_score_gemma":0.0012995234,"teacher_disagreement_score":0.007674374,"about_ca_system_score_codex":0.0011570432,"about_ca_system_score_gemma":0.0011421286,"threshold_uncertainty_score":0.02567333},"labels":[],"label_agreement":null},{"id":"W2146003645","doi":"10.1186/1471-2105-5-75","title":"Interaction profile-based protein classification of death domain","year":2004,"lang":"en","type":"article","venue":"BMC Bioinformatics","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":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"In silico; Protein–protein interaction; Computational biology; Computer science; Protein structure prediction; Protein structure; Homology modeling; Protein function prediction; Structural genomics; Protein domain; Protein family; Docking (animal); Macromolecular docking; Protein sequencing; Artificial intelligence; Bioinformatics; Biology; Peptide sequence; Genetics; Protein function; Biochemistry; Gene","score_opus":0.018933649688083556,"score_gpt":0.2507077440627499,"score_spread":0.23177409437466637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146003645","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9709501,0.0004709129,0.021856336,0.00007496732,0.000019632656,0.00012167528,0.004284175,0.00063384697,0.0015882439],"genre_scores_gemma":[0.9747209,0.00008229714,0.019457625,0.000018623441,0.000009208798,0.00005623932,0.0053127506,0.000016258953,0.0003261039],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99970907,0.000048232883,0.00003437083,0.00008121408,0.00007950696,0.00004762333],"domain_scores_gemma":[0.9990338,0.00034199108,0.00017408225,0.000064623375,0.00028232418,0.00010316471],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058297446,0.00029874183,0.00030923713,0.0021655313,0.00017083011,0.00043993685,0.00031447486,0.00030549977,0.0013535247],"category_scores_gemma":[0.0013738844,0.0000414732,0.0002988794,0.00087716733,0.00012834174,0.0002600736,0.00030237404,0.0002700903,0.00066282944],"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":[0.0014397242,0.0004015256,0.6475607,0.00044962263,0.00018122634,0.00031100193,0.00012015456,0.016128238,0.046638153,0.0006539519,0.0046501295,0.28146556],"study_design_scores_gemma":[0.000072167866,0.0005242507,0.42503104,0.00005511525,0.00013236828,0.0014676497,0.00022844746,0.5326266,0.032629587,0.0019327367,0.0052612764,0.000038792292],"about_ca_topic_score_codex":0.00093699,"about_ca_topic_score_gemma":0.0009864316,"teacher_disagreement_score":0.0021655313,"about_ca_system_score_codex":0.00029102855,"about_ca_system_score_gemma":0.00035731876,"threshold_uncertainty_score":0.0045280457},"labels":[],"label_agreement":null},{"id":"W2146389940","doi":"10.1186/1471-2105-6-151","title":"AutoFACT: An Auto matic F unctional A nnotation and C lassification T ool","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":189,"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; Université de Montréal","funders":"Canadian Institutes of Health Research; Genome Canada","keywords":"Perl; Annotation; Computer science; Software; Unix; Genomics; Functional genomics; Bioconductor; Computational biology; Information retrieval; Data mining; Programming language; Biology; Artificial intelligence; Genetics; Genome; Gene","score_opus":0.014767438856832656,"score_gpt":0.24020079870371533,"score_spread":0.22543335984688267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146389940","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004177786,0.00054771575,0.6469788,0.0005350795,0.0008426263,0.00037693276,0.02541506,0.3068232,0.01430283],"genre_scores_gemma":[0.03533145,0.00086907233,0.79654914,0.0006527787,0.00045595292,0.0007780978,0.075399876,0.06362967,0.026334012],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973092,0.0004696176,0.0002969044,0.0006897227,0.0010503383,0.00018419471],"domain_scores_gemma":[0.9949425,0.0018549392,0.00062494824,0.0013279004,0.0009798231,0.0002698608],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028208527,0.0028477707,0.0013757166,0.0060128137,0.0015676835,0.0038740898,0.0028658502,0.001410509,0.06290022],"category_scores_gemma":[0.010262299,0.0013353353,0.0028842553,0.0031980658,0.0012949291,0.0032764252,0.0031863642,0.0017070522,0.034955412],"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":[0.0010691454,0.00017192778,0.003294607,0.0016560457,0.00020755327,0.0012150377,0.0008354113,0.004590131,0.021302342,0.023035435,0.5052717,0.43735072],"study_design_scores_gemma":[0.00015266573,0.0001605531,0.002655117,0.0004256036,0.000105509724,0.0014978868,0.00023903254,0.05768335,0.040961202,0.032543678,0.86328,0.00029547815],"about_ca_topic_score_codex":0.0020742055,"about_ca_topic_score_gemma":0.002098049,"teacher_disagreement_score":0.06290022,"about_ca_system_score_codex":0.0009866101,"about_ca_system_score_gemma":0.0019236606,"threshold_uncertainty_score":0.21042216},"labels":[],"label_agreement":null},{"id":"W2146494984","doi":"10.1186/1471-2105-13-s19-s16","title":"A graph-theoretic approach for inparalog detection","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université de Montréal","funders":"","keywords":"Gene duplication; Biology; Heuristic; Gene; Comparative genomics; Computational biology; Graph; Event (particle physics); Function (biology); Genome; Genetic algorithm; DNA microarray; Cluster analysis; Set (abstract data type); Evolutionary biology; Genomics; Genetics; Computer science; Theoretical computer science; Artificial intelligence","score_opus":0.017883537988364544,"score_gpt":0.2323048496636832,"score_spread":0.21442131167531867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146494984","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007296478,0.00022967588,0.9899713,0.0004075099,0.000038479044,0.00012823657,0.0002525847,0.0004852904,0.0011904933],"genre_scores_gemma":[0.08644675,0.0005611115,0.9086454,0.00035447493,0.0002256345,0.00028681272,0.0014809719,0.0002742958,0.0017245836],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975262,0.00066246605,0.00015700952,0.0006688256,0.00081176095,0.00017380164],"domain_scores_gemma":[0.9818366,0.012074463,0.0016082296,0.0023626136,0.0015353365,0.0005827764],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026591013,0.002259913,0.0024063394,0.0072385115,0.0019815294,0.0030099368,0.005285755,0.0025936624,0.0046605216],"category_scores_gemma":[0.018960688,0.0015590888,0.002418866,0.0059047793,0.0023217406,0.00841599,0.0030023484,0.004354515,0.0014835529],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024472686,0.0005526501,0.0042327796,0.0010538066,0.00037579573,0.00055976986,0.0006607811,0.4240277,0.012930923,0.24805716,0.018143846,0.28916004],"study_design_scores_gemma":[0.000021327489,0.00010427005,0.00064874126,0.00003664488,0.00006967731,0.00046232756,0.000104823914,0.77855164,0.00219021,0.21268244,0.0050884993,0.000039501603],"about_ca_topic_score_codex":0.0027271747,"about_ca_topic_score_gemma":0.0025122652,"teacher_disagreement_score":0.0072385115,"about_ca_system_score_codex":0.0027153676,"about_ca_system_score_gemma":0.0018254241,"threshold_uncertainty_score":0.019701421},"labels":[],"label_agreement":null},{"id":"W2148362397","doi":"10.1186/1471-2105-12-s8-s8","title":"Benchmarking of the 2010 BioCreative Challenge III text-mining competition by the BioGRID and MINT interaction databases","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; Mount Sinai Hospital","funders":"Biotechnology and Biological Sciences Research Council; National Center for Research Resources; Directorate for Biological Sciences; National Institutes of Health; Associazione Italiana per la Ricerca sul Cancro; Canadian Institutes of Health Research; European Commission","keywords":"Computer science; Annotation; Benchmarking; Identification (biology); Test set; Information retrieval; Normalization (sociology); Data curation; Named-entity recognition; Natural language processing; Set (abstract data type); Information extraction; Artificial intelligence; Database; Data mining; Task (project management)","score_opus":0.050830729813296054,"score_gpt":0.26690982688537845,"score_spread":0.2160790970720824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148362397","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38303062,0.024003832,0.020467775,0.018491987,0.004480437,0.004463146,0.45886347,0.03780372,0.048395075],"genre_scores_gemma":[0.06302171,0.0014939314,0.023666956,0.0016327957,0.00036828124,0.0011473295,0.90161794,0.001429309,0.0056217937],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.97122586,0.009572006,0.0031544648,0.0052960995,0.009194469,0.0015569843],"domain_scores_gemma":[0.96072227,0.0141088385,0.002281567,0.0051039043,0.012211679,0.0055717146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.030688344,0.005638873,0.0040601934,0.0118660005,0.0037643872,0.008400519,0.009078763,0.0057506715,0.008413741],"category_scores_gemma":[0.04079245,0.0009449435,0.0037671959,0.013238704,0.0025896179,0.007244414,0.009059873,0.003399385,0.012742632],"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":[0.0060496344,0.006383222,0.015059685,0.008066518,0.0020021652,0.0013375891,0.0010124499,0.02543046,0.009636577,0.0049024783,0.801294,0.11882523],"study_design_scores_gemma":[0.006600252,0.0046219337,0.08686746,0.0013571391,0.0013843023,0.0035705287,0.0038274645,0.28747514,0.032792874,0.010032779,0.5607495,0.0007206378],"about_ca_topic_score_codex":0.03898377,"about_ca_topic_score_gemma":0.04764815,"teacher_disagreement_score":0.03898377,"about_ca_system_score_codex":0.006694376,"about_ca_system_score_gemma":0.0073661776,"threshold_uncertainty_score":0.16229743},"labels":[],"label_agreement":null},{"id":"W2149205772","doi":"10.1186/1471-2105-12-328","title":"Classifying short genomic fragments from novel lineages using composition and homology","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":73,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Genome Atlantic; Killam Trusts; Canada Research Chairs; Government of Canada; Genome Canada; Ontario Genomics; Ontario Genomics Institute","keywords":"Metagenomics; Taxonomic rank; Classifier (UML); Naive Bayes classifier; Artificial intelligence; Biology; Computer science; Rank (graph theory); Genome; Computational biology; Homology (biology); Bayes' theorem; Pattern recognition (psychology); Data mining; Machine learning; Mathematics; Genetics; Support vector machine; Bayesian probability; Gene; Ecology","score_opus":0.06827311741666486,"score_gpt":0.25665656560547695,"score_spread":0.18838344818881209,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2149205772","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4329837,0.0015327892,0.5575454,0.00026434663,0.00006162454,0.00026888412,0.0012733156,0.0024891964,0.003580616],"genre_scores_gemma":[0.63243556,0.00045372124,0.3626714,0.0001891268,0.000054054068,0.00014091014,0.0025009143,0.00014813323,0.0014061795],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990037,0.00015272346,0.00008381662,0.0003339505,0.00033821294,0.000087619104],"domain_scores_gemma":[0.9968629,0.0013305587,0.0007073607,0.00022526906,0.0006798975,0.00019414166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015928023,0.00076573837,0.00070414727,0.0028519116,0.0005239597,0.0013191592,0.00078594487,0.0012390204,0.0018578493],"category_scores_gemma":[0.0039644986,0.00023730018,0.0007652423,0.0015744839,0.0007061804,0.0014620132,0.0009203,0.0007726232,0.0015884124],"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":[0.001290537,0.00036904626,0.08362349,0.0011207671,0.0002759662,0.00043762682,0.000547438,0.04124871,0.28609845,0.0022888442,0.0019872542,0.58071184],"study_design_scores_gemma":[0.000055139215,0.00050548575,0.046218023,0.00019248616,0.00021609814,0.0009380316,0.0006661552,0.7915341,0.14414786,0.010355468,0.0050618574,0.0001092472],"about_ca_topic_score_codex":0.0015007749,"about_ca_topic_score_gemma":0.0017667306,"teacher_disagreement_score":0.0028519116,"about_ca_system_score_codex":0.0006068575,"about_ca_system_score_gemma":0.0006743261,"threshold_uncertainty_score":0.008423626},"labels":[],"label_agreement":null},{"id":"W2149954962","doi":"10.1186/1471-2105-7-228","title":"A stable gene selection in microarray data analysis","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":197,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Gene selection; Selection (genetic algorithm); Microarray analysis techniques; DNA microarray; Support vector machine; Computer science; Gene; Data mining; Significance analysis of microarrays; Microarray; Sample (material); Computational biology; Biology; Artificial intelligence; Genetics; Gene expression","score_opus":0.02232773026539993,"score_gpt":0.26402948074815574,"score_spread":0.2417017504827558,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2149954962","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025322642,0.0009359634,0.97161084,0.00022820324,0.00007869198,0.0001431011,0.00034709042,0.0010682597,0.0002651264],"genre_scores_gemma":[0.30103603,0.0009847891,0.6928438,0.0003096264,0.0002801498,0.0010274766,0.0017813138,0.0002863547,0.0014505559],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9940743,0.0026160572,0.00030154787,0.0012402124,0.0015555556,0.00021223402],"domain_scores_gemma":[0.99504083,0.0029716145,0.000386931,0.0005785874,0.0009124081,0.00010968781],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0070505235,0.0009185729,0.0012823322,0.0020149893,0.00080042484,0.0008120408,0.0012767233,0.00095812755,0.0011875564],"category_scores_gemma":[0.009047967,0.00039657936,0.0012293339,0.0037097775,0.0013605639,0.00072797964,0.00096674135,0.00082424015,0.0010103865],"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":[0.0014376014,0.00024332196,0.017022813,0.0009097118,0.0004948355,0.0005546516,0.00029883767,0.095968045,0.122673236,0.011434116,0.0064683245,0.74249446],"study_design_scores_gemma":[0.00014726509,0.0008179385,0.015046794,0.00007108572,0.00022239778,0.0007213898,0.00009187322,0.8793719,0.06886196,0.02238142,0.012186951,0.0000789865],"about_ca_topic_score_codex":0.00067726907,"about_ca_topic_score_gemma":0.0007189894,"teacher_disagreement_score":0.0070505235,"about_ca_system_score_codex":0.00073736353,"about_ca_system_score_gemma":0.0011463828,"threshold_uncertainty_score":0.037287235},"labels":[],"label_agreement":null},{"id":"W2150756255","doi":"10.1186/1471-2105-10-106","title":"flowCore: a Bioconductor package for high throughput flow cytometry","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":651,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Terry Fox Research Institute; BC Cancer Agency","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institutes of Health; Michael Smith Health Research BC","keywords":"Bioconductor; Computer science; Software; Data mining; Data management; Throughput; Automation; Data science; Data flow diagram; Software engineering; Database; Operating system; Engineering","score_opus":0.021869838695404036,"score_gpt":0.2510222181838827,"score_spread":0.22915237948847866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150756255","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019503917,0.0010734973,0.48366326,0.0010237709,0.0010475413,0.0010711474,0.09247484,0.40961534,0.008080252],"genre_scores_gemma":[0.019226639,0.0014915831,0.71201617,0.0021401048,0.00046795298,0.012825228,0.108418,0.12902561,0.014388742],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9950896,0.0011664524,0.00076375215,0.0011191831,0.0013684626,0.00049265363],"domain_scores_gemma":[0.98797077,0.005770591,0.0011295172,0.0017636213,0.00271995,0.0006456875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009944251,0.005066703,0.00469338,0.0071086693,0.0020886739,0.0041430653,0.011815541,0.0032456196,0.11299478],"category_scores_gemma":[0.025954813,0.0035973382,0.004079209,0.0068366253,0.0017111257,0.004164215,0.00486376,0.0071874806,0.09547021],"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":[0.0014708394,0.00021248517,0.0022107747,0.005021544,0.0010108361,0.00047829325,0.0005183999,0.00591849,0.0077787293,0.02579062,0.85691875,0.09267022],"study_design_scores_gemma":[0.00166365,0.00023486781,0.00637974,0.0010941722,0.00077077386,0.0009370553,0.00013611681,0.10755843,0.024073249,0.106587395,0.75007516,0.000489366],"about_ca_topic_score_codex":0.0055733463,"about_ca_topic_score_gemma":0.0047519174,"teacher_disagreement_score":0.11299478,"about_ca_system_score_codex":0.0019157332,"about_ca_system_score_gemma":0.0083287805,"threshold_uncertainty_score":0.3780052},"labels":[],"label_agreement":null},{"id":"W2150951857","doi":"10.1186/1471-2105-12-380","title":"iCTNet: A Cytoscape plugin to produce and analyze integrative complex traits networks","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Ontario Ministry of Research and Innovation; Multiple Sclerosis Society; National Multiple Sclerosis Society","keywords":"Plug-in; Biological network; Identification (biology); Computer science; Data integration; Visualization; Computational biology; Systems biology; Interface (matter); Data science; Biology; Data mining","score_opus":0.026278439747076315,"score_gpt":0.23801105044177925,"score_spread":0.21173261069470295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150951857","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009747295,0.0009890377,0.50071305,0.0010415397,0.0007791482,0.00085275376,0.08479435,0.38929188,0.011790901],"genre_scores_gemma":[0.09339768,0.0028268609,0.62730175,0.0017494597,0.0003364023,0.006685088,0.18843243,0.06609431,0.013176059],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992543,0.0001372433,0.00005720508,0.00018823198,0.00029922195,0.00006379808],"domain_scores_gemma":[0.9979151,0.0013322533,0.00013101865,0.00023713941,0.00018943418,0.00019510425],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016639496,0.0023459217,0.0008426596,0.0045428653,0.0011330972,0.001915004,0.002746892,0.0014109422,0.031871986],"category_scores_gemma":[0.005676291,0.0013239243,0.0018347235,0.0020623382,0.0006083411,0.0016691198,0.0026276782,0.0026971535,0.009126573],"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":[0.00076064246,0.00029992667,0.0061823614,0.0060528237,0.0016288545,0.0021802303,0.0010532112,0.06485188,0.03488495,0.041604765,0.64341164,0.19708875],"study_design_scores_gemma":[0.00059632125,0.00012919458,0.00538105,0.00064244226,0.00034571427,0.0012316816,0.00014483355,0.23443766,0.05223265,0.09133554,0.6131201,0.00040277702],"about_ca_topic_score_codex":0.0054433784,"about_ca_topic_score_gemma":0.0076962155,"teacher_disagreement_score":0.031871986,"about_ca_system_score_codex":0.00090823136,"about_ca_system_score_gemma":0.0025044945,"threshold_uncertainty_score":0.1066224},"labels":[],"label_agreement":null},{"id":"W2151109259","doi":"10.1186/1471-2105-14-58","title":"Prediction of a time-to-event trait using genome wide SNP data","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto","funders":"National Cancer Institute","keywords":"Single-nucleotide polymorphism; SNP; Genome-wide association study; Computational biology; Trait; Computer science; Event (particle physics); Biology; DNA microarray; Genome; Quantitative trait locus; Data mining; Genetics; Genotype; Gene","score_opus":0.054842597824317746,"score_gpt":0.2739561777448809,"score_spread":0.21911357992056316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151109259","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33751446,0.00030363476,0.6573431,0.00065122964,0.00006162441,0.000075551994,0.0023351142,0.0010799255,0.00063544844],"genre_scores_gemma":[0.91269726,0.00013575006,0.08426363,0.00008413421,0.000064906766,0.000088484245,0.0020585314,0.0000488362,0.000558364],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99904007,0.00043961822,0.00007788325,0.000278008,0.000111599635,0.000052856085],"domain_scores_gemma":[0.98150635,0.015840791,0.0012342886,0.00064965256,0.00045284774,0.00031605817],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004354472,0.0006089006,0.0005444192,0.0013248988,0.00030858952,0.0007169576,0.0009786596,0.0008365386,0.002207668],"category_scores_gemma":[0.01396341,0.00020855154,0.0009908627,0.0010954312,0.00039984306,0.0007121399,0.00046891262,0.00096677773,0.00035519846],"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":[0.0010518385,0.0002225725,0.5289933,0.0001788845,0.0006078492,0.0009068963,0.00014034654,0.35957152,0.003740903,0.0062322076,0.0020578625,0.0962958],"study_design_scores_gemma":[0.000047294663,0.00014742074,0.037503317,0.000021144444,0.000113941285,0.0004230809,0.000031791496,0.9440402,0.0026818204,0.014248877,0.0007078589,0.00003316804],"about_ca_topic_score_codex":0.0016347186,"about_ca_topic_score_gemma":0.0017492822,"teacher_disagreement_score":0.004354472,"about_ca_system_score_codex":0.00039284388,"about_ca_system_score_gemma":0.0005250936,"threshold_uncertainty_score":0.02302897},"labels":[],"label_agreement":null},{"id":"W2151432781","doi":"10.1186/1471-2105-7-516","title":"Integrated siRNA design based on surveying of features associated with high RNAi effectiveness","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA Interference and Gene Delivery","field":"Biochemistry, Genetics and Molecular Biology","cited_by":56,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Graduate School, University of Minnesota; Ryerson University; University of Minnesota","keywords":"RNA interference; Computational biology; DNA microarray; Computer science; Interference (communication); Biology; Bioinformatics; Genetics; Gene; Telecommunications; Gene expression; RNA","score_opus":0.014586936844769409,"score_gpt":0.22038578861930821,"score_spread":0.2057988517745388,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151432781","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54137164,0.0015530047,0.44476923,0.00021012806,0.00006765763,0.0007920578,0.003462325,0.004048426,0.0037255571],"genre_scores_gemma":[0.6356906,0.00034124998,0.35625473,0.00024116713,0.00003006592,0.00057968526,0.005975808,0.00019146624,0.000695105],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99650687,0.00063046475,0.00046488002,0.0011334809,0.0010856856,0.00017868944],"domain_scores_gemma":[0.9835029,0.011123129,0.001866726,0.0010067706,0.0022266677,0.00027374626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044035777,0.00092940533,0.0012348713,0.0027893053,0.00041416488,0.0013395171,0.0012628802,0.00076400366,0.0010055428],"category_scores_gemma":[0.013153387,0.00035989063,0.0018065142,0.0011935942,0.00061619765,0.0007424633,0.0007023605,0.0008685742,0.0005022771],"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":[0.0013637787,0.00073422276,0.18681687,0.001975543,0.00087202573,0.0015205697,0.00037831944,0.16819794,0.2104899,0.003799344,0.003604715,0.42024678],"study_design_scores_gemma":[0.00013875471,0.0012632934,0.04340932,0.00015017304,0.0008887482,0.0010940273,0.0001905639,0.7601269,0.18000048,0.0060994923,0.0065194983,0.00011876573],"about_ca_topic_score_codex":0.0012971096,"about_ca_topic_score_gemma":0.002146512,"teacher_disagreement_score":0.0044035777,"about_ca_system_score_codex":0.00065239886,"about_ca_system_score_gemma":0.0013082081,"threshold_uncertainty_score":0.023288608},"labels":[],"label_agreement":null},{"id":"W2152436336","doi":"10.1186/1471-2105-11-105","title":"Free energy estimation of short DNA duplex hybridizations","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"DNA microarray; Duplex (building); DNA; Computational biology; Biology; Genetics; Gene; Gene expression","score_opus":0.012044819640651365,"score_gpt":0.24810138362208925,"score_spread":0.23605656398143787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2152436336","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30078292,0.0020271523,0.69089586,0.00012024444,0.00005822371,0.000072022885,0.0011637411,0.0017822445,0.0030975747],"genre_scores_gemma":[0.8532335,0.0008320574,0.13969176,0.00006668457,0.00002317298,0.00021233807,0.0028271312,0.00054522476,0.0025680538],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991603,0.00015038371,0.00003853237,0.0002906359,0.0003167551,0.000043395223],"domain_scores_gemma":[0.9976682,0.001646665,0.00018817694,0.0001931466,0.00025752326,0.00004635359],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013140211,0.000592335,0.00068956456,0.0017262874,0.00035060933,0.0006049457,0.0011397358,0.0009647934,0.0021455777],"category_scores_gemma":[0.005171635,0.00029620354,0.0010432478,0.00095492223,0.0005128703,0.001058581,0.0005984323,0.00055968453,0.0007216976],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002510115,0.00010458506,0.0106815575,0.00074379117,0.00017143127,0.00014589337,0.00017789501,0.8530835,0.037422292,0.004764528,0.001036483,0.09141707],"study_design_scores_gemma":[0.0000058902488,0.00005920737,0.003262461,0.000027970302,0.000026638743,0.00010865834,0.000035613615,0.9712635,0.01864349,0.0051192576,0.0014171964,0.000030041312],"about_ca_topic_score_codex":0.0028388007,"about_ca_topic_score_gemma":0.0023136365,"teacher_disagreement_score":0.0028388007,"about_ca_system_score_codex":0.00069538347,"about_ca_system_score_gemma":0.0005916413,"threshold_uncertainty_score":0.0071777105},"labels":[],"label_agreement":null},{"id":"W2152809196","doi":"10.1186/1471-2105-12-s9-s10","title":"The evolution of the tape measure protein: units, duplications and losses","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bacteriophages and microbial interactions","field":"Environmental Science","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"National Center for Research Resources; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Gene duplication; Heuristic; Measure (data warehouse); Sequence (biology); Genome; Lineage (genetic); Biology; Computational biology; Genetics; Divergence (linguistics); Similarity (geometry); Genomics; Gene; Algorithm; Computer science; Artificial intelligence; Data mining; Image (mathematics)","score_opus":0.021874249157548,"score_gpt":0.1984610059880758,"score_spread":0.17658675683052782,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2152809196","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96411186,0.0007123454,0.03192115,0.0001660191,0.000017701155,0.00001995769,0.00023170776,0.00013556496,0.002683695],"genre_scores_gemma":[0.9665022,0.000373431,0.031563897,0.000057714395,0.000017746564,0.000023245075,0.00035687466,0.000069939,0.001035033],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998202,0.000029548928,0.000012177175,0.00006474608,0.00005275172,0.000020616557],"domain_scores_gemma":[0.9992118,0.00027908126,0.00020659431,0.00010130409,0.00010369507,0.00009755679],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003650389,0.00034170266,0.0002647601,0.0008527771,0.0008117928,0.0010284804,0.00048638473,0.00064556557,0.001060108],"category_scores_gemma":[0.0012935448,0.00023456305,0.0004146652,0.0009940346,0.00092303683,0.0010972463,0.0004993406,0.0007502911,0.00046989808],"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":[0.0014222896,0.00020766718,0.10446661,0.000553951,0.00011820314,0.0014016418,0.0011482446,0.02501293,0.72793424,0.03975213,0.0013499572,0.09663216],"study_design_scores_gemma":[0.00009739968,0.0013240376,0.18986966,0.00022239606,0.00033217215,0.009212228,0.0017371123,0.19116245,0.49565056,0.07312188,0.037060153,0.0002099643],"about_ca_topic_score_codex":0.0005642384,"about_ca_topic_score_gemma":0.0004195489,"teacher_disagreement_score":0.001060108,"about_ca_system_score_codex":0.0007459095,"about_ca_system_score_gemma":0.00033942054,"threshold_uncertainty_score":0.0054119825},"labels":[],"label_agreement":null},{"id":"W2153531183","doi":"10.1186/1471-2105-14-82","title":"Learning a peptide-protein binding affinity predictor with kernel ridge regression","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"vaccines and immunoinformatics approaches","field":"Biochemistry, Genetics and Molecular Biology","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto; Government of Ontario; Compute Canada","keywords":"Kernel (algebra); Affinities; Regression; Ridge; Kernel method; Binding affinities; Value (mathematics)","score_opus":0.013916969751074464,"score_gpt":0.21455401098658966,"score_spread":0.2006370412355152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153531183","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.109883115,0.0006387894,0.8858109,0.00032979253,0.00004275363,0.000058746282,0.00028836651,0.00224019,0.0007073937],"genre_scores_gemma":[0.7991,0.00028524062,0.19620687,0.00016953702,0.000059917205,0.00012893294,0.001268985,0.00016737117,0.002613077],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992118,0.00029054837,0.000049387352,0.00018108143,0.0001577295,0.00010942756],"domain_scores_gemma":[0.9979189,0.0011464207,0.00020353851,0.00017143291,0.00047692333,0.00008273857],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021073793,0.00088002416,0.001450017,0.00081380893,0.00026289595,0.0007631901,0.0014573261,0.0012525974,0.0012829878],"category_scores_gemma":[0.00386705,0.0004421512,0.00095462066,0.0009260958,0.0004521096,0.0008368061,0.0008334237,0.0021202143,0.0011886752],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037780605,0.00036384087,0.006530313,0.00010070106,0.0001375086,0.00011018232,0.000039339542,0.81738573,0.005507044,0.0018754132,0.0038287393,0.16374336],"study_design_scores_gemma":[0.0000034589655,0.000011000602,0.00008206139,0.0000011234479,0.0000023989369,0.000005020014,0.0000018313227,0.99921083,0.00035733642,0.0002647391,0.000058499,0.0000016567217],"about_ca_topic_score_codex":0.0030698078,"about_ca_topic_score_gemma":0.0018487946,"teacher_disagreement_score":0.0030698078,"about_ca_system_score_codex":0.0004723886,"about_ca_system_score_gemma":0.0011342992,"threshold_uncertainty_score":0.011145055},"labels":[],"label_agreement":null},{"id":"W2153542855","doi":"10.1186/1471-2105-13-s19-s5","title":"Medians seek the corners, and other conjectures","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Computational biology; Biology","score_opus":0.017517362560641996,"score_gpt":0.2381653842075965,"score_spread":0.22064802164695452,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153542855","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28763074,0.004267938,0.6194941,0.021554666,0.0009744275,0.0001581268,0.0006981574,0.00091487495,0.06430698],"genre_scores_gemma":[0.89006585,0.0014767747,0.09473678,0.0025732527,0.0012135071,0.0002828752,0.0008222249,0.00030997096,0.008518797],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973367,0.00091319304,0.00011177204,0.000906743,0.0004570215,0.00027456443],"domain_scores_gemma":[0.9461013,0.041842915,0.0034266755,0.004501985,0.0025578726,0.0015692691],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006686919,0.0005714347,0.0012144286,0.0016510952,0.003032214,0.0036065355,0.0019101067,0.0032791751,0.017398287],"category_scores_gemma":[0.06414336,0.00052116567,0.001629073,0.0017948202,0.007444027,0.009770156,0.0031683561,0.003875358,0.001479332],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023963104,0.00012359877,0.0063265464,0.000301552,0.00004527499,0.0001884516,0.00078219885,0.045373827,0.00075417093,0.9004198,0.010125288,0.035319738],"study_design_scores_gemma":[0.00004246518,0.000067552515,0.00071875314,0.00007378803,0.000012028759,0.0001073928,0.00028100298,0.04859026,0.0004914473,0.94573575,0.003856434,0.000023086552],"about_ca_topic_score_codex":0.0013512745,"about_ca_topic_score_gemma":0.00082154595,"teacher_disagreement_score":0.017398287,"about_ca_system_score_codex":0.0016007569,"about_ca_system_score_gemma":0.0013091536,"threshold_uncertainty_score":0.0582031},"labels":[],"label_agreement":null},{"id":"W2154003902","doi":"10.1186/s12859-015-0788-5","title":"Evaluation of shotgun metagenomics sequence classification methods using in silico and in vitro simulated communities","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":175,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Simon Fraser University; Public Health Agency; Michael Smith Health Research BC; Public Health Agency of Canada; Canadian Institutes of Health Research; University of Connecticut; Genome Canada; Genome British Columbia","keywords":"In silico; Metagenomics; Shotgun; Computational biology; Shotgun sequencing; Biology; DNA microarray; Bioinformatics; Sequence (biology); Computer science; Data mining; Genetics; DNA sequencing; Gene","score_opus":0.2892683905235093,"score_gpt":0.40553302523698453,"score_spread":0.11626463471347526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154003902","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9031841,0.0015750524,0.08886703,0.0002985504,0.00015324283,0.000296553,0.0016383764,0.0022962468,0.001690771],"genre_scores_gemma":[0.8432105,0.00088910264,0.14967938,0.00015017377,0.00003831172,0.00035102968,0.0048967684,0.0002641767,0.00052062556],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9931764,0.0021212776,0.0007849036,0.0011514504,0.0024615095,0.00030445727],"domain_scores_gemma":[0.9843693,0.00911909,0.0010912117,0.0008014756,0.0041485303,0.00047043292],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011015046,0.0017662883,0.0011022289,0.002248995,0.000746768,0.0016038029,0.0016572239,0.0014134302,0.00055798003],"category_scores_gemma":[0.018124923,0.00039717826,0.0013494149,0.001417107,0.0006379943,0.0011346558,0.0009860651,0.0011647869,0.00047719973],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006227355,0.002578136,0.115282916,0.0041122637,0.0017854242,0.00036613215,0.0012257975,0.40074685,0.22309777,0.0017375096,0.0032106605,0.23962915],"study_design_scores_gemma":[0.00006716493,0.0016247872,0.023031823,0.00015423006,0.00021562069,0.00019138475,0.0003612205,0.79656744,0.17477569,0.0008556839,0.0020395243,0.00011542532],"about_ca_topic_score_codex":0.004235831,"about_ca_topic_score_gemma":0.003217218,"teacher_disagreement_score":0.98898494,"about_ca_system_score_codex":0.0014554135,"about_ca_system_score_gemma":0.0012093546,"threshold_uncertainty_score":0.058253825},"labels":[],"label_agreement":null},{"id":"W2154496386","doi":"10.1186/s12859-015-0770-2","title":"Whole genome SNP genotype piecemeal imputation","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Genome Canada","keywords":"Imputation (statistics); SNP; Genotype; Single-nucleotide polymorphism; Biology; Genome-wide association study; SNP genotyping; Computational biology; Genetics; Statistics; Computer science; Mathematics; Missing data; Gene","score_opus":0.03597789474738615,"score_gpt":0.2812938896453417,"score_spread":0.24531599489795552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154496386","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025108226,0.00068082917,0.9650192,0.00030969322,0.00013015779,0.00010010428,0.0040242216,0.0030583236,0.001569228],"genre_scores_gemma":[0.21123257,0.00049287727,0.7607105,0.00083508936,0.0001551121,0.00053969584,0.019854518,0.0008975299,0.0052821417],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9946784,0.0023097082,0.00021413618,0.0016956788,0.00088098267,0.00022111002],"domain_scores_gemma":[0.9852874,0.0066985763,0.001191797,0.0051468173,0.0014618615,0.0002135285],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0063175936,0.0011251003,0.0021243151,0.0011343273,0.0007396565,0.0014149561,0.0039949375,0.0022588703,0.008602354],"category_scores_gemma":[0.015919594,0.0008313048,0.0029837794,0.0031855043,0.000828578,0.0013849298,0.0017679,0.0029025932,0.004098693],"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":[0.0032685124,0.00053466414,0.100385,0.0019116234,0.0053272853,0.0013903511,0.000733172,0.30298573,0.04421666,0.022758076,0.048538245,0.4679507],"study_design_scores_gemma":[0.00038739623,0.00078159943,0.06885905,0.00029176293,0.0014605743,0.0020281721,0.00014670062,0.75962347,0.042332746,0.06327605,0.06047163,0.00034082224],"about_ca_topic_score_codex":0.002669119,"about_ca_topic_score_gemma":0.0046688705,"teacher_disagreement_score":0.008602354,"about_ca_system_score_codex":0.0006336648,"about_ca_system_score_gemma":0.0010439721,"threshold_uncertainty_score":0.033411086},"labels":[],"label_agreement":null},{"id":"W2154714551","doi":"10.1186/1471-2105-11-114","title":"OrgConv: detection of gene conversion using consensus sequences and its application in plant mitochondrial and chloroplast homologs","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Photosynthetic Processes and Mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; Lilly Endowment; Eli Lilly and Company","keywords":"Genome; Biology; Gene; Computational biology; Chloroplast; Phylogenetic tree; Genetics; Homologous recombination; Plastid; Mitochondrial DNA; Sequence alignment; Homologous chromosome; Peptide sequence","score_opus":0.010293527756984836,"score_gpt":0.22312425727802512,"score_spread":0.2128307295210403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154714551","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37376064,0.0014888151,0.5154906,0.00040886734,0.00024833874,0.0007117724,0.028533032,0.07114578,0.00821207],"genre_scores_gemma":[0.3593394,0.00027149572,0.5989809,0.00024084038,0.000041388736,0.0014774734,0.031626433,0.005834341,0.0021877538],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969452,0.00071417936,0.00019568254,0.0011669365,0.0007451358,0.000232786],"domain_scores_gemma":[0.9957093,0.002358984,0.00066382665,0.0004414446,0.0005761994,0.0002502735],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00428257,0.0010541094,0.0010000331,0.0033728213,0.0007967823,0.0013540018,0.0015567486,0.0010758014,0.005020233],"category_scores_gemma":[0.0072222734,0.0007116578,0.0013033052,0.0020497954,0.00060286757,0.0009638205,0.0018623511,0.0010158898,0.0020283319],"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":[0.005386301,0.00090363837,0.13151462,0.0030795676,0.0013915943,0.0013717348,0.0016897683,0.016432064,0.29149395,0.009362933,0.06513939,0.47223443],"study_design_scores_gemma":[0.00058582483,0.0014336335,0.14212537,0.00050870073,0.00040843396,0.0030581907,0.0008810491,0.40648666,0.3503779,0.011049747,0.082516536,0.00056801026],"about_ca_topic_score_codex":0.0017310872,"about_ca_topic_score_gemma":0.002103378,"teacher_disagreement_score":0.005020233,"about_ca_system_score_codex":0.00080258324,"about_ca_system_score_gemma":0.0011528169,"threshold_uncertainty_score":0.022648633},"labels":[],"label_agreement":null},{"id":"W2155233998","doi":"10.1186/1471-2105-11-354","title":"Nonparametric methods for the analysis of single-color pathogen microarrays","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Infection and Immunity","funders":"National Institute of Allergy and Infectious Diseases; National Institute of General Medical Sciences; National Eye Institute; National Heart, Lung, and Blood Institute; National Institutes of Health","keywords":"Nonparametric statistics; DNA microarray; Normality; Pearson product-moment correlation coefficient; Computational biology; Exact test; Statistics; Computer science; Biology; Pattern recognition (psychology); Bioinformatics; Mathematics; Artificial intelligence; Genetics","score_opus":0.03156090557645123,"score_gpt":0.3328618730589619,"score_spread":0.3013009674825107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155233998","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012060434,0.00018989378,0.9972994,0.000060528662,0.000034130502,0.00007030688,0.00014429944,0.00079896615,0.0001964485],"genre_scores_gemma":[0.036569953,0.0002983614,0.96004266,0.00008631376,0.00012036659,0.0013070082,0.0006721985,0.00036765533,0.00053550623],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98750246,0.0070487447,0.0007751101,0.00112684,0.0032962873,0.00025068907],"domain_scores_gemma":[0.93725777,0.051730525,0.0029492583,0.004664187,0.0030365726,0.00036169065],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016485685,0.0014557545,0.0020232238,0.004392998,0.00095448154,0.0019800505,0.0032094808,0.0016007014,0.004275439],"category_scores_gemma":[0.07240626,0.001114536,0.0017135344,0.0038800142,0.0026730504,0.0016895939,0.0020875987,0.004005198,0.00214012],"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":[0.00062018516,0.00038799498,0.0070066154,0.0017283531,0.00088099774,0.00062321423,0.0005495715,0.19759016,0.01826226,0.1376776,0.011744088,0.62292886],"study_design_scores_gemma":[0.000065495624,0.00020064475,0.0033425794,0.000094417184,0.0000625795,0.0003202468,0.00007218109,0.82715166,0.0045162793,0.15345563,0.010607429,0.00011087949],"about_ca_topic_score_codex":0.001404995,"about_ca_topic_score_gemma":0.001481319,"teacher_disagreement_score":0.016485685,"about_ca_system_score_codex":0.001133785,"about_ca_system_score_gemma":0.0022993586,"threshold_uncertainty_score":0.08718568},"labels":[],"label_agreement":null},{"id":"W2155875572","doi":"10.1186/1471-2105-13-s5-s5","title":"Parametric modeling of cellular state transitions as measured with flow cytometry","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"National Science Council","keywords":"Outlier; Parametric statistics; Computer science; Skew; Gaussian; Biological system; Principle of maximum entropy; Nonparametric statistics; Robustness (evolution); Algorithm; Greedy algorithm; Pattern recognition (psychology); Mathematics; Artificial intelligence; Biology; Statistics; Physics","score_opus":0.02444447794471104,"score_gpt":0.2245223470422727,"score_spread":0.20007786909756164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155875572","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17690413,0.000100493104,0.8214536,0.00011120477,0.000008808383,0.000055740824,0.00024433303,0.000578186,0.0005436276],"genre_scores_gemma":[0.93321884,0.00011615267,0.0652522,0.000033831056,0.000008059771,0.00015869756,0.00039173575,0.000062366234,0.0007581419],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995629,0.00013088528,0.000021691816,0.00014662735,0.00008799223,0.000049969964],"domain_scores_gemma":[0.99712795,0.0020231712,0.00035080826,0.0002683317,0.00016625716,0.000063506304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013816146,0.0006566484,0.00046710024,0.0006005072,0.00026563596,0.0007554578,0.0010184117,0.0008694971,0.0008827005],"category_scores_gemma":[0.006138293,0.00038101996,0.0009850923,0.00047938633,0.0008344837,0.0008801059,0.0007061989,0.0013799373,0.00020917588],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010065473,0.00004544923,0.0055182762,0.000047709673,0.00005373502,0.000051066138,0.00013831239,0.9653958,0.008727348,0.00464937,0.00020478983,0.015067573],"study_design_scores_gemma":[0.0000018313146,0.000015286718,0.0009144091,0.0000024660383,0.000005740813,0.000018556135,0.00000577162,0.99441904,0.0018425696,0.002650599,0.00011550762,0.0000082046445],"about_ca_topic_score_codex":0.0027124817,"about_ca_topic_score_gemma":0.002191321,"teacher_disagreement_score":0.0027124817,"about_ca_system_score_codex":0.0009510267,"about_ca_system_score_gemma":0.0006432946,"threshold_uncertainty_score":0.007306814},"labels":[],"label_agreement":null},{"id":"W2156995746","doi":"10.1186/1471-2105-10-316","title":"Unsupervised statistical clustering of environmental shotgun sequences","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":111,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Advanced Research Projects Agency; Defense Advanced Research Projects Agency; Burroughs Wellcome Fund","keywords":"Cluster analysis; Computer science; Shotgun sequencing; Dimensionality reduction; Unsupervised learning; Pairwise comparison; Statistical model; Pattern recognition (psychology); Artificial intelligence; Computational biology; Data mining; Genome; Biology; Genetics","score_opus":0.013628305682145651,"score_gpt":0.22951481145326502,"score_spread":0.21588650577111937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156995746","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.064749874,0.00018868013,0.93245745,0.00006956203,0.000013180207,0.000072479255,0.00052394654,0.0013149059,0.0006099481],"genre_scores_gemma":[0.29064232,0.00025172305,0.70470995,0.000072624396,0.000027908292,0.00020009639,0.0029070794,0.00038702087,0.00080127723],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989109,0.00025211164,0.00007741003,0.00033716983,0.00036361557,0.0000587357],"domain_scores_gemma":[0.99739325,0.0011296297,0.00046585963,0.00036646263,0.00056014536,0.000084683335],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012567084,0.00051627966,0.0005749322,0.0020744198,0.00046026378,0.000672028,0.0012583919,0.0005854186,0.00092614786],"category_scores_gemma":[0.0038980725,0.00031456628,0.00071419886,0.0015967238,0.00094425376,0.0007996244,0.0007438794,0.00074300723,0.00052515895],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040378302,0.00026586637,0.025932206,0.0010833262,0.00041480258,0.00038791978,0.0005636118,0.45061392,0.21203645,0.037798043,0.0033800988,0.26712],"study_design_scores_gemma":[0.000016791586,0.00005950874,0.009911973,0.000048443377,0.000024998375,0.00025053447,0.00007915124,0.8990543,0.04859447,0.038412146,0.0034918673,0.000055832264],"about_ca_topic_score_codex":0.0013585052,"about_ca_topic_score_gemma":0.0022903646,"teacher_disagreement_score":0.0020744198,"about_ca_system_score_codex":0.00082821643,"about_ca_system_score_gemma":0.0011066514,"threshold_uncertainty_score":0.0066461563},"labels":[],"label_agreement":null},{"id":"W2157031164","doi":"10.1186/1471-2105-11-60","title":"Testing for mean and correlation changes in microarray experiments: an application for pathway analysis","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Health Canada","funders":"","keywords":"DNA microarray; Rank (graph theory); Microarray analysis techniques; Correlation; Microarray; Computational biology; Gene; Rank correlation; Function (biology); Representation (politics); Computer science; Set (abstract data type); Biological pathway; Biology; Genetics; Mathematics; Gene expression; Machine learning","score_opus":0.0178437617757931,"score_gpt":0.260471605891446,"score_spread":0.2426278441156529,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157031164","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048914164,0.0003894078,0.9468651,0.0002911175,0.00005590271,0.00020778201,0.00056965486,0.0019732597,0.00073361763],"genre_scores_gemma":[0.3045159,0.0002657832,0.692725,0.00009956847,0.000065409855,0.0005630154,0.0007256182,0.00022429306,0.0008154696],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99244845,0.0041139424,0.0003172801,0.0010061479,0.0018752287,0.00023898177],"domain_scores_gemma":[0.95664114,0.036514696,0.0019281814,0.0027621845,0.0018044536,0.00034935834],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01271851,0.0012528815,0.0015668775,0.0024567028,0.0009786343,0.001120823,0.0012531613,0.0013703894,0.0034542521],"category_scores_gemma":[0.04007858,0.00043384693,0.002511153,0.0028835533,0.0017441066,0.001525559,0.0011917425,0.0022261855,0.00056842196],"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":[0.0027706325,0.0007450065,0.06789303,0.0015966819,0.001655034,0.00135247,0.0005584557,0.1801843,0.07078172,0.033502314,0.005134313,0.63382596],"study_design_scores_gemma":[0.00021366576,0.0021859654,0.036734264,0.00008247516,0.0003967822,0.0017400318,0.00023104936,0.8248682,0.046251956,0.080690965,0.0064102146,0.00019428533],"about_ca_topic_score_codex":0.0009704511,"about_ca_topic_score_gemma":0.0011554345,"teacher_disagreement_score":0.01271851,"about_ca_system_score_codex":0.00079265656,"about_ca_system_score_gemma":0.0017486055,"threshold_uncertainty_score":0.06726271},"labels":[],"label_agreement":null},{"id":"W2157075067","doi":"10.1186/1471-2105-9-s10-o6","title":"Ranking single nucleotide polymorphisms by potential deleterious effects","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Single-nucleotide polymorphism; SNP genotyping; Genotyping; Biology; Computational biology; Human genome; Genetics; Mendelian inheritance; Genome-wide association study; DNA microarray; Genetic association; Bioinformatics; Genome; Gene; Genotype","score_opus":0.010665789022997446,"score_gpt":0.2159110418210307,"score_spread":0.20524525279803327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157075067","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43147406,0.0026155133,0.55144036,0.0013572779,0.0003151949,0.00053984876,0.0033980052,0.0049362434,0.0039235298],"genre_scores_gemma":[0.6575759,0.001059228,0.33278018,0.00036134952,0.00024993464,0.00022812175,0.004688611,0.00030698278,0.0027497471],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968953,0.0010735503,0.00033152825,0.00046057775,0.0010793454,0.00015969553],"domain_scores_gemma":[0.98997927,0.0058924393,0.00085925485,0.0008203709,0.002073139,0.0003754773],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0049166493,0.0011452285,0.0018772072,0.0053262576,0.00075706927,0.00188406,0.0010342095,0.0010587046,0.0022173317],"category_scores_gemma":[0.016763628,0.00030678342,0.0009990113,0.0037763962,0.000463345,0.0011994701,0.0012264163,0.0007389914,0.0007606242],"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":[0.0013279044,0.0004957298,0.22386745,0.0007335963,0.0010628378,0.0007848187,0.00027717164,0.10942018,0.03610882,0.008346885,0.016795272,0.6007793],"study_design_scores_gemma":[0.00032883344,0.00073577964,0.09055837,0.00010421775,0.00073779735,0.0020398377,0.0002753508,0.82454604,0.021476172,0.048351455,0.010601752,0.00024446662],"about_ca_topic_score_codex":0.0025582316,"about_ca_topic_score_gemma":0.0057659764,"teacher_disagreement_score":0.0053262576,"about_ca_system_score_codex":0.00045246765,"about_ca_system_score_gemma":0.001249103,"threshold_uncertainty_score":0.02600205},"labels":[],"label_agreement":null},{"id":"W2158055157","doi":"10.1186/1471-2105-14-s15-s7","title":"Phase change for the accuracy of the median value in estimating divergence time","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Divergence (linguistics); Statistics; Phase (matter); Value (mathematics); Mathematics; Computer science; Physics","score_opus":0.03238774637538646,"score_gpt":0.27991624986510255,"score_spread":0.24752850348971608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2158055157","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09269018,0.0025409898,0.89699036,0.002417133,0.0002993625,0.00003350839,0.0003031158,0.0008598062,0.0038655358],"genre_scores_gemma":[0.8406983,0.0011880401,0.15434802,0.0006693492,0.00042500257,0.00014470296,0.00056857883,0.0005205326,0.0014374491],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99524176,0.0022439915,0.00022982896,0.001022996,0.000854627,0.00040687586],"domain_scores_gemma":[0.88650745,0.09920873,0.0041081677,0.0061980383,0.0029456199,0.0010319469],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014481698,0.0008448694,0.0010747275,0.0018102359,0.0011454418,0.0025107611,0.0028920113,0.0020727718,0.002500042],"category_scores_gemma":[0.13010156,0.00076427305,0.0011869741,0.0013551202,0.0031576394,0.005684365,0.0027803895,0.0039587393,0.0007094635],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001607255,0.00014308022,0.046079118,0.00054582185,0.0002730674,0.00041917554,0.00066869875,0.6742872,0.01000019,0.16285697,0.004446975,0.098672524],"study_design_scores_gemma":[0.000034413682,0.000107019805,0.0025282064,0.000108117354,0.00003025408,0.0002905257,0.000052791533,0.8978157,0.0038541153,0.09397443,0.0011601772,0.000044131106],"about_ca_topic_score_codex":0.002486855,"about_ca_topic_score_gemma":0.0016192355,"teacher_disagreement_score":0.014481698,"about_ca_system_score_codex":0.0017834236,"about_ca_system_score_gemma":0.0015180578,"threshold_uncertainty_score":0.07658744},"labels":[],"label_agreement":null},{"id":"W2158386569","doi":"10.1186/1471-2105-6-305","title":"The Gene Set Builder: collation, curation, and distribution of sets of genes","year":2005,"lang":"en","type":"article","venue":"BMC Bioinformatics","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":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Child and Family Research Institute","funders":"Canadian Institutes of Health Research; Michael Smith Health Research BC","keywords":"Ensembl; Computer science; Identifier; Set (abstract data type); Gene nomenclature; Unique identifier; Database; Table (database); World Wide Web; Gene; Genome; Genomics; Biology; Genetics; Programming language","score_opus":0.009980879081941396,"score_gpt":0.23682597894491675,"score_spread":0.22684509986297535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2158386569","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040234867,0.000774463,0.34075728,0.00082064635,0.00057927874,0.001361485,0.25037938,0.38991973,0.011384277],"genre_scores_gemma":[0.012983227,0.00072652684,0.51966655,0.0006282093,0.00021325095,0.002900863,0.38328642,0.0736875,0.005907452],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99602365,0.00056664285,0.0005608462,0.0011030522,0.0014801179,0.00026551684],"domain_scores_gemma":[0.9918195,0.0022851482,0.0006977898,0.0025093819,0.0019634308,0.0007247366],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0052905777,0.0033331744,0.0019014812,0.015308381,0.002803688,0.0045271376,0.0041237413,0.0011771421,0.05533079],"category_scores_gemma":[0.017594308,0.0018107289,0.00220883,0.01379755,0.0011375108,0.0038510405,0.0071343496,0.003115383,0.053833514],"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":[0.00057884713,0.00009222693,0.005631277,0.0019087052,0.00019664537,0.00077479664,0.0009821978,0.0017143005,0.012458993,0.0076353126,0.8059666,0.16206007],"study_design_scores_gemma":[0.00022027598,0.00007454772,0.008045739,0.0006213744,0.0001235357,0.0013268483,0.00029760136,0.009375136,0.020253966,0.012504342,0.94690853,0.00024807354],"about_ca_topic_score_codex":0.0046712887,"about_ca_topic_score_gemma":0.0045384336,"teacher_disagreement_score":0.05533079,"about_ca_system_score_codex":0.001741646,"about_ca_system_score_gemma":0.0048119943,"threshold_uncertainty_score":0.1850999},"labels":[],"label_agreement":null},{"id":"W2158564991","doi":"10.1186/1471-2105-8-239","title":"Probabilistic prediction and ranking of human protein-protein interactions","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":134,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research","keywords":"Ranking (information retrieval); Computer science; Probabilistic logic; Bayes' theorem; Naive Bayes classifier; False positive rate; Set (abstract data type); False discovery rate; Bayesian probability; Data mining; Machine learning; Protein–protein interaction; Protein function prediction; Human proteome project; Bayesian network; Interaction network; Function (biology); Computational biology; Artificial intelligence; Protein function; Proteomics; Biology; Support vector machine; Genetics","score_opus":0.013808769752298883,"score_gpt":0.2508298393515291,"score_spread":0.2370210695992302,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2158564991","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4999891,0.005513181,0.468848,0.0006011541,0.00009690404,0.000216433,0.014645477,0.004345753,0.0057439986],"genre_scores_gemma":[0.8729041,0.0008507106,0.1131186,0.00010474887,0.000075394055,0.00011982199,0.011706953,0.00011101311,0.0010086496],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99809176,0.00056849234,0.0001065064,0.00045309274,0.0006628214,0.00011735599],"domain_scores_gemma":[0.9969896,0.0019023884,0.0004202485,0.0002050465,0.00039060356,0.00009202653],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017437107,0.00088987773,0.0007367349,0.002214934,0.0003760927,0.00076458044,0.0006331474,0.00080883165,0.002111154],"category_scores_gemma":[0.0053577255,0.0002970879,0.0006741079,0.0016980991,0.00029830151,0.00052276417,0.0007592504,0.0005870907,0.0012051775],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018764804,0.00046551332,0.16889028,0.0016750657,0.0010253163,0.0007136377,0.00016652534,0.40670058,0.050707545,0.0047424883,0.022735339,0.34030122],"study_design_scores_gemma":[0.000060581016,0.00022002734,0.048065394,0.000055202065,0.00013627039,0.0008984605,0.00004036367,0.922437,0.015708465,0.008025716,0.0042997296,0.000052796186],"about_ca_topic_score_codex":0.0019982061,"about_ca_topic_score_gemma":0.0034419717,"teacher_disagreement_score":0.002214934,"about_ca_system_score_codex":0.0005493336,"about_ca_system_score_gemma":0.0005957848,"threshold_uncertainty_score":0.009221673},"labels":[],"label_agreement":null},{"id":"W2159070430","doi":"10.1186/1471-2105-12-s9-s2","title":"Evolution of orthologous tandemly arrayed gene clusters","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bombardier (Canada); Université de Montréal","funders":"","keywords":"DNA microarray; Genetics; Biology; Computational biology; Gene; Evolutionary biology; Gene expression","score_opus":0.021895325964833415,"score_gpt":0.21869581851453831,"score_spread":0.1968004925497049,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159070430","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86989284,0.00028592427,0.1278332,0.00015056164,0.000014248194,0.000054926524,0.00040696288,0.00040323232,0.00095814536],"genre_scores_gemma":[0.8627934,0.00011544061,0.13485974,0.000069298025,0.000009456903,0.000068401,0.0014507958,0.000118024254,0.0005154244],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991817,0.00022040759,0.0000421554,0.00036020653,0.00013412109,0.000061391875],"domain_scores_gemma":[0.9964191,0.0025511072,0.00033044018,0.00020740749,0.00036532118,0.00012658608],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002142094,0.00037489925,0.00048610778,0.0010823936,0.00059062004,0.0009125063,0.0013186095,0.0009781902,0.0010923576],"category_scores_gemma":[0.0074991514,0.00043479443,0.00068690424,0.00096624787,0.00065360527,0.0008603111,0.0008355022,0.0007648024,0.00026196093],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046400394,0.00017451649,0.11473036,0.00028691726,0.00024833521,0.00036798787,0.0006378929,0.76836824,0.027749429,0.013685702,0.0010105456,0.072276086],"study_design_scores_gemma":[0.00003487675,0.00007304686,0.011868074,0.000024081934,0.000048095088,0.00028493974,0.00008512665,0.969053,0.008071236,0.009296867,0.0011402209,0.000020461493],"about_ca_topic_score_codex":0.0028840553,"about_ca_topic_score_gemma":0.0026493438,"teacher_disagreement_score":0.0028840553,"about_ca_system_score_codex":0.001435701,"about_ca_system_score_gemma":0.00079464185,"threshold_uncertainty_score":0.011328578},"labels":[],"label_agreement":null},{"id":"W2159184793","doi":"10.1186/1471-2105-11-420","title":"An improved classification of G-protein-coupled receptors using sequence-derived features","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Ministry of Education, India","keywords":"G protein-coupled receptor; Jackknife resampling; Computational biology; Identification (biology); Artificial intelligence; Subfamily; Computer science; Principal component analysis; Feature (linguistics); Sequence (biology); Biology; Pattern recognition (psychology); Machine learning; Bioinformatics; Receptor; Genetics; Mathematics; Estimator; Statistics; Gene","score_opus":0.02074571848625936,"score_gpt":0.29216161463697266,"score_spread":0.2714158961507133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159184793","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.64976966,0.0031600418,0.33242333,0.0007062928,0.00034237903,0.00030114144,0.0035055296,0.005100294,0.004691376],"genre_scores_gemma":[0.8338123,0.0007220387,0.1510016,0.0002865996,0.00017853662,0.00017657595,0.0100525785,0.00007377281,0.0036960181],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99933904,0.00009644731,0.00005234895,0.00016718387,0.000217957,0.00012703697],"domain_scores_gemma":[0.9992378,0.00023434177,0.000071987895,0.00007078172,0.0003305666,0.000054614662],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007629585,0.00079635275,0.000887128,0.0017264525,0.00036364968,0.0006473514,0.000903795,0.0010158055,0.0015336104],"category_scores_gemma":[0.0016404259,0.0001618591,0.0011133772,0.00097069814,0.0002597611,0.00073349767,0.0005541737,0.00082494656,0.0011185415],"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":[0.0013423229,0.00076680415,0.020815346,0.000249665,0.00020078602,0.00028978,0.000082429615,0.09406401,0.06953534,0.0016684756,0.016113268,0.79487175],"study_design_scores_gemma":[0.00004428804,0.00022009193,0.008231422,0.000014262467,0.000049309445,0.00012995645,0.00003447946,0.980342,0.008515748,0.00076676835,0.0016298761,0.000021820419],"about_ca_topic_score_codex":0.007172789,"about_ca_topic_score_gemma":0.0036722491,"teacher_disagreement_score":0.007172789,"about_ca_system_score_codex":0.0004828106,"about_ca_system_score_gemma":0.0012859612,"threshold_uncertainty_score":0.01426208},"labels":[],"label_agreement":null},{"id":"W2159230276","doi":"10.1186/1471-2105-9-s11-s10","title":"Recognizing speculative language in biomedical research articles: a linguistically motivated perspective","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":126,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Collège de Maisonneuve; Concordia University","funders":"","keywords":"Weighting; Computer science; Perspective (graphical); Sentence; Artificial intelligence; Natural language processing; Point (geometry); Scheme (mathematics); Machine learning; Mathematics","score_opus":0.09097231171662291,"score_gpt":0.36817676912295266,"score_spread":0.27720445740632976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159230276","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2928649,0.006336572,0.6434589,0.0070212707,0.00067832216,0.0011413686,0.008060624,0.025651952,0.014786094],"genre_scores_gemma":[0.42277995,0.001250708,0.5645206,0.0010723894,0.00053101406,0.0002724692,0.006495194,0.0004623568,0.0026153673],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9964045,0.0010042025,0.0005649048,0.0008120368,0.0010745046,0.00013981976],"domain_scores_gemma":[0.9785943,0.012075517,0.004012039,0.0018370869,0.002965168,0.00051581446],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0047557056,0.0008938216,0.00069762074,0.007906768,0.0006308471,0.0039170873,0.0013605853,0.0016156989,0.0022470066],"category_scores_gemma":[0.022767514,0.00040861944,0.0010322512,0.002808597,0.00088528893,0.005000348,0.002036643,0.0017167676,0.0022327534],"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":[0.0009945789,0.00044273285,0.025972921,0.0029125041,0.0003876229,0.0015171317,0.00411373,0.0052586338,0.18408361,0.013791716,0.021945909,0.7385789],"study_design_scores_gemma":[0.00019953446,0.0012335074,0.069585726,0.0016572108,0.0010030468,0.006475314,0.00608251,0.43663132,0.23429804,0.10330154,0.1389236,0.00060870306],"about_ca_topic_score_codex":0.0010295082,"about_ca_topic_score_gemma":0.0021221833,"teacher_disagreement_score":0.99524426,"about_ca_system_score_codex":0.00084704824,"about_ca_system_score_gemma":0.001224869,"threshold_uncertainty_score":0.025150895},"labels":[],"label_agreement":null},{"id":"W2159348493","doi":"10.1186/1471-2105-9-327","title":"Gene Ontology term overlap as a measure of gene functional similarity","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":205,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Michael Smith Health Research BC","funders":"National Institute of General Medical Sciences; National Institutes of Health; Michael Smith Health Research BC","keywords":"Semantic similarity; Computer science; Similarity (geometry); Term (time); Measure (data warehouse); Data mining; Similarity measure; Ontology; Gene ontology; Information retrieval; Artificial intelligence; Machine learning; Gene; Biology; Genetics","score_opus":0.024040132471224746,"score_gpt":0.2268267298727449,"score_spread":0.20278659740152016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159348493","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81929904,0.0016131096,0.16889045,0.00017163785,0.00009788878,0.00019378595,0.0030781708,0.00095826125,0.0056976746],"genre_scores_gemma":[0.93432564,0.00016906866,0.062950775,0.000027716498,0.00003794246,0.00016898228,0.0018338962,0.00007840723,0.00040749417],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964477,0.0009636542,0.00038296546,0.00051529234,0.0015125489,0.00017782513],"domain_scores_gemma":[0.98662347,0.008871399,0.0018824855,0.0008247301,0.0014662874,0.0003315379],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00330077,0.0005544442,0.00067493203,0.0075925817,0.0004681252,0.0011436212,0.00076714397,0.0006711867,0.0014041989],"category_scores_gemma":[0.016069267,0.00012733192,0.00077226775,0.0069258455,0.0008487486,0.0014791123,0.0012385483,0.0006267175,0.0002629223],"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":[0.0037208546,0.00079280476,0.44471583,0.0020891728,0.0022058014,0.00057468633,0.0019666357,0.07717814,0.096596226,0.033657752,0.0068347924,0.3296673],"study_design_scores_gemma":[0.00016152901,0.0018938102,0.4565187,0.00020669177,0.00075770076,0.002756566,0.001312749,0.3895998,0.061844386,0.069034636,0.015547258,0.00036618847],"about_ca_topic_score_codex":0.001196783,"about_ca_topic_score_gemma":0.0014899763,"teacher_disagreement_score":0.0075925817,"about_ca_system_score_codex":0.00092268025,"about_ca_system_score_gemma":0.00049698865,"threshold_uncertainty_score":0.017456353},"labels":[],"label_agreement":null},{"id":"W2159835316","doi":"10.1186/1471-2105-8-242","title":"Improving gene set analysis of microarray data by SAM-GS","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":263,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Cancer Institute; Astellas Pharma; Genome Alberta; Canada Research Chairs; Muttart Foundation; University of Alberta; Fondation pour la Recherche Médicale; Roche Organ Transplant Research Foundation; Kidney Foundation of Canada; Canadian Institutes of Health Research; Genome Canada","keywords":"Gene; Microarray analysis techniques; DNA microarray; Biology; Computational biology; Microarray; Genetics; Gene expression; Gene expression profiling; Significance analysis of microarrays; Phenotype; Microarray databases; Biological pathway","score_opus":0.018778310927165674,"score_gpt":0.25856707239389176,"score_spread":0.2397887614667261,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159835316","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015959162,0.00062647805,0.96756625,0.00021718643,0.00015828626,0.00016487727,0.0015858898,0.013239472,0.0004824625],"genre_scores_gemma":[0.051375877,0.00024500827,0.9423526,0.00015932201,0.000083198,0.00067344867,0.003377809,0.0014284366,0.00030434947],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9894847,0.005769706,0.0008777771,0.0019392364,0.0016491448,0.0002793783],"domain_scores_gemma":[0.975998,0.016720818,0.0010794717,0.0040204376,0.0019503945,0.00023091523],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017081562,0.0039808936,0.0033500558,0.0062146625,0.0013802055,0.0023385454,0.0029266137,0.0011368418,0.0046131527],"category_scores_gemma":[0.031378083,0.0011874241,0.006790022,0.0074832723,0.0013319079,0.0017975047,0.0024391075,0.0042248615,0.002639306],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022283185,0.0005278631,0.02910244,0.0033360305,0.006225902,0.00057972985,0.0010494668,0.12052326,0.09624361,0.014211268,0.023465596,0.7025066],"study_design_scores_gemma":[0.00033852577,0.000625739,0.02221272,0.0001406078,0.0014010217,0.00066970283,0.0003461981,0.8368705,0.06306286,0.039687485,0.034320805,0.0003239313],"about_ca_topic_score_codex":0.002453656,"about_ca_topic_score_gemma":0.0035593365,"teacher_disagreement_score":0.017081562,"about_ca_system_score_codex":0.0010102205,"about_ca_system_score_gemma":0.0017782723,"threshold_uncertainty_score":0.09033698},"labels":[],"label_agreement":null},{"id":"W2160824383","doi":"10.1186/1471-2105-14-s6-s1","title":"Reconstruction of regulatory networks through temporal enrichment profiling and its application to H1N1 influenza viral infection","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"interferon and immune responses","field":"Immunology and Microbiology","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"National Center for Advancing Translational Sciences; National Institute of Allergy and Infectious Diseases; NIH Clinical Center; National Institutes of Health","keywords":"Biology; Gene regulatory network; Computational biology; Influenza A virus; Gene expression profiling; Transcription factor; Genome; Gene; Virology; Virus; Gene expression; Genetics","score_opus":0.014866996160236071,"score_gpt":0.25093402042136187,"score_spread":0.2360670242611258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160824383","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35175535,0.00019710041,0.64400244,0.00011803799,0.000014313366,0.000052916115,0.0010584561,0.0019917223,0.0008096722],"genre_scores_gemma":[0.7359315,0.0002337632,0.26069397,0.00005838816,0.000013786579,0.00013821565,0.0020923577,0.0002013945,0.00063669606],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998491,0.000049206188,0.0000073370343,0.000044838223,0.000029665973,0.000019822293],"domain_scores_gemma":[0.9994017,0.0004108518,0.0000633215,0.00004266004,0.00005145945,0.000030118083],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052176334,0.0003675743,0.00031071831,0.0006660977,0.00027832616,0.0003794891,0.00037232877,0.00030718435,0.00072243076],"category_scores_gemma":[0.0015708429,0.00024718925,0.0007985405,0.0005996404,0.00028676767,0.00018240731,0.0003773905,0.00042651943,0.00017865843],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031178218,0.00010341235,0.018101308,0.00018596568,0.00014522411,0.00017592576,0.00022076686,0.8207145,0.100492254,0.0051659867,0.00051586534,0.053867064],"study_design_scores_gemma":[0.00000493226,0.00002000692,0.0024331023,0.0000026999658,0.000012176369,0.00002133631,0.000019366402,0.9880782,0.007314488,0.0015966516,0.0004899464,0.000007109393],"about_ca_topic_score_codex":0.005053082,"about_ca_topic_score_gemma":0.0061193346,"teacher_disagreement_score":0.005053082,"about_ca_system_score_codex":0.00049862853,"about_ca_system_score_gemma":0.00062841765,"threshold_uncertainty_score":0.010047317},"labels":[],"label_agreement":null},{"id":"W2160853918","doi":"10.1186/1471-2105-10-s1-s49","title":"Quality assessment of tandem mass spectra using support vector machine (SVM)","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University; Université Laval; University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Support vector machine; Tandem; Computer science; Data mining; Quality (philosophy); Pattern recognition (psychology); Quality assurance; DNA microarray; Artificial intelligence; Machine learning; Computational biology; Biology; Materials science; Engineering; Physics; Genetics; Gene expression; External quality assessment; Operations management","score_opus":0.04707407499927428,"score_gpt":0.3609859428142803,"score_spread":0.313911867815006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160853918","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27746594,0.0007805034,0.71883506,0.00027050782,0.00006279232,0.000080486425,0.00025140186,0.0015156433,0.0007377271],"genre_scores_gemma":[0.8577881,0.00021638993,0.1411524,0.00003479248,0.00004292125,0.000041993128,0.00043801326,0.00003153183,0.00025392426],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983968,0.00041014169,0.00022983574,0.00022181259,0.0006465277,0.00009492133],"domain_scores_gemma":[0.9930461,0.0029127584,0.0012602102,0.00035033844,0.0022647837,0.00016590265],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004037234,0.00065933616,0.0008537059,0.0019754395,0.00026004334,0.00091141195,0.0007049432,0.00081728504,0.00070170284],"category_scores_gemma":[0.007555407,0.0001528629,0.00057961117,0.0009982046,0.00042501182,0.00093764777,0.0004400025,0.00063698995,0.00038138297],"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":[0.0012254001,0.00035131746,0.06352363,0.00044642074,0.00034605226,0.00027982247,0.00017894956,0.09340133,0.045647733,0.00136774,0.002964237,0.79026735],"study_design_scores_gemma":[0.000032094646,0.00030695877,0.015442978,0.000028563489,0.000066457214,0.000275996,0.000063891835,0.962404,0.019117476,0.0015940355,0.0006368922,0.00003064538],"about_ca_topic_score_codex":0.0006446473,"about_ca_topic_score_gemma":0.00035342612,"teacher_disagreement_score":0.004037234,"about_ca_system_score_codex":0.00035396463,"about_ca_system_score_gemma":0.00036468427,"threshold_uncertainty_score":0.021351159},"labels":[],"label_agreement":null},{"id":"W2161701113","doi":"10.1186/1471-2105-7-365","title":"PIPE: a protein-protein interaction prediction engine based on the re-occurring short polypeptide sequences between known interacting protein pairs","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":219,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Tandem affinity purification; Saccharomyces cerevisiae; Protein–protein interaction; Yeast; Computational biology; Interaction network; Biology; Gene; Genetics; Bioinformatics; Biochemistry","score_opus":0.017602154927653123,"score_gpt":0.2389834037510581,"score_spread":0.22138124882340496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161701113","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055586524,0.0009455743,0.6943454,0.00023739961,0.00014012482,0.0004022402,0.018926164,0.22679015,0.002626435],"genre_scores_gemma":[0.24042206,0.0013724754,0.68236566,0.00040208016,0.00010115011,0.00084908074,0.06304176,0.0065115597,0.0049342182],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99962246,0.000041513773,0.000032557266,0.00013513581,0.00014056312,0.000027730011],"domain_scores_gemma":[0.9993463,0.00033209685,0.00012987363,0.000062043706,0.000083279796,0.00004636837],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008511827,0.001973407,0.0009177497,0.0014533694,0.00038988196,0.0008465125,0.0015672871,0.00084705674,0.0056597367],"category_scores_gemma":[0.0018989433,0.00068096403,0.0013234667,0.0008116668,0.00032425497,0.0015861101,0.00095227564,0.0009591738,0.0037401326],"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":[0.00616169,0.00072052085,0.03287801,0.0056399484,0.0012696028,0.0039082323,0.0006729617,0.072355464,0.26127294,0.010516357,0.14079285,0.46381146],"study_design_scores_gemma":[0.00032755252,0.0007387395,0.013562867,0.00018529907,0.00034620307,0.0025191216,0.00012258984,0.74973357,0.14494486,0.012441479,0.07482881,0.0002487878],"about_ca_topic_score_codex":0.0007640724,"about_ca_topic_score_gemma":0.0010262297,"teacher_disagreement_score":0.0056597367,"about_ca_system_score_codex":0.0003528143,"about_ca_system_score_gemma":0.0006010257,"threshold_uncertainty_score":0.018933654},"labels":[],"label_agreement":null},{"id":"W2161758034","doi":"10.1186/1471-2105-8-177","title":"Requirements and ontology for a G protein-coupled receptor oligomerization knowledge base","year":2007,"lang":"en","type":"editorial","venue":"BMC Bioinformatics","topic":"Receptor Mechanisms and Signaling","field":"Biochemistry, Genetics and Molecular Biology","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Université de Montréal; Institute for Research in Immunology and Cancer","funders":"National Institute on Drug Abuse; National Institutes of Health","keywords":"G protein-coupled receptor; Ontology; Context (archaeology); Computer science; Computational biology; Knowledge base; Data science; Knowledge management; Biology; Receptor; World Wide Web; Biochemistry","score_opus":0.020055085445667805,"score_gpt":0.28881668647521375,"score_spread":0.26876160102954594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161758034","genre_codex":"methods","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019698929,0.0005426444,0.94033855,0.006529126,0.00024275976,0.0029001457,0.012224186,0.0045847693,0.012938893],"genre_scores_gemma":[0.06369567,0.00082472933,0.9105044,0.00096592185,0.00010298853,0.0017080016,0.019201208,0.00045875664,0.0025384563],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9797223,0.0037530754,0.006670496,0.0021076098,0.0066276686,0.0011188249],"domain_scores_gemma":[0.97603965,0.009996507,0.0022888135,0.004240351,0.006149033,0.0012857079],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015335244,0.0012779039,0.00153428,0.008746397,0.0029328316,0.007971043,0.004310683,0.0035207258,0.0030230023],"category_scores_gemma":[0.02503775,0.0015042123,0.0044711023,0.0072707343,0.002680028,0.01365523,0.0057797804,0.0042446656,0.001778748],"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":[0.00063770934,0.0011616313,0.010531219,0.004566517,0.0005244168,0.005667527,0.009351131,0.049008537,0.02831496,0.6175374,0.04226224,0.23043662],"study_design_scores_gemma":[0.00026916896,0.0002597433,0.004624004,0.002597219,0.00075650157,0.0036259305,0.0049645314,0.17038013,0.022327805,0.32134593,0.46849075,0.00035834048],"about_ca_topic_score_codex":0.022482803,"about_ca_topic_score_gemma":0.014221985,"teacher_disagreement_score":0.022482803,"about_ca_system_score_codex":0.0036368957,"about_ca_system_score_gemma":0.010307853,"threshold_uncertainty_score":0.08110148},"labels":[],"label_agreement":null},{"id":"W2162224067","doi":"10.1186/1471-2105-9-340","title":"RNA STRAND: The RNA Secondary Structure and Statistical Analysis Database","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":287,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of British Columbia Hospital","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"RNA; Nucleic acid secondary structure; Database; Protein secondary structure; Computer science; Nucleic acid structure; Computational biology; Biology; Genetics; Gene","score_opus":0.013741878627289974,"score_gpt":0.2343050137810196,"score_spread":0.2205631351537296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162224067","genre_codex":"dataset","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034758276,0.005232446,0.096058615,0.00068947754,0.00039752954,0.0005545344,0.8195636,0.05750949,0.016518489],"genre_scores_gemma":[0.008659736,0.0019385513,0.09143086,0.00056595047,0.00018010699,0.0010973894,0.8841836,0.0073986277,0.0045451685],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977343,0.0004323342,0.00045026286,0.00051376194,0.00072251575,0.00014676753],"domain_scores_gemma":[0.99511766,0.0017893786,0.00073007547,0.00085891684,0.0010647743,0.00043918786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002992968,0.0021347478,0.002509757,0.004597024,0.0010464421,0.0031978667,0.0035717427,0.0018247657,0.046409998],"category_scores_gemma":[0.008541309,0.0009622249,0.0012225675,0.005842542,0.0005717433,0.0020654516,0.002385147,0.0019828272,0.06596905],"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":[0.0014297258,0.0001458613,0.0039582546,0.008195748,0.0003556358,0.0006904356,0.00036734788,0.0039051562,0.04050913,0.016969657,0.7614022,0.16207083],"study_design_scores_gemma":[0.00025137726,0.00013025122,0.0037083947,0.0005412009,0.00017272968,0.0006729636,0.00007774496,0.003593369,0.01169325,0.014326986,0.96470857,0.00012327834],"about_ca_topic_score_codex":0.0015801227,"about_ca_topic_score_gemma":0.0016635259,"teacher_disagreement_score":0.046409998,"about_ca_system_score_codex":0.00073769456,"about_ca_system_score_gemma":0.0037631555,"threshold_uncertainty_score":0.15525693},"labels":[],"label_agreement":null},{"id":"W2164147743","doi":"10.1186/1471-2105-9-422","title":"SIGMA2: A system for the integrative genomic multi-dimensional analysis of cancer genomes, epigenomes, and transcriptomes","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Epigenetics and DNA Methylation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"National Institute of Dental and Craniofacial Research; Canadian Institutes of Health Research; National Institutes of Health; Michael Smith Health Research BC; Genome Canada","keywords":"Computational biology; Genome; Biology; DNA microarray; Transcriptome; DNA methylation; Epigenomics; Genomics; Tiling array; Identification (biology); Genetics; Gene; Bioinformatics; Gene expression","score_opus":0.027245981636458732,"score_gpt":0.27723991678293497,"score_spread":0.24999393514647625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164147743","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012884239,0.000635417,0.7969692,0.00032879598,0.00026149082,0.00028039495,0.01167957,0.17523612,0.0017248647],"genre_scores_gemma":[0.071506925,0.0011543067,0.85614944,0.0006841765,0.000132918,0.0020445848,0.0463276,0.016992107,0.0050079157],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99900216,0.00020402041,0.0000972752,0.00024668587,0.0003473779,0.000102442624],"domain_scores_gemma":[0.99889284,0.000377695,0.0001421337,0.00025603274,0.0001717741,0.00015939487],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021710414,0.0018005479,0.001667853,0.0011665418,0.00072654674,0.0017526412,0.0019457217,0.001044898,0.00843786],"category_scores_gemma":[0.0022263466,0.001505289,0.0018879502,0.0009812873,0.000654188,0.0011980587,0.0020550857,0.0021849235,0.0061466936],"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":[0.0077416925,0.00038725632,0.010941897,0.0027552254,0.0013216161,0.0012005661,0.0011765531,0.014364373,0.49335366,0.016479848,0.18541951,0.2648578],"study_design_scores_gemma":[0.00131961,0.000983094,0.010183653,0.00033002193,0.00042689036,0.0020414256,0.00022516232,0.2829323,0.39467904,0.026279515,0.27985257,0.0007467008],"about_ca_topic_score_codex":0.0012210825,"about_ca_topic_score_gemma":0.00120385,"teacher_disagreement_score":0.00843786,"about_ca_system_score_codex":0.0005782915,"about_ca_system_score_gemma":0.001299209,"threshold_uncertainty_score":0.028227508},"labels":[],"label_agreement":null},{"id":"W2164314657","doi":"10.1186/1471-2105-7-s2-s18","title":"Differential gene expression in mouse primary hepatocytes exposed to the peroxisome proliferator-activated receptor α agonists","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Peroxisome Proliferator-Activated Receptors","field":"Biochemistry, Genetics and Molecular Biology","cited_by":69,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Alberta","keywords":"Bezafibrate; Peroxisome proliferator-activated receptor; Fenofibrate; Peroxisome proliferator-activated receptor alpha; Transactivation; Endocrinology; Internal medicine; Peroxisome proliferator-activated receptor gamma; Peroxisome; Clofibric acid; Biology; Agonist; Receptor; Pharmacology; Chemistry; Nuclear receptor; Gene expression; Medicine; Gene; Biochemistry; Transcription factor","score_opus":0.01067915524515267,"score_gpt":0.21851386693985134,"score_spread":0.20783471169469867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164314657","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9872344,0.0030813364,0.0036476566,0.00008989692,0.0000669724,0.000048373255,0.004115672,0.00009787353,0.0016177814],"genre_scores_gemma":[0.9762031,0.0031378018,0.0066756452,0.00023296713,0.00004291323,0.00030462633,0.0065920725,0.000033272026,0.0067774937],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99981886,0.000014279033,0.000011710548,0.00006353016,0.0000514855,0.00004014849],"domain_scores_gemma":[0.9999199,0.000015450583,0.00001876768,0.000006662295,0.000021320524,0.00001796711],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009707467,0.0002422333,0.00030815383,0.0004675,0.00018434478,0.0002216498,0.00008795634,0.00020452641,0.0010927911],"category_scores_gemma":[0.00006912434,0.000119163946,0.00033480578,0.0005523523,0.00020160609,0.000108432905,0.00012519263,0.0002857742,0.00041221632],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013787007,0.000010315347,0.0006848249,0.000028045664,0.000006713259,0.00004106444,0.0000110484125,0.000022722643,0.99852824,0.000012632253,0.000021626174,0.00049491785],"study_design_scores_gemma":[0.00002592494,0.0005695372,0.09248507,0.000010569529,0.000086698776,0.00044714147,0.00013653413,0.0006371528,0.90359664,0.00007747548,0.0019157663,0.000011422655],"about_ca_topic_score_codex":0.0005524655,"about_ca_topic_score_gemma":0.0009429879,"teacher_disagreement_score":0.0010927911,"about_ca_system_score_codex":0.00020975186,"about_ca_system_score_gemma":0.00012909473,"threshold_uncertainty_score":0.0036557317},"labels":[],"label_agreement":null},{"id":"W2165057277","doi":"10.1186/s12859-015-0488-1","title":"OTO: Ontology Term Organizer","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Agriculture and Agri-Food Canada","funders":"National Science Foundation","keywords":"Term (time); Ontology; Computer science; Computational biology; Information retrieval; DNA microarray; Gene ontology; Biology; Data science; Bioinformatics; World Wide Web; Genetics; Gene; Physics","score_opus":0.04411125647240074,"score_gpt":0.2846898439338195,"score_spread":0.24057858746141877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2165057277","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014829662,0.0014850679,0.5357282,0.0016956708,0.00077865104,0.0032160187,0.23069547,0.18002288,0.031548362],"genre_scores_gemma":[0.030814456,0.0009939584,0.5297168,0.0006156104,0.00023377,0.0036529456,0.40114912,0.02406706,0.008756206],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99690443,0.0003740743,0.00073132775,0.0007269803,0.0010064445,0.00025669788],"domain_scores_gemma":[0.9928068,0.0023629174,0.0013483324,0.0014737444,0.0013646653,0.0006434326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035898893,0.002112391,0.0010617848,0.010953894,0.0018338602,0.0041427976,0.0024375175,0.0010442641,0.018666627],"category_scores_gemma":[0.017008262,0.0011390537,0.0023963763,0.010506304,0.001234324,0.0070508546,0.0062422855,0.0023234366,0.01448491],"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":[0.00076213863,0.00021081467,0.011941557,0.0049069338,0.00026602278,0.0008993078,0.004671645,0.004025831,0.015551549,0.045128174,0.57019234,0.3414437],"study_design_scores_gemma":[0.00014506067,0.0000950252,0.007420312,0.00074107863,0.00012781053,0.0008453059,0.0011246693,0.0134976925,0.00942992,0.046197705,0.920182,0.0001935071],"about_ca_topic_score_codex":0.009752534,"about_ca_topic_score_gemma":0.010122339,"teacher_disagreement_score":0.018666627,"about_ca_system_score_codex":0.0018180998,"about_ca_system_score_gemma":0.005983253,"threshold_uncertainty_score":0.062446058},"labels":[],"label_agreement":null},{"id":"W2165145683","doi":"10.1186/1471-2105-14-69","title":"BOND: Basic OligoNucleotide Design","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Oligonucleotide; DNA microarray; Computer science; Software; Computational biology; DNA; Gene; Biology; Genetics; Programming language","score_opus":0.02351071718670648,"score_gpt":0.23917089378504766,"score_spread":0.2156601765983412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2165145683","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018797007,0.00079036306,0.9591559,0.00017143146,0.0001967084,0.00023856327,0.0020284937,0.024599459,0.010939323],"genre_scores_gemma":[0.025521656,0.0009604548,0.9507444,0.00044018053,0.0000674284,0.0014419812,0.004503367,0.0051667755,0.011153814],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983394,0.0003642316,0.00015329539,0.0003186245,0.00070957607,0.000114906165],"domain_scores_gemma":[0.9988846,0.0004686048,0.000114940194,0.0001436843,0.00032194145,0.00006616638],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014601676,0.0016602309,0.0010553438,0.0010681028,0.0006450822,0.0015351176,0.0025113297,0.001040546,0.049448032],"category_scores_gemma":[0.0039842394,0.0011865812,0.0014653471,0.0011365934,0.0007261889,0.0013803199,0.001188009,0.0019568345,0.026802285],"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":[0.0009829557,0.00020315876,0.0015061331,0.0033429847,0.00020242964,0.0003626214,0.00032047296,0.033556636,0.07977616,0.12053758,0.139952,0.61925673],"study_design_scores_gemma":[0.000351089,0.00049185177,0.000483711,0.00028329904,0.0001153794,0.001087944,0.0000758639,0.12300107,0.07813271,0.13217904,0.6636547,0.0001433889],"about_ca_topic_score_codex":0.0006424868,"about_ca_topic_score_gemma":0.0007457464,"teacher_disagreement_score":0.049448032,"about_ca_system_score_codex":0.0005925603,"about_ca_system_score_gemma":0.0011759268,"threshold_uncertainty_score":0.16542011},"labels":[],"label_agreement":null},{"id":"W2165336044","doi":"10.1186/1471-2105-11-304","title":"Scaffold filling, contig fusion and comparative gene order inference","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Genome; Contig; Synteny; Biology; Computational biology; Phylogenetic tree; Comparative genomics; Hybrid genome assembly; DNA microarray; Gene; Genetics; Genomics","score_opus":0.027260786510222387,"score_gpt":0.26934092065029847,"score_spread":0.24208013414007606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2165336044","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022277275,0.0001738729,0.97299296,0.00007577213,0.000017674047,0.000042193333,0.00030536603,0.0033655742,0.0007493222],"genre_scores_gemma":[0.14546375,0.000108496075,0.8514787,0.00007195514,0.000025946942,0.00012156143,0.0015039454,0.00038748016,0.0008381241],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99785787,0.00081879704,0.0000961943,0.0006552641,0.00043310397,0.00013865843],"domain_scores_gemma":[0.992396,0.005556236,0.000488588,0.0009637421,0.00044308527,0.0001523684],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0047783935,0.0012752825,0.0011561678,0.0025042908,0.0011923811,0.001301333,0.002747813,0.0015284088,0.0042803176],"category_scores_gemma":[0.01642442,0.00088544417,0.0012824617,0.0031651799,0.0018325355,0.0019698425,0.0015782205,0.0013993878,0.0013477312],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011496639,0.00022807944,0.008385431,0.00063273765,0.00022030906,0.0002785633,0.0005442636,0.49491796,0.018179491,0.043208025,0.0053067855,0.42694867],"study_design_scores_gemma":[0.00007666143,0.000119379794,0.0016121983,0.000029193656,0.00004980554,0.00024462646,0.00005344027,0.93317574,0.011299806,0.049293857,0.0040162145,0.000029104947],"about_ca_topic_score_codex":0.007057748,"about_ca_topic_score_gemma":0.0067671197,"teacher_disagreement_score":0.007057748,"about_ca_system_score_codex":0.0015729174,"about_ca_system_score_gemma":0.0022484856,"threshold_uncertainty_score":0.02527088},"labels":[],"label_agreement":null},{"id":"W2167155214","doi":"10.1186/1471-2105-10-192","title":"OrthoClusterDB: an online platform for synteny blocks","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Michael Smith Health Research BC; Universities Space Research Association","keywords":"Synteny; Genome; Comparative genomics; Identification (biology); Biology; Block (permutation group theory); Visualization; Computational biology; Genomics; Computer science; Gene; Genetics; Data mining; Mathematics","score_opus":0.03838297489699107,"score_gpt":0.276687611470927,"score_spread":0.23830463657393594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167155214","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007458787,0.0020078626,0.15078804,0.0005534485,0.00046172595,0.00066249154,0.19862802,0.61984164,0.01959804],"genre_scores_gemma":[0.04018293,0.0017770948,0.26290387,0.00077319395,0.00023255889,0.002218522,0.56127816,0.11621953,0.014414106],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980757,0.0002509877,0.00021985164,0.00050951,0.0007187302,0.00022515113],"domain_scores_gemma":[0.9973871,0.0009330122,0.00030584255,0.00054213824,0.0003894488,0.0004425175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029710666,0.004041218,0.0018164781,0.0070418958,0.0013994251,0.0047130985,0.0055001536,0.0015491025,0.07377655],"category_scores_gemma":[0.006511527,0.0023941954,0.0017196686,0.005637419,0.0007727757,0.006102286,0.008291994,0.0030072553,0.048201833],"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":[0.0060897786,0.00036160092,0.004782268,0.0045405724,0.00042781717,0.0011873496,0.0013786046,0.0032537472,0.036992002,0.016968623,0.74849796,0.17551982],"study_design_scores_gemma":[0.0013199332,0.00023824109,0.007083144,0.0007365835,0.0001956213,0.00094265095,0.0004989233,0.032422937,0.041950066,0.03619616,0.87792593,0.00048977346],"about_ca_topic_score_codex":0.0036043068,"about_ca_topic_score_gemma":0.002749103,"teacher_disagreement_score":0.07377655,"about_ca_system_score_codex":0.0014890947,"about_ca_system_score_gemma":0.002485976,"threshold_uncertainty_score":0.2468071},"labels":[],"label_agreement":null},{"id":"W2167432612","doi":"10.1186/1471-2105-16-s11-s2","title":"VisRseq: R-based visual framework for analysis of sequencing data","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":87,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; Simon Fraser University; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Genome British Columbia; Michael Smith Health Research BC","keywords":"Computer science; Workflow; Usability; Interactivity; Bioconductor; Set (abstract data type); Data science; Visualization; Graphical user interface; Software engineering; World Wide Web; Data mining; Human–computer interaction; Programming language; Database","score_opus":0.12628157001908993,"score_gpt":0.352157416540137,"score_spread":0.22587584652104706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167432612","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026531378,0.0005442948,0.61581683,0.000699059,0.0003874379,0.0004204396,0.036165923,0.34002396,0.0032889445],"genre_scores_gemma":[0.041830886,0.0010134786,0.7713115,0.0017884074,0.00025746351,0.0034983775,0.05453036,0.12037731,0.0053921957],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99651706,0.0011978777,0.00036617857,0.00071818975,0.0009584127,0.00024229879],"domain_scores_gemma":[0.99069715,0.006121514,0.00069285807,0.0008799462,0.0011510334,0.00045750727],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009377031,0.0039714603,0.0016245649,0.0042807017,0.0010291581,0.003416365,0.005849761,0.0019501621,0.051340584],"category_scores_gemma":[0.020259611,0.0019432489,0.0036475547,0.0018833517,0.0015520154,0.0029162546,0.004027081,0.004392251,0.022972116],"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":[0.0024207372,0.00018141381,0.0052868496,0.006026051,0.0012166859,0.001964874,0.0022840607,0.02824424,0.039154563,0.045842633,0.7298463,0.13753167],"study_design_scores_gemma":[0.00094583706,0.0002919211,0.0052322033,0.0013984327,0.00030691258,0.0017106263,0.00040875576,0.13683787,0.041475177,0.09706829,0.7135902,0.00073378393],"about_ca_topic_score_codex":0.0050637615,"about_ca_topic_score_gemma":0.0040725507,"teacher_disagreement_score":0.051340584,"about_ca_system_score_codex":0.0011385509,"about_ca_system_score_gemma":0.0036725614,"threshold_uncertainty_score":0.17175138},"labels":[],"label_agreement":null},{"id":"W2167516501","doi":"10.1186/1471-2105-15-147","title":"A fast and robust iterative algorithm for prediction of RNA pseudoknotted secondary structures","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pseudoknot; Algorithm; Computer science; Robustness (evolution); Iterative method; Iterative and incremental development; Nucleic acid secondary structure; Iterative refinement; Data mining; RNA; Biology","score_opus":0.012078838786371534,"score_gpt":0.21726912304457013,"score_spread":0.2051902842581986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167516501","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0058358023,0.00013981063,0.98985475,0.000056760444,0.000026851245,0.00006659984,0.00008902732,0.003444273,0.00048623522],"genre_scores_gemma":[0.042444613,0.0000878888,0.9549181,0.00008688766,0.000025391033,0.00022139984,0.00066763686,0.0004274324,0.0011206678],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998539,0.00030017635,0.000096899996,0.000346673,0.000596738,0.00012059504],"domain_scores_gemma":[0.9972373,0.0012633867,0.00023226492,0.00031844337,0.0008215211,0.0001268922],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018412295,0.0013536705,0.0012907253,0.0013095489,0.0010453375,0.0009733513,0.0027092963,0.0016362384,0.003963678],"category_scores_gemma":[0.0063273893,0.00083512015,0.0013594377,0.0010648628,0.0008046021,0.0012580454,0.0016393494,0.0018317401,0.0023900794],"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":[0.0003722327,0.00017292131,0.0025676773,0.00028873148,0.00018430846,0.00025218565,0.000278448,0.33221474,0.029269548,0.007542049,0.011672535,0.6151845],"study_design_scores_gemma":[0.00004058988,0.000061656116,0.00029556602,0.000016399998,0.000014489312,0.0000950423,0.000021618083,0.986665,0.0058342526,0.0047725462,0.0021607468,0.000022233042],"about_ca_topic_score_codex":0.0056340336,"about_ca_topic_score_gemma":0.007710857,"teacher_disagreement_score":0.0056340336,"about_ca_system_score_codex":0.00088579475,"about_ca_system_score_gemma":0.00303258,"threshold_uncertainty_score":0.013259828},"labels":[],"label_agreement":null},{"id":"W2170551185","doi":"10.1186/1471-2105-12-237","title":"Semi-Automatic segmentation of multiple mouse embryos in MR images","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Zebrafish Biomedical Research Applications","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Toronto Centre for Phenogenomics; Hospital for Sick Children","funders":"Genome Canada; Ontario Genomics; Institut national de recherche en informatique et en automatique (INRIA); British Heart Foundation; Wellcome Trust; Ontario Genomics Institute","keywords":"Initialization; Segmentation; Artificial intelligence; Computer science; Computer vision; Intersection (aeronautics); Image segmentation; Magnetic resonance imaging; Pattern recognition (psychology); Collision; Boundary (topology); Collision detection; Algorithm; Mathematics","score_opus":0.02431074920467926,"score_gpt":0.2803238978378402,"score_spread":0.25601314863316094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170551185","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12795806,0.00042272656,0.8672402,0.00013386563,0.000024728786,0.0001643245,0.00020140833,0.0028594586,0.0009952172],"genre_scores_gemma":[0.20849985,0.00032332368,0.7890798,0.0000621609,0.00001191449,0.00012861124,0.00041014832,0.00027928903,0.0012049263],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99940014,0.00009384161,0.000053882795,0.00013443804,0.00027620356,0.000041573512],"domain_scores_gemma":[0.9990565,0.00036728542,0.0001626453,0.0001860116,0.00018582719,0.00004171782],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007727477,0.0006468586,0.0004784092,0.00097365974,0.00033819713,0.0008174158,0.00092858076,0.0009470297,0.0016295229],"category_scores_gemma":[0.0014781913,0.00045735628,0.0006218422,0.0004137675,0.00041760388,0.00058155373,0.00074271736,0.0005616739,0.00075701124],"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":[0.00019091704,0.000050067658,0.0026871199,0.00019756306,0.00005954369,0.00031742282,0.00020954062,0.028094348,0.85814345,0.0011046471,0.0006101066,0.10833529],"study_design_scores_gemma":[0.000031157266,0.0002500132,0.011696051,0.000060732866,0.00007193962,0.0024113443,0.00012672093,0.32866055,0.64824784,0.0018604217,0.0065038567,0.00007948907],"about_ca_topic_score_codex":0.0011388405,"about_ca_topic_score_gemma":0.0021479004,"teacher_disagreement_score":0.0016295229,"about_ca_system_score_codex":0.0004913121,"about_ca_system_score_gemma":0.00086958986,"threshold_uncertainty_score":0.0054513216},"labels":[],"label_agreement":null},{"id":"W2170998535","doi":"10.1186/1471-2105-13-s9-s8","title":"Generalized adjacency and the conservation of gene clusters in genetic networks defined by synthetic lethals","year":2012,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Genome; Adjacency list; Biology; Schizosaccharomyces pombe; Computational biology; Genetics; Adjacency matrix; Gene; Vertex (graph theory); Saccharomyces cerevisiae; Computer science; Theoretical computer science; Graph; Algorithm","score_opus":0.01116216227566326,"score_gpt":0.21711234933954202,"score_spread":0.20595018706387874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170998535","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9286136,0.0001112272,0.06956968,0.000119250195,0.0000028734323,0.000019349562,0.00013474944,0.00010287855,0.0013263479],"genre_scores_gemma":[0.98932505,0.000042990276,0.010275575,0.000011130361,0.0000047238887,0.000018138833,0.0001413595,0.000009654799,0.00017135932],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99963653,0.00012064057,0.000019520823,0.00010853267,0.00008027448,0.00003444354],"domain_scores_gemma":[0.9951782,0.0030114676,0.0011203968,0.00023026446,0.00024234691,0.0002173424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005097108,0.00014926828,0.0002007299,0.0021017021,0.000513574,0.0007229256,0.00042536302,0.00034331897,0.0010691814],"category_scores_gemma":[0.005696984,0.00014447019,0.00023440542,0.0013473976,0.0012272758,0.0009862506,0.00066898664,0.0002898639,0.000056871675],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00076752243,0.00017526056,0.10823218,0.00046988722,0.00026272607,0.0008716038,0.0019604345,0.39739203,0.055069853,0.36440948,0.0014721589,0.06891696],"study_design_scores_gemma":[0.000056294004,0.00013961123,0.061474517,0.000038583996,0.00010085776,0.00090951705,0.00064838416,0.5377589,0.008813332,0.38772595,0.0022839734,0.000050065293],"about_ca_topic_score_codex":0.0016090508,"about_ca_topic_score_gemma":0.0017626263,"teacher_disagreement_score":0.0021017021,"about_ca_system_score_codex":0.00077693164,"about_ca_system_score_gemma":0.00030043902,"threshold_uncertainty_score":0.0056370497},"labels":[],"label_agreement":null},{"id":"W2171179395","doi":"10.1186/1471-2105-11-252","title":"Antisense DNA parameters derived from next-nearest-neighbor analysis of experimental data","year":2010,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"DNA and Nucleic Acid Chemistry","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":"Dalhousie University","funders":"University of Texas at Dallas; Welch Foundation","keywords":"k-nearest neighbors algorithm; DNA; Computational biology; DNA microarray; Sense (electronics); Nucleotide; Gene; Biology; Sequence (biology); DNA sequencing; Gene expression; Genetics; Molecular biology; Chemistry; Computer science; Artificial intelligence","score_opus":0.029404808140034006,"score_gpt":0.27252597040517273,"score_spread":0.24312116226513872,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171179395","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38112867,0.00035537302,0.61435264,0.00015739832,0.000045643046,0.0002446308,0.0009547056,0.0008176495,0.0019433273],"genre_scores_gemma":[0.909271,0.00015202869,0.08765808,0.000052717834,0.000020489824,0.00036519242,0.0017947258,0.00015810337,0.0005275855],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983997,0.00045256672,0.00017103952,0.0003935271,0.00049225707,0.00009099378],"domain_scores_gemma":[0.9919777,0.0050666844,0.00090591406,0.0009016218,0.00098405,0.00016397017],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035519877,0.0010306553,0.00071859185,0.0013746317,0.00035677332,0.0007273663,0.00087366323,0.0009111654,0.0010310693],"category_scores_gemma":[0.0151200155,0.0003514706,0.0016290024,0.0007389322,0.00056631997,0.001125912,0.000478024,0.0012725063,0.00044319057],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002542986,0.000156594,0.016459225,0.00022524751,0.00022784315,0.000120256605,0.00017839852,0.92202204,0.019448599,0.0030235494,0.00043668225,0.037447263],"study_design_scores_gemma":[0.0000069056964,0.00005198711,0.003892524,0.000010120384,0.000024093986,0.000102426835,0.000028042241,0.98804677,0.004719073,0.0026616838,0.00042478152,0.000031569896],"about_ca_topic_score_codex":0.0025913923,"about_ca_topic_score_gemma":0.0019540659,"teacher_disagreement_score":0.0035519877,"about_ca_system_score_codex":0.0011331706,"about_ca_system_score_gemma":0.00073775754,"threshold_uncertainty_score":0.01878494},"labels":[],"label_agreement":null},{"id":"W2171283513","doi":"10.1186/1471-2105-8-342","title":"A replica exchange Monte Carlo algorithm for protein folding in the HP model","year":2007,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":106,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"Canadian Institutes of Health Research; Mitacs; Michael Smith Health Research BC","keywords":"Protein structure prediction; Replica; Lattice protein; Protein folding; Ab initio; Monte Carlo method; Algorithm; Computer science; Statistical potential; Protein design; Ground state; Protein structure; Statistical physics; Physics; Mathematics","score_opus":0.016653440858015716,"score_gpt":0.2644799402148487,"score_spread":0.247826499356833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171283513","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.050409924,0.00047636434,0.93974084,0.00035567986,0.00006943766,0.00014158232,0.00014683028,0.0010642007,0.0075950692],"genre_scores_gemma":[0.41914868,0.000258278,0.5748203,0.00018226958,0.000054906766,0.00063742825,0.00039623425,0.00029980924,0.004202089],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996923,0.00013875114,0.000012105986,0.000041172465,0.000083811945,0.000031874104],"domain_scores_gemma":[0.9985481,0.0010554837,0.0000664074,0.000104655104,0.0001569147,0.0000684563],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001051659,0.00065041875,0.00090562255,0.0004971839,0.0005189793,0.0005612139,0.0016130075,0.0013542082,0.0037401204],"category_scores_gemma":[0.0030613958,0.00036408575,0.0005831215,0.00064982485,0.00067618594,0.00065191346,0.0008196442,0.0012142712,0.0006490719],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046616264,0.000034618453,0.00028349867,0.00003279942,0.000018889448,0.000045160967,0.000022495144,0.9738941,0.00036811814,0.008138283,0.0006771084,0.016438294],"study_design_scores_gemma":[0.000008173566,0.0000057161387,0.0000114414015,0.0000012953121,0.0000012798672,0.0000041127737,0.0000011357404,0.9981993,0.0000546222,0.0015848422,0.00012718877,9.680488e-7],"about_ca_topic_score_codex":0.0070443633,"about_ca_topic_score_gemma":0.006100123,"teacher_disagreement_score":0.0070443633,"about_ca_system_score_codex":0.00095170777,"about_ca_system_score_gemma":0.0017451531,"threshold_uncertainty_score":0.014006734},"labels":[],"label_agreement":null},{"id":"W2171898201","doi":"10.1186/1471-2105-15-s6-s6","title":"Functional and genetic analysis of the colon cancer network","year":2014,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto","funders":"Queen's University; Queen's University Belfast","keywords":"Gene; DNA microarray; Computational biology; Biology; Gene regulatory network; Interaction network; Genome; Complex disease; Cancer; Genetics; Network analysis; Set (abstract data type); Biological network; Functional analysis; Computer science; Gene expression","score_opus":0.009058436959456604,"score_gpt":0.21324121794806064,"score_spread":0.20418278098860404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171898201","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8492955,0.00088575494,0.1317424,0.0007800305,0.000023563733,0.00007347698,0.010663991,0.0005963845,0.0059388983],"genre_scores_gemma":[0.93952054,0.00037276003,0.050185658,0.0000438792,0.000014894462,0.0000669869,0.00827748,0.000043425895,0.0014743472],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997528,0.00007706548,0.0000066996627,0.00007452587,0.00006417844,0.000024734476],"domain_scores_gemma":[0.99925715,0.000395575,0.000111929505,0.00005830382,0.000134882,0.000042172538],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033045598,0.00031528686,0.00018432387,0.0015421603,0.0003854412,0.00034221009,0.00030457875,0.0002402055,0.0020685045],"category_scores_gemma":[0.001907772,0.00010996933,0.0004125666,0.0014178968,0.0002533754,0.00027473533,0.00027411367,0.00025882586,0.0002080691],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00063207606,0.00016145568,0.1156713,0.0006577056,0.00042651605,0.0014371586,0.0003197158,0.6841135,0.07107041,0.036359645,0.0046970467,0.084453456],"study_design_scores_gemma":[0.00002228896,0.00007766015,0.07648097,0.00003093217,0.0001227513,0.000539273,0.0001520644,0.88318986,0.008457639,0.022986982,0.007919399,0.000020151398],"about_ca_topic_score_codex":0.007975369,"about_ca_topic_score_gemma":0.008182556,"teacher_disagreement_score":0.007975369,"about_ca_system_score_codex":0.0006405883,"about_ca_system_score_gemma":0.0005165314,"threshold_uncertainty_score":0.015857875},"labels":[],"label_agreement":null},{"id":"W2174601642","doi":"10.1186/s12859-015-0826-3","title":"MSAIndelFR: a scheme for multiple protein sequence alignment using information on indel flanking regions","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Indel; INDEL Mutation; Sequence (biology); Genetics; Computational biology; Flanking maneuver; DNA microarray; Multiple sequence alignment; Alignment-free sequence analysis; Biology; Sequence analysis; Sequence alignment; 5' flanking region; Computer science; Gene; Peptide sequence; Single-nucleotide polymorphism; Engineering; Promoter; Genotype","score_opus":0.10191809340865522,"score_gpt":0.291020284811656,"score_spread":0.18910219140300077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2174601642","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014786048,0.00045990475,0.9623329,0.000174958,0.0001420228,0.00018200926,0.00077481027,0.020132309,0.0010149913],"genre_scores_gemma":[0.049936224,0.00016042533,0.94492143,0.00011823282,0.000048299426,0.00034487495,0.0019377574,0.0011594804,0.0013732058],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99779874,0.0005191364,0.0002507743,0.0005917667,0.00069606473,0.0001434858],"domain_scores_gemma":[0.9970475,0.00088194816,0.0006134276,0.0007602422,0.0005343356,0.00016248178],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034700755,0.0015806201,0.001454774,0.0036290386,0.0014770426,0.0015835726,0.0038497343,0.0022009904,0.0063737994],"category_scores_gemma":[0.009269191,0.0008768945,0.0012714524,0.0024014818,0.00090450404,0.0026401707,0.0024346425,0.0028395797,0.005243988],"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":[0.0024911007,0.000360584,0.007370228,0.00075182127,0.00026487804,0.000562941,0.00056369195,0.04525553,0.10154212,0.021337274,0.03495197,0.7845478],"study_design_scores_gemma":[0.0003945096,0.0006151528,0.0026722983,0.00013337175,0.000087529086,0.0012433493,0.00014136794,0.82784784,0.088441126,0.02176384,0.056411058,0.00024854255],"about_ca_topic_score_codex":0.0010311892,"about_ca_topic_score_gemma":0.0019442857,"teacher_disagreement_score":0.0063737994,"about_ca_system_score_codex":0.00088638027,"about_ca_system_score_gemma":0.001841949,"threshold_uncertainty_score":0.021322489},"labels":[],"label_agreement":null},{"id":"W2180283910","doi":"10.1186/1471-2105-9-s6-s13","title":"Quality assessment of peptide tandem mass spectra","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mass spectrum; Tandem; Computer science; Tandem mass spectrometry; Quality (philosophy); Spectral line; Classifier (UML); Pattern recognition (psychology); Linear discriminant analysis; Artificial intelligence; Data mining; Mass spectrometry; Biological system; Chemistry; Biology; Chromatography; Materials science; Physics","score_opus":0.04926022827379116,"score_gpt":0.3350040443686998,"score_spread":0.2857438160949086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2180283910","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4591834,0.005684584,0.52854383,0.0004327679,0.00021086697,0.0002310855,0.0013620093,0.002074091,0.0022774523],"genre_scores_gemma":[0.7972804,0.0011994297,0.19824684,0.00014724738,0.00015544757,0.000101572645,0.0019154297,0.00017453272,0.0007790537],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9963632,0.00041309994,0.0004000627,0.00059011363,0.0020699643,0.00016347546],"domain_scores_gemma":[0.98442036,0.003368226,0.004054809,0.0008321058,0.006997838,0.00032667533],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00564713,0.00068484584,0.00078978617,0.0038795609,0.0005100505,0.0014493004,0.00097363646,0.000936484,0.0009589046],"category_scores_gemma":[0.010561596,0.00019362535,0.00071329146,0.0021747428,0.00080006226,0.0013287087,0.00077609584,0.0007707686,0.00039910447],"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":[0.0019500426,0.00029875422,0.1657516,0.0016656446,0.0006382815,0.001075955,0.00052803685,0.021786815,0.2712535,0.0017102293,0.0046020346,0.52873915],"study_design_scores_gemma":[0.000103908955,0.00096877874,0.22143734,0.00029505,0.0005500966,0.0047963974,0.00067584397,0.42256534,0.33120957,0.005289678,0.011775723,0.0003323752],"about_ca_topic_score_codex":0.0012476607,"about_ca_topic_score_gemma":0.0011507148,"teacher_disagreement_score":0.00564713,"about_ca_system_score_codex":0.00067429716,"about_ca_system_score_gemma":0.00047555324,"threshold_uncertainty_score":0.029865205},"labels":[],"label_agreement":null},{"id":"W2209020362","doi":"10.1186/s12859-015-0840-5","title":"Pathosphere.org: pathogen detection and characterization through a web-based, open source informatics platform","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"SARS-CoV-2 detection and testing","field":"Medicine","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Infection and Immunity","funders":"Edgewood Chemical Biological Center; Defense Threat Reduction Agency","keywords":"Metagenomics; Computational biology; Computer science; Workflow; Biodefense; Traceability; Upload; Biology; World Wide Web; Database; Genetics; Software engineering; Microbiology","score_opus":0.07801965046886242,"score_gpt":0.2946562580478169,"score_spread":0.2166366075789545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2209020362","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016117644,0.0007712303,0.24735756,0.0012451377,0.00039660026,0.001457167,0.07438352,0.64386714,0.014404038],"genre_scores_gemma":[0.084840335,0.0013471602,0.4974702,0.0020389922,0.00040416676,0.0038722993,0.33770886,0.06019313,0.0121249],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99806076,0.0002064323,0.00013202887,0.0005741383,0.0007891052,0.0002375559],"domain_scores_gemma":[0.9968784,0.0008538994,0.00043222454,0.0006681776,0.00060141354,0.0005658687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032156985,0.002818927,0.0010028229,0.0046682125,0.0011746152,0.0028731932,0.0031843584,0.0014067474,0.016750427],"category_scores_gemma":[0.006083447,0.0010574557,0.0014287042,0.0021333606,0.0009895171,0.005145727,0.005967568,0.002672021,0.02134557],"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":[0.0034711903,0.0009058946,0.013752537,0.0022002694,0.00043962413,0.0013918681,0.0011020952,0.004891736,0.099856876,0.0129026165,0.5709809,0.28810444],"study_design_scores_gemma":[0.0013202783,0.00083070813,0.027561247,0.00074775424,0.00030917165,0.0026390774,0.00054604287,0.1168904,0.09326575,0.041182198,0.7139325,0.00077487424],"about_ca_topic_score_codex":0.0022821527,"about_ca_topic_score_gemma":0.0020492363,"teacher_disagreement_score":0.016750427,"about_ca_system_score_codex":0.0008665506,"about_ca_system_score_gemma":0.003437279,"threshold_uncertainty_score":0.056035757},"labels":[],"label_agreement":null},{"id":"W222181838","doi":"10.1186/s12859-015-0453-z","title":"MeSH ORA framework: R/Bioconductor packages to support MeSH over-representation analysis","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Genetics; RIKEN; Research Organization of Information and Systems","keywords":"Computer science","score_opus":0.0652034063736068,"score_gpt":0.3488638436000229,"score_spread":0.2836604372264161,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W222181838","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022277262,0.0017683101,0.40258223,0.001387138,0.0014313234,0.0007422217,0.11695118,0.4640723,0.008837546],"genre_scores_gemma":[0.027951762,0.0018657345,0.6673913,0.0019247261,0.00050148007,0.00887402,0.122746184,0.16022046,0.008524341],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99539906,0.0013010069,0.00063421857,0.0013324387,0.0010038887,0.00032942012],"domain_scores_gemma":[0.9851247,0.008011955,0.001561387,0.002477126,0.002210724,0.0006139895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009416809,0.0046961787,0.003813253,0.009706597,0.0016607391,0.004338349,0.008475476,0.002344449,0.08993926],"category_scores_gemma":[0.037796836,0.002625742,0.0047617736,0.008365436,0.0012843736,0.0038591085,0.0061073694,0.003820694,0.060265336],"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":[0.0013170523,0.00012117083,0.0039251633,0.009739837,0.0026117568,0.00059249636,0.000886708,0.0051661357,0.00678894,0.033208273,0.84820384,0.08743866],"study_design_scores_gemma":[0.0007735131,0.00020689101,0.0077867997,0.0017929489,0.0015970925,0.0009271457,0.00028128512,0.05520011,0.010978715,0.09751735,0.8225274,0.00041073113],"about_ca_topic_score_codex":0.0053146095,"about_ca_topic_score_gemma":0.0054663494,"teacher_disagreement_score":0.08993926,"about_ca_system_score_codex":0.001440737,"about_ca_system_score_gemma":0.0051177144,"threshold_uncertainty_score":0.3008768},"labels":[],"label_agreement":null},{"id":"W2235905640","doi":"10.1186/s12859-015-0869-5","title":"Aligning the unalignable: bacteriophage whole genome alignments","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"European Research Council; Natural Sciences and Engineering Research Council of Canada; Horizon 2020 Framework Programme; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Agence Nationale de la Recherche","keywords":"Genome; Computational biology; Similarity (geometry); Bacteriophage; Bacterial genome size; Function (biology); Biology; Computer science; Genetics; Artificial intelligence; Image (mathematics); Gene","score_opus":0.013088884900744172,"score_gpt":0.21883196323003912,"score_spread":0.20574307832929495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2235905640","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32539,0.0026224174,0.6371008,0.0004167446,0.00023122599,0.00019906825,0.0069710533,0.02075182,0.0063168774],"genre_scores_gemma":[0.29427806,0.0010034143,0.68500376,0.00013737039,0.00005984111,0.00014279275,0.013418521,0.00244949,0.003506847],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993482,0.00010407403,0.000059890674,0.0002661692,0.00018426719,0.000037354268],"domain_scores_gemma":[0.99922156,0.00025196958,0.00012150582,0.00018847316,0.00015992337,0.00005651521],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057585957,0.0008631545,0.0006024549,0.0008096945,0.0005693264,0.0010254014,0.0007782922,0.00060116575,0.0052837846],"category_scores_gemma":[0.0026422194,0.0003944737,0.00059987453,0.0015542079,0.0003659054,0.0010050485,0.0006883119,0.00078322005,0.0019218965],"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":[0.0020399624,0.00024997443,0.0104057975,0.0020431674,0.00024219585,0.0010130509,0.00045999617,0.03203379,0.62422085,0.014488868,0.01506142,0.2977409],"study_design_scores_gemma":[0.00016967431,0.0007399914,0.022945294,0.00022488378,0.000225521,0.0037711032,0.00030585652,0.19010095,0.61906135,0.03488655,0.12740292,0.00016597284],"about_ca_topic_score_codex":0.00059786276,"about_ca_topic_score_gemma":0.0008423694,"teacher_disagreement_score":0.0052837846,"about_ca_system_score_codex":0.00042071816,"about_ca_system_score_gemma":0.00060351833,"threshold_uncertainty_score":0.017675996},"labels":[],"label_agreement":null},{"id":"W2290848280","doi":"10.1186/s12859-016-0970-4","title":"MetICA: independent component analysis for high-resolution mass-spectrometry based non-targeted metabolomics","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Lallemand","keywords":"Independent component analysis; Overfitting; Principal component analysis; Metabolomics; Computer science; Component (thermodynamics); Data mining; Artificial intelligence; Pattern recognition (psychology); Bioinformatics; Biology; Artificial neural network","score_opus":0.01337171532866286,"score_gpt":0.23613748659713293,"score_spread":0.22276577126847008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2290848280","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015306073,0.0005280905,0.99387854,0.00014033826,0.00005915467,0.00007588624,0.00017229124,0.0029891543,0.0006258984],"genre_scores_gemma":[0.09282797,0.0012357942,0.8999813,0.00018720297,0.00016144308,0.0009102509,0.0016712053,0.000799433,0.002225429],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989102,0.00041322882,0.00008556271,0.00020527365,0.00032779056,0.00005790882],"domain_scores_gemma":[0.9980259,0.0012355641,0.00017587857,0.00014867348,0.00036327058,0.00005085656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023824433,0.002626485,0.0012923079,0.0020462691,0.0007426062,0.0017563995,0.0016148168,0.0017613992,0.005392352],"category_scores_gemma":[0.0064866557,0.0006723797,0.0024595344,0.0016836077,0.0007230751,0.00091409095,0.0011080507,0.0031694751,0.0030397985],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032448772,0.00018350243,0.0014036791,0.0010389747,0.00058634655,0.00048210743,0.0002393549,0.51804286,0.016773334,0.01907609,0.015351077,0.42649823],"study_design_scores_gemma":[0.000019747613,0.000048664697,0.00048807758,0.00004654294,0.000033795186,0.00008619055,0.000015367888,0.9833598,0.0025367045,0.007628002,0.0057032458,0.00003375657],"about_ca_topic_score_codex":0.0044805547,"about_ca_topic_score_gemma":0.003984192,"teacher_disagreement_score":0.005392352,"about_ca_system_score_codex":0.0006772791,"about_ca_system_score_gemma":0.0018191896,"threshold_uncertainty_score":0.018039167},"labels":[],"label_agreement":null},{"id":"W2295126179","doi":"10.1186/s12859-016-0943-7","title":"Improving cell mixture deconvolution by identifying optimal DNA methylation libraries (IDOL)","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Epigenetics and DNA Methylation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":230,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Child and Family Research Institute; University of British Columbia","funders":"National Center for Advancing Translational Sciences; National Institute of Dental and Craniofacial Research; National Institutes of Health; National Cancer Institute; University of California, San Francisco; National Institute of General Medical Sciences; Kansas IDeA Network of Biomedical Research Excellence; Child and Family Research Institute","keywords":"DNA methylation; Deconvolution; Methylation; Flow cytometry; Computational biology; Biology; DNA; Computer science; Molecular biology; Algorithm; Genetics; Gene; Gene expression","score_opus":0.012194397400628061,"score_gpt":0.23053550395858227,"score_spread":0.21834110655795422,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2295126179","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09090001,0.0007858922,0.9041508,0.00018521013,0.000034475335,0.0001023572,0.00030234133,0.002787729,0.0007511867],"genre_scores_gemma":[0.20082399,0.00041072018,0.7956171,0.00026033368,0.000027240992,0.00022400428,0.0010299687,0.00035381987,0.0012527428],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99909425,0.00021351031,0.000049983744,0.0003226795,0.0002355154,0.00008412798],"domain_scores_gemma":[0.9982337,0.0009802553,0.00021709516,0.0001753049,0.00031184757,0.000081778904],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035816687,0.0015246323,0.0011388997,0.0015987214,0.0005176332,0.0017028895,0.0012317847,0.0010491677,0.0011962719],"category_scores_gemma":[0.0063475533,0.0006144114,0.001217365,0.0010318962,0.00067786546,0.0010942437,0.0018236908,0.0014838899,0.0011674373],"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":[0.0013003872,0.0005188857,0.027638538,0.0005579241,0.0004963643,0.00014995689,0.0003971087,0.18595788,0.27564302,0.0050262427,0.0025500113,0.49976367],"study_design_scores_gemma":[0.00006860377,0.00024410404,0.003876736,0.000026454176,0.00012420287,0.00013010502,0.00006364689,0.801,0.18718486,0.0039982772,0.0032091932,0.000073772426],"about_ca_topic_score_codex":0.0019797536,"about_ca_topic_score_gemma":0.003330508,"teacher_disagreement_score":0.0035816687,"about_ca_system_score_codex":0.0010165859,"about_ca_system_score_gemma":0.0014425926,"threshold_uncertainty_score":0.018941939},"labels":[],"label_agreement":null},{"id":"W2319368514","doi":"10.1186/s12859-016-0997-6","title":"Unaccounted uncertainty from qPCR efficiency estimates entails uncontrolled false positive rates","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Molecular Biology Techniques and Applications","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Danish Agency for Science and Higher Education; Forsknings- og Innovationsstyrelsen; Stem Cell Network","keywords":"Statistics; DNA microarray; Computational biology; Biology; Computer science; Econometrics; Genetics; Mathematics; Gene","score_opus":0.00815022176829765,"score_gpt":0.2639605235602022,"score_spread":0.25581030179190456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2319368514","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008645574,0.0012581964,0.9856514,0.00045106307,0.00033194743,0.00013200167,0.00031418228,0.001371847,0.0018437549],"genre_scores_gemma":[0.39196247,0.001755065,0.59632367,0.0016785034,0.00035265947,0.0013906115,0.0011761102,0.0020009133,0.0033599983],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9498824,0.01774045,0.0033458679,0.011223816,0.016762925,0.0010445811],"domain_scores_gemma":[0.8434366,0.11575634,0.01137983,0.018177612,0.010770816,0.00047876933],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.052567393,0.0024239374,0.0027093932,0.0019236213,0.0014970945,0.0047100997,0.003863048,0.0030044785,0.0027911644],"category_scores_gemma":[0.13309507,0.0016637406,0.0029340212,0.0021432992,0.0053134374,0.0030095205,0.0037355924,0.0049403757,0.001842727],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011355646,0.00035695103,0.07033739,0.0067467373,0.0017856515,0.0013874446,0.003271591,0.10002952,0.28530094,0.1197605,0.01187791,0.39800975],"study_design_scores_gemma":[0.00011225621,0.00075916486,0.028475974,0.0015234128,0.0009237657,0.0026656284,0.00041386663,0.23870951,0.47710398,0.18061388,0.06798982,0.0007087054],"about_ca_topic_score_codex":0.0022302151,"about_ca_topic_score_gemma":0.0026540956,"teacher_disagreement_score":0.94743264,"about_ca_system_score_codex":0.0024876276,"about_ca_system_score_gemma":0.0025506904,"threshold_uncertainty_score":0.27800626},"labels":[],"label_agreement":null},{"id":"W2333744840","doi":"10.1186/s12859-016-1001-1","title":"PAT: predictor for structured units and its application for the optimization of target molecules for the generation of synthetic antibodies","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Monoclonal and Polyclonal Antibodies Research","field":"Medicine","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 Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Ministry of Education, Science and Technology; National Research Foundation of Korea; Canadian Institutes of Health Research; National Research Foundation","keywords":"Identification (biology); Computer science; Computational biology; Domain (mathematical analysis); Sequence (biology); Folding (DSP implementation); Biology; Mathematics; Genetics; Engineering","score_opus":0.051578017763264324,"score_gpt":0.29771693629819546,"score_spread":0.24613891853493114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2333744840","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15835355,0.0008689941,0.7649688,0.0001793942,0.000059197664,0.00026060612,0.0035904928,0.06912863,0.0025903755],"genre_scores_gemma":[0.37023678,0.0004920072,0.61452246,0.00012988177,0.000032378543,0.00060011697,0.0080367,0.0035848022,0.0023647987],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99959606,0.00007318523,0.00004297511,0.000111937254,0.00013083447,0.00004493079],"domain_scores_gemma":[0.99916124,0.00041302273,0.00017353221,0.00007442802,0.00014155617,0.000036287645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010306445,0.0012788483,0.0005946774,0.0010736489,0.0002899598,0.0006638906,0.0007872146,0.00063512765,0.0063796337],"category_scores_gemma":[0.0021646454,0.00041248676,0.00091089617,0.00080867135,0.00021424452,0.00077036663,0.000614092,0.0008363588,0.0017975364],"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":[0.0033263266,0.00058715564,0.033956636,0.0024320197,0.00038785455,0.001173705,0.00022378581,0.15839952,0.3133319,0.005997343,0.031497046,0.4486867],"study_design_scores_gemma":[0.000134869,0.000422291,0.0039033378,0.000040607243,0.00009993578,0.0004964523,0.000028684419,0.8251284,0.1574768,0.0020647957,0.01016619,0.000037703627],"about_ca_topic_score_codex":0.00046963053,"about_ca_topic_score_gemma":0.00045311678,"teacher_disagreement_score":0.0063796337,"about_ca_system_score_codex":0.00030384408,"about_ca_system_score_gemma":0.0006208701,"threshold_uncertainty_score":0.02134198},"labels":[],"label_agreement":null},{"id":"W2338215681","doi":"10.1186/s12859-016-1015-8","title":"BAGEL: a computational framework for identifying essential genes from pooled library screens","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"CRISPR and Genetic Engineering","field":"Biochemistry, Genetics and Molecular Biology","cited_by":325,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Cancer Institute; Canadian Institutes of Health Research","keywords":"Computational biology; DNA microarray; Gene; Computer science; Biology; Genetics; Bioinformatics; Gene expression","score_opus":0.01657515414873308,"score_gpt":0.3018650987314888,"score_spread":0.28528994458275575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2338215681","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032341946,0.00018572353,0.981128,0.0001439393,0.00003224235,0.00007001687,0.0012481303,0.013599921,0.00035793518],"genre_scores_gemma":[0.053267036,0.00031023604,0.937247,0.00042779473,0.00006809212,0.0007774678,0.0046270974,0.00225399,0.0010212563],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99882036,0.00053275866,0.00006330882,0.00022441971,0.000290223,0.00006887204],"domain_scores_gemma":[0.9950524,0.003945145,0.00023101285,0.0002801901,0.00032914086,0.00016201429],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041412986,0.0019461735,0.0018653603,0.0025259855,0.00071461516,0.0020347503,0.0031553484,0.0017236251,0.0073494613],"category_scores_gemma":[0.008983421,0.0009737205,0.0026919125,0.0011824651,0.0008631106,0.0015369026,0.0020995012,0.0028915175,0.0023533897],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010894781,0.00039338443,0.0057415464,0.0014364335,0.0013059059,0.00043188248,0.0001802725,0.7176157,0.009972141,0.03642218,0.022071708,0.20333932],"study_design_scores_gemma":[0.000056031087,0.000038131508,0.00021186647,0.000024240935,0.00004463606,0.00004165994,0.000011413322,0.9728118,0.0010223783,0.023157626,0.0025600211,0.000020051606],"about_ca_topic_score_codex":0.0036234893,"about_ca_topic_score_gemma":0.009332381,"teacher_disagreement_score":0.0073494613,"about_ca_system_score_codex":0.00095888233,"about_ca_system_score_gemma":0.0021434186,"threshold_uncertainty_score":0.02458638},"labels":[],"label_agreement":null},{"id":"W2342801191","doi":"10.1186/s12859-016-1057-y","title":"ImiRP: a computational approach to microRNA target site mutation","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"MicroRNA in disease regulation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Canadian Institutes of Health Research; Alexander and Margaret Stewart Trust","keywords":"MiRBase; Biology; microRNA; Computational biology; Genetics; Mutation; Protein-fragment complementation assay; Mutant; Complementation; Gene","score_opus":0.011113234247392027,"score_gpt":0.23200430746932216,"score_spread":0.22089107322193013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2342801191","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029026879,0.00066900905,0.9007668,0.0005546496,0.00031056406,0.00036030082,0.0035687846,0.058934547,0.005808492],"genre_scores_gemma":[0.12846307,0.00034424025,0.8563044,0.00049530854,0.00008591901,0.0011242803,0.005809678,0.005033533,0.0023395997],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992976,0.00026294056,0.000046549176,0.00017773811,0.00014953437,0.00006564799],"domain_scores_gemma":[0.99768543,0.001804024,0.000107126885,0.0001403191,0.00016310833,0.00010000362],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017568592,0.0021327173,0.0016458342,0.0012542909,0.00075986783,0.0014443836,0.0039186594,0.0018967295,0.009097829],"category_scores_gemma":[0.0048170895,0.0010603176,0.0022819582,0.0008691649,0.0006451974,0.001060941,0.0016949155,0.0021902712,0.0018369289],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009609476,0.00061636564,0.0060734157,0.0012839459,0.00089752034,0.00091668725,0.00026406054,0.8062523,0.008983853,0.020339454,0.031940814,0.12147064],"study_design_scores_gemma":[0.00009433331,0.000048010752,0.00015899938,0.000018399498,0.00004253874,0.000049263042,0.000021280479,0.9894555,0.0013850278,0.004743874,0.0039666016,0.00001618736],"about_ca_topic_score_codex":0.0043998435,"about_ca_topic_score_gemma":0.008827782,"teacher_disagreement_score":0.009097829,"about_ca_system_score_codex":0.00088020146,"about_ca_system_score_gemma":0.0018383791,"threshold_uncertainty_score":0.030435324},"labels":[],"label_agreement":null},{"id":"W2395761288","doi":"10.1186/s12859-016-1074-x","title":"RNA motif search with data-driven element ordering","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Institute of General Medical Sciences; Division of Molecular and Cellular Biosciences; Vedecká Grantová Agentúra MŠVVaŠ SR a SAV; Eurostars; Agentúra na Podporu Výskumu a Vývoja; Pew Charitable Trusts; National Institutes of Health; National Science Foundation","keywords":"Speedup; RNA; Motif (music); Computer science; Computational biology; Backtracking; Search algorithm; Structural motif; Nucleic acid structure; Algorithm; Biology; Genetics; Gene; Physics","score_opus":0.03514694564220968,"score_gpt":0.2618498593336783,"score_spread":0.22670291369146864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2395761288","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.101780206,0.00051109726,0.8903445,0.0002216812,0.000040155846,0.00011288911,0.00071697007,0.00421522,0.0020572974],"genre_scores_gemma":[0.2885255,0.00012563913,0.70730215,0.00010991745,0.000030205081,0.00024255287,0.0018547854,0.00044098246,0.0013682494],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993766,0.00018116503,0.000041202424,0.0001676038,0.00016452077,0.00006889955],"domain_scores_gemma":[0.99873775,0.0008012021,0.00008926835,0.00015059144,0.0001539703,0.00006724725],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00065357226,0.00061823655,0.0008038545,0.0006852875,0.0002939294,0.00067341287,0.0015007742,0.0009679663,0.002994957],"category_scores_gemma":[0.0024810326,0.00034615243,0.00059086806,0.0010083305,0.0004346133,0.0008919958,0.0011556563,0.000862335,0.0010270067],"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":[0.0018535786,0.00048491565,0.005470115,0.0010143328,0.00018635958,0.00047980013,0.00019875634,0.56087804,0.077060305,0.0203364,0.007580295,0.32445708],"study_design_scores_gemma":[0.00012491489,0.00010447885,0.00020240934,0.000010336366,0.000012806518,0.00010507269,0.000015003167,0.9768286,0.011814497,0.008819693,0.0019506594,0.000011639324],"about_ca_topic_score_codex":0.000955925,"about_ca_topic_score_gemma":0.0016096828,"teacher_disagreement_score":0.002994957,"about_ca_system_score_codex":0.00043086463,"about_ca_system_score_gemma":0.0008691409,"threshold_uncertainty_score":0.010019124},"labels":[],"label_agreement":null},{"id":"W2467978015","doi":"10.1186/s12859-016-1125-3","title":"Reusable, extensible, and modifiable R scripts and Kepler workflows for comprehensive single set ChIP-seq analysis","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Stellar, planetary, and galactic studies","field":"Physics and Astronomy","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"University of Calgary","keywords":"Computer science; Pipeline (software); Workflow; Pipeline transport; Turnkey; Software; Scripting language; XML; Set (abstract data type); Modular design; Software engineering; Database; Operating system; Programming language; Engineering","score_opus":0.05041953886822691,"score_gpt":0.25351163983451525,"score_spread":0.20309210096628832,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2467978015","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005971207,0.00033892415,0.59830815,0.00035455663,0.00025089708,0.0006900664,0.021467801,0.36827025,0.004348176],"genre_scores_gemma":[0.034220554,0.00068933755,0.811627,0.00071526057,0.000120205696,0.0037287364,0.054054692,0.089238055,0.0056061433],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99481225,0.0012009393,0.0007986739,0.0014532225,0.0012972538,0.00043761276],"domain_scores_gemma":[0.9890126,0.0035677645,0.0011932242,0.0034661756,0.0020488573,0.00071138574],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009478104,0.0036633674,0.00151272,0.0036106159,0.0014507296,0.0030274494,0.0047532683,0.0011755476,0.021619422],"category_scores_gemma":[0.024873745,0.0022716627,0.0027850894,0.002679883,0.001336539,0.0020811933,0.004290002,0.003712459,0.03884106],"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":[0.004516143,0.0004272751,0.0140675185,0.003956921,0.0012007765,0.0021386158,0.0017037991,0.037715673,0.13511817,0.028559614,0.43178457,0.33881092],"study_design_scores_gemma":[0.0007824208,0.0004941438,0.012177333,0.0007544767,0.0005725708,0.0025139416,0.00030096452,0.09474238,0.30738384,0.04407861,0.5352489,0.00095034036],"about_ca_topic_score_codex":0.0026376345,"about_ca_topic_score_gemma":0.0024099709,"teacher_disagreement_score":0.021619422,"about_ca_system_score_codex":0.0012206592,"about_ca_system_score_gemma":0.0048881997,"threshold_uncertainty_score":0.07232416},"labels":[],"label_agreement":null},{"id":"W2474345237","doi":"10.1186/s12859-016-1142-2","title":"A De-Novo Genome Analysis Pipeline (DeNoGAP) for large-scale comparative prokaryotic genomics studies","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computational biology; Genomics; Genome; DNA microarray; Comparative genomics; Biology; Pipeline (software); Genetics; Computer science; Gene; Gene expression","score_opus":0.03974294721149125,"score_gpt":0.30524999874263525,"score_spread":0.265507051531144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2474345237","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008000239,0.00045088012,0.885009,0.00026562484,0.0001631224,0.0006462287,0.01381304,0.08948058,0.0021712382],"genre_scores_gemma":[0.01843232,0.0003173448,0.9365509,0.00016432996,0.00002915072,0.0013043693,0.033678375,0.008457336,0.0010659113],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99843496,0.0002674693,0.00014355812,0.0005339311,0.00047099276,0.00014908277],"domain_scores_gemma":[0.9976649,0.00081041333,0.00027617769,0.0004031724,0.0005764695,0.00026888362],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004457687,0.0022159417,0.0014691413,0.0024276518,0.0016231254,0.0020961252,0.0031404314,0.0010197574,0.012105494],"category_scores_gemma":[0.0053825304,0.0015925574,0.0022428841,0.0016640606,0.0006750392,0.0016494275,0.0032198476,0.0035850895,0.008912188],"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":[0.0024714312,0.00068680104,0.008735558,0.0051859226,0.0010337302,0.0013657614,0.0016407558,0.024519082,0.33187336,0.024561808,0.23745136,0.36047444],"study_design_scores_gemma":[0.0008466348,0.00068393664,0.016499538,0.0007070314,0.00041096786,0.0018113058,0.00036418397,0.2779514,0.21204731,0.035078403,0.45302457,0.00057472417],"about_ca_topic_score_codex":0.0018825307,"about_ca_topic_score_gemma":0.002716836,"teacher_disagreement_score":0.012105494,"about_ca_system_score_codex":0.0012394766,"about_ca_system_score_gemma":0.0032410105,"threshold_uncertainty_score":0.040496886},"labels":[],"label_agreement":null},{"id":"W2482431271","doi":"10.1186/s12859-016-1098-2","title":"Sensorimotor control: computing the immediate future from the delayed present","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Vestibular and auditory disorders","field":"Neuroscience","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 Alberta","funders":"","keywords":"Computer science; Model predictive control; Sensory system; Control (management); Artificial intelligence; Control theory (sociology); Neuroscience; Psychology","score_opus":0.017707616601213155,"score_gpt":0.23337582189107875,"score_spread":0.2156682052898656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2482431271","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03818454,0.00065209647,0.9560946,0.00039818883,0.0000770067,0.00002816499,0.00005416734,0.00027645886,0.004234769],"genre_scores_gemma":[0.93374944,0.00053368736,0.06377043,0.00006931469,0.000057642163,0.0000713674,0.000052287152,0.00003345452,0.001662352],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998921,0.000020095473,0.000005135781,0.000036072568,0.000033501063,0.000013133489],"domain_scores_gemma":[0.99969983,0.000148576,0.00005702128,0.00002524849,0.000050383627,0.000018968822],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032022226,0.0004108088,0.000266076,0.00025405246,0.00030105317,0.00059166347,0.0007537313,0.0004534318,0.0022038606],"category_scores_gemma":[0.0012437298,0.00016783364,0.0003930108,0.00024924392,0.0006852859,0.0008652321,0.0005470351,0.0006644024,0.00016452395],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008552621,0.000037865113,0.0011815224,0.00010125772,0.000036565973,0.00013646432,0.000096191165,0.8724885,0.008307929,0.047304977,0.0008805268,0.06934272],"study_design_scores_gemma":[0.0000053416684,0.000019357658,0.00022705318,0.000006504962,0.000007136819,0.000014814879,0.000005661249,0.9874464,0.00071895745,0.011085896,0.00045767755,0.000005132307],"about_ca_topic_score_codex":0.006112309,"about_ca_topic_score_gemma":0.002944429,"teacher_disagreement_score":0.006112309,"about_ca_system_score_codex":0.0005263905,"about_ca_system_score_gemma":0.00068113056,"threshold_uncertainty_score":0.012153447},"labels":[],"label_agreement":null},{"id":"W2501117253","doi":"10.1186/s12859-016-1097-3","title":"Evaluating the necessity of PCR duplicate removal from next-generation sequencing data and a comparison of approaches","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":178,"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; IXICO; H. Lundbeck A/S; Eisai; Northern California Institute for Research and Education; University of California, San Diego; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; Servier; Brigham Young University; University of Southern California; Novartis Pharmaceuticals Corporation; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Transversion; Computational biology; Reference genome; Biology; DNA sequencing; Concordance; Genetics; Exome; Population; Data mining; Computer science; Bioinformatics; Exome sequencing; Gene; Mutation; Medicine","score_opus":0.3861978566480501,"score_gpt":0.34933855266425884,"score_spread":0.03685930398379128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2501117253","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74176836,0.020065466,0.2204788,0.0013235958,0.0011009504,0.0028185188,0.0031743706,0.0016608466,0.007609065],"genre_scores_gemma":[0.6673804,0.0025808294,0.32130924,0.0009171935,0.00017042673,0.0016445728,0.004309527,0.0006499085,0.0010378994],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.937059,0.025599279,0.0074502225,0.010504629,0.017994525,0.0013923906],"domain_scores_gemma":[0.73779696,0.21271311,0.012588214,0.009506389,0.025853299,0.0015420245],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.08482776,0.0012178863,0.0011959865,0.0036747847,0.0021573931,0.003355269,0.002108899,0.0019640976,0.0018038685],"category_scores_gemma":[0.16393736,0.0006294568,0.003534363,0.0027266627,0.0017065493,0.0027004762,0.0023569188,0.0019483985,0.00063241314],"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":[0.020052612,0.0019869427,0.34199044,0.015630081,0.012227007,0.0011549664,0.0057536075,0.036510978,0.07890572,0.0071247327,0.008911291,0.46975172],"study_design_scores_gemma":[0.0014136529,0.015989177,0.40491742,0.0036306754,0.012682672,0.0062473007,0.0073330854,0.18823272,0.27581725,0.02436572,0.058109842,0.0012604306],"about_ca_topic_score_codex":0.003319571,"about_ca_topic_score_gemma":0.005211914,"teacher_disagreement_score":0.9151722,"about_ca_system_score_codex":0.003080441,"about_ca_system_score_gemma":0.0029090608,"threshold_uncertainty_score":0.4486174},"labels":[],"label_agreement":null},{"id":"W2507335589","doi":"10.1186/s12859-016-1157-8","title":"Additive methods for genomic signatures","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Fractal and DNA sequence analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Saint Mary's University; University of Waterloo; Western University","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo","keywords":"Computational biology; DNA microarray; Genomics; Biology; Computer science; Genetics; Data science; Genome; Gene; Gene expression","score_opus":0.016123286081176188,"score_gpt":0.31055983991457325,"score_spread":0.29443655383339706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2507335589","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022471175,0.0005168549,0.99368274,0.00034433938,0.00008790535,0.000054627293,0.0003907581,0.00084159244,0.0018340122],"genre_scores_gemma":[0.17725056,0.001081231,0.80587953,0.00088745914,0.0006428034,0.0008652848,0.003578661,0.0012687643,0.008545745],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99572927,0.0017807498,0.00027014065,0.0010614721,0.0009289269,0.00022934061],"domain_scores_gemma":[0.9882159,0.008708632,0.0006406937,0.0012948633,0.00088311144,0.00025679957],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004784799,0.0014692274,0.0011812977,0.003844035,0.0006659974,0.0028054044,0.002619255,0.0020676965,0.010287486],"category_scores_gemma":[0.021702278,0.00055887294,0.0022485403,0.0027207679,0.0021660794,0.0029718888,0.0044641546,0.0035902269,0.0028320947],"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":[0.00016541168,0.0001023012,0.0025021478,0.0005639118,0.00021944898,0.000171378,0.00026824445,0.19055645,0.0019495278,0.4304675,0.01044313,0.3625905],"study_design_scores_gemma":[0.000022996728,0.000047691832,0.00032721166,0.00007442567,0.00002872111,0.00009051545,0.000047338388,0.59317017,0.00077920745,0.39401042,0.01138027,0.00002104841],"about_ca_topic_score_codex":0.0015998961,"about_ca_topic_score_gemma":0.0014897941,"teacher_disagreement_score":0.010287486,"about_ca_system_score_codex":0.0013811983,"about_ca_system_score_gemma":0.001338474,"threshold_uncertainty_score":0.034415066},"labels":[],"label_agreement":null},{"id":"W2511892808","doi":"10.1186/s12859-016-1228-x","title":"The parameter sensitivity of random forests","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":182,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Occupational Cancer Research Centre; University of Toronto; Ontario Institute for Cancer Research","funders":"Prostate Cancer Canada; Canadian Institutes of Health Research; Government of Ontario; Movember Foundation","keywords":"Sensitivity (control systems); Random forest; DNA microarray; Computational biology; Computer science; Biology; Artificial intelligence; Genetics; Engineering; Gene","score_opus":0.015477327724937201,"score_gpt":0.2505137324377511,"score_spread":0.2350364047128139,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2511892808","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46722448,0.0077615534,0.51312923,0.0017550724,0.00033196414,0.00026704508,0.0013186448,0.002233237,0.0059787575],"genre_scores_gemma":[0.9591705,0.00071265997,0.037774503,0.0003377162,0.00014475003,0.00016144321,0.0010473895,0.0003449424,0.00030612707],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9806362,0.011348488,0.001044665,0.0034283896,0.0028804962,0.0006619366],"domain_scores_gemma":[0.85576516,0.12241652,0.0067974404,0.00963131,0.004780155,0.00060943054],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.030299073,0.0015629362,0.0013929291,0.0023920608,0.0010316097,0.0021294542,0.0017304305,0.0018527869,0.0012704579],"category_scores_gemma":[0.10726726,0.0006268235,0.0015257326,0.0016332562,0.0019503013,0.0028427462,0.0016348385,0.0023949326,0.0005883407],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00067908055,0.00013778568,0.050822385,0.0005284802,0.00078767515,0.00022133777,0.00038535177,0.84378344,0.0057880767,0.011417917,0.0030118243,0.082436755],"study_design_scores_gemma":[0.000042527405,0.00027905518,0.012320462,0.00019179749,0.0001873502,0.0005456897,0.00014613604,0.91329515,0.010017295,0.059523486,0.0033109672,0.00014005051],"about_ca_topic_score_codex":0.002194073,"about_ca_topic_score_gemma":0.0011527939,"teacher_disagreement_score":0.030299073,"about_ca_system_score_codex":0.0013779203,"about_ca_system_score_gemma":0.0008099816,"threshold_uncertainty_score":0.16023868},"labels":[],"label_agreement":null},{"id":"W2512143001","doi":"10.1186/s12859-016-1115-5","title":"Predicting essential proteins based on subcellular localization, orthology and PPI networks","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":88,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"National Natural Science Foundation of China","keywords":"Subcellular localization; Computational biology; DNA microarray; Protein subcellular localization prediction; Biology; Computer science; Genetics; Gene; Gene expression","score_opus":0.00529630127268006,"score_gpt":0.21752425144842968,"score_spread":0.21222795017574964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2512143001","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5338508,0.0026973006,0.4533421,0.00035385173,0.000058839,0.0001316825,0.0039217453,0.0023842377,0.003259347],"genre_scores_gemma":[0.8717709,0.0008379729,0.121610515,0.000054212804,0.00003402073,0.00006612365,0.005024604,0.000074263895,0.00052737637],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996265,0.00007819936,0.00003675821,0.000109428205,0.000121640995,0.00002742481],"domain_scores_gemma":[0.99896944,0.0005166442,0.00021228743,0.00006172563,0.00016856135,0.00007137364],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005434365,0.00082961575,0.0005953614,0.002626274,0.0002769056,0.00042698663,0.00042025401,0.00038122866,0.0009166574],"category_scores_gemma":[0.002091159,0.0001596619,0.0006143677,0.0013559529,0.00024825352,0.00072703674,0.0004531883,0.00040421708,0.00034072757],"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":[0.0013151927,0.00059250847,0.22014104,0.0019341607,0.0008127948,0.0020613158,0.00022527251,0.22929205,0.15976466,0.008161784,0.011066939,0.36463228],"study_design_scores_gemma":[0.000031640444,0.000096852076,0.029700382,0.000030711046,0.00014433532,0.0009083676,0.00006248632,0.93944544,0.021225382,0.0060214666,0.002300118,0.000032791722],"about_ca_topic_score_codex":0.0012958075,"about_ca_topic_score_gemma":0.0017396689,"teacher_disagreement_score":0.002626274,"about_ca_system_score_codex":0.0003568228,"about_ca_system_score_gemma":0.0005358446,"threshold_uncertainty_score":0.0030665398},"labels":[],"label_agreement":null},{"id":"W2515914883","doi":"10.1186/s12859-016-1174-7","title":"CloneCNA: detecting subclonal somatic copy number alterations in heterogeneous tumor samples from whole-exome sequencing data","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Cancer Genomics and Diagnostics","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":"BC Cancer Agency; National Natural Science Foundation of China","keywords":"Biology; Exome sequencing; Somatic cell; Computational biology; Copy-number variation; Copy number analysis; DNA microarray; Genetics; Exome; Genome; Mutation; Gene","score_opus":0.04086990124518253,"score_gpt":0.2729770383497744,"score_spread":0.23210713710459185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2515914883","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15150486,0.000847568,0.8176847,0.00030514295,0.00009415423,0.0003249785,0.0057718065,0.022638313,0.0008284479],"genre_scores_gemma":[0.33428824,0.0002617608,0.6517328,0.00028689642,0.000057261805,0.0006204402,0.009914578,0.0011811516,0.0016567967],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99893075,0.00018918842,0.00009602609,0.00048334594,0.00024162124,0.000059141006],"domain_scores_gemma":[0.9952793,0.002925613,0.0006095277,0.00040677484,0.00062053325,0.00015833869],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024181274,0.0010773418,0.0010247496,0.003634503,0.000794473,0.0012779642,0.0013445658,0.001431113,0.0022214307],"category_scores_gemma":[0.010036182,0.0004935568,0.0011501263,0.0022629448,0.0005259008,0.0009896839,0.0011969729,0.00089497666,0.0006130143],"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":[0.0012841121,0.0003327658,0.122033365,0.0009186504,0.0014733415,0.0014701413,0.0004966243,0.17688549,0.08262458,0.0060632955,0.026096065,0.5803216],"study_design_scores_gemma":[0.000060567858,0.00007624922,0.011549834,0.00001920452,0.0000765413,0.0005036532,0.000047637925,0.96420705,0.014941372,0.0040947343,0.0043806313,0.00004265832],"about_ca_topic_score_codex":0.005933426,"about_ca_topic_score_gemma":0.012158064,"teacher_disagreement_score":0.005933426,"about_ca_system_score_codex":0.0009502206,"about_ca_system_score_gemma":0.0017082202,"threshold_uncertainty_score":0.012788475},"labels":[],"label_agreement":null},{"id":"W2516950472","doi":"10.1186/s12859-016-1162-y","title":"BAMQL: a query language for extracting reads from BAM files","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network; University of Toronto; Ontario Institute for Cancer Research","funders":"Prostate Cancer Canada; Government of Ontario; Canadian Institutes of Health Research; Genome Canada; Ontario Institute for Cancer Research; Terry Fox Research Institute; Movember Foundation; Johns Hopkins University","keywords":"Computer science; Web search query; Information retrieval; Database; Programming language; Search engine","score_opus":0.017234525637118803,"score_gpt":0.252842834337511,"score_spread":0.23560830870039218,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2516950472","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0051487084,0.00062355393,0.56013143,0.00066594075,0.00018931153,0.00062378414,0.0670269,0.36052084,0.005069613],"genre_scores_gemma":[0.054187525,0.0010494302,0.61894935,0.0023193029,0.00027284693,0.0028283915,0.18362239,0.12819922,0.008571578],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99640584,0.0007634794,0.00062626565,0.0008120398,0.0011310796,0.00026146352],"domain_scores_gemma":[0.99213374,0.0045986483,0.0006451495,0.00094932725,0.001269621,0.0004034587],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006976806,0.0024814727,0.0015146262,0.0022637178,0.001375327,0.0034003141,0.004266557,0.0017838478,0.035605438],"category_scores_gemma":[0.013509329,0.001802136,0.0015525091,0.0024362274,0.0012553631,0.004573593,0.0044164867,0.0028326106,0.026720831],"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":[0.0034158973,0.00034386723,0.008122421,0.009766342,0.00051652046,0.0017271925,0.0032091693,0.0056414525,0.13002068,0.022940628,0.58235025,0.23194566],"study_design_scores_gemma":[0.00059186824,0.00043858672,0.0056124376,0.0009439024,0.00017643595,0.002585978,0.0010793554,0.050191745,0.1750883,0.04096634,0.7216555,0.0006694898],"about_ca_topic_score_codex":0.0024388558,"about_ca_topic_score_gemma":0.0018257126,"teacher_disagreement_score":0.035605438,"about_ca_system_score_codex":0.00093222025,"about_ca_system_score_gemma":0.001970165,"threshold_uncertainty_score":0.119112015},"labels":[],"label_agreement":null},{"id":"W2520927888","doi":"10.1186/s12859-016-1238-8","title":"A haplotype-based normalization technique for the analysis and detection of allele specific expression","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic Syndromes and Imprinting","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Cancer Research; University of Toronto; Ontario Institute for Cancer Research; Université de Montréal; Centre Hospitalier Universitaire Sainte-Justine","funders":"Medical Research Council; Partenariat Canadien Contre Le Cancer; Fonds Québécois de la Recherche sur la Nature et les Technologies; Ontario Institute for Cancer Research","keywords":"Haplotype; DNA microarray; Normalization (sociology); Allele; Genetics; Computational biology; Biology; Haplotype estimation; Gene expression; Gene","score_opus":0.011896984848092967,"score_gpt":0.22670366014951726,"score_spread":0.2148066753014243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2520927888","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012373676,0.00026195557,0.97863173,0.00007419908,0.00016108139,0.00010729822,0.0021225275,0.005241803,0.0010256935],"genre_scores_gemma":[0.058920838,0.00021956331,0.93260866,0.00013348353,0.00008199233,0.000649196,0.0041160095,0.0010970159,0.0021732158],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9976332,0.0004813216,0.00019664587,0.00085741293,0.0007048159,0.00012663676],"domain_scores_gemma":[0.9969313,0.0011750299,0.00042382343,0.00086547213,0.00053591916,0.000068497095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031673983,0.00078482257,0.00077969854,0.0018521193,0.0005951313,0.0009636332,0.0010127935,0.0007590519,0.0067262505],"category_scores_gemma":[0.009303691,0.00049106585,0.0010844975,0.0026748728,0.00054638815,0.0007076805,0.0008065896,0.0019299532,0.0035590017],"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":[0.00047899145,0.00018194133,0.016742287,0.00067103317,0.00062870973,0.00038229194,0.00053415133,0.014200527,0.32432923,0.011361622,0.013978282,0.61651105],"study_design_scores_gemma":[0.00013414522,0.0005837768,0.0795549,0.00014372135,0.00044167793,0.0024390572,0.00022740402,0.3986609,0.37066293,0.028427076,0.11839692,0.00032746897],"about_ca_topic_score_codex":0.0017195647,"about_ca_topic_score_gemma":0.0035752894,"teacher_disagreement_score":0.0067262505,"about_ca_system_score_codex":0.0005957337,"about_ca_system_score_gemma":0.0011291843,"threshold_uncertainty_score":0.022501588},"labels":[],"label_agreement":null},{"id":"W2527996525","doi":"10.1186/s12859-016-1214-3","title":"VDJML: a file format with tools for capturing the results of inferring immune receptor rearrangements","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"T-cell and B-cell Immunology","field":"Immunology and Microbiology","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":"Simon Fraser University","funders":"U.S. National Library of Medicine; National Institute of Allergy and Infectious Diseases; National Institutes of Health; Pharmaceutical Research and Manufacturers of America Foundation","keywords":"DNA microarray; File format; Computational biology; Computer science; Immune receptor; Immune system; Biology; Genetics; Programming language; Gene; Gene expression","score_opus":0.0258210095417527,"score_gpt":0.22303082367523128,"score_spread":0.19720981413347857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2527996525","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025822662,0.00045548333,0.2437344,0.001442229,0.0009578557,0.0006863348,0.35306725,0.38875255,0.008321662],"genre_scores_gemma":[0.019074276,0.0007825079,0.3413929,0.0021028153,0.0005853268,0.0032207253,0.5309163,0.09146343,0.010461678],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99577576,0.000792487,0.0013232676,0.0007344906,0.0009713508,0.00040269704],"domain_scores_gemma":[0.975255,0.012762638,0.0022384308,0.004303057,0.0046748254,0.0007660665],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00807685,0.0040450217,0.001606053,0.008584929,0.0014764913,0.005783577,0.006586196,0.0041951723,0.11059771],"category_scores_gemma":[0.0352712,0.002035363,0.0022452434,0.0050051217,0.0011816313,0.0066321157,0.0060636806,0.0030386236,0.06250556],"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":[0.0017708668,0.00017575877,0.0045869015,0.0026077502,0.0001285431,0.00088585116,0.0004528033,0.00292241,0.005832664,0.010482008,0.8708047,0.09934981],"study_design_scores_gemma":[0.00091745827,0.00022198402,0.0047385665,0.0014941948,0.000106179796,0.0013433737,0.00035532773,0.019019296,0.032288488,0.028659288,0.9103868,0.0004690581],"about_ca_topic_score_codex":0.0031983852,"about_ca_topic_score_gemma":0.002463505,"teacher_disagreement_score":0.11059771,"about_ca_system_score_codex":0.00280144,"about_ca_system_score_gemma":0.003150515,"threshold_uncertainty_score":0.36998618},"labels":[],"label_agreement":null},{"id":"W2528057066","doi":"10.1186/s12859-016-1281-5","title":"VennDiagramWeb: a web application for the generation of highly customizable Venn and Euler diagrams","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research","funders":"Natural Sciences and Engineering Research Council of Canada; Department of Medical Biophysics, University of Toronto; Canadian Institutes of Health Research; Prostate Cancer Canada; Government of Ontario; Movember Foundation; Terry Fox Research Institute; University of Toronto","keywords":"Venn diagram; Computer science; Visualization; Web application; Upload; Wizard; Documentation; Graphics; Pipeline (software); Data visualization; Interface (matter); Programming language; Data mining; World Wide Web; Computer graphics (images); Operating system","score_opus":0.013876133246091655,"score_gpt":0.24759717050703609,"score_spread":0.23372103726094443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2528057066","genre_codex":"software","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036029867,0.0010846952,0.25567266,0.0006027107,0.00060114125,0.00048742344,0.043346673,0.6863584,0.008243301],"genre_scores_gemma":[0.034711674,0.0016582746,0.5360336,0.0018910902,0.00029082262,0.0037914112,0.12142959,0.2832592,0.016934382],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99842715,0.000384181,0.00018625162,0.0003952981,0.0004620593,0.00014505582],"domain_scores_gemma":[0.99561065,0.0025667057,0.00031363804,0.0006730245,0.0005157225,0.00032022866],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029630302,0.002599234,0.0017285552,0.0037494062,0.0009247084,0.0025569482,0.003552877,0.0019053394,0.121107616],"category_scores_gemma":[0.012189883,0.0019118794,0.0022480215,0.0019372615,0.00064383866,0.0031636774,0.0046602315,0.0026651046,0.05398754],"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":[0.0008574529,0.00016681956,0.003862815,0.003049284,0.00037548866,0.0009265929,0.0005969135,0.0051507656,0.015241268,0.007435541,0.8217223,0.14061473],"study_design_scores_gemma":[0.00084419624,0.00015689917,0.007850228,0.0011450611,0.00018185476,0.0018105675,0.00021087316,0.06740001,0.036022566,0.039787043,0.84394294,0.00064774486],"about_ca_topic_score_codex":0.0016970438,"about_ca_topic_score_gemma":0.002509978,"teacher_disagreement_score":0.121107616,"about_ca_system_score_codex":0.0009008603,"about_ca_system_score_gemma":0.0017042048,"threshold_uncertainty_score":0.4051453},"labels":[],"label_agreement":null},{"id":"W2529628971","doi":"10.1186/s12859-016-1265-5","title":"A continuous analog of run length distributions reflecting accumulated fractionation events","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Chromosomal and Genetic Variations","field":"Agricultural and Biological Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Fractionation; Inference; Biological system; Computer science; Algorithm; Series (stratigraphy); Distribution (mathematics); Line (geometry); DNA microarray; Computational biology; Biology; Artificial intelligence; Mathematics; Gene; Chemistry; Chromatography; Geometry; Genetics","score_opus":0.04314688451154655,"score_gpt":0.27792341373562685,"score_spread":0.2347765292240803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2529628971","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23942983,0.00023765104,0.7561389,0.0005173138,0.0000516852,0.00004902013,0.00029862078,0.00046561199,0.0028113152],"genre_scores_gemma":[0.9571299,0.00021821463,0.038139895,0.00013286022,0.000050696442,0.00008502032,0.00025853395,0.00013357295,0.0038513131],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992544,0.00014406478,0.000029511486,0.00034283687,0.0001301708,0.000098954144],"domain_scores_gemma":[0.99287355,0.004122139,0.0012124488,0.0009323985,0.00047517868,0.00038418567],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023243974,0.000540147,0.0005513755,0.001031675,0.00037678063,0.0016275481,0.0027997047,0.0015632779,0.0037884726],"category_scores_gemma":[0.010474199,0.0005058636,0.0009350031,0.00089217775,0.0029418839,0.0030494318,0.0008678822,0.0019123735,0.00056331174],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014732232,0.00010000549,0.010450171,0.00014181693,0.000066368426,0.0005080502,0.00044712878,0.7978931,0.01891944,0.16084968,0.00070241606,0.009774465],"study_design_scores_gemma":[0.000022131,0.000038622926,0.0019588983,0.000011808491,0.00001858775,0.0002056722,0.000029255578,0.9547688,0.0015884177,0.0407302,0.000596194,0.000031400305],"about_ca_topic_score_codex":0.003278349,"about_ca_topic_score_gemma":0.0019219596,"teacher_disagreement_score":0.0037884726,"about_ca_system_score_codex":0.0021766876,"about_ca_system_score_gemma":0.0007073912,"threshold_uncertainty_score":0.015793025},"labels":[],"label_agreement":null},{"id":"W2550915265","doi":"10.1186/s12859-016-1352-7","title":"Introducing Explorer of Taxon Concepts with a case study on spider measurement matrix building","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Agriculture and Agri-Food Canada","funders":"Consejo Nacional de Investigaciones Científicas y Técnicas; University of Florida; Stony Brook University; National Science Foundation","keywords":"Spider; Taxon; Data science; Biology; Evolutionary biology; Computer science; Matrix (chemical analysis); Computational biology; Geography; Ecology; Chemistry","score_opus":0.051289187817629374,"score_gpt":0.3172159791570347,"score_spread":0.26592679133940533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2550915265","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3638966,0.001960649,0.52545184,0.00667228,0.0005452874,0.0015826811,0.011991289,0.01458602,0.07331341],"genre_scores_gemma":[0.2673993,0.0007257533,0.7007939,0.00052164093,0.00012323688,0.00071131706,0.007515323,0.0029726003,0.019236796],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974015,0.0012654212,0.0001778416,0.00039285855,0.00066678907,0.00009559295],"domain_scores_gemma":[0.98943627,0.008036718,0.00047917763,0.0008607982,0.00082186045,0.00036508692],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003084648,0.0005733395,0.00024924582,0.0034588838,0.00145146,0.0025706945,0.0010911692,0.0010711842,0.011540936],"category_scores_gemma":[0.011169539,0.00030861745,0.00081582257,0.0030961507,0.0013400327,0.0038830047,0.0027471974,0.0011095221,0.0025051008],"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":[0.00048385427,0.0006092006,0.034860924,0.0038356031,0.000098281555,0.028494177,0.14730005,0.0074599907,0.053825334,0.0883555,0.10378802,0.5308891],"study_design_scores_gemma":[0.000055191776,0.00018117634,0.015520187,0.0009018101,0.000058003163,0.010442158,0.03129274,0.027542131,0.024727508,0.026954576,0.8621727,0.0001519314],"about_ca_topic_score_codex":0.0028579482,"about_ca_topic_score_gemma":0.007798171,"teacher_disagreement_score":0.011540936,"about_ca_system_score_codex":0.0010163002,"about_ca_system_score_gemma":0.0011054013,"threshold_uncertainty_score":0.038608313},"labels":[],"label_agreement":null},{"id":"W2555781494","doi":"10.1186/s12859-016-1319-8","title":"SABRE: a method for assessing the stability of gene modules in complex tissues and subject populations","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia Hospital; BC Centre for Disease Control; Prevention of Organ Failure","funders":"Canadian Institutes of Health Research; Genome British Columbia; Providence Health Care; St. Paul's Foundation; Genome Canada","keywords":"Computational biology; Subject (documents); DNA microarray; Biology; Gene; Stability (learning theory); Computer science; Genetics; Bioinformatics; Gene expression; World Wide Web","score_opus":0.058376568827618255,"score_gpt":0.33337908630893925,"score_spread":0.275002517481321,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2555781494","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043694023,0.0002984535,0.95029193,0.00014650807,0.00006881426,0.0002974439,0.0013060819,0.0029748094,0.0009219643],"genre_scores_gemma":[0.35758358,0.00016167766,0.63416266,0.0002737742,0.00014549651,0.0014783209,0.003871703,0.0010143413,0.0013084344],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99317086,0.0031295808,0.0005240271,0.0015773519,0.001407562,0.00019056904],"domain_scores_gemma":[0.961861,0.025979396,0.0037592582,0.004523034,0.0033516947,0.0005256721],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0145193655,0.0011730923,0.001081486,0.006310458,0.0011778056,0.0017641716,0.0019712942,0.0015312093,0.004349108],"category_scores_gemma":[0.058738843,0.00045040398,0.0021928188,0.002493992,0.0017778617,0.0014383182,0.0019948636,0.0017079578,0.001428039],"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":[0.0018946497,0.00035812956,0.15571441,0.0013906666,0.0029342165,0.00090329355,0.0016842848,0.16521217,0.057211358,0.044916555,0.022051636,0.5457287],"study_design_scores_gemma":[0.00014907285,0.00056323496,0.05064826,0.00015431871,0.00044137705,0.0012834703,0.00032974978,0.8399532,0.026533583,0.061825894,0.017924672,0.00019322557],"about_ca_topic_score_codex":0.0016611408,"about_ca_topic_score_gemma":0.0022439803,"teacher_disagreement_score":0.0145193655,"about_ca_system_score_codex":0.00083844824,"about_ca_system_score_gemma":0.001419322,"threshold_uncertainty_score":0.07678664},"labels":[],"label_agreement":null},{"id":"W2561707810","doi":"10.1186/s12859-016-1431-9","title":"Fast-GBS: a new pipeline for the efficient and highly accurate calling of SNPs from genotyping-by-sequencing data","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic diversity and population structure","field":"Biochemistry, Genetics and Molecular Biology","cited_by":142,"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":"Canadian Field Crop Research Alliance; Université Laval","keywords":"Genotyping; Indel; Genome; Biology; Reference genome; DNA sequencing; Computational biology; Whole genome sequencing; Genetics; Single-nucleotide polymorphism; Deep sequencing; SNP genotyping; Genotype; Gene","score_opus":0.06061099289774968,"score_gpt":0.2842035901364003,"score_spread":0.2235925972386506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2561707810","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0050007454,0.0003670826,0.8535949,0.00030194785,0.00018054839,0.00027705624,0.016595429,0.12234425,0.0013380653],"genre_scores_gemma":[0.01754645,0.00034715293,0.9211315,0.00041434547,0.000068577465,0.0008245861,0.04849297,0.008831428,0.0023430297],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9964005,0.0005806646,0.00035056286,0.0011268347,0.0012920579,0.0002494299],"domain_scores_gemma":[0.996398,0.0013083806,0.00046659334,0.0008170683,0.00078570546,0.00022424338],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0056868074,0.00300577,0.0018354589,0.0029898782,0.0014545392,0.0026856624,0.0038823204,0.0015385214,0.009380348],"category_scores_gemma":[0.008041114,0.0020236166,0.0021760063,0.0028586225,0.00092625467,0.0024888122,0.0023561532,0.003281788,0.010117538],"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":[0.001994585,0.00032038262,0.0075880643,0.0017551058,0.0007853785,0.00079896423,0.0009194198,0.020698994,0.21058199,0.010234762,0.22343448,0.52088785],"study_design_scores_gemma":[0.00057776755,0.00039691266,0.011087421,0.0003174818,0.00028647677,0.0015170851,0.00016255201,0.4698197,0.18952063,0.024776379,0.3008397,0.00069795136],"about_ca_topic_score_codex":0.0045742984,"about_ca_topic_score_gemma":0.0056856535,"teacher_disagreement_score":0.009380348,"about_ca_system_score_codex":0.0011846625,"about_ca_system_score_gemma":0.0032156007,"threshold_uncertainty_score":0.031380355},"labels":[],"label_agreement":null},{"id":"W2562192001","doi":"10.1186/s12859-016-1387-9","title":"Prior knowledge guided eQTL mapping for identifying candidate genes","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Wheat and Barley Genetics and Pathology","field":"Agricultural and Biological Sciences","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":"National Research Council Canada","funders":"National Research Council Canada","keywords":"Computational biology; DNA microarray; Expression quantitative trait loci; Gene; Biology; Genetics; Candidate gene; Gene expression; Single-nucleotide polymorphism; Genotype","score_opus":0.08867604310489179,"score_gpt":0.2864843301914792,"score_spread":0.19780828708658738,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2562192001","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06903446,0.00033116556,0.9280637,0.00034179958,0.000019732457,0.00007119931,0.00045659606,0.00071094796,0.0009703494],"genre_scores_gemma":[0.74216825,0.00024156389,0.2542023,0.00035168094,0.000039313236,0.00028497353,0.0014803681,0.00013779446,0.0010938324],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982937,0.0006480128,0.00008740674,0.00050327036,0.00034157187,0.00012616941],"domain_scores_gemma":[0.987094,0.011188914,0.0005379647,0.00043622954,0.0005998371,0.00014302468],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004502571,0.0012038816,0.0010599176,0.002001699,0.00059628417,0.00094612414,0.001627952,0.0011923573,0.0033282596],"category_scores_gemma":[0.013320077,0.0005580726,0.002080813,0.001044379,0.0011246615,0.0011923908,0.0014858348,0.0016392034,0.00037523857],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049709895,0.00017753638,0.025598291,0.00029949824,0.00043273057,0.0007298482,0.0003207803,0.84687185,0.01146839,0.014092021,0.0010056845,0.09850621],"study_design_scores_gemma":[0.00005453554,0.00005057826,0.0023483331,0.000023795086,0.00011061107,0.0001003305,0.00002793956,0.9805798,0.0030395777,0.013056022,0.0005848165,0.00002362737],"about_ca_topic_score_codex":0.0059853215,"about_ca_topic_score_gemma":0.004817297,"teacher_disagreement_score":0.0059853215,"about_ca_system_score_codex":0.001349433,"about_ca_system_score_gemma":0.00151062,"threshold_uncertainty_score":0.023812115},"labels":[],"label_agreement":null},{"id":"W2562995081","doi":"10.1186/s12859-016-1340-y","title":"Compromise or optimize? The breakpoint anti-median","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Genome; Compromise; Phylogenetic tree; Generality; Biology; Adjacency list; Computational biology; Computer science; Data mining; Mathematics; Algorithm; Genetics; Gene","score_opus":0.020010118488466774,"score_gpt":0.2385707755167301,"score_spread":0.21856065702826333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2562995081","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07971445,0.00040054266,0.9129457,0.00082241726,0.00004288555,0.00007353984,0.0001382228,0.00055587466,0.0053063463],"genre_scores_gemma":[0.5052973,0.00029823027,0.4891855,0.0005961512,0.00008817037,0.00022089237,0.00046001142,0.00048801064,0.003365678],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981968,0.00071997615,0.000086168504,0.00046201062,0.0003826172,0.00015251803],"domain_scores_gemma":[0.995002,0.0031490168,0.00042767628,0.00086589874,0.00033007597,0.00022523441],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038246962,0.0007201593,0.0011437584,0.0008953588,0.00078815286,0.0014271316,0.0018697288,0.0015516542,0.0054496755],"category_scores_gemma":[0.012986916,0.00059045793,0.0009106797,0.0009678703,0.0018041288,0.00408137,0.0036107735,0.0020786952,0.0010192133],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008752971,0.00026770006,0.008729014,0.0003976732,0.00021714559,0.00017619063,0.00082882214,0.45797566,0.013627818,0.26869026,0.0067452043,0.24146925],"study_design_scores_gemma":[0.00008467433,0.00040823693,0.001152232,0.00009372773,0.000060488514,0.00027724536,0.00024617006,0.6943236,0.010159999,0.28354934,0.009609006,0.00003527759],"about_ca_topic_score_codex":0.00045887748,"about_ca_topic_score_gemma":0.0004870159,"teacher_disagreement_score":0.0054496755,"about_ca_system_score_codex":0.00109606,"about_ca_system_score_gemma":0.000666453,"threshold_uncertainty_score":0.020227194},"labels":[],"label_agreement":null},{"id":"W2565874974","doi":"10.1186/s12859-016-1330-0","title":"Spectra library assisted de novo peptide sequencing for HCD and ETD spectra pairs","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computational biology; Biology","score_opus":0.025093549680734226,"score_gpt":0.25720118263225245,"score_spread":0.2321076329515182,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2565874974","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10316074,0.0007752436,0.8871383,0.00015030002,0.00014447073,0.00025826218,0.0016595243,0.004896881,0.0018162248],"genre_scores_gemma":[0.13306102,0.0002939926,0.8593928,0.0001432147,0.000046506004,0.0001473051,0.004723893,0.0003217129,0.0018695291],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99830675,0.0002453913,0.00016427708,0.0005784986,0.00061216473,0.00009297433],"domain_scores_gemma":[0.9972752,0.00076591555,0.000361816,0.00045742234,0.00097365346,0.00016601487],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020674074,0.0012691125,0.00083979196,0.0020723792,0.0008286076,0.00096923974,0.0011613906,0.0010592191,0.002521587],"category_scores_gemma":[0.0025886465,0.00040227443,0.0014247375,0.0014392087,0.00038061079,0.0012860751,0.0013136456,0.0010269344,0.0014635572],"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":[0.0015070027,0.00046717943,0.012409993,0.0007461639,0.0003557336,0.001031162,0.00019998681,0.027827678,0.47411472,0.0026535583,0.004428329,0.47425857],"study_design_scores_gemma":[0.0001229711,0.00030055863,0.011584798,0.00003716589,0.00016808092,0.0018474786,0.000112603186,0.53268164,0.433213,0.0037614645,0.016029604,0.0001405497],"about_ca_topic_score_codex":0.0014346582,"about_ca_topic_score_gemma":0.0023855586,"teacher_disagreement_score":0.002521587,"about_ca_system_score_codex":0.0005740722,"about_ca_system_score_gemma":0.0010060094,"threshold_uncertainty_score":0.010933578},"labels":[],"label_agreement":null},{"id":"W2567538927","doi":"10.1186/s12859-016-1370-5","title":"Ceph-X: development and evaluation of 2D cephalometric system","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Dental Radiography and Imaging","field":"Dentistry","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Universiti Malaya; Ryerson University","keywords":"Cephalometric analysis; Usability; Reliability (semiconductor); Computer science; Orthodontics; Metric (unit); Artificial intelligence; Medicine; Engineering","score_opus":0.03751919568225653,"score_gpt":0.27639536932325015,"score_spread":0.23887617364099362,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2567538927","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5849303,0.0013150498,0.3898689,0.00040203735,0.00029948796,0.002691155,0.0029196069,0.00965133,0.007922136],"genre_scores_gemma":[0.63736993,0.00071752944,0.35315204,0.00010199448,0.00006683114,0.0011208245,0.0027155103,0.00029638148,0.0044588824],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99762696,0.000502212,0.00015907858,0.00023527516,0.001411192,0.000065324835],"domain_scores_gemma":[0.9980076,0.00045599387,0.00012962114,0.00012267158,0.0012156828,0.00006842087],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023551928,0.0005768168,0.00051868724,0.0014528234,0.00026845903,0.0006347685,0.0006949337,0.00043492747,0.0033248523],"category_scores_gemma":[0.003951042,0.00027049694,0.00032617632,0.00068780105,0.00032574811,0.00070661,0.00068229216,0.0003192724,0.0005523341],"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":[0.0012538921,0.00033029605,0.046947584,0.0011182904,0.0001554107,0.00067591626,0.0009532728,0.009727515,0.14445719,0.002909007,0.01268095,0.7787908],"study_design_scores_gemma":[0.00044307328,0.0049674814,0.3428138,0.00026665637,0.00037317985,0.004713087,0.0010961777,0.36463794,0.23561421,0.0010972644,0.04362876,0.00034845842],"about_ca_topic_score_codex":0.0028388547,"about_ca_topic_score_gemma":0.0018175868,"teacher_disagreement_score":0.0033248523,"about_ca_system_score_codex":0.0004663477,"about_ca_system_score_gemma":0.0008700349,"threshold_uncertainty_score":0.012455583},"labels":[],"label_agreement":null},{"id":"W2592654158","doi":"10.1186/s12859-017-1558-3","title":"Drug voyager: a computational platform for exploring unintended drug action","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"National Research Foundation of Korea; Ministry of Science, ICT and Future Planning; National Research Foundation","keywords":"Pharmacogenomics; Drug; Computer science; Adverse effect; Systems pharmacology; Drug action; Drug discovery; Exploit; Mechanism (biology); Computational biology; Bioinformatics; Medicine; Risk analysis (engineering); Pharmacology; Biology; Computer security","score_opus":0.17984133807801395,"score_gpt":0.35653701162446017,"score_spread":0.17669567354644622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2592654158","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05468021,0.004238527,0.8263975,0.0042142607,0.0007821125,0.0009005168,0.02639272,0.065822236,0.016571872],"genre_scores_gemma":[0.3117337,0.0037054953,0.6502393,0.0017445245,0.00026401234,0.0026317718,0.02157665,0.0037700383,0.00433456],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996338,0.00013988961,0.000035332687,0.00007448878,0.00008494175,0.000031451596],"domain_scores_gemma":[0.99836546,0.0012480823,0.00008523166,0.00012222513,0.000085099105,0.00009397594],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016826142,0.0015629699,0.0012069471,0.0017982818,0.0006527907,0.0016256092,0.0026808223,0.0018076822,0.011405498],"category_scores_gemma":[0.0045975936,0.000727706,0.0026123482,0.001008848,0.0005840748,0.0011483644,0.0017266028,0.0018844877,0.0015530518],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008235914,0.0003587794,0.009780153,0.0020172982,0.0011320679,0.0007681997,0.00023163344,0.81879914,0.002980205,0.03829995,0.037387803,0.08742122],"study_design_scores_gemma":[0.00012905012,0.000060455797,0.00026858857,0.000059291287,0.00009396507,0.00007589331,0.00001913529,0.97207266,0.0007157872,0.01440218,0.012078847,0.000024174191],"about_ca_topic_score_codex":0.006229151,"about_ca_topic_score_gemma":0.012095148,"teacher_disagreement_score":0.011405498,"about_ca_system_score_codex":0.00092156715,"about_ca_system_score_gemma":0.0030061633,"threshold_uncertainty_score":0.038155198},"labels":[],"label_agreement":null},{"id":"W2594310188","doi":"10.1186/s12859-017-1564-5","title":"Two-way learning with one-way supervision for gene expression data","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; McMaster University","funders":"Canadian Institutes of Health Research; Canada Research Chairs","keywords":"Biclustering; Mixture model; Computer science; Data set; Covariance matrix; Data mining; Bayesian probability; Expectation–maximization algorithm; Pattern recognition (psychology); Microarray analysis techniques; Artificial intelligence; Algorithm; Cluster analysis; Mathematics; Gene expression; Gene; Statistics; Biology; Genetics","score_opus":0.0696000141553618,"score_gpt":0.31492623011808707,"score_spread":0.24532621596272527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2594310188","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002604329,0.00011256877,0.9964496,0.000070264796,0.00001547017,0.000038210685,0.00003870198,0.0005111052,0.0001597132],"genre_scores_gemma":[0.21302919,0.00029787564,0.7819631,0.00026936602,0.0001270719,0.0010230492,0.00080365007,0.00035875413,0.002127915],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99281996,0.0034471927,0.00038687975,0.0018569226,0.0012151441,0.0002738781],"domain_scores_gemma":[0.9862606,0.008818425,0.0011294209,0.0020926956,0.0013712373,0.00032761515],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008722076,0.0016311147,0.0019313314,0.0013384867,0.0010468434,0.0015271992,0.0033751877,0.0016626004,0.0019022423],"category_scores_gemma":[0.021749003,0.0011000355,0.002720733,0.0017756942,0.002356985,0.0020588504,0.0024752107,0.0034373738,0.0011517149],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039609807,0.00025195145,0.005039925,0.000311139,0.00032653796,0.00015812299,0.0003974666,0.6219897,0.003919519,0.02463805,0.0028850972,0.33968636],"study_design_scores_gemma":[0.000010761772,0.000039016923,0.00026205686,0.0000072157886,0.000011427793,0.000030721705,0.000006917815,0.98872685,0.0008606225,0.009492478,0.00053695496,0.0000149036],"about_ca_topic_score_codex":0.0037245704,"about_ca_topic_score_gemma":0.0037044487,"teacher_disagreement_score":0.008722076,"about_ca_system_score_codex":0.0013920253,"about_ca_system_score_gemma":0.002041174,"threshold_uncertainty_score":0.04612732},"labels":[],"label_agreement":null},{"id":"W2594844287","doi":"10.1186/s12859-017-1559-2","title":"Reactome pathway analysis: a high-performance in-memory approach","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":927,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research; University of Toronto","funders":"National Institute of General Medical Sciences; National Human Genome Research Institute; National Institutes of Health; European Bioinformatics Institute","keywords":"Computer science; DNA microarray; Computational biology; Biology; Genetics; Gene; Gene expression","score_opus":0.014243692549370851,"score_gpt":0.22662885348526707,"score_spread":0.2123851609358962,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2594844287","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0058910316,0.00036435953,0.9278795,0.0002628238,0.00009639111,0.00014462597,0.002484547,0.06067876,0.002197953],"genre_scores_gemma":[0.08499535,0.00082864624,0.89097226,0.00026786258,0.00010164804,0.0008040512,0.011231723,0.005797583,0.005000864],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981384,0.00037607568,0.0001695764,0.00050062576,0.0006378749,0.00017742207],"domain_scores_gemma":[0.99801564,0.0007133873,0.00014313468,0.0006107968,0.000383197,0.00013388487],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024414954,0.0033929807,0.001229356,0.0035268087,0.00088038604,0.0046797097,0.004673027,0.0014599367,0.015448743],"category_scores_gemma":[0.0052973153,0.0013904844,0.0029668163,0.003112856,0.0007066746,0.004000768,0.003546591,0.0021588514,0.008006428],"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":[0.004515299,0.00075650355,0.008668948,0.0030775869,0.0016734098,0.0014552854,0.0012172457,0.13026291,0.09469573,0.091932625,0.06632474,0.59541965],"study_design_scores_gemma":[0.00030635408,0.00022813924,0.0015181784,0.00014615356,0.0002946541,0.0005968427,0.00020049732,0.7462888,0.0720367,0.10052936,0.07765988,0.00019452782],"about_ca_topic_score_codex":0.0026316738,"about_ca_topic_score_gemma":0.002403557,"teacher_disagreement_score":0.015448743,"about_ca_system_score_codex":0.0011093598,"about_ca_system_score_gemma":0.0016660516,"threshold_uncertainty_score":0.05168122},"labels":[],"label_agreement":null},{"id":"W2595675726","doi":"10.1186/s12859-017-1596-x","title":"Bioinformatics identification of new targets for improving low temperature stress tolerance in spring and winter wheat","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Plant Stress Responses and Tolerance","field":"Agricultural and Biological Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"National Research Council Canada","keywords":"Biology; Gene; Cultivar; Cold stress; Genetics; Gene expression; Phenotype; DNA microarray; Adaptation (eye); Botany","score_opus":0.017537560967064183,"score_gpt":0.23500215439806982,"score_spread":0.21746459343100563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2595675726","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87652427,0.0019931798,0.09781827,0.00094092527,0.00008812363,0.00021374835,0.013518076,0.0061842916,0.002719113],"genre_scores_gemma":[0.8493681,0.0011003684,0.12054398,0.00030715062,0.000042303007,0.00035494505,0.027105113,0.00030621485,0.0008717786],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998424,0.00003167331,0.00001149205,0.000056373814,0.00003502851,0.000023023382],"domain_scores_gemma":[0.99978226,0.00008712565,0.00003991502,0.000014543212,0.000052858035,0.000023190923],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035536036,0.000665343,0.0008336476,0.0010314033,0.00044020952,0.00067398173,0.00048815346,0.00034596867,0.0011702831],"category_scores_gemma":[0.00062838057,0.0001980176,0.001134484,0.0009990851,0.00017335758,0.00031975366,0.00030344664,0.00033825004,0.00029976576],"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":[0.0040649287,0.001009146,0.10604882,0.0035287207,0.0013175923,0.0009451297,0.00050890516,0.23224841,0.4127079,0.004717998,0.019603256,0.21329917],"study_design_scores_gemma":[0.0002670314,0.0006420644,0.053771004,0.00006388543,0.00081410207,0.0002359481,0.0002269227,0.88914496,0.040810432,0.004886169,0.009092061,0.00004543005],"about_ca_topic_score_codex":0.0022040263,"about_ca_topic_score_gemma":0.00412445,"teacher_disagreement_score":0.0022040263,"about_ca_system_score_codex":0.0005614999,"about_ca_system_score_gemma":0.00075283257,"threshold_uncertainty_score":0.004382372},"labels":[],"label_agreement":null},{"id":"W2605595174","doi":"10.1186/s12859-017-1602-3","title":"A machine learning approach for viral genome classification","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":69,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Genome; Biology; Subtyping; Computational biology; In silico; Genetics; Artificial intelligence; Computer science; Gene","score_opus":0.029051288775398105,"score_gpt":0.28135736090967217,"score_spread":0.2523060721342741,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2605595174","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013281988,0.0019878268,0.97954637,0.00068213505,0.00023821197,0.00018130335,0.00063541124,0.0014395746,0.0020070241],"genre_scores_gemma":[0.2974702,0.0016559222,0.68930703,0.0005903452,0.00083230657,0.00073558505,0.0033230295,0.00020071697,0.0058848737],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982778,0.0005079946,0.00014808844,0.00039907306,0.0005270333,0.00014008328],"domain_scores_gemma":[0.9969748,0.0017306772,0.00021261226,0.00027316256,0.00071722915,0.00009150778],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002286714,0.0012207231,0.0012370899,0.003472177,0.0006912575,0.0016883373,0.0019447422,0.0020073033,0.0026907953],"category_scores_gemma":[0.0048107933,0.0003188964,0.001518986,0.0022446197,0.0007565597,0.0011855542,0.0010204434,0.0021159449,0.0016972303],"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":[0.00011876532,0.00025173425,0.0052735507,0.00029180694,0.00018149402,0.00013166486,0.00008787884,0.23720396,0.002986186,0.012749812,0.00948228,0.73124075],"study_design_scores_gemma":[0.0000064367673,0.00003647373,0.0003673735,0.00002216596,0.000011588833,0.00004940084,0.00001601437,0.9798324,0.000836031,0.016440852,0.0023707543,0.000010465526],"about_ca_topic_score_codex":0.0020621556,"about_ca_topic_score_gemma":0.0013799801,"teacher_disagreement_score":0.003472177,"about_ca_system_score_codex":0.0011844024,"about_ca_system_score_gemma":0.0010599671,"threshold_uncertainty_score":0.012093484},"labels":[],"label_agreement":null},{"id":"W2610063871","doi":"10.1186/1471-2105-13-180","title":"Erratum to: A linear classifier based on entity recognition tools and a statistical approach to method extraction in the protein-protein interaction literature","year":2012,"lang":"en","type":"erratum","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Classifier (UML); Computer science; Pattern recognition (psychology); Artificial intelligence; Computational biology; Biology","score_opus":0.05961479667506053,"score_gpt":0.33777227297490175,"score_spread":0.2781574762998412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2610063871","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010271575,0.0038002518,0.012581435,0.10700121,0.85438025,0.00016454823,0.010519514,0.0023140514,0.008211539],"genre_scores_gemma":[0.036188103,0.021222884,0.1036501,0.16764727,0.12485524,0.00096552743,0.05624242,0.009270046,0.47995844],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9929408,0.0009797459,0.0017039651,0.0007461863,0.0033893746,0.00023997504],"domain_scores_gemma":[0.9432934,0.013095987,0.002240241,0.0024797835,0.03781918,0.0010714482],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004658589,0.0013720903,0.0012416762,0.0066393893,0.0030908433,0.0037865508,0.0020809695,0.0029881997,0.035154074],"category_scores_gemma":[0.073891945,0.0009680548,0.0012139776,0.005672788,0.0016901055,0.0030086907,0.0021754433,0.0057196827,0.031031849],"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":[0.000034146702,0.000009278402,0.00016428725,0.00019583525,0.000009973505,0.00022828786,0.000037291567,0.00006804937,0.00012757859,0.000712424,0.9847799,0.013632966],"study_design_scores_gemma":[0.00002308561,0.000020295973,0.0008146476,0.00044254318,0.00003861959,0.00081699254,0.000104944396,0.00045291966,0.00076283823,0.0009664373,0.9955135,0.00004319323],"about_ca_topic_score_codex":0.025584986,"about_ca_topic_score_gemma":0.032427587,"teacher_disagreement_score":0.035154074,"about_ca_system_score_codex":0.0037239934,"about_ca_system_score_gemma":0.007293215,"threshold_uncertainty_score":0.11760211},"labels":[],"label_agreement":null},{"id":"W2612656963","doi":"10.1186/1471-2105-9-s10-i1","title":"Highlights from the Fourth International Society for Computational Biology Student Council Symposium at the Sixteenth Annual International Conference on Intelligent Systems for Molecular Biology","year":2008,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"University of Oxford; Ontario Genomics; Ontario Genomics Institute; European Bioinformatics Institute","keywords":"Context (archaeology); Library science; Systems biology; Research council; Engineering ethics; Biology; Computational biology; Computer science; Engineering","score_opus":0.058017625929177606,"score_gpt":0.321326207184666,"score_spread":0.2633085812554884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2612656963","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0050699175,0.037676547,0.013882826,0.2930153,0.550431,0.0006777551,0.0019579306,0.0008116619,0.09647705],"genre_scores_gemma":[0.035236992,0.055486582,0.013817653,0.0314648,0.39513436,0.00093446695,0.0077142543,0.0022610275,0.45794985],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99529934,0.00078733783,0.0002434736,0.0005422423,0.0023424197,0.00078527484],"domain_scores_gemma":[0.9750547,0.0011646649,0.00057457516,0.00044814087,0.010567611,0.012190368],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012821088,0.0020571325,0.0011747977,0.0027754821,0.0033693288,0.009772915,0.002058246,0.0033957039,0.046046685],"category_scores_gemma":[0.009918094,0.0005891532,0.001646893,0.0026139438,0.00080392347,0.0035389774,0.005521347,0.0076432223,0.024482563],"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":[0.00010855253,0.000058601596,0.0002908692,0.00017792234,0.0000133742815,0.00005860104,0.00011923391,0.00015015391,0.0004154392,0.0019179427,0.95444745,0.042241942],"study_design_scores_gemma":[0.000027852537,0.000059928418,0.0008596897,0.00019117328,0.000020219833,0.00005409173,0.00025498998,0.0002998725,0.0003714036,0.001485677,0.99635124,0.000023795268],"about_ca_topic_score_codex":0.0033114406,"about_ca_topic_score_gemma":0.008792035,"teacher_disagreement_score":0.046046685,"about_ca_system_score_codex":0.0029010412,"about_ca_system_score_gemma":0.00778402,"threshold_uncertainty_score":0.15404147},"labels":[],"label_agreement":null},{"id":"W2617372835","doi":"10.1186/s12859-017-1682-0","title":"Numerical integration methods and layout improvements in the context of dynamic RNA visualization","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Simon Fraser University","keywords":"Computer science; Graph drawing; Visualization; Graph; Theoretical computer science; Graph Layout; RNA; Software; Algorithm; Data mining; Programming language","score_opus":0.02155877607544754,"score_gpt":0.3447552094190393,"score_spread":0.32319643334359177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2617372835","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0065994593,0.00041663824,0.98742604,0.0004033895,0.0002025311,0.00003969969,0.00007264938,0.0023414667,0.0024980446],"genre_scores_gemma":[0.061568815,0.000506935,0.9349319,0.000114542025,0.00008720108,0.000099547455,0.00022946222,0.0011067423,0.0013548547],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983986,0.0005273676,0.00008231687,0.00017000636,0.00075287605,0.00006871262],"domain_scores_gemma":[0.99385,0.0036205638,0.00038149566,0.0007246005,0.0012866862,0.00013667454],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019655807,0.0009437015,0.00051819877,0.0010376406,0.0004943006,0.0016163598,0.0017877743,0.0011258235,0.008336926],"category_scores_gemma":[0.012439017,0.000522679,0.0007696786,0.0012580635,0.000728005,0.0019202625,0.0014300947,0.002181863,0.0019284025],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021385768,0.00020312362,0.001983439,0.0009842328,0.00008675534,0.00035375456,0.00065398525,0.44841382,0.05887962,0.09807826,0.011307643,0.37884155],"study_design_scores_gemma":[0.00004410083,0.00007632741,0.0003772693,0.000086810745,0.000017376826,0.00020615282,0.00006033528,0.927495,0.023844318,0.021595227,0.026154228,0.000042835316],"about_ca_topic_score_codex":0.0028220883,"about_ca_topic_score_gemma":0.0025704524,"teacher_disagreement_score":0.008336926,"about_ca_system_score_codex":0.0008267971,"about_ca_system_score_gemma":0.0011674562,"threshold_uncertainty_score":0.027889788},"labels":[],"label_agreement":null},{"id":"W2618529956","doi":"10.1186/s12859-017-1871-x","title":"SPRINT: ultrafast protein-protein interaction prediction of the entire human interactome","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":82,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Interactome; Sprint; Computer science; Sequence (biology); Task (project management); Artificial intelligence; Machine learning; Data mining; Biology; Genetics","score_opus":0.019005543283534595,"score_gpt":0.255963703538983,"score_spread":0.2369581602554484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2618529956","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21414202,0.0035800056,0.41387272,0.0015054586,0.00019970608,0.00044551314,0.1480058,0.20914964,0.009099165],"genre_scores_gemma":[0.37609723,0.0016898359,0.39419955,0.00041620218,0.00009184627,0.0009711633,0.21459238,0.0073622633,0.0045796004],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99954516,0.00009846211,0.0000278625,0.00017158117,0.00011939234,0.000037485403],"domain_scores_gemma":[0.99905974,0.00047572865,0.00015510096,0.00014424346,0.00008676967,0.00007840886],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010347195,0.0017759342,0.0011039901,0.0015175093,0.0006847392,0.000883574,0.0016491832,0.00092945574,0.007445113],"category_scores_gemma":[0.0033032747,0.0007782525,0.0015873875,0.0014316242,0.00034563112,0.0012461458,0.001399527,0.0012867992,0.004213905],"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":[0.0057475404,0.0006089573,0.048320327,0.0059907967,0.0021311897,0.0012482874,0.0008729497,0.17543097,0.06611886,0.014726441,0.41629115,0.26251256],"study_design_scores_gemma":[0.00035651328,0.00029610694,0.0178253,0.00013665267,0.00020514209,0.001207595,0.00010797175,0.8930216,0.026685841,0.019167064,0.040880416,0.00010982947],"about_ca_topic_score_codex":0.0029905634,"about_ca_topic_score_gemma":0.004682769,"teacher_disagreement_score":0.007445113,"about_ca_system_score_codex":0.00047525935,"about_ca_system_score_gemma":0.0011436031,"threshold_uncertainty_score":0.024906456},"labels":[],"label_agreement":null},{"id":"W2620564586","doi":"10.1186/s12859-017-1699-4","title":"Identification of the sequence determinants of protein N-terminal acetylation through a decision tree approach","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Peptidase Inhibition and Analysis","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Ministry of Education, Culture, Sports, Science and Technology; Institute of Genetics; Japan Agency for Medical Research and Development","keywords":"Acetylation; Context (archaeology); Biochemistry; Protein sequencing; Biology; Sequence (biology); UniProt; Computational biology; Peptide sequence; Consensus sequence; Gene","score_opus":0.06452521856600396,"score_gpt":0.33763603737817166,"score_spread":0.2731108188121677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2620564586","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47391748,0.0014140683,0.51599234,0.0005021018,0.0001170816,0.00036965034,0.0024763541,0.0025664484,0.0026445524],"genre_scores_gemma":[0.72162515,0.00063030183,0.2686037,0.00020767257,0.00008456846,0.00030203906,0.007055879,0.00013247094,0.0013582474],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99938726,0.00017085655,0.000062940686,0.00014743638,0.000105630934,0.00012582945],"domain_scores_gemma":[0.9982187,0.0011223878,0.00013337171,0.000043143318,0.00034592638,0.00013642247],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014952524,0.0011410015,0.0012088271,0.0023415433,0.00051609095,0.00086816587,0.00084363454,0.0009699922,0.0020449006],"category_scores_gemma":[0.0026864328,0.00039107332,0.00132687,0.0013029416,0.00028443141,0.00058639527,0.00052535546,0.001171303,0.00075006916],"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":[0.0024567088,0.0013270586,0.051724486,0.0010156395,0.00058369484,0.0013158194,0.00032410581,0.40691882,0.060537744,0.004219472,0.0073437635,0.46223262],"study_design_scores_gemma":[0.00004037627,0.00020747751,0.0029697216,0.00002703449,0.00009404476,0.00012125669,0.00003759357,0.9899734,0.0037888603,0.0018647563,0.00085899176,0.000016348124],"about_ca_topic_score_codex":0.0022922559,"about_ca_topic_score_gemma":0.0021426608,"teacher_disagreement_score":0.0023415433,"about_ca_system_score_codex":0.0005281818,"about_ca_system_score_gemma":0.0013934632,"threshold_uncertainty_score":0.007907748},"labels":[],"label_agreement":null},{"id":"W2626203030","doi":"10.1186/s12859-017-1718-5","title":"Biomarker correlation network in colorectal carcinoma by tumor anatomic location","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic factors in colorectal cancer","field":"Medicine","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Cancer Institute; National Institutes of Health; Uehara Memorial Foundation; Gary Bennett Family Fund; Mochida Memorial Foundation for Medical and Pharmaceutical Research; Dana-Farber/Harvard Cancer Center; National Institute of Diabetes and Digestive and Kidney Diseases; Entertainment Industry Foundation","keywords":"Biomarker; DNA microarray; Colorectal cancer; Correlation; Oncology; Carcinoma; Medicine; Computational biology; Biology; Pathology; Internal medicine; Cancer; Gene; Genetics; Gene expression; Mathematics","score_opus":0.02191543732902508,"score_gpt":0.2761201421532842,"score_spread":0.2542047048242591,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2626203030","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9909769,0.0007182453,0.0059227557,0.00016498797,0.0000069199696,0.000036509056,0.0013894188,0.000047011476,0.00073711225],"genre_scores_gemma":[0.99605066,0.00017825337,0.0024233938,0.00001882665,0.0000074981435,0.000032540516,0.0010920274,0.000004994002,0.00019182426],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9993636,0.00020791391,0.000053130432,0.00021155635,0.00009298724,0.00007071959],"domain_scores_gemma":[0.9965276,0.0017529067,0.0010290705,0.00013705193,0.00034614292,0.0002071375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000704781,0.00026429404,0.00038149173,0.003143514,0.00045966683,0.0005826281,0.00030640868,0.00033979336,0.0017422114],"category_scores_gemma":[0.0039659454,0.00019008444,0.00054391637,0.0027647626,0.00034176992,0.0005168363,0.0005528081,0.00023153162,0.00018467623],"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":[0.0003598804,0.000045907418,0.96049017,0.0002255614,0.000599561,0.00050595833,0.0002340411,0.016146118,0.004847861,0.0010919864,0.00090084935,0.014552143],"study_design_scores_gemma":[0.000027537975,0.00015944349,0.91625434,0.00004831756,0.00060136744,0.0015406609,0.00037528443,0.07236414,0.001528987,0.004766222,0.0022993616,0.000034435998],"about_ca_topic_score_codex":0.0045411964,"about_ca_topic_score_gemma":0.005503584,"teacher_disagreement_score":0.0045411964,"about_ca_system_score_codex":0.0005729044,"about_ca_system_score_gemma":0.00052527705,"threshold_uncertainty_score":0.009029508},"labels":[],"label_agreement":null},{"id":"W2649123629","doi":"10.1186/s12859-017-1728-3","title":"Optimal alpha reduces error rates in gene expression studies: a meta-analysis approach","year":2017,"lang":"en","type":"review","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Type I and type II errors; Bonferroni correction; False discovery rate; Statistical power; Multiple comparisons problem; Word error rate; Computer science; DNA microarray; Replication (statistics); Meta-analysis; Sample size determination; Nominal level; Throughput; Data mining; Statistics; Computational biology; Biology; Mathematics; Artificial intelligence; Confidence interval; Gene expression; Gene; Genetics; Medicine","score_opus":0.3857963681457757,"score_gpt":0.45388906396090556,"score_spread":0.06809269581512983,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2649123629","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021577384,0.15431082,0.80867934,0.0052010184,0.0025304628,0.002405904,0.0016968629,0.0019848726,0.001613333],"genre_scores_gemma":[0.4861556,0.018920489,0.4820282,0.0025033506,0.0012908464,0.0066856844,0.00092332636,0.0007159697,0.0007766102],"study_design_codex":"meta_analysis","study_design_gemma":"meta_analysis","domain_scores_codex":[0.5324506,0.4132655,0.020343486,0.020559087,0.011733688,0.0016476626],"domain_scores_gemma":[0.46187437,0.49759963,0.011775244,0.021755548,0.00580173,0.0011935398],"candidate_categories":["metaresearch","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.28082895,0.008007573,0.017614625,0.01654568,0.0015504225,0.007677571,0.008038661,0.006302205,0.002735655],"category_scores_gemma":[0.33694142,0.003477522,0.056195132,0.0140279615,0.0025906714,0.0054545724,0.0046240324,0.00790424,0.00045170833],"study_design_candidate":"meta_analysis","study_design_consensus":"meta_analysis","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0041763843,0.00016491844,0.021159954,0.021412041,0.8588624,0.0005004248,0.00050612766,0.030448092,0.0014213206,0.0057749944,0.0024288467,0.05314455],"study_design_scores_gemma":[0.0031817893,0.0024961997,0.011270745,0.006853102,0.8003048,0.0006618864,0.00043721974,0.090111114,0.004311892,0.06971116,0.010235505,0.0004246506],"about_ca_topic_score_codex":0.0029830316,"about_ca_topic_score_gemma":0.0023674367,"teacher_disagreement_score":0.9823854,"about_ca_system_score_codex":0.0033291008,"about_ca_system_score_gemma":0.00491455,"threshold_uncertainty_score":0.886866},"labels":[],"label_agreement":null},{"id":"W2737578470","doi":"10.1186/s12859-017-1758-x","title":"Exploring general-purpose protein features for distinguishing enzymes and non-enzymes within the twilight zone","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"European Regional Development Fund; Dirección General de Asuntos del Personal Académico, Universidad Nacional Autónoma de México; Fundação para a Ciência e a Tecnologia; Universitat de València","keywords":"Benchmark (surveying); Proteome; Computational biology; Computer science; Protein function prediction; Structural bioinformatics; Protein structure database; Sequence alignment; Similarity (geometry); Structural alignment; Protein methods; Protein sequencing; Annotation; Protein family; Protein function; Function (biology); Structural similarity; Sequence (biology); Protein structure; Multiple sequence alignment; Artificial intelligence; Biology; Bioinformatics; Peptide sequence; Sequence database; Genetics; Gene; Biochemistry","score_opus":0.04100894492899753,"score_gpt":0.2774749193984699,"score_spread":0.23646597446947237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2737578470","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8879244,0.0019364561,0.098912045,0.00016528441,0.000036068694,0.00011413226,0.0053261938,0.0029477952,0.0026376871],"genre_scores_gemma":[0.91672367,0.0006852045,0.06341241,0.000066161105,0.00002016382,0.000121915415,0.017571205,0.00020024419,0.0011990607],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99974006,0.000027028253,0.00002057794,0.00007815628,0.000089455396,0.000044602275],"domain_scores_gemma":[0.99929535,0.00023595469,0.00017833621,0.00007653974,0.00013530136,0.00007849245],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006803446,0.0007951349,0.000794997,0.0031062062,0.00032126927,0.00092443795,0.00067484204,0.00056707405,0.00095180765],"category_scores_gemma":[0.0013655007,0.00010872488,0.00063616055,0.0026408515,0.00040463594,0.0007750807,0.00095983426,0.0006168866,0.0006657724],"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":[0.0019378271,0.0010121645,0.19204767,0.0016081737,0.00032572445,0.0006792374,0.0003109205,0.08006486,0.19184192,0.005561159,0.015360624,0.5092497],"study_design_scores_gemma":[0.00012465952,0.0010183649,0.1045273,0.000074116426,0.00013688937,0.00090328505,0.000643404,0.7857097,0.08286601,0.007978571,0.015918292,0.00009950019],"about_ca_topic_score_codex":0.0023925616,"about_ca_topic_score_gemma":0.0030879332,"teacher_disagreement_score":0.0031062062,"about_ca_system_score_codex":0.0004242001,"about_ca_system_score_gemma":0.00061640324,"threshold_uncertainty_score":0.0047573447},"labels":[],"label_agreement":null},{"id":"W2761379268","doi":"10.1186/s12859-017-1843-1","title":"Interpretation of microbiota-based diagnostics by explaining individual classifier decisions","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Advanced Research","funders":"National Science Council; Vrije Universiteit Amsterdam; ZonMw","keywords":"Classifier (UML); Machine learning; Artificial intelligence; Gut flora; Computer science; Biology; Immunology","score_opus":0.031172426348228102,"score_gpt":0.2971729783402441,"score_spread":0.266000551992016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2761379268","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11589695,0.00076902105,0.8775586,0.00141812,0.00016139384,0.00018629363,0.00076933496,0.0016315535,0.0016087529],"genre_scores_gemma":[0.7013895,0.00025480974,0.29587469,0.00034335416,0.00012230639,0.00018763136,0.0009364076,0.0001652938,0.0007259702],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967487,0.0012702624,0.0002712644,0.00088672724,0.0006398163,0.00018315921],"domain_scores_gemma":[0.9872463,0.009196688,0.0010981831,0.001022288,0.0012264287,0.00021010452],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0053546797,0.0015407783,0.00080047484,0.0018618194,0.0005617582,0.0024051608,0.001294325,0.0019132011,0.0022273997],"category_scores_gemma":[0.022201406,0.00034217632,0.0014326308,0.00056151435,0.0010069434,0.001157821,0.0010610825,0.0015921125,0.00049514096],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014716495,0.00034786997,0.1006066,0.00082118774,0.000677498,0.0014507299,0.0016452663,0.42688745,0.028686805,0.02082924,0.006028399,0.41054732],"study_design_scores_gemma":[0.000039000573,0.0001310664,0.0055855513,0.00009463352,0.00011938522,0.00026768766,0.00012633462,0.9482968,0.009209777,0.033297393,0.0027834973,0.000048891092],"about_ca_topic_score_codex":0.0020296306,"about_ca_topic_score_gemma":0.0015610987,"teacher_disagreement_score":0.0053546797,"about_ca_system_score_codex":0.0012978528,"about_ca_system_score_gemma":0.0013411064,"threshold_uncertainty_score":0.028318584},"labels":[],"label_agreement":null},{"id":"W2765773784","doi":"10.1186/s12859-017-1830-6","title":"DCJ-RNA - double cut and join for RNA secondary structures","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"National Plan for Science, Technology and Innovation; King Saud University","keywords":"Nucleic acid secondary structure; Protein secondary structure; Genome; Computer science; Join (topology); RNA; Similarity (geometry); Algorithm; Time complexity; Sequence (biology); Data structure; Representation (politics); Theoretical computer science; Computational biology; Mathematics; Biology; Genetics; Combinatorics; Gene; Artificial intelligence","score_opus":0.02485877873433138,"score_gpt":0.2729704115021062,"score_spread":0.24811163276777484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2765773784","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020034237,0.00033312305,0.9732695,0.00015074218,0.000073565636,0.0002670493,0.0004986632,0.0033532607,0.0020198144],"genre_scores_gemma":[0.0536675,0.00008985285,0.9424838,0.00006717414,0.000034106342,0.0002445232,0.0017776086,0.00034289996,0.0012924782],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99893945,0.00016431068,0.00007572847,0.0003491825,0.00038764416,0.000083756735],"domain_scores_gemma":[0.99795413,0.0011184722,0.00021839266,0.00029588086,0.00032526974,0.00008784524],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012533959,0.001126583,0.00087974075,0.0015091398,0.001087808,0.0015748844,0.0017575083,0.0016080055,0.0053030844],"category_scores_gemma":[0.0035793367,0.00044137452,0.0015322932,0.0012403463,0.00076702697,0.0014587117,0.001298251,0.001708522,0.0020824147],"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":[0.00075524184,0.0005060114,0.0050649666,0.000815881,0.00020034966,0.00024871505,0.00037977216,0.22212353,0.065719046,0.048073675,0.015397519,0.6407153],"study_design_scores_gemma":[0.00013248035,0.00034278602,0.00087049644,0.000037988848,0.000038584363,0.0003693557,0.000088468514,0.9165942,0.031698562,0.03654469,0.01324736,0.000035025518],"about_ca_topic_score_codex":0.0013116272,"about_ca_topic_score_gemma":0.0016866641,"teacher_disagreement_score":0.0053030844,"about_ca_system_score_codex":0.0011178752,"about_ca_system_score_gemma":0.0012535416,"threshold_uncertainty_score":0.017740607},"labels":[],"label_agreement":null},{"id":"W2766029068","doi":"10.1186/s12859-017-1827-1","title":"VAliBS: a visual aligner for bisulfite sequences","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Epigenetics and DNA Methylation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"National Natural Science Foundation of China","keywords":"Bisulfite; Computer science; Bisulfite sequencing; DNA methylation; Computational biology; Methylation; Visualization; Artificial intelligence; DNA; Genetics; Biology; Gene","score_opus":0.034252719927802516,"score_gpt":0.33410641764742605,"score_spread":0.29985369771962356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766029068","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004929467,0.0011668777,0.49393007,0.00027267248,0.00042715718,0.00035568554,0.021513987,0.4737606,0.0036434757],"genre_scores_gemma":[0.036202528,0.0010433444,0.8234395,0.0008768309,0.00013099136,0.0019890892,0.04974285,0.07606226,0.010512613],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984896,0.00032564453,0.00022573092,0.00042216736,0.00039881514,0.00013797273],"domain_scores_gemma":[0.9983669,0.0008780032,0.00020386635,0.00016314162,0.00027229753,0.000115793344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027173376,0.0030106525,0.0015073724,0.003183529,0.0009349946,0.0015496543,0.0032682274,0.0014932163,0.054210633],"category_scores_gemma":[0.0069578527,0.0016793892,0.0017769954,0.0019413162,0.00051392464,0.0020318078,0.0024846687,0.002431969,0.016654704],"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":[0.0042732693,0.00025408447,0.0035606062,0.006753239,0.00084877026,0.0010433599,0.0013957924,0.007353289,0.10443295,0.011759855,0.40310428,0.45522052],"study_design_scores_gemma":[0.0013062119,0.00064529915,0.0055753505,0.0009516408,0.00031363007,0.0015905274,0.000300791,0.12827136,0.18919934,0.028102737,0.6432005,0.00054253143],"about_ca_topic_score_codex":0.001885698,"about_ca_topic_score_gemma":0.0017735097,"teacher_disagreement_score":0.054210633,"about_ca_system_score_codex":0.00083792466,"about_ca_system_score_gemma":0.0014171961,"threshold_uncertainty_score":0.18135262},"labels":[],"label_agreement":null},{"id":"W2766787629","doi":"10.1186/s12859-018-2046-0","title":"Germline contamination and leakage in whole genome somatic single nucleotide variant detection","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research","funders":"National Cancer Institute; Ontario Institute for Cancer Research; National Human Genome Research Institute; Natural Sciences and Engineering Research Council of Canada; Prostate Cancer Canada; Government of Ontario; Google; Canadian Institutes of Health Research; Genome Canada; National Institutes of Health; Terry Fox Research Institute; Movember Foundation","keywords":"Germline; Somatic cell; Biology; Germline mutation; Genetics; Computational biology; Genome; Gene; Mutation","score_opus":0.009098428916075674,"score_gpt":0.21410578895007318,"score_spread":0.2050073600339975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766787629","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77218145,0.005774413,0.20408443,0.0025473516,0.0003417375,0.0003222784,0.0048127105,0.005165511,0.0047701434],"genre_scores_gemma":[0.9274383,0.00067513785,0.064925194,0.0012545958,0.000096520926,0.00015569512,0.0042769494,0.00069624494,0.00048136635],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.96334743,0.013206105,0.0036776783,0.007242797,0.011243868,0.0012821474],"domain_scores_gemma":[0.90056866,0.06835039,0.011342557,0.011439932,0.007384383,0.00091406633],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.031000393,0.00066027156,0.0006895928,0.0023556522,0.0009464767,0.0026413149,0.0012972363,0.0014339213,0.0009689143],"category_scores_gemma":[0.10835259,0.0005545396,0.0010767458,0.0030494756,0.001943779,0.0026103698,0.003599845,0.0015897683,0.0005348335],"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":[0.002528105,0.00018606655,0.6566383,0.0016874418,0.001339644,0.0012329727,0.0030495278,0.033439543,0.051948585,0.008812125,0.008225303,0.23091233],"study_design_scores_gemma":[0.00018031817,0.0015310069,0.33123142,0.001349741,0.0012763416,0.008152363,0.0017516308,0.24693078,0.30236176,0.05919131,0.045605503,0.00043785383],"about_ca_topic_score_codex":0.0021354854,"about_ca_topic_score_gemma":0.0023143818,"teacher_disagreement_score":0.031000393,"about_ca_system_score_codex":0.00136211,"about_ca_system_score_gemma":0.0014965379,"threshold_uncertainty_score":0.1639477},"labels":[],"label_agreement":null},{"id":"W2767173690","doi":"10.1186/s12859-018-2111-8","title":"ATMAD: robust image analysis for Automatic Tissue MicroArray De-arraying","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Queen's University; Queen's University Belfast","keywords":"Artificial intelligence; Thresholding; Computer science; Computer vision; Pattern recognition (psychology); Bright-field microscopy; Preprocessor; Sample (material); Biomedical engineering; Microscope; Image (mathematics); Engineering; Optics","score_opus":0.027508111410899483,"score_gpt":0.2767364041537164,"score_spread":0.24922829274281694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2767173690","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021389665,0.00016152457,0.9871824,0.000057385016,0.00003913154,0.000048818518,0.00034517975,0.009692043,0.0003345879],"genre_scores_gemma":[0.022136843,0.00017429725,0.97443885,0.00007929976,0.000045377357,0.00033795237,0.00097264396,0.0007416027,0.0010730858],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99855286,0.00025169415,0.00008473152,0.00033037498,0.00067316677,0.000107156135],"domain_scores_gemma":[0.9989812,0.00033107412,0.00014918113,0.0002064661,0.00028189094,0.000050197246],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017051738,0.0013591964,0.0008053323,0.0019561828,0.0004534921,0.0013109572,0.0020574196,0.0010543007,0.01072681],"category_scores_gemma":[0.0027685896,0.0005311853,0.0014900295,0.0010521094,0.000638299,0.0008235061,0.0015421506,0.0014649845,0.005398969],"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":[0.00060660474,0.00013587403,0.0011673191,0.0004859291,0.00020499765,0.00018604893,0.00011729697,0.034262925,0.19774012,0.0106094675,0.020683596,0.73379976],"study_design_scores_gemma":[0.000043984222,0.00018336216,0.0026914827,0.000037575872,0.00005838176,0.000565028,0.000042883537,0.795357,0.15940802,0.006159449,0.035354797,0.000098054734],"about_ca_topic_score_codex":0.00082216505,"about_ca_topic_score_gemma":0.0010774815,"teacher_disagreement_score":0.01072681,"about_ca_system_score_codex":0.0007059506,"about_ca_system_score_gemma":0.000859506,"threshold_uncertainty_score":0.035884738},"labels":[],"label_agreement":null},{"id":"W2768591110","doi":"10.1186/s12859-017-1912-5","title":"DBNorm: normalizing high-density oligonucleotide microarray data based on distributions","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"University of Technology Sydney","keywords":"Normalization (sociology); Computer science; Data mining; Quantile; Data set; Visualization; Merge (version control); Gaussian; Algorithm; Pattern recognition (psychology); Artificial intelligence; Mathematics; Statistics; Information retrieval","score_opus":0.04508076352832052,"score_gpt":0.29599593996764995,"score_spread":0.2509151764393294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2768591110","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019581031,0.0002702513,0.95866674,0.00027373465,0.00013008813,0.00014796211,0.00251621,0.016876437,0.0015375821],"genre_scores_gemma":[0.1102142,0.00037316434,0.87463456,0.0003130766,0.00009714893,0.00077733974,0.008070268,0.0034775625,0.0020426912],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99364316,0.0016806837,0.00044955962,0.0017101816,0.002312905,0.0002035299],"domain_scores_gemma":[0.99321306,0.0031897346,0.0007719611,0.0013312857,0.0013626345,0.00013126286],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007751461,0.0014202455,0.0013023125,0.00301426,0.00094552356,0.0024296609,0.002039113,0.0008139671,0.004387562],"category_scores_gemma":[0.018933363,0.00073622435,0.0018526141,0.0032983988,0.0014407735,0.0017288027,0.0018914021,0.0021535524,0.0025642067],"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":[0.0010170323,0.00038793508,0.025278851,0.0011722007,0.00083149335,0.00030660635,0.0007353322,0.091426305,0.092064776,0.032055188,0.040895656,0.71382856],"study_design_scores_gemma":[0.00015980832,0.00029080163,0.022208799,0.00012179208,0.00018396966,0.0008609477,0.00041689273,0.6991531,0.15405677,0.059255168,0.06303462,0.00025723578],"about_ca_topic_score_codex":0.0027631458,"about_ca_topic_score_gemma":0.0040533333,"teacher_disagreement_score":0.007751461,"about_ca_system_score_codex":0.0018389646,"about_ca_system_score_gemma":0.0022667008,"threshold_uncertainty_score":0.040994167},"labels":[],"label_agreement":null},{"id":"W2769794976","doi":"10.1186/s12859-017-1930-3","title":"GFF3sort: a novel tool to sort GFF3 files for tabix indexing","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Biotechnology Research Institute","funders":"Ministry of Agriculture of the People's Republic of China; National Natural Science Foundation of China","keywords":"Computer science; Search engine indexing; sort; Rendering (computer graphics); Sorting; Visualization; Annotation; JSON; Sorting algorithm; Information retrieval; File format; Data mining; Database; Computer graphics (images); Artificial intelligence; Programming language","score_opus":0.032521873715545255,"score_gpt":0.27872664572990075,"score_spread":0.24620477201435548,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2769794976","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004830998,0.00049464864,0.31273523,0.00032054377,0.00044103933,0.00029203354,0.035105273,0.6403761,0.005404113],"genre_scores_gemma":[0.039697185,0.0007490995,0.673554,0.0008599794,0.00019295921,0.0014870111,0.11494728,0.15759283,0.010919694],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987091,0.0001246322,0.00021187215,0.00032497084,0.00045443504,0.0001749799],"domain_scores_gemma":[0.99730945,0.0010836762,0.00026285448,0.00044888956,0.00070620474,0.00018890479],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019735384,0.003146627,0.0012880695,0.0036596654,0.0014311349,0.0029287266,0.0036169651,0.0015302094,0.057606723],"category_scores_gemma":[0.00780405,0.0013922342,0.0028852965,0.003059102,0.0008155071,0.003697479,0.0023463427,0.0022146094,0.03248678],"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":[0.0010465685,0.0001543467,0.0036936796,0.0021953403,0.00023125413,0.00094213535,0.001016752,0.0035163031,0.04064354,0.0055596246,0.62985593,0.3111446],"study_design_scores_gemma":[0.00051561056,0.00020722489,0.004727269,0.0005598304,0.00013744437,0.0017891497,0.00039708728,0.052335884,0.14153121,0.015253043,0.7819964,0.0005498178],"about_ca_topic_score_codex":0.00590514,"about_ca_topic_score_gemma":0.0047812606,"teacher_disagreement_score":0.057606723,"about_ca_system_score_codex":0.0011596621,"about_ca_system_score_gemma":0.0020720253,"threshold_uncertainty_score":0.19271368},"labels":[],"label_agreement":null},{"id":"W2769985287","doi":"10.1186/s12859-017-1936-x","title":"Software for rapid time dependent ChIP-sequencing analysis (TDCA)","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"AXYS Technologies (Canada); Burnaby Hospital; Simon Fraser University","funders":"Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Computer science; Software; DNA microarray; DNA sequencing; ChIP-sequencing; Data mining; Computational biology; Chip; Chromatin; Algorithm; Bioinformatics; Biology; Genetics; DNA; Gene","score_opus":0.014760311125796347,"score_gpt":0.24256794723702324,"score_spread":0.2278076361112269,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2769985287","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021627224,0.00017246419,0.556393,0.0001575807,0.00019962646,0.0006719542,0.019741518,0.41805655,0.0024446014],"genre_scores_gemma":[0.018869242,0.0003810663,0.8458927,0.0007611661,0.00009964769,0.00837996,0.037699074,0.081814386,0.006102744],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9973199,0.0004945992,0.00043687253,0.00086697115,0.000667639,0.00021398121],"domain_scores_gemma":[0.9934041,0.003495203,0.00053932634,0.001002651,0.0012798749,0.00027881036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0060954876,0.0032052794,0.0019456623,0.00297268,0.001041572,0.002265334,0.003872892,0.0018359203,0.07563618],"category_scores_gemma":[0.010940923,0.002307212,0.0027393939,0.0017705299,0.0009207767,0.0021299222,0.0024120365,0.0047223344,0.03179808],"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":[0.0029103495,0.00053018564,0.00763127,0.005087809,0.0012343297,0.0008665751,0.0011748422,0.023527952,0.097117044,0.017173186,0.53319794,0.30954853],"study_design_scores_gemma":[0.0011711321,0.0004988964,0.008189367,0.000665415,0.0004449098,0.0013026192,0.00017691072,0.35290882,0.14733697,0.03849776,0.44806403,0.0007432485],"about_ca_topic_score_codex":0.0025958822,"about_ca_topic_score_gemma":0.002366249,"teacher_disagreement_score":0.07563618,"about_ca_system_score_codex":0.0011576319,"about_ca_system_score_gemma":0.0031001803,"threshold_uncertainty_score":0.2530282},"labels":[],"label_agreement":null},{"id":"W2770091706","doi":"10.1186/s12859-017-1906-3","title":"fLPS: Fast discovery of compositional biases for the protein universe","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":96,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation","keywords":"Computational biology; Contig; Asparagine; Biology; Residue (chemistry); Metagenomics; Sequence (biology); Amino acid; Computer science; Genetics; Biochemistry; Genome; Gene","score_opus":0.033725925211328396,"score_gpt":0.26788335994723483,"score_spread":0.23415743473590644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2770091706","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.082936406,0.0015375719,0.7845118,0.0008176015,0.00018320358,0.00033046785,0.009790567,0.11655298,0.0033394566],"genre_scores_gemma":[0.12679537,0.0006793109,0.84563595,0.0004377906,0.00013421595,0.0009340917,0.014182325,0.009819524,0.0013813778],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985678,0.00028426936,0.0000813797,0.000511301,0.00044825693,0.00010690124],"domain_scores_gemma":[0.996585,0.0019267075,0.00052062393,0.00044056636,0.00035096682,0.00017614815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004207295,0.002986595,0.001827208,0.005088677,0.001738679,0.002736376,0.0029240292,0.0023019724,0.008158216],"category_scores_gemma":[0.011012641,0.0016330035,0.0031431362,0.0026898906,0.0013354727,0.0043758024,0.0036599385,0.0030661803,0.0051352708],"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":[0.0027949242,0.00038469996,0.04913163,0.004484783,0.0018785415,0.0011102846,0.0017997652,0.07408097,0.19414496,0.028461885,0.09181368,0.54991394],"study_design_scores_gemma":[0.0003806118,0.0002835013,0.009875851,0.00025991065,0.00030463003,0.0009772842,0.0002768083,0.8010766,0.06006608,0.07316389,0.05311031,0.00022450936],"about_ca_topic_score_codex":0.0015643531,"about_ca_topic_score_gemma":0.002087858,"teacher_disagreement_score":0.008158216,"about_ca_system_score_codex":0.0014731705,"about_ca_system_score_gemma":0.0015688033,"threshold_uncertainty_score":0.027291894},"labels":[],"label_agreement":null},{"id":"W2770792541","doi":"10.1186/s12859-017-1903-6","title":"Brain medical image diagnosis based on corners with importance-values","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":11,"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; Servier; H. Lundbeck A/S; IXICO; Natural Science Foundation of Heilongjiang Province; National Natural Science Foundation of China; Eisai; Genentech; Northern California Institute for Research and Education; Eli Lilly and Company; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; F. Hoffmann-La Roche; University of Southern California; Pfizer; Biogen; BioClinica; Novartis Pharmaceuticals Corporation; Bristol-Myers Squibb; Foundation for the National Institutes of Health","keywords":"Artificial intelligence; Computer science; Classifier (UML); Pattern recognition (psychology); Matching (statistics); Similarity (geometry); Image registration; Image (mathematics); Medical imaging; Computer vision; Medicine; Pathology","score_opus":0.023194025837499698,"score_gpt":0.3068828850040999,"score_spread":0.2836888591666002,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2770792541","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.210449,0.0011238521,0.7824902,0.00039200915,0.00016011065,0.00026871677,0.00047462888,0.0011881111,0.0034533904],"genre_scores_gemma":[0.82992095,0.00048321235,0.16746438,0.00009329119,0.000117819494,0.000087142995,0.0005304975,0.000056393692,0.0012462931],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99924374,0.00007212315,0.00006586557,0.00017940557,0.00033152738,0.0001074141],"domain_scores_gemma":[0.9981688,0.00064237823,0.00031754968,0.0001238888,0.0006291215,0.00011818463],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005442,0.00060511415,0.00082821125,0.0032164918,0.00030443998,0.00082433526,0.00077352015,0.0010617358,0.001934518],"category_scores_gemma":[0.004325058,0.00025093785,0.00073314173,0.0013254598,0.00043460168,0.0009850782,0.00066561886,0.00057517143,0.0008254593],"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":[0.0016663962,0.00026712337,0.039899975,0.00056184747,0.00020836291,0.001704828,0.00029187178,0.0613526,0.094084926,0.005725829,0.0076662824,0.78656995],"study_design_scores_gemma":[0.000040629406,0.0002033682,0.017374024,0.00005532543,0.00011158195,0.0013382316,0.000117414485,0.94231373,0.029878244,0.006787376,0.0017355675,0.000044376742],"about_ca_topic_score_codex":0.0015161869,"about_ca_topic_score_gemma":0.001389303,"teacher_disagreement_score":0.0032164918,"about_ca_system_score_codex":0.00044386322,"about_ca_system_score_gemma":0.0004631774,"threshold_uncertainty_score":0.006471634},"labels":[],"label_agreement":null},{"id":"W2771761215","doi":"10.1186/s12859-019-2916-0","title":"A multivariate Poisson-log normal mixture model for clustering transcriptome sequencing data","year":2019,"lang":"en","type":"preprint","venue":"BMC Bioinformatics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"Cluster analysis; Mixture model; Overdispersion; Markov chain Monte Carlo; Computer science; Multivariate statistics; Expectation–maximization algorithm; Context (archaeology); Poisson distribution; Count data; Data mining; Mathematics; Statistics; Biology; Artificial intelligence; Machine learning; Bayesian probability","score_opus":0.11826977902242625,"score_gpt":0.3252396361446816,"score_spread":0.20696985712225535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2771761215","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004062818,0.0002487833,0.9935796,0.0002623401,0.000052015544,0.00014047867,0.0005876801,0.0005664053,0.00049982045],"genre_scores_gemma":[0.17102638,0.0012751679,0.8047778,0.00067694916,0.0003312818,0.002725953,0.0073846215,0.0010838554,0.010718024],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99405587,0.0032386433,0.00026403295,0.0012513566,0.00086094294,0.00032915446],"domain_scores_gemma":[0.9904156,0.006416971,0.0008629162,0.0008054236,0.001211509,0.00028762227],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011873736,0.001731556,0.00230849,0.0033024065,0.0014867809,0.003161391,0.0067279716,0.0037645393,0.0055763335],"category_scores_gemma":[0.025465205,0.0014869069,0.0037815198,0.0046793325,0.002284871,0.00327927,0.0025534385,0.0045617963,0.003959717],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003335646,0.00012429524,0.006590661,0.0004624739,0.00031123575,0.00030804734,0.0006298084,0.74330664,0.0031484477,0.17451882,0.009673996,0.060592037],"study_design_scores_gemma":[0.000021692487,0.000027799622,0.00064615754,0.00003378853,0.000030395368,0.00009106031,0.000030516952,0.9512175,0.00035003875,0.04446497,0.0030419552,0.000044183264],"about_ca_topic_score_codex":0.0175059,"about_ca_topic_score_gemma":0.016157132,"teacher_disagreement_score":0.0175059,"about_ca_system_score_codex":0.003057148,"about_ca_system_score_gemma":0.0030407896,"threshold_uncertainty_score":0.0627951},"labels":[],"label_agreement":null},{"id":"W2776730476","doi":"10.1186/s12859-017-1995-z","title":"fDETECT webserver: fast predictor of propensity for protein production, purification, and crystallization","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Enzyme Structure and Function","field":"Materials Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"China Scholarship Council","keywords":"Crystallization; Propensity score matching; Production (economics); Web server; Computational biology; Computer science; Biology; Chemistry; Mathematics; World Wide Web; Statistics; The Internet","score_opus":0.030323302359978817,"score_gpt":0.23701246349019098,"score_spread":0.20668916113021216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2776730476","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06388631,0.0036843696,0.09293674,0.00096837385,0.00058593747,0.0003408892,0.28840435,0.54177886,0.0074141836],"genre_scores_gemma":[0.20560466,0.0025805652,0.16614982,0.0010885043,0.00031637063,0.0016931437,0.59304154,0.02310919,0.0064161667],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986553,0.0001394622,0.00010925466,0.00040505713,0.00053727865,0.00015355946],"domain_scores_gemma":[0.9967452,0.0015574521,0.00037657702,0.00046581012,0.0006025611,0.00025237413],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023920415,0.0050291796,0.002060246,0.0034862377,0.0010031483,0.0023345537,0.0039402046,0.002219034,0.016052078],"category_scores_gemma":[0.00897091,0.0012380341,0.0020357738,0.0032388084,0.00055332977,0.0027751813,0.001985272,0.0029082433,0.017110849],"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":[0.0018634724,0.0005425458,0.04229509,0.0018896725,0.0006365034,0.0004934632,0.00017405565,0.03726907,0.008289358,0.003515873,0.82036686,0.08266395],"study_design_scores_gemma":[0.0005612267,0.0003854333,0.0184629,0.00022130755,0.00017384667,0.0007145374,0.000087130284,0.8267508,0.029582214,0.011768171,0.11093543,0.00035703657],"about_ca_topic_score_codex":0.0059285313,"about_ca_topic_score_gemma":0.008289924,"teacher_disagreement_score":0.016052078,"about_ca_system_score_codex":0.0012656605,"about_ca_system_score_gemma":0.0027417252,"threshold_uncertainty_score":0.053699493},"labels":[],"label_agreement":null},{"id":"W2778042508","doi":"10.1186/s12859-017-1953-9","title":"HISEA: HIerarchical SEed Aligner for PacBio data","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Computer science; Computational biology; DNA microarray; Biology; Genetics; Gene; Gene expression","score_opus":0.06171987483104954,"score_gpt":0.3073502706344804,"score_spread":0.24563039580343085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2778042508","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0053230147,0.0010609777,0.51249576,0.00041546824,0.0004583883,0.0009488353,0.0790982,0.39090165,0.009297748],"genre_scores_gemma":[0.010268014,0.0004042031,0.8505724,0.00049756985,0.00007987796,0.0015118392,0.09880903,0.032152876,0.0057042455],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99838483,0.00025313423,0.00015900705,0.0005508019,0.00052986323,0.00012242698],"domain_scores_gemma":[0.99908423,0.00026186826,0.0001567865,0.00018657694,0.00022535241,0.00008521448],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002093419,0.0027360625,0.0017618445,0.0034346925,0.0014293069,0.0019956706,0.0034153324,0.0015628017,0.06347994],"category_scores_gemma":[0.004424469,0.0014909968,0.0014068345,0.0037996664,0.00057537184,0.001981435,0.001557261,0.0042661335,0.045663692],"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":[0.0017593802,0.00023759743,0.002426321,0.0023480002,0.00048206717,0.0007947212,0.00064690836,0.005332144,0.066828266,0.009617068,0.5816383,0.3278893],"study_design_scores_gemma":[0.0006233283,0.0002212824,0.0042894427,0.00026328355,0.00014101937,0.0009434371,0.00018223541,0.065107346,0.12148837,0.016895255,0.78956616,0.00027891548],"about_ca_topic_score_codex":0.002621613,"about_ca_topic_score_gemma":0.0036430869,"teacher_disagreement_score":0.06347994,"about_ca_system_score_codex":0.00092377723,"about_ca_system_score_gemma":0.0020623205,"threshold_uncertainty_score":0.21236151},"labels":[],"label_agreement":null},{"id":"W2783873704","doi":"10.1186/s12859-017-1996-y","title":"diceR: an R package for class discovery using an ensemble driven approach","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":62,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"BC Cancer Foundation","keywords":"Computer science; Dicer; Cluster analysis; Context (archaeology); Data mining; Set (abstract data type); Class (philosophy); Permutation (music); Generalization; Cluster (spacecraft); Machine learning; Artificial intelligence; Data science; Biology; Mathematics","score_opus":0.08579926171176273,"score_gpt":0.34100829396308385,"score_spread":0.25520903225132113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2783873704","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013707225,0.0010630309,0.8547183,0.00067263906,0.00055472355,0.00081600685,0.03219429,0.10616066,0.0024496529],"genre_scores_gemma":[0.013646309,0.0006818832,0.92482424,0.0007313746,0.0002745494,0.0047552823,0.021339044,0.031765163,0.0019821783],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.98375136,0.0075297314,0.001727452,0.0034001975,0.0031583044,0.0004330793],"domain_scores_gemma":[0.9297916,0.048568424,0.0048346166,0.008724692,0.0070000384,0.0010805819],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.023153238,0.003914279,0.0047044144,0.009180763,0.0022751638,0.0063226903,0.007729058,0.002847473,0.061650783],"category_scores_gemma":[0.10757555,0.003794423,0.0059009735,0.0066715917,0.0023406758,0.004112719,0.0063874405,0.0076840254,0.03254007],"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":[0.0010742848,0.00014672539,0.0074288487,0.0066146837,0.004286401,0.00059772795,0.0011298931,0.02779114,0.004328352,0.04227517,0.63740057,0.26692635],"study_design_scores_gemma":[0.0009468817,0.00023107047,0.005912778,0.0010664475,0.0014004378,0.001232554,0.0003029339,0.15832351,0.01158805,0.19554465,0.6228955,0.0005551748],"about_ca_topic_score_codex":0.004472909,"about_ca_topic_score_gemma":0.0065453704,"teacher_disagreement_score":0.061650783,"about_ca_system_score_codex":0.0016863173,"about_ca_system_score_gemma":0.007401756,"threshold_uncertainty_score":0.20624244},"labels":[],"label_agreement":null},{"id":"W2785096815","doi":"10.1186/s12859-018-2315-y","title":"bioSyntax: syntax highlighting for computational biology","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Genome British Columbia; University of Waterloo; Terry Fox Research Institute; University of British Columbia","funders":"Faculty of Medicine, University of British Columbia","keywords":"Legibility; Parsing; Computer science; Syntax; DECIPHER; Suite; Biological data; Programming language; Data science; Artificial intelligence; Bioinformatics; Biology","score_opus":0.19608345861600962,"score_gpt":0.42366593650439754,"score_spread":0.22758247788838792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2785096815","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022835454,0.0011623933,0.4129319,0.0015578292,0.0008109761,0.0005217671,0.045810405,0.5256542,0.009267014],"genre_scores_gemma":[0.028845252,0.0019617146,0.6325534,0.0023029912,0.0004916331,0.0028252546,0.10132848,0.2197062,0.009985071],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.995697,0.0012790276,0.0005725134,0.0009779766,0.0011352831,0.00033822985],"domain_scores_gemma":[0.9873412,0.007666154,0.00087426737,0.0019041627,0.0014476709,0.0007664787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008268493,0.004186488,0.0017758809,0.004357633,0.0019458547,0.0058257952,0.005147883,0.0023220268,0.08472561],"category_scores_gemma":[0.030542897,0.0028561144,0.0031098877,0.0040196422,0.0020780338,0.009095349,0.008054951,0.0058561647,0.05679828],"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":[0.0014761892,0.00014133376,0.00178729,0.0033196495,0.0002052403,0.0007172713,0.0012820004,0.0023753985,0.010774113,0.059127282,0.77465206,0.14414215],"study_design_scores_gemma":[0.0005291335,0.00012435303,0.0016351938,0.0014982217,0.00012537422,0.0008063096,0.00028812626,0.021637436,0.027512513,0.15585506,0.78965324,0.00033498128],"about_ca_topic_score_codex":0.0020086877,"about_ca_topic_score_gemma":0.001653147,"teacher_disagreement_score":0.08472561,"about_ca_system_score_codex":0.0015222201,"about_ca_system_score_gemma":0.0039763604,"threshold_uncertainty_score":0.2834354},"labels":[],"label_agreement":null},{"id":"W2792331414","doi":"10.1186/s12859-018-2391-z","title":"Valection: design optimization for validation and verification studies","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network; University of Toronto; Ontario Institute for Cancer Research","funders":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation; Prostate Cancer Canada; Government of Ontario; Canadian Institutes of Health Research; Genome Canada; National Cancer Institute; National Institutes of Health; Ontario Institute for Cancer Research; Terry Fox Research Institute; Movember Foundation","keywords":"Computer science; Software; Selection (genetic algorithm); Inference; Data mining; Machine learning; Artificial intelligence; Programming language","score_opus":0.09419023023291122,"score_gpt":0.3327364530797012,"score_spread":0.23854622284678995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2792331414","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004406358,0.000059177568,0.9906222,0.000058448317,0.000021319209,0.00013882355,0.00008743667,0.0035221698,0.0010841537],"genre_scores_gemma":[0.16136068,0.00009869419,0.83406293,0.00016610461,0.0000286444,0.0009386245,0.00040872546,0.0015946568,0.0013409174],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960573,0.0018815988,0.00022452015,0.00053925684,0.0010777441,0.00021958997],"domain_scores_gemma":[0.9881626,0.0084610805,0.00084675173,0.0011857157,0.0011684762,0.00017540563],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009349621,0.0021930982,0.0007798381,0.0012189925,0.00049004535,0.0011596545,0.0015972728,0.0010414831,0.0078230435],"category_scores_gemma":[0.022928597,0.0009091032,0.0014611245,0.00047004188,0.0012324831,0.0010173382,0.0019157003,0.0021112093,0.0016410579],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000704032,0.00021353549,0.0039338856,0.0006229305,0.000267252,0.0002819506,0.00022572993,0.71956336,0.020712757,0.025107747,0.0092077525,0.21915914],"study_design_scores_gemma":[0.000078516714,0.00022048905,0.00031179667,0.000061831925,0.000039240596,0.00009641708,0.000024341281,0.9696835,0.012459593,0.0121890055,0.0048151086,0.000020181382],"about_ca_topic_score_codex":0.0007930476,"about_ca_topic_score_gemma":0.0009384606,"teacher_disagreement_score":0.009349621,"about_ca_system_score_codex":0.0007622943,"about_ca_system_score_gemma":0.0018670381,"threshold_uncertainty_score":0.049446106},"labels":[],"label_agreement":null},{"id":"W2794562641","doi":"10.1186/s12859-018-2076-7","title":"NoLogo: a new statistical model highlights the diversity and suggests new classes of Crm1-dependent nuclear export signals","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Nuclear Structure and Function","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Representation (politics); Probabilistic logic; Computational biology; Statistical model; Generative model; Perspective (graphical); Nuclear export signal; Computer science; Generative grammar; Biology; Machine learning; Artificial intelligence; Genetics; RNA; Gene","score_opus":0.019934787242034534,"score_gpt":0.2360017211959825,"score_spread":0.21606693395394796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2794562641","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2579876,0.00057892624,0.7304307,0.0025274104,0.00016158412,0.00011117043,0.0018686428,0.0014815433,0.004852454],"genre_scores_gemma":[0.92772126,0.00042306862,0.060886737,0.0008895066,0.00018381092,0.00024404601,0.0020061042,0.00036546573,0.0072800377],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997329,0.00008089661,0.000008668736,0.00008635413,0.000046284582,0.000044900535],"domain_scores_gemma":[0.9990632,0.0005901652,0.00012618324,0.00007564567,0.00006203169,0.00008286023],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009460156,0.00058812427,0.0006885769,0.00082184,0.00050099206,0.0010354073,0.0015495621,0.0012155015,0.0027223208],"category_scores_gemma":[0.0024994034,0.00032105955,0.000942207,0.0004448326,0.0010771917,0.001281621,0.0009976004,0.0012507138,0.00067355856],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005422864,0.0002087632,0.028269552,0.00018249122,0.00015394585,0.000542363,0.00035367388,0.8298139,0.009677079,0.07298821,0.006611443,0.050656296],"study_design_scores_gemma":[0.000016206968,0.00003054464,0.0007590098,0.000008214953,0.000013510844,0.00006907594,0.0000148274985,0.98243976,0.0003278367,0.015180869,0.0011270505,0.000013145058],"about_ca_topic_score_codex":0.0057251686,"about_ca_topic_score_gemma":0.008930879,"teacher_disagreement_score":0.0057251686,"about_ca_system_score_codex":0.0010892297,"about_ca_system_score_gemma":0.001016832,"threshold_uncertainty_score":0.011383712},"labels":[],"label_agreement":null},{"id":"W2795167067","doi":"10.1186/s12859-018-2091-8","title":"Inferring RNA sequence preferences for poorly studied RNA-binding proteins based on co-evolution","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA Research and Splicing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of British Columbia Hospital","funders":"Natural Sciences and Engineering Research Council of Canada; Genome Canada","keywords":"RNA-binding protein; Computational biology; RNA; Sequence (biology); Biology; Computer science; Genetics; Gene","score_opus":0.060630971087458595,"score_gpt":0.3307538457633682,"score_spread":0.2701228746759096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2795167067","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5798699,0.0018883679,0.41346198,0.0002319592,0.00004567909,0.00014340518,0.0006944771,0.0012806847,0.002383448],"genre_scores_gemma":[0.8057777,0.000414789,0.19063549,0.00020955005,0.00003572119,0.00012850895,0.0015478987,0.00020530072,0.0010449652],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987852,0.00026835303,0.00007713413,0.0005004018,0.0002750679,0.00009381508],"domain_scores_gemma":[0.9979206,0.0010999151,0.00034665645,0.00021138268,0.00030659445,0.00011492917],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013781296,0.0010569994,0.0014210024,0.0024620746,0.00090033514,0.0007626644,0.0013400664,0.0014169876,0.00094696245],"category_scores_gemma":[0.0037228246,0.0004487072,0.0013003814,0.0017055221,0.00061739626,0.0009154873,0.00076443405,0.0009897324,0.00052549044],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011965698,0.0007632145,0.10960527,0.0007157047,0.0009572814,0.00082147913,0.00045102765,0.5574779,0.07486406,0.0032695166,0.0025533112,0.24732473],"study_design_scores_gemma":[0.0000123836035,0.000049186823,0.0039353906,0.000013148905,0.000055184904,0.00018573945,0.000032613698,0.9885872,0.00516804,0.0013803346,0.0005643432,0.000016402293],"about_ca_topic_score_codex":0.005405062,"about_ca_topic_score_gemma":0.008432193,"teacher_disagreement_score":0.005405062,"about_ca_system_score_codex":0.0008208632,"about_ca_system_score_gemma":0.0009942249,"threshold_uncertainty_score":0.010747194},"labels":[],"label_agreement":null},{"id":"W2797768225","doi":"10.1186/s12859-018-2106-5","title":"A hidden Markov tree model for testing multiple hypotheses corresponding to Gene Ontology gene sets","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","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":"University of Waterloo","funders":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; National Science Foundation","keywords":"Computational biology; Gene; DNA microarray; Tree (set theory); Genetics; Computer science; Gene ontology; Hidden Markov model; Markov chain; Markov model; Biology; Data mining; Artificial intelligence; Machine learning; Mathematics; Gene expression; Combinatorics","score_opus":0.047579954999098395,"score_gpt":0.27225235799392294,"score_spread":0.22467240299482455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2797768225","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01989648,0.00031057902,0.9767121,0.0005611634,0.000064907974,0.00013324604,0.00078748475,0.00055290764,0.0009812667],"genre_scores_gemma":[0.5482718,0.0006144361,0.4393054,0.00059873064,0.00033165934,0.0015967359,0.00436075,0.00034603276,0.004574549],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99543375,0.0025071132,0.00020021225,0.0010052085,0.00054984045,0.00030386253],"domain_scores_gemma":[0.9541453,0.041696675,0.0013859785,0.0010272628,0.0012261886,0.00051860313],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012022379,0.0011289185,0.0019833774,0.0020396332,0.0013230577,0.0019141356,0.0043096007,0.0026762572,0.007866317],"category_scores_gemma":[0.03438357,0.0011071876,0.002871531,0.002143438,0.0024316702,0.0035876895,0.0017828336,0.0033462797,0.0011370709],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007484253,0.00013648153,0.0073167887,0.000395197,0.0003612569,0.0005161498,0.00042909157,0.7276975,0.0019936208,0.20065333,0.0044275187,0.05532458],"study_design_scores_gemma":[0.00003848488,0.000030018593,0.00035752982,0.000019266172,0.000038349393,0.000051267456,0.000014318044,0.9091758,0.00021758552,0.08952736,0.0005152287,0.000014785938],"about_ca_topic_score_codex":0.0076310295,"about_ca_topic_score_gemma":0.0077115283,"teacher_disagreement_score":0.012022379,"about_ca_system_score_codex":0.0022994243,"about_ca_system_score_gemma":0.0028036465,"threshold_uncertainty_score":0.06358117},"labels":[],"label_agreement":null},{"id":"W2798055326","doi":"10.1186/s12859-018-2118-1","title":"Encompassing new use cases - level 3.0 of the HUPO-PSI format for molecular interactions","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":63,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University Health Network","funders":"FP7 Health; National Institute of General Medical Sciences; Biotechnology and Biological Sciences Research Council; National Institutes of Health; European Commission; Fondation pour la Recherche Médicale; Institut Français de Bioinformatique; EMBL Australia; British Heart Foundation; Wellcome Trust","keywords":"Computer science; Workgroup; XML; Suite; Data exchange; Collaboratory; Data format; Database; Information retrieval; World Wide Web","score_opus":0.09992559651893787,"score_gpt":0.30643933956922,"score_spread":0.2065137430502821,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2798055326","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010652629,0.00079678383,0.67679375,0.007332229,0.001562922,0.00269204,0.068919346,0.1898859,0.041364364],"genre_scores_gemma":[0.05041304,0.0015366799,0.5911991,0.0056921863,0.0009606303,0.0041233706,0.26446712,0.060459483,0.021148337],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97435117,0.005141927,0.007468439,0.0022624705,0.009105322,0.0016706341],"domain_scores_gemma":[0.9478771,0.015158404,0.0030313653,0.022585137,0.009476442,0.0018715871],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.035791103,0.0029046878,0.001862096,0.0066542244,0.002212442,0.014056588,0.007942854,0.005578965,0.028639514],"category_scores_gemma":[0.059833337,0.0032065636,0.003886248,0.0067836805,0.0029425386,0.019723626,0.0142907845,0.0099378675,0.024521433],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016205709,0.0005977705,0.011952134,0.0039577708,0.00023374264,0.0029035835,0.0048504616,0.005767767,0.015527562,0.24753734,0.5486569,0.15639454],"study_design_scores_gemma":[0.00011243945,0.000106165455,0.0016859235,0.00090786355,0.000055208493,0.0010569657,0.00040143935,0.009876099,0.013235661,0.0324367,0.9399401,0.00018553057],"about_ca_topic_score_codex":0.0054005804,"about_ca_topic_score_gemma":0.0030528537,"teacher_disagreement_score":0.035791103,"about_ca_system_score_codex":0.003921592,"about_ca_system_score_gemma":0.0050222627,"threshold_uncertainty_score":0.18928367},"labels":[],"label_agreement":null},{"id":"W2798884003","doi":"10.1186/s12859-018-2142-1","title":"Realizing drug repositioning by adapting a recommendation system to handle the process","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Türkiye Bilimsel ve Teknolojik Araştırma Kurumu","keywords":"Drug repositioning; Computer science; Process (computing); Machine learning; Risk analysis (engineering); Collaborative filtering; Data science; Drug discovery; Precision medicine; Drug; Data mining; Recommender system; Artificial intelligence; Bioinformatics; Medicine","score_opus":0.02224553199740555,"score_gpt":0.30394974581836304,"score_spread":0.2817042138209575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2798884003","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04687701,0.0007940578,0.93881714,0.00056079024,0.0001943088,0.00064607005,0.0005450107,0.0068895645,0.0046760766],"genre_scores_gemma":[0.25710046,0.00060948153,0.73612297,0.00035317236,0.00013909469,0.0003044976,0.0011381374,0.00012276701,0.0041093887],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99848807,0.00027388157,0.00020569435,0.00044078086,0.00043816183,0.00015343275],"domain_scores_gemma":[0.99713385,0.00086845603,0.0002013526,0.00064038404,0.0010330111,0.00012294066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018377003,0.0011661001,0.0013885822,0.0018382182,0.00095167663,0.00122657,0.0020893596,0.002425317,0.0032973504],"category_scores_gemma":[0.0040092156,0.00048551342,0.0014081313,0.0016522912,0.00034844063,0.0013689864,0.00064593455,0.001065085,0.0025057301],"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":[0.0004703985,0.0007938524,0.013077215,0.00048017557,0.00044320134,0.00061801996,0.00023998879,0.16427562,0.037083447,0.0030085798,0.0111045865,0.7684049],"study_design_scores_gemma":[0.00008014357,0.00016543521,0.002447937,0.000043224773,0.00020224362,0.00041664627,0.000073811854,0.97160363,0.01627564,0.0019665337,0.006653066,0.00007161873],"about_ca_topic_score_codex":0.024056876,"about_ca_topic_score_gemma":0.02405217,"teacher_disagreement_score":0.024056876,"about_ca_system_score_codex":0.0008066549,"about_ca_system_score_gemma":0.0022908691,"threshold_uncertainty_score":0.04783368},"labels":[],"label_agreement":null},{"id":"W2800043800","doi":"10.1186/s12859-018-2131-4","title":"On the rank-distance median of 3 permutations","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Fundação de Amparo à Pesquisa do Estado de São Paulo; Genome Canada; Alfred P. Sloan Foundation","keywords":"Combinatorics; Permutation (music); Mathematics; Median; Rank (graph theory); Distance matrix; Matrix (chemical analysis); Heuristic; Discrete mathematics; Algorithm; Mathematical optimization","score_opus":0.015539769042076981,"score_gpt":0.24492022515144965,"score_spread":0.22938045610937266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2800043800","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03677912,0.0002959548,0.95885473,0.00035331878,0.000055800134,0.000055261655,0.00022654793,0.00038403703,0.002995228],"genre_scores_gemma":[0.42692372,0.00056738534,0.56608665,0.00034231192,0.0002652988,0.00018203157,0.0009990887,0.0002535222,0.004379913],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99830866,0.00045585269,0.00009008443,0.00043517063,0.0005075615,0.00020270063],"domain_scores_gemma":[0.99285614,0.0049021016,0.00071467494,0.00058897206,0.00070659263,0.00023149561],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00176531,0.0009248679,0.0012594693,0.0014784145,0.00090937305,0.0017477535,0.0011511002,0.0013429059,0.005907304],"category_scores_gemma":[0.012621906,0.00049388054,0.0011127198,0.001958915,0.0018356792,0.002761588,0.0016831926,0.0020232226,0.0013361941],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00094502047,0.00020883998,0.0036231503,0.00032577734,0.00010237635,0.00035522642,0.0004277471,0.5609147,0.009315781,0.19973366,0.007472712,0.21657501],"study_design_scores_gemma":[0.00004115007,0.00015417853,0.00054110656,0.000043678836,0.000018371411,0.00023626858,0.000105369894,0.8274982,0.005672355,0.16186842,0.0037783652,0.000042553558],"about_ca_topic_score_codex":0.0022146408,"about_ca_topic_score_gemma":0.0015817371,"teacher_disagreement_score":0.005907304,"about_ca_system_score_codex":0.0012489442,"about_ca_system_score_gemma":0.0018174225,"threshold_uncertainty_score":0.01976186},"labels":[],"label_agreement":null},{"id":"W2801401057","doi":"10.1186/s12859-018-2066-9","title":"Pathway-based approach using hierarchical components of rare variants to analyze multiple phenotypes","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Korea Health Industry Development Institute; Ministry of Science, ICT and Future Planning; National Research Foundation","keywords":"Computational biology; Phenotype; Univariate; Missing heritability problem; Pathway analysis; Biology; Exome; Biological pathway; Exome sequencing; Bioinformatics; Computer science; Multivariate statistics; Genetics; Genetic variants; Gene; Genotype; Machine learning","score_opus":0.02683591815347687,"score_gpt":0.2506160568930316,"score_spread":0.22378013873955477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2801401057","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017978396,0.0005010411,0.9785472,0.00015849748,0.000042472653,0.00014955922,0.00094076653,0.0010862013,0.0005958102],"genre_scores_gemma":[0.3259452,0.0007244892,0.66819674,0.00012467518,0.00008319505,0.00051366823,0.0026169491,0.00020347473,0.001591651],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99929774,0.00022588216,0.000045300858,0.00021060076,0.0001613856,0.00005906723],"domain_scores_gemma":[0.998451,0.0009002814,0.00013194112,0.00015439537,0.00026188104,0.00010046756],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00131843,0.000952116,0.00092840387,0.0032952512,0.00058001373,0.001037294,0.0011202183,0.000567624,0.0035210738],"category_scores_gemma":[0.0037172928,0.00030719608,0.0022070652,0.0031747175,0.00038936254,0.00068385946,0.0010614455,0.0010083632,0.0005502016],"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":[0.0010845024,0.000527785,0.04545738,0.0013697412,0.0026525187,0.0014941313,0.00049712724,0.37953722,0.028930895,0.047828656,0.006327962,0.48429212],"study_design_scores_gemma":[0.000072873954,0.0001023922,0.005695999,0.00003569273,0.0003969844,0.0003087495,0.000068438705,0.950221,0.002906087,0.03643114,0.0037060312,0.000054553995],"about_ca_topic_score_codex":0.00907658,"about_ca_topic_score_gemma":0.009548237,"teacher_disagreement_score":0.00907658,"about_ca_system_score_codex":0.000609158,"about_ca_system_score_gemma":0.0024285598,"threshold_uncertainty_score":0.018047512},"labels":[],"label_agreement":null},{"id":"W2801476357","doi":"10.1186/s12859-018-2146-x","title":"Prediction of microRNA-disease associations based on distance correlation set","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Cancer-related molecular mechanisms research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"Construct Program of the Key Discipline in Hunan Province; Xiangtan University; National Natural Science Foundation of China","keywords":"Correlation; microRNA; DNA microarray; Computational biology; Set (abstract data type); Biology; Disease; Computer science; Bioinformatics; Genetics; Mathematics; Medicine; Gene; Pathology; Gene expression","score_opus":0.022365185662987383,"score_gpt":0.2693788444475479,"score_spread":0.2470136587845605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2801476357","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.56589854,0.0012425935,0.42510253,0.00046741375,0.000080149985,0.00033887944,0.002743619,0.0017137117,0.0024125965],"genre_scores_gemma":[0.87681884,0.00023842335,0.11915968,0.00010288412,0.000044493187,0.0003080359,0.0028802853,0.00003949396,0.0004078408],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983576,0.00050736876,0.00019128752,0.0004240792,0.0004281208,0.00009164728],"domain_scores_gemma":[0.9925256,0.0055248677,0.0007125189,0.0003364117,0.00069643505,0.00020423609],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022784176,0.0009513824,0.0010664769,0.0039020367,0.0006000872,0.00087974116,0.00097177475,0.0007828227,0.0015359268],"category_scores_gemma":[0.007835088,0.00031163442,0.0017549301,0.0018081865,0.00046336357,0.00058937137,0.0010980933,0.0009586809,0.00045055797],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010691119,0.0007384738,0.20298235,0.00049127627,0.0012130261,0.0009991103,0.00017659696,0.56559265,0.0088303285,0.0035901673,0.0044439575,0.20987292],"study_design_scores_gemma":[0.000028440263,0.000095306976,0.0073461994,0.000015384128,0.0000668782,0.00024266617,0.00001840872,0.98877406,0.0014728354,0.0014948277,0.00042883336,0.00001620187],"about_ca_topic_score_codex":0.0035704768,"about_ca_topic_score_gemma":0.0035670397,"teacher_disagreement_score":0.0039020367,"about_ca_system_score_codex":0.0007063736,"about_ca_system_score_gemma":0.0016166444,"threshold_uncertainty_score":0.012049556},"labels":[],"label_agreement":null},{"id":"W2803405718","doi":"10.1186/s12859-018-2184-4","title":"Visualizing histopathologic deep learning classification and anomaly detection using nonlinear feature space dimensionality reduction","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":69,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network; University of Toronto","funders":"Brain Tumour Foundation of Canada; Brain Tumour Research; Nvidia","keywords":"Dimensionality reduction; Anomaly detection; Artificial intelligence; Pattern recognition (psychology); Feature (linguistics); Computer science; Nonlinear dimensionality reduction; Anomaly (physics); Reduction (mathematics); Feature vector; Space (punctuation); Curse of dimensionality; Physics; Mathematics","score_opus":0.03943739908664989,"score_gpt":0.2879302342849939,"score_spread":0.24849283519834403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2803405718","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1028299,0.0008982992,0.8688935,0.0021555098,0.00016822104,0.00014304796,0.003590052,0.015678925,0.005642467],"genre_scores_gemma":[0.41421825,0.0007050346,0.57730883,0.0003494719,0.000102707956,0.00018095874,0.0018593709,0.0015303893,0.0037449657],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99948186,0.00014817546,0.00004051981,0.00009528556,0.00019347445,0.00004076209],"domain_scores_gemma":[0.997511,0.0010675812,0.00045322767,0.00033128564,0.00051474664,0.00012210668],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001736406,0.0006959739,0.00029084884,0.0026947418,0.00028101492,0.0016149728,0.00066866825,0.0007383733,0.0067452514],"category_scores_gemma":[0.0045917183,0.00029924265,0.00054692745,0.000961544,0.0005379525,0.0009206297,0.0010507125,0.0010061978,0.0011659103],"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":[0.0007349897,0.00016234469,0.024164867,0.0016741463,0.00019548679,0.0011219659,0.001993777,0.111638136,0.19842985,0.052639857,0.04296863,0.564276],"study_design_scores_gemma":[0.000057388435,0.00017861731,0.02142793,0.00035804685,0.00007506494,0.001411011,0.0006924545,0.7105733,0.15087774,0.06673916,0.047456555,0.00015275906],"about_ca_topic_score_codex":0.0014674132,"about_ca_topic_score_gemma":0.0024098102,"teacher_disagreement_score":0.0067452514,"about_ca_system_score_codex":0.00074107177,"about_ca_system_score_gemma":0.00090175477,"threshold_uncertainty_score":0.022565126},"labels":[],"label_agreement":null},{"id":"W2805544673","doi":"10.1186/s12859-018-2185-3","title":"Robust joint score tests in the application of DNA methylation data analysis","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Epigenetics and DNA Methylation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Outlier; Statistics; DNA methylation; Power analysis; Mathematics; Statistical power; Biology; Algorithm; Genetics; Gene; Gene expression","score_opus":0.08401537177493584,"score_gpt":0.3076311488138606,"score_spread":0.22361577703892477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2805544673","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023385476,0.00093359797,0.9732046,0.00029093583,0.000110511595,0.00021902865,0.00037113318,0.0008341324,0.0006505648],"genre_scores_gemma":[0.48057437,0.0006711311,0.51367646,0.00039338967,0.0003470705,0.0013560113,0.0015382877,0.00042482297,0.0010185002],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.93925124,0.043270092,0.002588795,0.007171603,0.0069341087,0.0007841404],"domain_scores_gemma":[0.7285935,0.23633008,0.010750643,0.014254247,0.008770509,0.0013009122],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06445107,0.0020661918,0.0030262074,0.0050448445,0.0009960135,0.0028576318,0.004511807,0.0024895237,0.0029921473],"category_scores_gemma":[0.22140202,0.0009330462,0.0042405864,0.0056736083,0.0042831292,0.0032084726,0.004369417,0.004739807,0.0008696793],"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":[0.002188619,0.00042542737,0.09432792,0.0018786783,0.0054533985,0.0009551653,0.00083408906,0.30538133,0.007498284,0.09123883,0.004962128,0.48485616],"study_design_scores_gemma":[0.00027159727,0.00097089645,0.01834588,0.00014502519,0.000621281,0.0004297532,0.00014468025,0.8450409,0.006369387,0.12256459,0.00491049,0.00018550985],"about_ca_topic_score_codex":0.002625602,"about_ca_topic_score_gemma":0.0014842453,"teacher_disagreement_score":0.06445107,"about_ca_system_score_codex":0.0013437964,"about_ca_system_score_gemma":0.002947561,"threshold_uncertainty_score":0.34085393},"labels":[],"label_agreement":null},{"id":"W2806785716","doi":"10.1186/s12859-018-2202-6","title":"Correction to: Identification and characterization of conserved lncRNAs in human and rat brain","year":2018,"lang":"en","type":"erratum","venue":"BMC Bioinformatics","topic":"Cancer-related molecular mechanisms research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of General Medical Sciences; National Institutes of Health; Hamilton Health Sciences Foundation; National Institute for Health and Care Research","keywords":"Statement (logic); Acknowledgement; Identification (biology); Computational biology; Computer science; DNA microarray; Bioinformatics; Information retrieval; Data science; Natural language processing; Biology; Genetics; Linguistics; Philosophy; Gene; Ecology; Computer security","score_opus":0.012937076468085007,"score_gpt":0.2772080472680571,"score_spread":0.2642709707999721,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2806785716","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003798288,0.0010266122,0.002079694,0.058025964,0.93336636,0.00002592497,0.0022035753,0.00079974224,0.0020922306],"genre_scores_gemma":[0.026367454,0.012066951,0.020011602,0.15833838,0.4630867,0.00031324162,0.012340226,0.006429888,0.3010455],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965044,0.0004588792,0.0006761265,0.0005022083,0.0015847851,0.0002735495],"domain_scores_gemma":[0.97033405,0.008411631,0.001649017,0.0015878357,0.016712692,0.0013047641],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0030308994,0.0018717437,0.0014573794,0.0031860722,0.0023244547,0.002712148,0.0026354338,0.0044651334,0.04877727],"category_scores_gemma":[0.052640256,0.00085547747,0.0014234803,0.0020017733,0.0020065955,0.0020495679,0.002090964,0.008515115,0.03319752],"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":[0.00006672277,0.0000098793735,0.00011125633,0.00017580115,0.0000138806,0.00044033106,0.000049231938,0.00005679037,0.00018885531,0.00058361015,0.99100494,0.00729861],"study_design_scores_gemma":[0.00003771713,0.000033608652,0.0007330126,0.00037298515,0.000050034076,0.0015028027,0.00008879876,0.00027949034,0.0008669791,0.0014240099,0.994558,0.0000525508],"about_ca_topic_score_codex":0.010596514,"about_ca_topic_score_gemma":0.009758629,"teacher_disagreement_score":0.99553484,"about_ca_system_score_codex":0.0026603509,"about_ca_system_score_gemma":0.004442462,"threshold_uncertainty_score":0.16317624},"labels":[],"label_agreement":null},{"id":"W2811242925","doi":"10.1186/s12859-018-2255-6","title":"BROCKMAN: deciphering variance in epigenomic regulators by k-mer factorization","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Human Genome Research Institute; Howard Hughes Medical Institute","keywords":"Epigenomics; Variance (accounting); Computational biology; Computer science; Biology; Bioinformatics; Genetics; Business; DNA methylation; Gene; Gene expression","score_opus":0.006188141073960664,"score_gpt":0.2146536632581338,"score_spread":0.20846552218417314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2811242925","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028663449,0.00068221847,0.96581894,0.00022033112,0.000059520866,0.00006918759,0.0017292892,0.0019624494,0.00079458393],"genre_scores_gemma":[0.26540887,0.00082205475,0.72298926,0.00030035674,0.00015515338,0.00041601856,0.0056630746,0.001054893,0.0031902955],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991677,0.0002151057,0.000041805662,0.00031169318,0.00016724163,0.00009649627],"domain_scores_gemma":[0.9979867,0.0009841942,0.0003175347,0.00037640956,0.00022026263,0.000114953895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002101411,0.0007867672,0.00082702725,0.0017017793,0.0005840929,0.0010460907,0.0011850935,0.0009011071,0.003280073],"category_scores_gemma":[0.00613049,0.0005889575,0.001287915,0.0012633433,0.0010114845,0.0013215162,0.00088815944,0.001352472,0.001362326],"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":[0.0016105613,0.00023450998,0.02317328,0.0011618823,0.00055042753,0.00049875875,0.0010995923,0.20453122,0.18905221,0.09904157,0.021106053,0.4579399],"study_design_scores_gemma":[0.000064198,0.00012886823,0.009580959,0.000087804096,0.00007248776,0.00024383585,0.000114724186,0.8610583,0.02096333,0.09165025,0.015940337,0.00009495218],"about_ca_topic_score_codex":0.004878984,"about_ca_topic_score_gemma":0.006485141,"teacher_disagreement_score":0.004878984,"about_ca_system_score_codex":0.0007100513,"about_ca_system_score_gemma":0.001109715,"threshold_uncertainty_score":0.011113405},"labels":[],"label_agreement":null},{"id":"W2811465744","doi":"10.1186/s12859-018-2258-3","title":"Correction to: Realizing drug repositioning by adapting a recommendation system to handle the process","year":2018,"lang":"en","type":"erratum","venue":"BMC Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Process (computing); Drug repositioning; Drug; Information retrieval; Data science; World Wide Web; Computational biology; Medicine; Biology; Pharmacology; Programming language","score_opus":0.01998176224378667,"score_gpt":0.30039261567210024,"score_spread":0.28041085342831357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2811465744","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00021238124,0.0008826791,0.0025201712,0.07541912,0.9154149,0.00003095915,0.0017912321,0.00089200406,0.0028365436],"genre_scores_gemma":[0.026704319,0.012891352,0.029437091,0.21255435,0.38917008,0.00036668504,0.0082240105,0.0047921054,0.31585997],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9929575,0.0009060507,0.001344349,0.00096257747,0.003301209,0.0005283611],"domain_scores_gemma":[0.9440669,0.014731053,0.002890394,0.0033769484,0.032963496,0.0019712602],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0051309434,0.0025877836,0.0019512186,0.0037691128,0.0036484285,0.003955289,0.0038774123,0.008002998,0.052120488],"category_scores_gemma":[0.09071047,0.001198064,0.0017211017,0.0032011473,0.0028493092,0.0026285294,0.0024794303,0.011678466,0.045651693],"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":[0.0000372188,0.000009090152,0.00006761213,0.00010679949,0.000011618524,0.00034536715,0.00003993527,0.00007847049,0.00006064383,0.0010426778,0.9916367,0.0065638507],"study_design_scores_gemma":[0.0000424709,0.000031739957,0.00038971033,0.000343778,0.000035058365,0.0010268034,0.00009016609,0.00059870305,0.0005757458,0.002085859,0.99473155,0.000048550814],"about_ca_topic_score_codex":0.019415611,"about_ca_topic_score_gemma":0.019782288,"teacher_disagreement_score":0.052120488,"about_ca_system_score_codex":0.005076011,"about_ca_system_score_gemma":0.007966271,"threshold_uncertainty_score":0.1743604},"labels":[],"label_agreement":null},{"id":"W2883667799","doi":"10.1186/s12859-018-2251-x","title":"An integrative network-based approach to identify novel disease genes and pathways: a case study in the context of inflammatory bowel disease","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; George & Fay Yee Centre for Healthcare Innovation","funders":"Mitacs; Nara Institute of Science and Technology; Research Manitoba; Health Sciences Centre Foundation","keywords":"Inflammatory bowel disease; Context (archaeology); Disease; DNA microarray; Computational biology; Gene; Gene regulatory network; Bioinformatics; Biology; Medicine; Genetics; Gene expression; Pathology","score_opus":0.022723043864488365,"score_gpt":0.2716813573990211,"score_spread":0.24895831353453274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2883667799","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67849374,0.004855537,0.29154146,0.0048104282,0.00010559165,0.00069442997,0.0030356252,0.0010244611,0.015438719],"genre_scores_gemma":[0.75862527,0.0020799178,0.234784,0.00024904244,0.000050101764,0.00020075594,0.0016260995,0.00009353236,0.0022912505],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99948883,0.00023562594,0.000025514646,0.00009787612,0.000109325614,0.000042779262],"domain_scores_gemma":[0.99892765,0.000718587,0.00008320768,0.0000777072,0.00010811111,0.000084701256],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011072024,0.00051667594,0.00029516302,0.0020810103,0.0007781212,0.0009155047,0.000681742,0.00082930666,0.0028144673],"category_scores_gemma":[0.0025267978,0.00014717037,0.0007060879,0.0016244999,0.0005171169,0.0007181844,0.00080080586,0.0006443761,0.00030897307],"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":[0.0011847123,0.001013139,0.2295995,0.0023069803,0.000703554,0.08486199,0.0066985227,0.07300458,0.033905953,0.038111564,0.015882852,0.51272666],"study_design_scores_gemma":[0.00020781597,0.0008171987,0.1158855,0.0007887139,0.0012533679,0.089974426,0.009371857,0.5789745,0.023857586,0.07572446,0.10295926,0.00018537077],"about_ca_topic_score_codex":0.0030837054,"about_ca_topic_score_gemma":0.006839193,"teacher_disagreement_score":0.0030837054,"about_ca_system_score_codex":0.0007858872,"about_ca_system_score_gemma":0.0006285725,"threshold_uncertainty_score":0.0094153285},"labels":[],"label_agreement":null},{"id":"W2886919764","doi":"10.1186/s12859-019-2737-1","title":"Multiscale modeling reveals angiogenesis-induced drug resistance in brain tumors and predicts a synergistic drug combination targeting EGFR and VEGFR pathways","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Mathematical Biology Tumor Growth","field":"Mathematics","cited_by":30,"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":"Guangdong Province Key Laboratory of Computational Science; Sun Yat-sen University; National Natural Science Foundation of China; York University","keywords":"Angiogenesis; Drug; Drug resistance; VEGF receptors; Cancer research; EGFR inhibitors; DNA microarray; Computational biology; Epidermal growth factor receptor; Biology; Medicine; Bioinformatics; Pharmacology; Receptor; Genetics; Gene; Gene expression","score_opus":0.026850568775776608,"score_gpt":0.2511634707739949,"score_spread":0.22431290199821832,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2886919764","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82925916,0.000871398,0.16285099,0.0005653526,0.00007710865,0.00006498874,0.0003146409,0.00035435337,0.0056421054],"genre_scores_gemma":[0.98885214,0.00027692734,0.01000682,0.0000357471,0.000011049207,0.00005660872,0.00007303808,0.00002257084,0.00066503615],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99993145,0.000011913741,0.0000045008387,0.00001645312,0.000017939872,0.000017607903],"domain_scores_gemma":[0.99986887,0.00005703168,0.00003434257,0.000009276248,0.000015500149,0.000014977969],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014894936,0.0005337801,0.0005111266,0.000427704,0.00019583743,0.00038840162,0.00049060874,0.0009087663,0.00057782873],"category_scores_gemma":[0.00041002632,0.0002639264,0.00096852944,0.00021971486,0.00036612942,0.0003223861,0.00035952168,0.00033442202,0.00006858226],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025542866,0.00003296568,0.0011581614,0.000029011511,0.00001907503,0.00013728117,0.000017426017,0.978434,0.0168682,0.0013557193,0.000114164366,0.0018084204],"study_design_scores_gemma":[0.0000024930519,0.000008650331,0.00018028195,9.764738e-7,0.000004341636,0.0000107036585,0.0000019932909,0.9990043,0.000539158,0.00018494025,0.000059900158,0.0000023452799],"about_ca_topic_score_codex":0.00648507,"about_ca_topic_score_gemma":0.0032413276,"teacher_disagreement_score":0.00648507,"about_ca_system_score_codex":0.0006581656,"about_ca_system_score_gemma":0.0006042007,"threshold_uncertainty_score":0.01289463},"labels":[],"label_agreement":null},{"id":"W2889813947","doi":"10.1186/s12859-018-2350-8","title":"SuperNoder: a tool to discover over-represented modular structures in networks","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"York University; Università degli Studi di Cagliari; National Science Foundation","keywords":"Computer science; Network motif; Disjoint sets; Modular design; Theoretical computer science; Motif (music); Network analysis; Artificial intelligence; Complex network; Data mining; World Wide Web; Mathematics","score_opus":0.008945370019507059,"score_gpt":0.2444919388931529,"score_spread":0.23554656887364583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889813947","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011911871,0.0005342648,0.8599592,0.0002824027,0.00009822698,0.00020012159,0.00919731,0.11572301,0.0020935382],"genre_scores_gemma":[0.057514213,0.0006433621,0.9135466,0.00013367124,0.00005336358,0.00056124135,0.018563032,0.006740404,0.0022441482],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992275,0.00021187722,0.000076837976,0.00022200414,0.00021879899,0.000042990087],"domain_scores_gemma":[0.99576217,0.0032045264,0.00027687292,0.00040533798,0.00021782446,0.00013339007],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002065814,0.002448506,0.0012018478,0.0054317764,0.0009930213,0.0023128309,0.0024571142,0.001484446,0.015449309],"category_scores_gemma":[0.009938553,0.0016083975,0.0022706771,0.0028405397,0.000822783,0.0034114833,0.0025306141,0.0017923096,0.004409464],"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":[0.0012282309,0.00043227995,0.018040977,0.005124867,0.00123849,0.002390922,0.0019688564,0.16062276,0.033044063,0.06110762,0.15513395,0.559667],"study_design_scores_gemma":[0.0001896325,0.00012893318,0.0020928557,0.00029162987,0.00016162299,0.0010654461,0.00023966626,0.8276298,0.013038099,0.08696854,0.06810534,0.00008837859],"about_ca_topic_score_codex":0.001786687,"about_ca_topic_score_gemma":0.004424671,"teacher_disagreement_score":0.015449309,"about_ca_system_score_codex":0.0008093586,"about_ca_system_score_gemma":0.0012495855,"threshold_uncertainty_score":0.051683128},"labels":[],"label_agreement":null},{"id":"W2896411685","doi":"10.1186/s12859-018-2286-z","title":"Dense neural networks for predicting chromatin conformation","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","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":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Fondation pour la Recherche Médicale","keywords":"Chromatin; Sequence (biology); Computer science; Histone; Computational biology; Convolutional neural network; Nucleosome; ChIA-PET; Artificial neural network; Algorithm; DNA; Biological system; Biology; Artificial intelligence; Genetics","score_opus":0.010213924458796984,"score_gpt":0.23309639881696703,"score_spread":0.22288247435817005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2896411685","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35372454,0.0024737357,0.6347968,0.001576729,0.00014907475,0.00015911646,0.001183547,0.0023338727,0.0036026037],"genre_scores_gemma":[0.9188449,0.0004511352,0.075946964,0.00028037175,0.00007727433,0.0001710206,0.0016422762,0.00006395731,0.002522204],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999723,0.00008169965,0.000016165312,0.00007802641,0.000057159916,0.000043837394],"domain_scores_gemma":[0.9977354,0.0017040839,0.00015148321,0.000089239424,0.00026283736,0.00005693116],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010356595,0.0009647925,0.0005835223,0.00086639286,0.00029273526,0.0006109096,0.0011667452,0.0013543979,0.0016835332],"category_scores_gemma":[0.0050605005,0.00054528343,0.00044912595,0.0007307491,0.00062468724,0.00092158245,0.0006281126,0.0014005502,0.0003094362],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006506283,0.000047570302,0.0011303275,0.000036678975,0.00003254952,0.000022836346,0.00001397022,0.9754318,0.000628612,0.00096750015,0.0005194328,0.021103743],"study_design_scores_gemma":[0.0000018045803,0.000004953128,0.00008771679,0.0000020996117,0.0000016416043,0.000001729764,0.0000014275691,0.9989869,0.00016192779,0.000716458,0.000032363354,9.459595e-7],"about_ca_topic_score_codex":0.014005985,"about_ca_topic_score_gemma":0.013747305,"teacher_disagreement_score":0.014005985,"about_ca_system_score_codex":0.0015433208,"about_ca_system_score_gemma":0.0007282916,"threshold_uncertainty_score":0.027848959},"labels":[],"label_agreement":null},{"id":"W2899194228","doi":"10.1186/s12859-018-2430-9","title":"A comparative study of survival models for breast cancer prognostication revisited: the benefits of multi-gene models","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Ferroptosis and cancer prognosis","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research","funders":"Canadian Institutes of Health Research; Government of Ontario; Terry Fox Research Institute; Ontario Institute for Cancer Research","keywords":"Breast cancer; Computational biology; DNA microarray; Gene; Biology; Bioinformatics; Computer science; Cancer; Gene expression; Genetics","score_opus":0.13615996009016712,"score_gpt":0.3501244586300445,"score_spread":0.21396449853987737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2899194228","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69684345,0.021212839,0.26487675,0.009842842,0.00043755246,0.00020975665,0.0025909543,0.0006950497,0.0032907636],"genre_scores_gemma":[0.96889883,0.0017418368,0.026550053,0.00054660015,0.00024083033,0.00007487697,0.0012798741,0.00011804135,0.0005491203],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99143887,0.0066168695,0.00025659078,0.001022564,0.00048826064,0.00017681907],"domain_scores_gemma":[0.916952,0.07518731,0.0022169466,0.0032776564,0.0015399735,0.00082615117],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03511232,0.0016941378,0.002038266,0.0030654343,0.00058221095,0.0020864843,0.001650842,0.0014111062,0.0015658522],"category_scores_gemma":[0.054890692,0.00038506696,0.0037401859,0.002065368,0.0010663022,0.0022122208,0.0013416876,0.0020778568,0.00035915856],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022395698,0.00022610743,0.14330815,0.00056489627,0.004868635,0.00026908703,0.0004321219,0.7464672,0.00074769283,0.012470808,0.0032910143,0.08511465],"study_design_scores_gemma":[0.00009641337,0.0006754063,0.01832421,0.00012995557,0.00069352717,0.00020589674,0.00016564413,0.9490253,0.00033283827,0.028954752,0.0013347423,0.000061360966],"about_ca_topic_score_codex":0.004769393,"about_ca_topic_score_gemma":0.004186999,"teacher_disagreement_score":0.03511232,"about_ca_system_score_codex":0.0018319077,"about_ca_system_score_gemma":0.0013638729,"threshold_uncertainty_score":0.18569392},"labels":[],"label_agreement":null},{"id":"W2899264342","doi":"10.1186/s12859-018-2363-3","title":"Cluster oligonucleotide signatures for rapid identification by sequencing","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Food Inspection Agency; Agriculture and Agri-Food Canada","funders":"Agriculture and Agri-Food Canada","keywords":"Computational biology; In silico; DNA sequencing; Biology; Identification (biology); DNA microarray; Oligonucleotide; Pipeline (software); Phylogenetic tree; Sequence (biology); Cluster analysis; Genetics; Computer science; DNA; Gene; Artificial intelligence","score_opus":0.01587598900723189,"score_gpt":0.24672767650827784,"score_spread":0.23085168750104595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2899264342","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008535115,0.0005173655,0.9429982,0.00015917895,0.0001414331,0.00037175944,0.0057885544,0.039114185,0.002374199],"genre_scores_gemma":[0.028235689,0.00018777564,0.9600243,0.00017537887,0.000035836412,0.0007469659,0.0063361055,0.0025391472,0.0017188237],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9970843,0.00056976953,0.00028630884,0.00089347275,0.0009859194,0.00018019839],"domain_scores_gemma":[0.9961056,0.0015292892,0.0005296276,0.00067274575,0.0009671112,0.00019565408],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024998423,0.0016314082,0.0011723964,0.0026730937,0.00077547116,0.0016768873,0.0015338799,0.0012976632,0.015654374],"category_scores_gemma":[0.010205807,0.0010829247,0.0012689105,0.0023799671,0.00065008784,0.0014454667,0.0018331019,0.0016617292,0.011710629],"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":[0.002410278,0.00021699353,0.003974823,0.0023833169,0.00029896197,0.00040184578,0.0006095233,0.01662254,0.3077191,0.021448482,0.05169779,0.59221643],"study_design_scores_gemma":[0.0002481067,0.0005164068,0.003461294,0.00029499806,0.00016906728,0.0011576442,0.00021467093,0.34219489,0.44600877,0.04088092,0.16460668,0.00024660706],"about_ca_topic_score_codex":0.0011090919,"about_ca_topic_score_gemma":0.0014326022,"teacher_disagreement_score":0.015654374,"about_ca_system_score_codex":0.0009901107,"about_ca_system_score_gemma":0.0016909344,"threshold_uncertainty_score":0.052369118},"labels":[],"label_agreement":null},{"id":"W2900916532","doi":"10.1186/s12859-018-2378-9","title":"The predictive performance of short-linear motif features in the prediction of calmodulin-binding proteins","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada; University of Windsor","keywords":"Calmodulin; Motif (music); Computational biology; DNA microarray; Calmodulin-binding proteins; Bioinformatics; Biology; Computer science; Genetics; Biochemistry; Gene; Gene expression","score_opus":0.012059938183981482,"score_gpt":0.2541088111200603,"score_spread":0.2420488729360788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2900916532","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9570683,0.0025624956,0.037102412,0.00014940648,0.000070122114,0.000054284334,0.0013826323,0.00078801735,0.00082220056],"genre_scores_gemma":[0.98900235,0.00018836945,0.008830231,0.000022027165,0.000026673037,0.000028500215,0.0016713208,0.00001701605,0.00021348332],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99961567,0.000094562296,0.0000340804,0.00011112915,0.00009088115,0.000053651747],"domain_scores_gemma":[0.99711215,0.0020420132,0.0002286717,0.000099846315,0.00039281632,0.00012438608],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001550624,0.0007506026,0.0006232027,0.001732416,0.00024920853,0.00046500826,0.00048824417,0.00059324206,0.0010053229],"category_scores_gemma":[0.0036590814,0.00012277582,0.000602171,0.0009584863,0.00020366686,0.0004536681,0.0003496962,0.0006080293,0.00042233657],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002160043,0.0008775503,0.25454995,0.0004382317,0.0005855258,0.0003498469,0.000071262555,0.37979603,0.017413335,0.0004077741,0.006063378,0.33728704],"study_design_scores_gemma":[0.000021170887,0.00014740114,0.017524248,0.0000150754195,0.000036027217,0.00006838199,0.000013163392,0.979117,0.0026195142,0.00022460242,0.00020372517,0.000009779927],"about_ca_topic_score_codex":0.0045644757,"about_ca_topic_score_gemma":0.0031592606,"teacher_disagreement_score":0.0045644757,"about_ca_system_score_codex":0.00032543368,"about_ca_system_score_gemma":0.00037161156,"threshold_uncertainty_score":0.00907582},"labels":[],"label_agreement":null},{"id":"W2902011814","doi":"10.1186/s12859-018-2501-y","title":"SMuRF: a novel tool to identify regulatory elements enriched for somatic point mutations","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research; Princess Margaret Cancer Centre; University Health Network","funders":"Institute of Cancer Research; Prostate Cancer Canada; Government of Canada; Ontario Institute for Cancer Research; American Association for Cancer Research; Movember Foundation; Princess Margaret Cancer Foundation; Canadian Institutes of Health Research; Genome Canada; Stand Up To Cancer; Entertainment Industry Foundation; Government of Ontario","keywords":"Biology; Genetics; Point mutation; Computational biology; Gene; Context (archaeology); Mutation; Somatic cell; DNA microarray; Single-nucleotide polymorphism; Identification (biology); Genome; Gene expression; Genotype","score_opus":0.01517129533268553,"score_gpt":0.2824969322047588,"score_spread":0.2673256368720733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2902011814","genre_codex":"software","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038058367,0.0034661216,0.25496835,0.0007120248,0.0004419543,0.00045519858,0.15004238,0.54666543,0.005190253],"genre_scores_gemma":[0.21778905,0.0019852712,0.49426714,0.0014353858,0.00037633962,0.0030917733,0.21020247,0.06469433,0.0061582406],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987367,0.00021239248,0.00010617076,0.00046365566,0.00033733054,0.00014383478],"domain_scores_gemma":[0.99758756,0.0016382524,0.00030419487,0.00017667715,0.00016060486,0.00013269634],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024834825,0.003578491,0.0020929768,0.0076017277,0.0013626122,0.0016824332,0.0035929573,0.002227531,0.03416583],"category_scores_gemma":[0.0094026085,0.0014310183,0.0031685818,0.0033678608,0.0008388043,0.001898273,0.0025095923,0.0015574953,0.0124714635],"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":[0.004138452,0.00044987124,0.034073632,0.0089834705,0.0017484031,0.0048835087,0.002399406,0.01961778,0.07025702,0.011021394,0.55050987,0.2919172],"study_design_scores_gemma":[0.0027603665,0.0008285204,0.03347987,0.0011756595,0.0009875859,0.008454268,0.0006755392,0.3109031,0.11454656,0.047109954,0.4782999,0.0007787297],"about_ca_topic_score_codex":0.003190899,"about_ca_topic_score_gemma":0.0041282554,"teacher_disagreement_score":0.03416583,"about_ca_system_score_codex":0.0010537956,"about_ca_system_score_gemma":0.0015836648,"threshold_uncertainty_score":0.11429608},"labels":[],"label_agreement":null},{"id":"W2902892882","doi":"10.1186/s12859-018-2499-1","title":"Integrated genome sizing (IGS) approach for the parallelization of whole genome analysis","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bioinformatics Solutions (Canada)","funders":"INNOPOLIS Foundation; Korea Health Industry Development Institute","keywords":"Genome; Computer science; Reference genome; Whole genome sequencing; Leverage (statistics); Computational biology; Genome project; DNA sequencing; Biology; Genetics; Gene; Artificial intelligence","score_opus":0.024951918293970355,"score_gpt":0.24383852589272173,"score_spread":0.21888660759875136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2902892882","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036294438,0.00046747806,0.94222176,0.00018349368,0.00011414089,0.0001465299,0.0010548377,0.01696354,0.002553735],"genre_scores_gemma":[0.084504046,0.00015130398,0.9105097,0.00008803408,0.000028805463,0.00022861017,0.002301875,0.00088521326,0.0013024467],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993345,0.0001253293,0.000053996173,0.00019991976,0.00022385361,0.000062397456],"domain_scores_gemma":[0.99924755,0.00027171065,0.000078759826,0.00017605472,0.00018182876,0.000044155153],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006993608,0.001010117,0.00063473044,0.0012660633,0.0005004668,0.0008953857,0.0010211227,0.0004731987,0.0053860773],"category_scores_gemma":[0.0017040174,0.00041722864,0.0012280366,0.0018618053,0.0004150482,0.00064619345,0.0008765674,0.000849119,0.0017147469],"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":[0.0009407098,0.00023425555,0.007421903,0.00057598785,0.00030109016,0.00042906118,0.0005297971,0.059102155,0.30641025,0.012753934,0.015855068,0.5954458],"study_design_scores_gemma":[0.00017307287,0.00045774385,0.0075156735,0.000042923515,0.00023268719,0.00052134896,0.00018621224,0.706584,0.20976104,0.017037734,0.05739131,0.0000962896],"about_ca_topic_score_codex":0.0030611183,"about_ca_topic_score_gemma":0.0032531654,"teacher_disagreement_score":0.0053860773,"about_ca_system_score_codex":0.00077811565,"about_ca_system_score_gemma":0.0011837729,"threshold_uncertainty_score":0.018018246},"labels":[],"label_agreement":null},{"id":"W2903125175","doi":"10.1186/s12859-018-2485-7","title":"Purge Haplotigs: allelic contig reassignment for third-gen diploid genome assemblies","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1285,"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":"Wine Australia; Australian Government; Alberta Water Research Institute; Bioplatforms Australia","keywords":"Contig; Genome; Ploidy; Biology; Haplotype; Genetics; Sequence assembly; Purge; Computational biology; Allele; Gene; Transcriptome","score_opus":0.024740876154589482,"score_gpt":0.2563884776234654,"score_spread":0.23164760146887592,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2903125175","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06524167,0.0013107032,0.74926716,0.00032133047,0.0004848719,0.00093720254,0.014355615,0.16304101,0.0050404062],"genre_scores_gemma":[0.09269521,0.0004998283,0.84239286,0.00033959353,0.000065240805,0.0008923107,0.040147886,0.018591823,0.004375278],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99829155,0.00025996266,0.00016740251,0.0006704593,0.00047343376,0.00013713854],"domain_scores_gemma":[0.99711215,0.0011017153,0.0004324789,0.0007414519,0.00042231512,0.00018993091],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039323745,0.0021224157,0.0014029846,0.0021284665,0.0014808663,0.002335866,0.0019393195,0.0011815081,0.010710206],"category_scores_gemma":[0.0068166936,0.0019746677,0.0020947892,0.0013918444,0.00079246017,0.0015508861,0.0030812332,0.0028603438,0.0066541014],"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":[0.0032182029,0.0003147244,0.018781174,0.0041146404,0.0009795267,0.002133916,0.0033771715,0.024222499,0.4352126,0.008585918,0.08436553,0.41469407],"study_design_scores_gemma":[0.00050400314,0.0006452704,0.020114107,0.0004288079,0.0004266484,0.002463349,0.0004991647,0.13554452,0.52957964,0.008767663,0.30051494,0.0005119283],"about_ca_topic_score_codex":0.0026376897,"about_ca_topic_score_gemma":0.004696571,"teacher_disagreement_score":0.010710206,"about_ca_system_score_codex":0.0010179417,"about_ca_system_score_gemma":0.0015809587,"threshold_uncertainty_score":0.035829246},"labels":[],"label_agreement":null},{"id":"W2904436729","doi":"10.1186/s12859-018-2470-1","title":"Towards a supervised classification of neocortical interneuron morphologies","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Addiction and Mental Health","funders":"Horizon 2020 Framework Programme; Consejería de Educación, Juventud y Deporte, Comunidad de Madrid; Banco Bilbao Vizcaya Argentaria; Ministerio de Economía y Competitividad; École Polytechnique Fédérale de Lausanne; European Commission; Fundación BBVA","keywords":"Interneuron; Neuroscience; Neocortex; Biology; Computer science; Artificial intelligence","score_opus":0.08261878739241624,"score_gpt":0.29348978196076975,"score_spread":0.2108709945683535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2904436729","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3040507,0.00033745446,0.6856756,0.00043466114,0.00007509852,0.00014797247,0.0012952808,0.0062431106,0.0017400645],"genre_scores_gemma":[0.7242199,0.00009558689,0.27006623,0.00020078766,0.00005941304,0.00020416465,0.0029871904,0.00034386973,0.0018228245],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99925894,0.00017794679,0.000042497868,0.00031017725,0.00012990514,0.00008040135],"domain_scores_gemma":[0.9968719,0.0012024471,0.0003127335,0.0005341376,0.00090636674,0.00017235671],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019118049,0.0011923908,0.0007769402,0.0011430972,0.00045294774,0.0012859171,0.0016483691,0.0013680377,0.0012240094],"category_scores_gemma":[0.004093846,0.00048387467,0.0012083638,0.0005119755,0.0005715286,0.0009921725,0.0010524864,0.0013660722,0.0010914251],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035011975,0.00051530544,0.03140071,0.00019578151,0.00026778132,0.00009412639,0.00025790816,0.5904898,0.021333896,0.002579838,0.008026016,0.34448877],"study_design_scores_gemma":[0.000005058563,0.000023776654,0.0007118722,0.000008778807,0.000007307062,0.000012594181,0.00001846684,0.9949663,0.0023607817,0.0015885851,0.0002918317,0.0000046562177],"about_ca_topic_score_codex":0.0035429043,"about_ca_topic_score_gemma":0.0052867047,"teacher_disagreement_score":0.0035429043,"about_ca_system_score_codex":0.0011241833,"about_ca_system_score_gemma":0.0012413888,"threshold_uncertainty_score":0.010110736},"labels":[],"label_agreement":null},{"id":"W2906953716","doi":"10.1186/s12859-018-2522-6","title":"DWNN-RLS: regularized least squares method for predicting circRNA-disease associations","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Circular RNAs in diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":104,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"National Natural Science Foundation of China","keywords":"Kronecker product; Similarity (geometry); Computational biology; Computer science; Kernel (algebra); Disease; Data mining; Kronecker delta; Bioinformatics; Mathematics; Artificial intelligence; Biology; Medicine","score_opus":0.02468362127228896,"score_gpt":0.31545334908923983,"score_spread":0.2907697278169509,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2906953716","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017021809,0.00021808161,0.98092765,0.00011958927,0.00003576957,0.000040628485,0.00017185777,0.0011811843,0.0002833807],"genre_scores_gemma":[0.3976282,0.0002767069,0.5962794,0.00026014744,0.000058999874,0.00025934976,0.0016036498,0.00034221244,0.0032913093],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999132,0.00030265318,0.00006911733,0.0002692898,0.00016510834,0.000061966246],"domain_scores_gemma":[0.9983907,0.0008449792,0.00018114518,0.00014408886,0.00037273217,0.00006640181],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014535056,0.00086465565,0.000975765,0.0008174423,0.00034175868,0.0006300326,0.0013028334,0.0011541157,0.0015495119],"category_scores_gemma":[0.0040241387,0.00046712873,0.0012439762,0.000723246,0.0005654996,0.00068178616,0.00072509836,0.0013217415,0.0008639317],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031578727,0.00018409436,0.009047786,0.00018842123,0.0002890637,0.000251488,0.00012689961,0.75795394,0.010042492,0.00349853,0.005078611,0.21302289],"study_design_scores_gemma":[0.000004660565,0.000015798427,0.0002647368,0.0000029570838,0.0000053687713,0.00002004573,0.0000057435923,0.99830306,0.0004527085,0.0006887895,0.00023066654,0.0000054699685],"about_ca_topic_score_codex":0.007859509,"about_ca_topic_score_gemma":0.0071325265,"teacher_disagreement_score":0.007859509,"about_ca_system_score_codex":0.000497742,"about_ca_system_score_gemma":0.0013252831,"threshold_uncertainty_score":0.015627503},"labels":[],"label_agreement":null},{"id":"W2914488418","doi":"10.1186/s12859-019-2611-1","title":"sim1000G: a user-friendly genetic variant simulator in R for unrelated individuals and family-based designs","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; Public Health Ontario; University of Toronto; Mount Sinai Hospital","funders":"Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Linkage disequilibrium; Population; Context (archaeology); Pedigree chart; Computer science; Genetics; Biology; Haplotype; Allele","score_opus":0.018971536646536783,"score_gpt":0.2630115897239511,"score_spread":0.24404005307741433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2914488418","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014045885,0.0006417943,0.87677777,0.0005293781,0.0002721922,0.0004650617,0.020359335,0.08126364,0.005644955],"genre_scores_gemma":[0.11682847,0.0010517072,0.8196633,0.0011735732,0.0001339287,0.0047359155,0.018033165,0.031758737,0.0066212704],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986494,0.0008110011,0.00007701494,0.00015887605,0.00021165975,0.00009208563],"domain_scores_gemma":[0.99361295,0.005080136,0.00033524487,0.0004742866,0.00031795725,0.00017956023],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004430224,0.0017671731,0.0016890456,0.0009505316,0.00038966423,0.00112332,0.0045929435,0.0017985848,0.036662526],"category_scores_gemma":[0.015588191,0.0014141661,0.0024163923,0.0009197842,0.00060681265,0.00080027187,0.001677058,0.0025175824,0.009577498],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011591521,0.00025830508,0.01432592,0.0024953648,0.0017929132,0.0010811572,0.00065048377,0.65469193,0.006128226,0.046614513,0.17022337,0.10057876],"study_design_scores_gemma":[0.0010914145,0.00018226428,0.0013797996,0.00016728415,0.0002882538,0.00045428443,0.00004863397,0.8844865,0.00329633,0.032058008,0.076428786,0.000118467105],"about_ca_topic_score_codex":0.0053872983,"about_ca_topic_score_gemma":0.0058277617,"teacher_disagreement_score":0.036662526,"about_ca_system_score_codex":0.0007391752,"about_ca_system_score_gemma":0.002477755,"threshold_uncertainty_score":0.12264836},"labels":[],"label_agreement":null},{"id":"W2931795699","doi":"10.1186/s12859-019-2649-0","title":"Protein complex detection based on flower pollination mechanism in multi-relation reconstructed dynamic protein networks","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Pollination; Relation (database); Computer science; Field (mathematics); Algorithm; Biological system; Pollen; Data mining; Biology; Botany; Mathematics","score_opus":0.01130909627175362,"score_gpt":0.222545292909813,"score_spread":0.2112361966380594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2931795699","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25880244,0.0007693253,0.7355443,0.00018304316,0.000024693298,0.00012725631,0.0006248903,0.002155179,0.0017687841],"genre_scores_gemma":[0.67510164,0.0003051926,0.32159936,0.00008076964,0.000015232484,0.0000890445,0.0017083897,0.00011796278,0.0009823901],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994461,0.00008069189,0.000031380678,0.00025901684,0.00013425281,0.00004862927],"domain_scores_gemma":[0.9991123,0.0004050321,0.00017163432,0.00012224636,0.00013479481,0.000053946136],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068235066,0.0006523401,0.0005613126,0.0020899454,0.00047393766,0.00078864384,0.0010178457,0.0007994038,0.0010404701],"category_scores_gemma":[0.002436174,0.00027958467,0.0010025353,0.0011067779,0.0004004797,0.0012508353,0.0007174597,0.0004337824,0.00028209618],"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":[0.00093650084,0.000264575,0.07070545,0.00061723025,0.00061012426,0.0013407517,0.0004993423,0.33679014,0.11827061,0.012635782,0.005523472,0.45180607],"study_design_scores_gemma":[0.000017395148,0.000043898704,0.0063884547,0.000011644464,0.00006232746,0.0003932549,0.000043407963,0.97457856,0.013389851,0.0035829544,0.0014719933,0.000016274851],"about_ca_topic_score_codex":0.002704171,"about_ca_topic_score_gemma":0.003343215,"teacher_disagreement_score":0.002704171,"about_ca_system_score_codex":0.00065979094,"about_ca_system_score_gemma":0.00056853745,"threshold_uncertainty_score":0.005376816},"labels":[],"label_agreement":null},{"id":"W2942866405","doi":"10.1186/s12859-019-2659-y","title":"IMMAN: an R/Bioconductor package for Interolog protein network reconstruction, mapping and mining analysis","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","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":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Directorate for Biological Sciences; Institute for Research in Fundamental Sciences","keywords":"Benchmark (surveying); Bioconductor; Computer science; Network analysis; Protein–protein interaction; Biological network; Data mining; Computational biology; Biology; Machine learning; Theoretical computer science; Artificial intelligence; Genetics; Gene; Geography; Cartography","score_opus":0.014502702304429302,"score_gpt":0.22769188452797498,"score_spread":0.2131891822235457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2942866405","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004160301,0.002812356,0.41157442,0.0015496967,0.0011577996,0.00062148244,0.111282885,0.4592962,0.007544775],"genre_scores_gemma":[0.031672847,0.002351459,0.69655496,0.001682681,0.0003607476,0.005291868,0.118167356,0.133921,0.009997051],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968919,0.001121107,0.0002902832,0.00084180676,0.0006212957,0.00023353935],"domain_scores_gemma":[0.992717,0.003969175,0.0007893474,0.001011168,0.0010457004,0.00046757763],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006526307,0.004727126,0.0038585293,0.0047300723,0.0012151673,0.0030923912,0.0068734447,0.0016636226,0.06880629],"category_scores_gemma":[0.017821642,0.0021375755,0.0033134602,0.0037760248,0.0013620094,0.002742809,0.004713754,0.0056240163,0.06017763],"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":[0.0011029099,0.00018163695,0.0041753235,0.00940481,0.0024291272,0.0008107251,0.00075587427,0.009592091,0.00742079,0.023554137,0.8584351,0.08213755],"study_design_scores_gemma":[0.000720508,0.0002476626,0.0067140255,0.0015013955,0.001241633,0.0013873216,0.0002597698,0.09077133,0.013044761,0.08162312,0.8021121,0.00037641247],"about_ca_topic_score_codex":0.0034680942,"about_ca_topic_score_gemma":0.0040581925,"teacher_disagreement_score":0.06880629,"about_ca_system_score_codex":0.0010302328,"about_ca_system_score_gemma":0.004977764,"threshold_uncertainty_score":0.23017997},"labels":[],"label_agreement":null},{"id":"W2947100013","doi":"10.1186/s12859-019-2801-x","title":"Automated assessment of biological database assertions using the scientific literature","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Bhabha Atomic Research Centre; Australian Research Council","keywords":"Computer science; Consistency (knowledge bases); Information retrieval; Assertion; Relevance (law); Relation (database); Biological database; Classifier (UML); Set (abstract data type); Data mining; Data science; Database; Bioinformatics; Artificial intelligence; Biology; Programming language","score_opus":0.045762540862951104,"score_gpt":0.34215141589784726,"score_spread":0.29638887503489614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2947100013","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.50500166,0.011225694,0.40234768,0.0027922126,0.00035908344,0.0018296165,0.029464314,0.038053308,0.00892653],"genre_scores_gemma":[0.5306989,0.001196376,0.43341228,0.00030196737,0.00023617731,0.00033015865,0.0323475,0.00040960815,0.0010670853],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9840577,0.0036583606,0.0026407943,0.0023896564,0.0069019473,0.00035151135],"domain_scores_gemma":[0.86854345,0.07798688,0.01400302,0.008757228,0.028889097,0.0018202905],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01567042,0.0012368548,0.0011707848,0.042697478,0.0014147358,0.0045163115,0.0023497853,0.0016203546,0.0019042362],"category_scores_gemma":[0.08046678,0.00038455613,0.0011457053,0.01148153,0.000707281,0.0034182211,0.003459313,0.0008554673,0.001377871],"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":[0.0013086902,0.00055315305,0.16566287,0.0061188675,0.0008405885,0.0020614236,0.0034323542,0.009749067,0.045019522,0.0057480126,0.029455055,0.7300504],"study_design_scores_gemma":[0.00029012802,0.0009260915,0.19031313,0.0019086681,0.0016169924,0.0061134077,0.0047818352,0.56943035,0.123670794,0.019129219,0.08140146,0.0004178644],"about_ca_topic_score_codex":0.006640622,"about_ca_topic_score_gemma":0.008072565,"teacher_disagreement_score":0.9843296,"about_ca_system_score_codex":0.0013328494,"about_ca_system_score_gemma":0.0041124127,"threshold_uncertainty_score":0.08287406},"labels":[],"label_agreement":null},{"id":"W2947681169","doi":"10.1186/s12859-019-2902-6","title":"Pairwise visual comparison of small RNA secondary structures with base pair probabilities","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; National Research Council Canada","funders":"","keywords":"Pairwise comparison; Protein secondary structure; Nucleic acid secondary structure; Computer science; Base pair; RNA; Visualization; Base (topology); Graph; Web server; Nucleic acid structure; Algorithm; Computational biology; Theoretical computer science; Bioinformatics; Data mining; Biology; Mathematics; Artificial intelligence; DNA; Genetics; The Internet","score_opus":0.015766328157067185,"score_gpt":0.23911802043266156,"score_spread":0.22335169227559437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2947681169","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49755198,0.00080567057,0.46895465,0.00021490674,0.00010152981,0.00012863686,0.005297122,0.01754821,0.009397221],"genre_scores_gemma":[0.8179029,0.00024939046,0.17642674,0.00006333223,0.000038631748,0.00012814207,0.0021937354,0.0010674469,0.0019296497],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997079,0.000074072515,0.000020048321,0.00007347729,0.00009644528,0.000028107625],"domain_scores_gemma":[0.99917835,0.00045286698,0.00011190349,0.000056499186,0.00014370817,0.000056705874],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046562232,0.00046052577,0.00032534523,0.0020537504,0.00020054606,0.0007750937,0.0003027196,0.00035116347,0.012993959],"category_scores_gemma":[0.0015253666,0.00019769144,0.00034399764,0.0007654123,0.00019833278,0.0006605164,0.0004832669,0.00033581484,0.0012544517],"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":[0.0017087965,0.00016514567,0.016943913,0.0011536467,0.00020720724,0.000530451,0.00053991907,0.026998097,0.73018426,0.008983102,0.007578351,0.2050071],"study_design_scores_gemma":[0.00012703401,0.0010291202,0.082127444,0.00016431163,0.00021332297,0.0018055647,0.0007756237,0.38407022,0.48935178,0.015631324,0.024487527,0.00021676686],"about_ca_topic_score_codex":0.0005712291,"about_ca_topic_score_gemma":0.0005358855,"teacher_disagreement_score":0.012993959,"about_ca_system_score_codex":0.00024210954,"about_ca_system_score_gemma":0.00020899983,"threshold_uncertainty_score":0.04346913},"labels":[],"label_agreement":null},{"id":"W2949158578","doi":"10.1186/s12859-019-2647-2","title":"SplicedFamAlign: CDS-to-gene spliced alignment and identification of transcript orthology groups","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; Université de Sherbrooke","keywords":"Exon; RNA splicing; Intron; Biology; Genetics; Gene; Computational biology; Sequence alignment; Alternative splicing; Genome; DNA microarray; Gene prediction; Sequence analysis; Alignment-free sequence analysis; Peptide sequence; Gene expression; RNA","score_opus":0.01001318829358899,"score_gpt":0.22447683452546693,"score_spread":0.21446364623187794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949158578","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03476633,0.0012336146,0.9234191,0.00026838205,0.00022748458,0.00032589908,0.004818514,0.033829875,0.0011107526],"genre_scores_gemma":[0.050987203,0.00019956919,0.93783545,0.00011964227,0.000061918356,0.00030785296,0.009204931,0.00078005914,0.00050333433],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99752027,0.0006250378,0.00024400852,0.0010829521,0.00039530304,0.00013242888],"domain_scores_gemma":[0.9978902,0.0010276305,0.0003251729,0.00043879703,0.00020579617,0.0001124013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025671744,0.0022897697,0.0022566156,0.0020309456,0.0013285164,0.0018564642,0.0022488066,0.0022723393,0.0055241357],"category_scores_gemma":[0.004715034,0.0009571686,0.002184522,0.0030126486,0.0013349017,0.002106041,0.0017214435,0.0024198487,0.0039470335],"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":[0.0036138992,0.00064147485,0.012468903,0.0023957219,0.0007109966,0.0009704515,0.00062692416,0.080878906,0.12416826,0.011483266,0.043055426,0.71898574],"study_design_scores_gemma":[0.00032968484,0.00043014146,0.0037830307,0.00010088235,0.000106386884,0.0013892632,0.00014946873,0.8731241,0.067040324,0.026439877,0.026982699,0.00012410244],"about_ca_topic_score_codex":0.00094774447,"about_ca_topic_score_gemma":0.0010685022,"teacher_disagreement_score":0.0055241357,"about_ca_system_score_codex":0.00073594484,"about_ca_system_score_gemma":0.0013932355,"threshold_uncertainty_score":0.018480062},"labels":[],"label_agreement":null},{"id":"W2949244194","doi":"10.1186/s12859-017-1553-8","title":"MINT: a multivariate integrative method to identify reproducible molecular signatures across independent experiments and platforms","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":109,"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":"Diamantina Institute, University of Queensland; National Health and Medical Research Council; Medical Research Council; Australian Research Council; University of Queensland; Australian Cancer Research Foundation","keywords":"Multivariate statistics; Overfitting; Computer science; Data mining; Computational biology; DNA microarray; Artificial intelligence; Machine learning; Biology; Gene; Genetics","score_opus":0.04099443180788442,"score_gpt":0.41060038708721674,"score_spread":0.3696059552793323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949244194","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006142902,0.0002329398,0.9844987,0.00015306928,0.00008291992,0.00023604056,0.00090152666,0.0074071335,0.00034476785],"genre_scores_gemma":[0.07370075,0.00029647996,0.91427845,0.0002507827,0.000209377,0.00196779,0.0047718585,0.0036081555,0.0009164515],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9926617,0.0028036097,0.0005614882,0.001884993,0.0017248539,0.00036333172],"domain_scores_gemma":[0.9881819,0.0066371732,0.001518723,0.0016512804,0.0015431906,0.00046774498],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014458712,0.0038122805,0.0029957301,0.0058476925,0.0014342088,0.0038827423,0.0034634466,0.0015516639,0.0068320325],"category_scores_gemma":[0.02825358,0.0013831418,0.008179299,0.004450211,0.0017000675,0.0023416146,0.0037308321,0.004890483,0.0024576846],"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":[0.00169242,0.0006324977,0.029104233,0.0025887596,0.006285822,0.0008956125,0.0014815249,0.13017912,0.08218141,0.023885014,0.029686054,0.6913875],"study_design_scores_gemma":[0.00015667891,0.00047050178,0.008408939,0.00010738581,0.0006501894,0.000588035,0.00019306602,0.9228097,0.01909738,0.031033432,0.016240504,0.0002442525],"about_ca_topic_score_codex":0.0024883058,"about_ca_topic_score_gemma":0.0024842185,"teacher_disagreement_score":0.014458712,"about_ca_system_score_codex":0.0015173807,"about_ca_system_score_gemma":0.0035328988,"threshold_uncertainty_score":0.076465905},"labels":[],"label_agreement":null},{"id":"W2949294873","doi":"10.1186/s12859-018-2425-6","title":"Tigmint: correcting assembly errors using linked reads from large molecules","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":137,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Canada's Michael Smith Genome Sciences Centre; Genome British Columbia","funders":"National Human Genome Research Institute; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; Genome British Columbia; Genome Canada","keywords":"Sequence assembly; Genome; Computational biology; Hybrid genome assembly; Reference genome; Contig; Genomics; Whole genome sequencing; Sequence (biology); Biology; DNA sequencing; Computer science; Genetics; DNA; Gene","score_opus":0.029060927699152965,"score_gpt":0.27393547331175083,"score_spread":0.24487454561259786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949294873","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020401588,0.00070003973,0.6535816,0.0002767912,0.0005600216,0.00035708564,0.0037774884,0.31859553,0.0017498488],"genre_scores_gemma":[0.05116958,0.0003445987,0.9078821,0.00044514352,0.0001011248,0.0008092577,0.008008696,0.029167054,0.0020725266],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9960919,0.0007527343,0.0005170917,0.00091983005,0.0014623633,0.0002560275],"domain_scores_gemma":[0.9907504,0.004289406,0.0020152195,0.0016933525,0.0009985289,0.00025317963],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007475003,0.0036024011,0.0013877744,0.0032085122,0.0014406658,0.0027281747,0.0045465003,0.002373509,0.010174914],"category_scores_gemma":[0.018825376,0.0017974499,0.0026408453,0.0024412458,0.0010911548,0.0022254928,0.0037856316,0.0042461874,0.0061509362],"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":[0.0029707705,0.00043758375,0.016324675,0.005757915,0.0013838572,0.0024280215,0.0030595022,0.030891199,0.25271532,0.008670507,0.10346167,0.57189894],"study_design_scores_gemma":[0.0005422898,0.0009849189,0.008870063,0.00092148647,0.00044805734,0.0024000031,0.00040039897,0.19783811,0.61507803,0.010089827,0.16173859,0.00068817136],"about_ca_topic_score_codex":0.0010972656,"about_ca_topic_score_gemma":0.0016719613,"teacher_disagreement_score":0.010174914,"about_ca_system_score_codex":0.0009892272,"about_ca_system_score_gemma":0.0014807006,"threshold_uncertainty_score":0.039532065},"labels":[],"label_agreement":null},{"id":"W2949358764","doi":"10.1186/s12859-019-2905-3","title":"Testing adequacy for DNA substitution models","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Model selection; Goodness of fit; Inference; Computer science; Type I and type II errors; Simple (philosophy); Tree (set theory); Data mining; Range (aeronautics); Statistical hypothesis testing; Substitution (logic); Selection (genetic algorithm); Algorithm; Statistics; Mathematics; Machine learning; Artificial intelligence; Engineering","score_opus":0.03981830111788477,"score_gpt":0.2454632519774044,"score_spread":0.20564495085951962,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949358764","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29436076,0.00073961756,0.69358283,0.0020545542,0.00024598133,0.0005139656,0.0011992677,0.0011861367,0.0061169364],"genre_scores_gemma":[0.90431,0.00014576523,0.093090914,0.00034945988,0.00013235204,0.00049181806,0.0009726842,0.00020673341,0.00030024853],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.90798783,0.0675461,0.004648489,0.0077740704,0.010567937,0.001475606],"domain_scores_gemma":[0.33372566,0.61855274,0.01619464,0.020948648,0.008291085,0.0022871601],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07766553,0.0014328641,0.002004717,0.0047455463,0.0020875947,0.0031934513,0.004184894,0.0030116774,0.0062194588],"category_scores_gemma":[0.41411406,0.0006738119,0.0035876164,0.0032872627,0.00694593,0.0051619904,0.0035168016,0.0040047755,0.00085074],"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":[0.002204676,0.00054078037,0.3422732,0.0023119329,0.0041106674,0.0037843522,0.0036057252,0.29970872,0.005415065,0.22576408,0.006831285,0.103449576],"study_design_scores_gemma":[0.00018291792,0.0007581563,0.019499833,0.0004131791,0.00033579484,0.0016835503,0.0011216516,0.6757691,0.00441184,0.29001182,0.0056542656,0.00015790571],"about_ca_topic_score_codex":0.002251378,"about_ca_topic_score_gemma":0.0013310626,"teacher_disagreement_score":0.07766553,"about_ca_system_score_codex":0.0018064652,"about_ca_system_score_gemma":0.00329364,"threshold_uncertainty_score":0.41073948},"labels":[],"label_agreement":null},{"id":"W2949514040","doi":"10.1186/s12859-018-2284-1","title":"De novo profile generation based on sequence context specificity with the long short-term memory network","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Medical Science, University of Tokyo; Japan Society for the Promotion of Science; Ministry of Education, Culture, Sports, Science and Technology; Institute of Genetics; Japan Agency for Medical Research and Development","keywords":"Context (archaeology); Term (time); Sequence (biology); DNA microarray; Long short term memory; Computational biology; Computer science; Biology; Genetics; Artificial intelligence; Gene; Artificial neural network; Recurrent neural network; Gene expression; Paleontology","score_opus":0.025768379538747735,"score_gpt":0.2655191005374179,"score_spread":0.23975072099867017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949514040","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06277535,0.00023334088,0.9318459,0.0001436971,0.00006030004,0.00010136343,0.00022890602,0.003662875,0.0009482341],"genre_scores_gemma":[0.56873375,0.00021767923,0.42759877,0.00026602464,0.000035126755,0.00021028452,0.0008827906,0.00024022849,0.001815457],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99976367,0.000024937754,0.000017506203,0.000097318254,0.00006376039,0.000032808734],"domain_scores_gemma":[0.99943966,0.0002277011,0.0000725781,0.00007359318,0.0001464575,0.00004000902],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005048701,0.0009276046,0.00051422964,0.0006933573,0.00030601135,0.00041637738,0.0009404993,0.00071016874,0.0013725418],"category_scores_gemma":[0.0017881067,0.00042281792,0.0006424112,0.00050296413,0.00030186278,0.0012766387,0.00072000903,0.0011032609,0.00056950934],"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":[0.00040657376,0.00021569045,0.0048629846,0.00016497006,0.00010614023,0.00048387068,0.00017692629,0.29750186,0.054464214,0.004919393,0.003637731,0.6330597],"study_design_scores_gemma":[0.000010283586,0.000025775236,0.00021943661,0.0000047921776,0.00001128998,0.00005391678,0.0000073179162,0.9879303,0.009713613,0.0016692259,0.00034706047,0.000007003345],"about_ca_topic_score_codex":0.0028621408,"about_ca_topic_score_gemma":0.0036206495,"teacher_disagreement_score":0.0028621408,"about_ca_system_score_codex":0.00052953477,"about_ca_system_score_gemma":0.0009509325,"threshold_uncertainty_score":0.005690992},"labels":[],"label_agreement":null},{"id":"W2949538565","doi":"10.1186/s12859-019-2610-2","title":"BPG: Seamless, automated and interactive visualization of scientific data","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":113,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research","funders":"Natural Sciences and Engineering Research Council of Canada; Terry Fox Research Institute; University of Toronto; Government of Ontario; Government of Canada; Canadian Institutes of Health Research; National Science Foundation; Ontario Institute for Cancer Research; Center for Translational Molecular Medicine; University of Pennsylvania; Ontario Genomics Institute; Movember Foundation; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Ontario Genomics; Genome Canada; Prostate Cancer Canada","keywords":"Visualization; Computer science; Data science; Data visualization; World Wide Web; Information retrieval; Data mining","score_opus":0.16096035470620532,"score_gpt":0.41811129736815916,"score_spread":0.2571509426619538,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949538565","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013361174,0.00058535737,0.5703738,0.0011499153,0.00043558603,0.00026150828,0.019282611,0.40333158,0.0032436708],"genre_scores_gemma":[0.020794386,0.0014453866,0.8293978,0.0012108595,0.0003751365,0.0015565138,0.036137335,0.10512027,0.0039623124],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99560803,0.0013196664,0.00037980225,0.0007336858,0.0016489035,0.00030997582],"domain_scores_gemma":[0.99021006,0.004526953,0.00080007414,0.002138331,0.0016319652,0.000692701],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008149027,0.0035555016,0.0017473741,0.0061212345,0.0010381087,0.0057919044,0.004850657,0.0020525262,0.05898784],"category_scores_gemma":[0.024823923,0.0019418475,0.0026289257,0.004401734,0.0011676591,0.004474578,0.006564626,0.0054485486,0.0387341],"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":[0.00047337802,0.00011372613,0.0024413795,0.00225542,0.0003953006,0.00060565694,0.00097359234,0.0063962587,0.013032056,0.01476047,0.76331514,0.19523768],"study_design_scores_gemma":[0.0005435195,0.00013548172,0.0062079127,0.0010909382,0.00018242329,0.001419481,0.0001978842,0.09214258,0.02644127,0.0975221,0.7735805,0.00053587434],"about_ca_topic_score_codex":0.00357707,"about_ca_topic_score_gemma":0.0034437908,"teacher_disagreement_score":0.05898784,"about_ca_system_score_codex":0.0008638605,"about_ca_system_score_gemma":0.002836437,"threshold_uncertainty_score":0.19733399},"labels":[],"label_agreement":null},{"id":"W2951265437","doi":"10.1186/s12859-018-2243-x","title":"ARKS: chromosome-scale scaffolding of human genome drafts with linked read kmers","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":142,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; Genome British Columbia","funders":"National Human Genome Research Institute; National Institutes of Health; Genome Alberta; Genome British Columbia; Genome Canada","keywords":"Genome; Computer science; Human genome; Sequence assembly; Computational biology; Genomics; Reference genome; Whole genome sequencing; Biology; Genetics; Gene; Transcriptome","score_opus":0.014628542740856858,"score_gpt":0.24061249135199989,"score_spread":0.22598394861114302,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951265437","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04582364,0.0010420787,0.8052942,0.0004406062,0.00052852,0.0005660008,0.017373115,0.12329987,0.005631958],"genre_scores_gemma":[0.06426571,0.00040851385,0.89109313,0.00019348627,0.00009442547,0.00044871177,0.031126533,0.00792497,0.004444554],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9980489,0.00040037933,0.00021042062,0.0006806208,0.00055754324,0.0001021554],"domain_scores_gemma":[0.99552476,0.0016577676,0.0005960782,0.001318835,0.0006750397,0.00022754882],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035995508,0.0014062332,0.00084429357,0.0017716206,0.00085016905,0.0019213019,0.0020219071,0.0010314893,0.015743855],"category_scores_gemma":[0.008556681,0.0010996556,0.0015247521,0.0017771518,0.0006563031,0.0014470539,0.002433751,0.0016649726,0.012066431],"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":[0.0041453117,0.00040589576,0.01131787,0.004646764,0.0012899642,0.0015204776,0.002387371,0.024384778,0.34171942,0.016466802,0.10474431,0.48697117],"study_design_scores_gemma":[0.00065078883,0.0007456977,0.012674146,0.0004101535,0.00040695426,0.0013123503,0.0006228494,0.19019999,0.52394766,0.014881386,0.2536567,0.00049135153],"about_ca_topic_score_codex":0.0015029116,"about_ca_topic_score_gemma":0.0034621088,"teacher_disagreement_score":0.015743855,"about_ca_system_score_codex":0.00064133905,"about_ca_system_score_gemma":0.0013057198,"threshold_uncertainty_score":0.052668452},"labels":[],"label_agreement":null},{"id":"W2951375448","doi":"10.1186/s12859-019-2897-z","title":"Identification of critical connectors in the directed reaction-centric graphs of microbial metabolic networks","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Microbial Metabolic Engineering and Bioproduction","field":"Biochemistry, Genetics and Molecular Biology","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada; National Research Foundation of Korea; National Research Foundation","keywords":"Identification (biology); Computational biology; DNA microarray; Computer science; Biology; Data science; Genetics; Gene; Ecology; Gene expression","score_opus":0.006113777070007351,"score_gpt":0.22234721154885362,"score_spread":0.21623343447884627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951375448","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.767315,0.0005053741,0.22728117,0.00015596686,0.00001703867,0.00012171248,0.0007183407,0.0003702226,0.003515227],"genre_scores_gemma":[0.96721834,0.00016942214,0.031572193,0.00002191744,0.000008822866,0.000059119222,0.00061400584,0.000032143605,0.00030405176],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99960905,0.00008398546,0.000027337925,0.00012844538,0.0001012833,0.00004997918],"domain_scores_gemma":[0.9940773,0.0030800344,0.0015646152,0.00020814437,0.0006308289,0.00043913285],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078600104,0.0006174339,0.0003955047,0.0032310085,0.00044999804,0.0009631063,0.00039672494,0.00042579893,0.002199528],"category_scores_gemma":[0.0058450266,0.00024465093,0.0004272364,0.0015120634,0.0007290221,0.0010468514,0.00074479333,0.00043357757,0.00023815014],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013390997,0.00045949995,0.19096886,0.0022059858,0.0003722873,0.002060542,0.0013553905,0.21803512,0.21028948,0.18739618,0.0032153185,0.18230225],"study_design_scores_gemma":[0.00009870332,0.0003373827,0.07140022,0.00014461011,0.00027050424,0.0013597787,0.00054334843,0.67415893,0.053208873,0.19307184,0.005316942,0.00008884625],"about_ca_topic_score_codex":0.0008540412,"about_ca_topic_score_gemma":0.0013501098,"teacher_disagreement_score":0.0032310085,"about_ca_system_score_codex":0.0008143197,"about_ca_system_score_gemma":0.00060158904,"threshold_uncertainty_score":0.007358134},"labels":[],"label_agreement":null},{"id":"W2951901532","doi":"10.1186/s12859-018-2187-1","title":"Genome-wide prediction of cis-regulatory regions using supervised deep learning methods","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":129,"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; BC Children's Hospital; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; Michael Smith Health Research BC; Genome British Columbia; National Institute of General Medical Sciences; Western Canada Research Grid; Compute Canada; Canadian Institutes of Health Research; Genome Canada","keywords":"Genome; ENCODE; Human genome; Computational biology; Genomics; Biology; Genome project; Enhancer; Regulatory sequence; DNA sequencing; Functional genomics; Gene Annotation; Noncoding DNA; DNA microarray; Deep learning; Gene; Genetics; Regulation of gene expression; Computer science; Artificial intelligence; Transcription factor; Gene expression","score_opus":0.021935659757517,"score_gpt":0.2688406461527417,"score_spread":0.24690498639522473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951901532","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3295092,0.0022042037,0.64951074,0.00086889387,0.00011502507,0.00011692294,0.007946849,0.006679538,0.0030485922],"genre_scores_gemma":[0.83662784,0.0006214787,0.1383288,0.00059156946,0.0000778809,0.00024599166,0.019688955,0.0002948442,0.0035225977],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99958307,0.00008844267,0.000019304827,0.00019270826,0.000064095686,0.000052377418],"domain_scores_gemma":[0.9988134,0.00072620413,0.000108210035,0.00007867592,0.00021600696,0.00005751762],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000826273,0.0009283172,0.000799269,0.0013416666,0.0002947505,0.0005947715,0.0011357286,0.0009544343,0.0016029167],"category_scores_gemma":[0.001733943,0.00036231396,0.0009831899,0.0008271738,0.00051665946,0.0003426294,0.0006085154,0.001398683,0.0006257542],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005692211,0.00047444052,0.019796208,0.00030262748,0.0002509162,0.00030558434,0.000088482804,0.8013022,0.019655878,0.0035252234,0.009165166,0.14456412],"study_design_scores_gemma":[0.000015869704,0.000017705166,0.0007542798,0.0000063831117,0.000011988475,0.000013728662,0.000006217706,0.99475163,0.0018603714,0.0021328633,0.0004242049,0.0000047122976],"about_ca_topic_score_codex":0.009148915,"about_ca_topic_score_gemma":0.012598555,"teacher_disagreement_score":0.009148915,"about_ca_system_score_codex":0.0009580061,"about_ca_system_score_gemma":0.001104555,"threshold_uncertainty_score":0.018191338},"labels":[],"label_agreement":null},{"id":"W2952523648","doi":"10.1186/s12859-017-1865-8","title":"A rapid and accurate approach for prediction of interactomes from co-elution data (PrInCE)","year":2017,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":75,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"Canadian Institutes of Health Research; Genome British Columbia; Genome Canada","keywords":"Interactome; Computational biology; Elution; Executable; Computer science; Protein–protein interaction; Stable isotope labeling by amino acids in cell culture; Proteomics; Biology; Data mining; Chemistry; Programming language; Chromatography; Biochemistry","score_opus":0.05843736934127653,"score_gpt":0.2942363894918856,"score_spread":0.23579902015060905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952523648","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022573575,0.0006708717,0.89072895,0.000406397,0.000089382185,0.00030314235,0.014253068,0.0698444,0.0011302131],"genre_scores_gemma":[0.066012025,0.00041318292,0.9030872,0.00021233996,0.0000633451,0.0005306606,0.026020978,0.002093953,0.0015662737],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972736,0.0004719674,0.00021702706,0.0008748902,0.0009806448,0.00018173453],"domain_scores_gemma":[0.9955745,0.0019333091,0.0005503072,0.0006727716,0.0010159264,0.00025317437],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036842786,0.00243403,0.0018021617,0.006181385,0.0009600958,0.0022662804,0.0018449102,0.0015621047,0.006969285],"category_scores_gemma":[0.008709453,0.0011682916,0.0028406018,0.002915424,0.000587811,0.0022861417,0.0027813853,0.0023895793,0.0078004766],"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":[0.0028309778,0.00082973414,0.041924432,0.0028701783,0.0018577543,0.0017134554,0.0005681227,0.045301672,0.15907551,0.011201397,0.106780574,0.62504625],"study_design_scores_gemma":[0.0001404257,0.0002567416,0.016595878,0.000096526055,0.00017892133,0.0015083745,0.0001331488,0.8608721,0.06920895,0.014835399,0.03595287,0.00022053607],"about_ca_topic_score_codex":0.0014368473,"about_ca_topic_score_gemma":0.0026709158,"teacher_disagreement_score":0.006969285,"about_ca_system_score_codex":0.0006528632,"about_ca_system_score_gemma":0.0014454239,"threshold_uncertainty_score":0.023314536},"labels":[],"label_agreement":null},{"id":"W2952683761","doi":"10.1186/s12859-018-2289-9","title":"PRS-on-Spark (PRSoS): a novel, efficient and flexible approach for generating polygenic risk scores","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Jewish General Hospital; Canadian Institute for Advanced Research; University of British Columbia; McGill University; Douglas Mental Health University Institute","funders":"Health Canada; Ludmer Centre for Neuroinformatics and Mental Health; Fondation Brain Canada; McGill University; Canadian Institute for Advanced Research","keywords":"Single-nucleotide polymorphism; SNP; Major depressive disorder; Software; Biology; Computer science; Computational biology; Statistics; Genetics; Mathematics; Gene; Genotype","score_opus":0.026161680960704148,"score_gpt":0.2715539279775312,"score_spread":0.24539224701682705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952683761","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032913316,0.0005735948,0.71081346,0.0010827793,0.0005567648,0.0006538681,0.014306877,0.23342335,0.0056760823],"genre_scores_gemma":[0.21314923,0.00059407763,0.702602,0.001353972,0.00033838325,0.0016298573,0.044079296,0.032316234,0.0039368705],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99765885,0.00047838318,0.00022652393,0.00078855694,0.00064077653,0.00020680387],"domain_scores_gemma":[0.995411,0.0020578208,0.00040943682,0.00093804183,0.0006962404,0.00048753325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0053104972,0.0024292378,0.0016825645,0.0020717257,0.0013001355,0.002233676,0.005269041,0.0010733211,0.006682645],"category_scores_gemma":[0.016007291,0.0015536612,0.0033850602,0.0021510883,0.0010803059,0.0021542236,0.004262171,0.002432502,0.0042660725],"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":[0.0031088514,0.00077321543,0.054260034,0.0020409152,0.0028783742,0.0023432102,0.002195949,0.17359586,0.014724309,0.042975347,0.37626296,0.32484102],"study_design_scores_gemma":[0.001038944,0.00017462115,0.005727374,0.00007820228,0.00019170243,0.0006372913,0.00018989125,0.85562307,0.0065758857,0.08142159,0.048121642,0.00021981497],"about_ca_topic_score_codex":0.007961027,"about_ca_topic_score_gemma":0.008724018,"teacher_disagreement_score":0.007961027,"about_ca_system_score_codex":0.0009063196,"about_ca_system_score_gemma":0.003970991,"threshold_uncertainty_score":0.028084874},"labels":[],"label_agreement":null},{"id":"W2962703814","doi":"10.1186/s12859-018-2347-3","title":"DM-PhyClus: a Bayesian phylogenetic algorithm for infectious disease transmission cluster inference","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Jewish General Hospital; HEC Montréal; Centre Hospitalier de l’Université de Montréal; McGill University; McGill University Health Centre","funders":"Fonds de Recherche du Québec - Santé; Ministère de l'Économie, de la Science et de l'Innovation - Québec; Centre de Recherches Mathématiques; Canadian Institutes of Health Research; Ministère de la Santé; Ministère de la Santé et des Services sociaux; Compute Canada; Natural Sciences and Engineering Research Council of Canada; Université de Sherbrooke; McGill University; Styrelsen för Internationellt Utvecklingssamarbete","keywords":"Cluster analysis; Phylogenetic tree; Bayesian probability; Inference; Bayesian inference; Computer science; Cluster (spacecraft); Data mining; Algorithm; A priori and a posteriori; Set (abstract data type); Artificial intelligence; Machine learning; Biology; Statistics; Mathematics; Genetics","score_opus":0.011749222327809337,"score_gpt":0.2558560780779773,"score_spread":0.24410685575016794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2962703814","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034904347,0.00020673052,0.9930616,0.00022756301,0.000044164608,0.000094979885,0.00047953468,0.0018322401,0.0005627777],"genre_scores_gemma":[0.035215273,0.00014042939,0.9617034,0.00016028549,0.00004547602,0.00032212024,0.001198502,0.000537346,0.0006771724],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964533,0.0019333104,0.00018966934,0.0005962186,0.000685089,0.000142464],"domain_scores_gemma":[0.99362856,0.004110757,0.00041073706,0.00062812964,0.00092329684,0.0002984166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0061301207,0.001343502,0.0018327076,0.0027729191,0.0023637535,0.0025010316,0.004682531,0.0026715978,0.007314443],"category_scores_gemma":[0.024185829,0.001344583,0.00215106,0.0029586353,0.0015029581,0.002122652,0.0039933934,0.004083675,0.0024092854],"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":[0.0009011489,0.00022083636,0.011419296,0.0011019979,0.0011091242,0.00035142447,0.0011066644,0.38575727,0.0067780428,0.10740373,0.035139333,0.44871113],"study_design_scores_gemma":[0.00012418363,0.00003342338,0.0006600519,0.000060010978,0.00004903141,0.00014258418,0.00007137846,0.9319839,0.0015254584,0.05697901,0.008326938,0.000044048233],"about_ca_topic_score_codex":0.008170557,"about_ca_topic_score_gemma":0.012487935,"teacher_disagreement_score":0.008170557,"about_ca_system_score_codex":0.0020528145,"about_ca_system_score_gemma":0.0050089797,"threshold_uncertainty_score":0.032419503},"labels":[],"label_agreement":null},{"id":"W2982540799","doi":"10.1186/s12859-019-3100-2","title":"RACS: rapid analysis of ChIP-Seq data for contig based genomes","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Canada Research Chairs; Toronto Metropolitan University","funders":"University of Toronto","keywords":"Genome; Contig; Pipeline (software); DNA microarray; Intergenic region; Gene prediction; Gene; Genomics; Model organism","score_opus":0.018268240161205464,"score_gpt":0.2498390884317334,"score_spread":0.23157084827052796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2982540799","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.063852705,0.000581376,0.3935448,0.0009836184,0.0006078775,0.0011531248,0.19971865,0.33324665,0.00631127],"genre_scores_gemma":[0.08383065,0.00042555266,0.6824706,0.0007649786,0.00012634147,0.0024312362,0.20442961,0.022769518,0.0027515145],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979867,0.0002614282,0.00015106687,0.0006477476,0.000743563,0.00020944595],"domain_scores_gemma":[0.99673104,0.001322896,0.0003143643,0.0005964093,0.00077428395,0.00026100068],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003683652,0.001676504,0.0012008912,0.0023110106,0.0012353114,0.0017641288,0.0026480653,0.0008448851,0.01712765],"category_scores_gemma":[0.0058580027,0.0011302765,0.0024713133,0.0018291536,0.0007640473,0.0012120347,0.0021925338,0.0022809207,0.009955412],"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":[0.0030316056,0.0005200929,0.02090392,0.0030269804,0.0012899311,0.0009900219,0.0011004667,0.028960606,0.28402397,0.0107410615,0.4954021,0.15000929],"study_design_scores_gemma":[0.0010581643,0.00080430065,0.0393037,0.00030176667,0.00035041888,0.001053552,0.00046140965,0.36164364,0.28815198,0.014068777,0.29205427,0.0007479575],"about_ca_topic_score_codex":0.004010476,"about_ca_topic_score_gemma":0.0068774894,"teacher_disagreement_score":0.01712765,"about_ca_system_score_codex":0.0012299458,"about_ca_system_score_gemma":0.0024968702,"threshold_uncertainty_score":0.057297766},"labels":[],"label_agreement":null},{"id":"W2986366856","doi":"10.1186/s12859-019-3174-x","title":"omicplotR: visualizing omic datasets as compositions","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Geochemistry and Geologic Mapping","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":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Government of Ontario","keywords":"Computer science; Visualization; Graphical user interface; Software; Scripting language; Cluster analysis; Data mining; Hierarchical clustering; Set (abstract data type); Interface (matter); Principal component analysis; Machine learning; Artificial intelligence; Programming language; Operating system","score_opus":0.01666856512170442,"score_gpt":0.25611391975791,"score_spread":0.23944535463620556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2986366856","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018067276,0.0011058068,0.40929008,0.0012986325,0.000476202,0.0004594258,0.10617255,0.45442405,0.008705998],"genre_scores_gemma":[0.09686182,0.0013915616,0.74538195,0.0008946053,0.0002781344,0.0017751412,0.08224898,0.0662166,0.004951253],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99881124,0.00029149215,0.00014740256,0.00023830951,0.00042172198,0.00008984298],"domain_scores_gemma":[0.99512154,0.0024934302,0.0006593469,0.00058527204,0.00090567564,0.00023467401],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035867286,0.0021964167,0.0012172161,0.005575503,0.0008700254,0.003326784,0.002025982,0.0010918545,0.03990166],"category_scores_gemma":[0.008108482,0.00082317117,0.001659466,0.0044232723,0.0005165135,0.0031290802,0.0025505035,0.0022774856,0.010755382],"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":[0.0020826706,0.00035341879,0.013956544,0.0060316226,0.0006806045,0.001038646,0.003607791,0.008950738,0.06696035,0.02020091,0.6135565,0.26258028],"study_design_scores_gemma":[0.00064078695,0.00027528958,0.025408946,0.001770657,0.00038266002,0.0015861761,0.0013351103,0.19610366,0.10390051,0.054018963,0.61396843,0.00060874433],"about_ca_topic_score_codex":0.00208801,"about_ca_topic_score_gemma":0.0022102327,"teacher_disagreement_score":0.03990166,"about_ca_system_score_codex":0.0006355561,"about_ca_system_score_gemma":0.0015275257,"threshold_uncertainty_score":0.1334843},"labels":[],"label_agreement":null},{"id":"W2991321419","doi":"10.1186/s12859-019-3076-y","title":"DeepEP: a deep learning framework for identifying essential proteins","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":73,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Higher Education Discipline Innovation Project; Fundamental Research Funds for the Central Universities; Central South University; National Natural Science Foundation of China","keywords":"Computational biology; Computer science; DNA microarray; Data science; Bioinformatics; Artificial intelligence; Biology; Genetics; Gene; Gene expression","score_opus":0.01332949612210963,"score_gpt":0.2613690999301562,"score_spread":0.2480396038080466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2991321419","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021172257,0.0011549874,0.97076,0.0004283193,0.00006534226,0.000056831333,0.0011838112,0.0032859806,0.0018924278],"genre_scores_gemma":[0.49752134,0.0021960472,0.48042643,0.00078209554,0.0001286914,0.00033250157,0.0066783004,0.00037494377,0.011559638],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998086,0.000024671164,0.00001013658,0.000054451357,0.00006232284,0.000039848976],"domain_scores_gemma":[0.9997571,0.0000712073,0.000029428502,0.000024137931,0.000088455876,0.000029668932],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043819429,0.0009842245,0.0006647551,0.00082501105,0.00034544614,0.0006993532,0.0018418991,0.0010752323,0.0026285667],"category_scores_gemma":[0.0009010088,0.0004662297,0.00086818944,0.0006476439,0.0004976753,0.0014331527,0.0010255245,0.0017890773,0.0006433872],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021810808,0.00023464218,0.0032455642,0.00031468456,0.00018761905,0.0003904392,0.00008480374,0.64676696,0.014245933,0.036304433,0.017431375,0.2805755],"study_design_scores_gemma":[0.0000047741014,0.000014242399,0.00013541657,0.000005915875,0.0000069233274,0.000022536306,0.0000041996427,0.9910919,0.0016282146,0.006084687,0.0009971166,0.000004020216],"about_ca_topic_score_codex":0.008295587,"about_ca_topic_score_gemma":0.011355696,"teacher_disagreement_score":0.008295587,"about_ca_system_score_codex":0.0010609789,"about_ca_system_score_gemma":0.0013894923,"threshold_uncertainty_score":0.016494632},"labels":[],"label_agreement":null},{"id":"W2995213394","doi":"10.1186/s12859-019-3207-5","title":"SimSpliceEvol: alternative splicing-aware simulation of biological sequence evolution","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA Research and Splicing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Université de Sherbrooke","keywords":"Computational biology; Biology; RNA splicing; Alternative splicing; Alignment-free sequence analysis; Intron; Genetics; Gene; Exon; Sequence analysis; Multiple sequence alignment; Sequence (biology); Inference; Sequence alignment; Computer science; RNA; Peptide sequence; Artificial intelligence","score_opus":0.04217693886673031,"score_gpt":0.3160184066930021,"score_spread":0.2738414678262718,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995213394","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.075089164,0.00093003875,0.8124172,0.0007439143,0.0005896624,0.00035302914,0.00894933,0.089420214,0.011507502],"genre_scores_gemma":[0.37965384,0.000935549,0.5739291,0.0010480075,0.00018290286,0.0022486092,0.01613535,0.019532679,0.006334061],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99937457,0.00021806601,0.00004643411,0.00014172433,0.00014214827,0.00007707784],"domain_scores_gemma":[0.9978077,0.001592631,0.00010072651,0.0001802,0.00017135758,0.00014737752],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016555373,0.0015507614,0.0013945564,0.0008937666,0.00089283806,0.0016808418,0.003970148,0.0025178443,0.012841472],"category_scores_gemma":[0.004811647,0.0010660868,0.0024835179,0.0008706561,0.0011788955,0.0012194797,0.0017668079,0.0027869348,0.002863374],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048950413,0.0001917892,0.0057426,0.0008548195,0.00038816652,0.0005026264,0.00044808583,0.9188661,0.0073017287,0.02081086,0.016890166,0.02751357],"study_design_scores_gemma":[0.000071832306,0.000024383837,0.00017101032,0.000020624586,0.00001842443,0.000046825244,0.000016956183,0.98433083,0.0016348059,0.0075185876,0.0061263437,0.00001937349],"about_ca_topic_score_codex":0.0061828997,"about_ca_topic_score_gemma":0.006199467,"teacher_disagreement_score":0.012841472,"about_ca_system_score_codex":0.0010032277,"about_ca_system_score_gemma":0.0019400868,"threshold_uncertainty_score":0.042958975},"labels":[],"label_agreement":null},{"id":"W2995300996","doi":"10.1186/s12859-019-3202-x","title":"Distinguishing successive ancient polyploidy levels based on genome-internal syntenic alignment","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Plant Reproductive Biology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Genome; Biology; Ploidy; Computational biology; Evolutionary biology; Genetics; Gene","score_opus":0.014250251769733331,"score_gpt":0.24168979627093648,"score_spread":0.22743954450120316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995300996","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9842554,0.00008470548,0.014406264,0.000010251969,0.0000019026171,0.000014246948,0.0002779935,0.00010404078,0.00084526493],"genre_scores_gemma":[0.9944238,0.000030634943,0.00483057,0.0000035549274,0.0000013360557,0.00000972227,0.00056088006,0.000017203702,0.00012239716],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998124,0.00002418233,0.000018230938,0.00007330705,0.000044104636,0.000027784892],"domain_scores_gemma":[0.99884427,0.00049272785,0.00029427008,0.000117524345,0.00010280074,0.00014847009],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055600645,0.00020710715,0.00020038226,0.0013370024,0.00027155847,0.00047239877,0.0002943927,0.00025744812,0.001969074],"category_scores_gemma":[0.0015532937,0.00011036223,0.00042075105,0.00094323535,0.00031516814,0.00050889933,0.00051656464,0.00029397564,0.0003293935],"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":[0.001487228,0.0001266754,0.63496685,0.00032229727,0.00032088804,0.0006556618,0.00059116445,0.032559033,0.27771363,0.004606429,0.00040151633,0.046248637],"study_design_scores_gemma":[0.00003392256,0.0003921313,0.76426804,0.000029569786,0.00024372655,0.0016722839,0.00031719968,0.15973707,0.0650585,0.0063058008,0.0018745256,0.00006715565],"about_ca_topic_score_codex":0.0008496783,"about_ca_topic_score_gemma":0.0010760039,"teacher_disagreement_score":0.001969074,"about_ca_system_score_codex":0.00039418685,"about_ca_system_score_gemma":0.0001841554,"threshold_uncertainty_score":0.0065872073},"labels":[],"label_agreement":null},{"id":"W2995791792","doi":"10.1186/s12859-019-3221-7","title":"Longitudinal linear combination test for gene set analysis","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia; University of Alberta","funders":"","keywords":"DNA microarray; Computational biology; Set (abstract data type); Test (biology); Genetics; Biology; Gene; Computer science; Gene expression; Programming language","score_opus":0.02564994100882009,"score_gpt":0.28636622829989716,"score_spread":0.2607162872910771,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995791792","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.090804294,0.00095232617,0.8956719,0.001150199,0.0006681293,0.00125513,0.003918378,0.0033083286,0.0022713114],"genre_scores_gemma":[0.6448858,0.0002662223,0.3396757,0.00055018486,0.00054140406,0.005277945,0.005906919,0.00045802016,0.0024377347],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.94921994,0.03543678,0.0016104227,0.00765761,0.004947327,0.0011278769],"domain_scores_gemma":[0.7884771,0.18996353,0.006184057,0.0076221176,0.005921467,0.001831732],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.037124842,0.0017584831,0.0035676365,0.0043692407,0.0020672155,0.0021732852,0.0042151315,0.002216375,0.016687214],"category_scores_gemma":[0.13727628,0.00069169904,0.0043930183,0.003954173,0.0028120633,0.0026263664,0.00216802,0.0052994913,0.002211538],"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":[0.013155958,0.0022330899,0.23800321,0.0019046315,0.011574257,0.0027563346,0.0007566645,0.14594424,0.006868451,0.043884695,0.026392626,0.5065259],"study_design_scores_gemma":[0.00064901134,0.0033640387,0.024457138,0.00010483676,0.00079259905,0.00068015454,0.0002479408,0.92378134,0.0030527299,0.037112173,0.005587054,0.00017096408],"about_ca_topic_score_codex":0.002436647,"about_ca_topic_score_gemma":0.0015199829,"teacher_disagreement_score":0.037124842,"about_ca_system_score_codex":0.001835506,"about_ca_system_score_gemma":0.0034663691,"threshold_uncertainty_score":0.19633728},"labels":[],"label_agreement":null},{"id":"W2995918088","doi":"10.1186/s12859-019-3158-x","title":"Benchmarking machine learning models for late-onset alzheimer’s disease prediction from genomic data","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":72,"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; IXICO; Centre hospitalier régional universitaire de Lille; H. Lundbeck A/S; Development of Innovative Strategies for a Transdisciplinary approach to ALZheimer's disease; Eisai; Genentech; Erasmus Medisch Centrum; Servier; Institut National de la Santé et de la Recherche Médicale; Bundesministerium für Bildung und Forschung; Hjartavernd; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; Consejo Nacional de Ciencia y Tecnología; Wellcome Trust; University of Southern California; Université de Lille; Eli Lilly and Company; U.S. Department of Defense; Medical Research Council; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; National Heart, Lung, and Blood Institute; Novartis Pharmaceuticals Corporation; Bristol-Myers Squibb; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Machine learning; Computer science; Artificial intelligence; Disease; Benchmarking; Neuroimaging; Dementia; Selection (genetic algorithm); Medicine; Bioinformatics; Biology; Pathology; Psychiatry","score_opus":0.08631620591382395,"score_gpt":0.31297661523466136,"score_spread":0.22666040932083742,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995918088","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8103528,0.010995034,0.16456917,0.0020352914,0.0003299871,0.0005283317,0.006547371,0.0020875426,0.0025544504],"genre_scores_gemma":[0.9308095,0.0010366315,0.058157615,0.0002880326,0.00008807214,0.0003082001,0.008862791,0.00012407801,0.00032499686],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98778,0.008909994,0.0007982394,0.0013839046,0.0008271849,0.0003006174],"domain_scores_gemma":[0.94937366,0.042833827,0.0014403932,0.0029784692,0.0028813744,0.00049222255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024378195,0.0016523871,0.0011289079,0.0030774465,0.00065638224,0.0015643523,0.0017360217,0.0017387468,0.0009198157],"category_scores_gemma":[0.052894514,0.00042165248,0.0017362937,0.002244874,0.0006889793,0.0012719835,0.0013804244,0.002004988,0.00057560165],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012176797,0.0008834469,0.07549142,0.00080570346,0.0024195907,0.00020651269,0.00019275368,0.81497437,0.0014928483,0.0019114035,0.005839598,0.09456464],"study_design_scores_gemma":[0.00009148007,0.00045860632,0.01128447,0.00010551074,0.00019986268,0.000080615166,0.00006926779,0.9809646,0.0012612415,0.0044900626,0.0009629294,0.000031446038],"about_ca_topic_score_codex":0.008488894,"about_ca_topic_score_gemma":0.0076307585,"teacher_disagreement_score":0.024378195,"about_ca_system_score_codex":0.0015525807,"about_ca_system_score_gemma":0.0017102748,"threshold_uncertainty_score":0.12892574},"labels":[],"label_agreement":null},{"id":"W2996010403","doi":"10.1186/s12859-019-3204-8","title":"Deconvoluting the diversity of within-host pathogen strains in a multi-locus sequence typing framework","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Vector-borne infectious diseases","field":"Immunology and Microbiology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Genome Canada; Alfred P. Sloan Foundation","keywords":"Multilocus sequence typing; Biology; Locus (genetics); Typing; Genetics; Genome; Computational biology; Pathogen; Borrelia burgdorferi; Allele; Genotype; Gene","score_opus":0.036781714347454066,"score_gpt":0.2643672236064904,"score_spread":0.22758550925903634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996010403","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.082910545,0.00043748075,0.9155608,0.00026964128,0.00002905011,0.00003607987,0.00024301864,0.00022306177,0.0002902501],"genre_scores_gemma":[0.59111917,0.0004187101,0.40592808,0.00024024145,0.00015534929,0.00011175579,0.0012052638,0.0001205363,0.0007008699],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981098,0.0008421723,0.000097685916,0.00049107504,0.00027228973,0.00018700247],"domain_scores_gemma":[0.991525,0.005860408,0.0009992706,0.0006096516,0.00056115503,0.00044448796],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005402366,0.0010377705,0.0011336419,0.0021028947,0.0005323272,0.0019106015,0.0015970871,0.0015743145,0.00058214494],"category_scores_gemma":[0.0075026094,0.0006416689,0.0015255741,0.0015597637,0.0011737753,0.0014420808,0.001472932,0.0023345728,0.00026864084],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014326863,0.00013295459,0.021637551,0.000099583995,0.00014252184,0.00025704256,0.0001088503,0.9303095,0.0061039575,0.0057394416,0.00037943444,0.03494591],"study_design_scores_gemma":[0.000004585534,0.000025611618,0.0014205032,0.000008060114,0.000011845692,0.000025493842,0.000016177557,0.991546,0.0004920595,0.006233796,0.00020674853,0.000009102307],"about_ca_topic_score_codex":0.004310147,"about_ca_topic_score_gemma":0.0041199364,"teacher_disagreement_score":0.005402366,"about_ca_system_score_codex":0.0008324157,"about_ca_system_score_gemma":0.001279494,"threshold_uncertainty_score":0.02857083},"labels":[],"label_agreement":null},{"id":"W2996627222","doi":"10.1186/s12859-019-3313-4","title":"perfectphyloR: An R package for reconstructing perfect phylogenies","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Simon Fraser University","keywords":"Partition (number theory); Phylogenetics; Sequence (biology); R package; Evolutionary biology; Biology; Binary number; Computer science; Tree (set theory); Computational biology; Theoretical computer science; Combinatorics; Genetics; Mathematics; Gene; Programming language","score_opus":0.018901358297216276,"score_gpt":0.26608482746657935,"score_spread":0.24718346916936307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996627222","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008445036,0.0018089494,0.63702,0.0009822227,0.00043427374,0.00028155273,0.12428197,0.22160268,0.005143295],"genre_scores_gemma":[0.050228644,0.0014531114,0.7002015,0.0008732058,0.00022737293,0.0015575701,0.11423646,0.12624992,0.004972272],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99610233,0.0018099173,0.0003193247,0.00091984315,0.00064457214,0.00020406416],"domain_scores_gemma":[0.9879637,0.008460834,0.0011208591,0.0014191504,0.0007134439,0.0003220101],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006084834,0.0034289374,0.002933081,0.003953942,0.0012676754,0.0033286724,0.0048633446,0.0016639782,0.06299197],"category_scores_gemma":[0.035183884,0.0027954413,0.0042005205,0.0033453226,0.0016215353,0.0036598358,0.003623835,0.0046096114,0.03778814],"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":[0.0011947284,0.00014257991,0.020701176,0.007072007,0.004057765,0.0012699547,0.001389756,0.03096881,0.01141641,0.03932555,0.7181742,0.16428702],"study_design_scores_gemma":[0.0009732536,0.00027577914,0.013091456,0.0011492628,0.001509195,0.0024740836,0.0003630722,0.17514141,0.0133217275,0.1517748,0.6393968,0.00052927656],"about_ca_topic_score_codex":0.0037003974,"about_ca_topic_score_gemma":0.0047606686,"teacher_disagreement_score":0.06299197,"about_ca_system_score_codex":0.00082008366,"about_ca_system_score_gemma":0.0035533498,"threshold_uncertainty_score":0.21072918},"labels":[],"label_agreement":null},{"id":"W2996835999","doi":"10.1186/s12859-019-3090-0","title":"CSA: a web service for the complete process of ChIP-Seq analysis","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Higher Education Discipline Innovation Project; National Natural Science Foundation of China","keywords":"Computer science; Chromatin immunoprecipitation; Visualization; Chip; Workflow; Personalization; Web service; Bioconductor; Data visualization; Data mining; Computational biology; World Wide Web; Database; Biology; Genetics","score_opus":0.011190339897307547,"score_gpt":0.23813488634227506,"score_spread":0.2269445464449675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996835999","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018816816,0.00031402073,0.19466807,0.00045808946,0.00025429422,0.00068773475,0.025556717,0.7709353,0.005244029],"genre_scores_gemma":[0.041412085,0.0017140846,0.4507983,0.004970942,0.0006003015,0.0067793303,0.24778903,0.22264157,0.023294406],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99775875,0.00041527604,0.00030396983,0.00037788876,0.00082521257,0.00031887923],"domain_scores_gemma":[0.9949562,0.0012538697,0.00039537478,0.0010358685,0.0016371957,0.0007216351],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038462342,0.0040652677,0.0025155032,0.0037069535,0.0012460076,0.002169252,0.0036003771,0.0030500207,0.0675882],"category_scores_gemma":[0.0064754337,0.0014853078,0.002921513,0.00275765,0.0007655603,0.0027593225,0.004435782,0.0033749184,0.10040113],"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":[0.0020056483,0.0005476357,0.003895996,0.0021718186,0.000386442,0.00080632267,0.0004371672,0.00298797,0.05050746,0.005710409,0.7587394,0.17180374],"study_design_scores_gemma":[0.0013404326,0.0002814837,0.008366084,0.000532635,0.00022366412,0.001498763,0.00022819171,0.08767727,0.0656553,0.014836954,0.81862086,0.0007383008],"about_ca_topic_score_codex":0.0039351326,"about_ca_topic_score_gemma":0.0022265944,"teacher_disagreement_score":0.0675882,"about_ca_system_score_codex":0.0011768602,"about_ca_system_score_gemma":0.003442935,"threshold_uncertainty_score":0.2261051},"labels":[],"label_agreement":null},{"id":"W2996913857","doi":"10.1186/s12859-019-3292-5","title":"LMAP_S: Lightweight Multigene Alignment and Phylogeny eStimation","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Australian National University; University of Ottawa; Konkuk University; Helsingin Yliopisto","keywords":"Workflow; Computer science; Software; Data mining; File format; DNA microarray; Workstation; Biology; Database; Gene; Programming language","score_opus":0.008499432732594413,"score_gpt":0.21809406372563014,"score_spread":0.20959463099303574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996913857","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00543956,0.00044194853,0.7139072,0.00028725681,0.00019408761,0.00020364413,0.014945769,0.26306272,0.001517797],"genre_scores_gemma":[0.026449287,0.00039720285,0.8960292,0.0003430363,0.00010111344,0.001199196,0.040310323,0.033381138,0.0017895576],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971641,0.0008199658,0.00024219496,0.000828129,0.00074529054,0.00020040177],"domain_scores_gemma":[0.99588156,0.002065991,0.000584512,0.0006643659,0.0005312854,0.000272267],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0046545113,0.003525753,0.0019594857,0.003251887,0.0017495513,0.00278215,0.0054048696,0.0019319684,0.019875469],"category_scores_gemma":[0.012499855,0.0021728405,0.003396593,0.0034052106,0.0009670698,0.003727663,0.0038377298,0.004492908,0.024048101],"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":[0.0020247805,0.0003548243,0.009184751,0.0040536993,0.0011744845,0.0009569535,0.0011895875,0.036054123,0.05441266,0.015176762,0.4593297,0.41608766],"study_design_scores_gemma":[0.00051835837,0.0004698003,0.008971005,0.0006037708,0.00033520322,0.0014624224,0.00032140588,0.58564675,0.077681415,0.03648027,0.28698525,0.00052428007],"about_ca_topic_score_codex":0.002664495,"about_ca_topic_score_gemma":0.0025713635,"teacher_disagreement_score":0.019875469,"about_ca_system_score_codex":0.0010014557,"about_ca_system_score_gemma":0.0033149973,"threshold_uncertainty_score":0.066490054},"labels":[],"label_agreement":null},{"id":"W2997053614","doi":"10.1186/s12859-019-3315-2","title":"Improvement of the memory function of a mutual repression network in a stochastic environment by negative autoregulation","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Bistability; Biological network; Computer science; Gene regulatory network; Autoregulation; Function (biology); Stochastic process; Robustness (evolution); Mathematics; Biology; Physics; Bioinformatics; Genetics","score_opus":0.004249827032259076,"score_gpt":0.1854823751677977,"score_spread":0.18123254813553863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997053614","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8245522,0.00020218015,0.17130272,0.000271908,0.00003084301,0.000016312753,0.000034717963,0.00027669137,0.0033124592],"genre_scores_gemma":[0.99370825,0.00005440036,0.005842795,0.000019183171,0.0000036869674,0.000011055751,0.00001143482,0.000013162114,0.00033591266],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99989784,0.000027889186,0.0000051518414,0.000026706677,0.00002038909,0.000022039976],"domain_scores_gemma":[0.9991922,0.000503573,0.00014145476,0.000049773775,0.00005853435,0.000054501037],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038898725,0.00029636483,0.00027582294,0.00026730463,0.0002391789,0.00034666614,0.0005363388,0.0003547509,0.00089410646],"category_scores_gemma":[0.0018944644,0.00013435775,0.0002891063,0.0001341744,0.0005595088,0.00047900196,0.00044702814,0.0003969744,0.00008101073],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016902239,0.000120512144,0.0017687863,0.00010430123,0.000035757224,0.00016736498,0.00007871366,0.82124966,0.13082352,0.03184962,0.0002648524,0.013367847],"study_design_scores_gemma":[0.000007587219,0.00003903188,0.00029324068,0.0000023758948,0.000011056406,0.000021967538,0.0000046802375,0.9849133,0.011835391,0.0027024967,0.00016284469,0.000006095292],"about_ca_topic_score_codex":0.0010265578,"about_ca_topic_score_gemma":0.0007456242,"teacher_disagreement_score":0.0010265578,"about_ca_system_score_codex":0.0006657851,"about_ca_system_score_gemma":0.0003791944,"threshold_uncertainty_score":0.004830599},"labels":[],"label_agreement":null},{"id":"W2997277473","doi":"10.1186/s12859-019-3093-x","title":"DDIGIP: predicting drug-drug interactions based on Gaussian interaction profile kernels","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Higher Education Discipline Innovation Project; National Natural Science Foundation of China","keywords":"Drug; Drug-drug interaction; Cross-validation; Computer science; Drug discovery; Drug development; Computational biology; Pharmacology; Data mining; Machine learning; Bioinformatics; Medicine; Biology","score_opus":0.021704322912649888,"score_gpt":0.29665587510186947,"score_spread":0.2749515521892196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997277473","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1793079,0.0021074973,0.81040394,0.000674354,0.00008306035,0.00022910461,0.0014263827,0.004098708,0.0016690464],"genre_scores_gemma":[0.87639076,0.00070764346,0.118985154,0.00019988936,0.000041658273,0.00016726358,0.0016633644,0.00011413447,0.001730211],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99927205,0.00016387126,0.00006508398,0.00015383141,0.00025919187,0.00008601275],"domain_scores_gemma":[0.9987431,0.0006266891,0.00020267341,0.00008974326,0.00026159815,0.00007628835],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015066764,0.00091580447,0.0012028757,0.0014500736,0.00028431375,0.0007900568,0.0012905211,0.0010369468,0.0010589926],"category_scores_gemma":[0.0033932421,0.00038851495,0.0015423937,0.00081386085,0.00037916724,0.0007967155,0.0009037705,0.0012204429,0.00043428031],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045982725,0.00027395054,0.025246443,0.00025594363,0.0003492228,0.00029317115,0.000056291225,0.81019497,0.004096432,0.0018824368,0.0038656935,0.15302567],"study_design_scores_gemma":[0.000008340978,0.000036376136,0.000713121,0.0000030215936,0.000012568368,0.000044189423,0.0000036920499,0.9978891,0.0006329725,0.00041626257,0.00023450649,0.000005777263],"about_ca_topic_score_codex":0.011588018,"about_ca_topic_score_gemma":0.005825519,"teacher_disagreement_score":0.011588018,"about_ca_system_score_codex":0.001048689,"about_ca_system_score_gemma":0.0018200392,"threshold_uncertainty_score":0.02304113},"labels":[],"label_agreement":null},{"id":"W2997640910","doi":"10.1186/s12859-019-3266-7","title":"A systematic evaluation of copy number alterations detection methods on real SNP array and deep sequencing data","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomic variations and chromosomal abnormalities","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Natural Science Foundation of China; McGill University; National Science Foundation","keywords":"Computer science; Benchmark (surveying); Data mining; SNP array; SNP; Scale (ratio); Computational biology; Biology; Single-nucleotide polymorphism; Genetics; Gene","score_opus":0.057937045641693906,"score_gpt":0.34181766453312307,"score_spread":0.2838806188914292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997640910","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7455041,0.030563591,0.15237221,0.0015059062,0.0017668406,0.00151187,0.04792215,0.011027216,0.007826171],"genre_scores_gemma":[0.62659127,0.0026987619,0.24167879,0.0009513278,0.00028805522,0.0008592346,0.122942984,0.00063342275,0.0033562079],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9826695,0.004537955,0.0017978001,0.004745547,0.0056455894,0.00060367567],"domain_scores_gemma":[0.9792271,0.009490418,0.0014898727,0.0027910974,0.006396424,0.00060508563],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014491767,0.0021668267,0.0016260319,0.0051105325,0.0011298088,0.0018701426,0.0023783974,0.0017731771,0.0008632935],"category_scores_gemma":[0.022678716,0.00043312047,0.0017992012,0.003034592,0.0008272219,0.0019662497,0.0017617691,0.0011081917,0.0007547353],"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":[0.0030453757,0.001320453,0.2671569,0.0072023096,0.0041669593,0.0011394421,0.00060172094,0.06602665,0.04910032,0.0024080982,0.069596104,0.5282357],"study_design_scores_gemma":[0.00066468416,0.0026948298,0.25700194,0.000981787,0.0017754628,0.003169761,0.0013861078,0.5733733,0.10006772,0.0048292195,0.053566165,0.0004890834],"about_ca_topic_score_codex":0.008532277,"about_ca_topic_score_gemma":0.015029049,"teacher_disagreement_score":0.014491767,"about_ca_system_score_codex":0.0012862055,"about_ca_system_score_gemma":0.0019893206,"threshold_uncertainty_score":0.076640725},"labels":[],"label_agreement":null},{"id":"W2997828579","doi":"10.1186/s12859-019-3054-4","title":"Antimicrobial resistance genetic factor identification from whole-genome sequence data using deep feature selection","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Identification (biology); Computational biology; Feature selection; Whole genome sequencing; Biology; Selection (genetic algorithm); DNA microarray; Genetics; Genome; Artificial intelligence; Bioinformatics; Computer science; Gene; Gene expression","score_opus":0.03449597150938384,"score_gpt":0.2599799649302015,"score_spread":0.22548399342081765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997828579","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6551321,0.0015743792,0.33463863,0.00074577244,0.00009576533,0.0001432775,0.0034102541,0.0027121457,0.0015477337],"genre_scores_gemma":[0.92204785,0.00026006892,0.07119886,0.00020867452,0.000039041024,0.00011830071,0.005269993,0.00003766309,0.00081961235],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994956,0.00013999052,0.00004345908,0.00015616817,0.00009604265,0.00006868297],"domain_scores_gemma":[0.9990746,0.0004353859,0.00012805707,0.00006836331,0.00025051227,0.000043094245],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010102546,0.0008526779,0.0007722732,0.0014188166,0.0002794168,0.0005518944,0.00065862184,0.0006505908,0.00055053475],"category_scores_gemma":[0.002038815,0.00018496525,0.0009852893,0.0010485176,0.0002427734,0.0005126577,0.0006080168,0.00080573343,0.00026697834],"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":[0.0007621383,0.00081908016,0.10130691,0.0003397699,0.0008019518,0.0007655189,0.00018826737,0.23960859,0.057327732,0.00089285965,0.008232362,0.58895487],"study_design_scores_gemma":[0.00002322608,0.00011651768,0.010292834,0.000013007669,0.000051843548,0.00012656163,0.000037966794,0.9812439,0.0059155324,0.0012961591,0.000865221,0.000017151877],"about_ca_topic_score_codex":0.004311776,"about_ca_topic_score_gemma":0.004128273,"teacher_disagreement_score":0.004311776,"about_ca_system_score_codex":0.00045390902,"about_ca_system_score_gemma":0.0006471919,"threshold_uncertainty_score":0.008573353},"labels":[],"label_agreement":null},{"id":"W2998018748","doi":"10.1186/s12859-019-3278-3","title":"IILLS: predicting virus-receptor interactions based on similarity and semi-supervised learning","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","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":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Higher Education Discipline Innovation Project; National Natural Science Foundation of China","keywords":"Similarity (geometry); Computational biology; Artificial intelligence; Computer science; Cross-validation; Virus; Pattern recognition (psychology); Machine learning; Biology; Virology","score_opus":0.008804090554234723,"score_gpt":0.24521196154674885,"score_spread":0.23640787099251412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2998018748","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2146801,0.001922185,0.7714974,0.00066687056,0.00023373197,0.00041342064,0.0012436276,0.006333482,0.0030092474],"genre_scores_gemma":[0.8375644,0.00043881548,0.15365863,0.0005120839,0.0002417469,0.0003071656,0.003960906,0.00016988155,0.0031463448],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977958,0.000590992,0.00019740665,0.0006040044,0.0005958116,0.00021593964],"domain_scores_gemma":[0.9969674,0.001343421,0.00050639873,0.00029725785,0.00065662054,0.00022890774],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027791548,0.0014673349,0.001767575,0.0027264007,0.0006363428,0.0010795128,0.0022868642,0.0015399753,0.0015814006],"category_scores_gemma":[0.0037815897,0.0004407741,0.001951536,0.0010052952,0.0007145828,0.0014535617,0.001203,0.0016146116,0.0008884591],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008558517,0.0014634638,0.04391016,0.00055264466,0.0009688313,0.0005327942,0.00019432761,0.524768,0.009085748,0.002255202,0.016179485,0.39923355],"study_design_scores_gemma":[0.000010305069,0.0000460606,0.0006261028,0.000005351111,0.000015335263,0.00003873047,0.000008898974,0.9979177,0.0006320593,0.0005095139,0.0001816952,0.000008199488],"about_ca_topic_score_codex":0.0065012164,"about_ca_topic_score_gemma":0.0055994675,"teacher_disagreement_score":0.0065012164,"about_ca_system_score_codex":0.00087267935,"about_ca_system_score_gemma":0.0014059419,"threshold_uncertainty_score":0.014697731},"labels":[],"label_agreement":null},{"id":"W2998581384","doi":"10.1186/s12859-019-3268-5","title":"Using discriminative vector machine model with 2DPCA to predict interactions among proteins","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","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":"Alberta Children's Hospital; University of Calgary","funders":"National Natural Science Foundation of China; National Science Foundation","keywords":"Discriminative model; Computational biology; Computer science; Support vector machine; Artificial intelligence; DNA microarray; Machine learning; Vector (molecular biology); Pattern recognition (psychology); Bioinformatics; Biology; Genetics; Gene expression","score_opus":0.01863703357937437,"score_gpt":0.25302364867889704,"score_spread":0.23438661509952266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2998581384","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12769833,0.0027621763,0.862617,0.0008271346,0.00034849663,0.00020065186,0.00043427563,0.0026222563,0.002489692],"genre_scores_gemma":[0.8851839,0.0007112244,0.109353825,0.00032023934,0.00018962311,0.0002906372,0.0013491012,0.00008906599,0.0025123474],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993843,0.00017383618,0.000042442924,0.00019756523,0.00012135617,0.00008047963],"domain_scores_gemma":[0.99894446,0.0005274514,0.00009675989,0.000091298876,0.00028524385,0.00005480752],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012323104,0.0011458582,0.0012088111,0.001319396,0.00044716918,0.0009236068,0.0013676494,0.0011247837,0.0014466654],"category_scores_gemma":[0.0025002644,0.0003370643,0.0011627637,0.0010791374,0.00042670753,0.00082941767,0.0006202721,0.0015902102,0.00056218426],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018170702,0.00022476778,0.004665835,0.000119048695,0.000155086,0.00015351384,0.00005178383,0.78861815,0.0031275472,0.002497845,0.0049354336,0.19526924],"study_design_scores_gemma":[0.000002011951,0.000009694173,0.000116574025,0.0000017606783,0.0000037710413,0.0000057179586,0.0000019092984,0.9992811,0.00011904386,0.00036522176,0.00009085931,0.0000024154492],"about_ca_topic_score_codex":0.008938613,"about_ca_topic_score_gemma":0.0049306243,"teacher_disagreement_score":0.008938613,"about_ca_system_score_codex":0.0006130651,"about_ca_system_score_gemma":0.001277433,"threshold_uncertainty_score":0.017773151},"labels":[],"label_agreement":null},{"id":"W2998682161","doi":"10.1186/s12859-019-3293-4","title":"Rearrangement analysis of multiple bacterial genomes","year":2019,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute for Basic Biology; Institute of Genetics; National Cancer Institute; National Bioscience Database Center; Japan Society for the Promotion of Science; Ministry of Education, Culture, Sports, Science and Technology","keywords":"Genome; Computational biology; Bacterial genome size; DNA microarray; Biology; Computer science; Genetics; Gene; Gene expression","score_opus":0.011779181864968055,"score_gpt":0.22678324183369095,"score_spread":0.2150040599687229,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2998682161","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9084008,0.0015561813,0.082329765,0.00011674132,0.000045022643,0.00015224631,0.0025909718,0.0020646215,0.0027436372],"genre_scores_gemma":[0.9131525,0.0005534011,0.0763884,0.00005769041,0.000030439265,0.00014454019,0.008376881,0.00026684886,0.0010292018],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99926454,0.00012337927,0.000055973305,0.0002500214,0.00020641735,0.00009963354],"domain_scores_gemma":[0.9990791,0.00040587859,0.00018985348,0.00009084268,0.00016133214,0.00007288048],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060088764,0.0004007098,0.00048142482,0.0038539902,0.00054679427,0.00063871156,0.0005718251,0.00039071857,0.0028114456],"category_scores_gemma":[0.0022228898,0.00023313497,0.00091000623,0.0027068688,0.0002544767,0.00067676004,0.00075945054,0.00040403733,0.0006810487],"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":[0.0021554886,0.00031770056,0.11835182,0.0015016065,0.000779777,0.00200541,0.0008571942,0.069135964,0.46814835,0.004892721,0.0029300775,0.32892385],"study_design_scores_gemma":[0.00015513152,0.0016939206,0.24285665,0.00019413736,0.00071021606,0.0058492026,0.0013266964,0.5367209,0.16598955,0.011519889,0.032814257,0.00016948262],"about_ca_topic_score_codex":0.0012801448,"about_ca_topic_score_gemma":0.0010426209,"teacher_disagreement_score":0.0038539902,"about_ca_system_score_codex":0.00048675018,"about_ca_system_score_gemma":0.00034775797,"threshold_uncertainty_score":0.009405196},"labels":[],"label_agreement":null},{"id":"W3000659041","doi":"10.1186/s12859-019-3312-5","title":"Optimization and expansion of non-negative matrix factorization","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Tensor decomposition and applications","field":"Mathematics","cited_by":125,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"Natural Sciences and Engineering Research Council of Canada; Prostate Cancer Canada; Government of Ontario; Canadian Institutes of Health Research; Ontario Genomics; Genome Canada; Government of Canada; Ontario Institute for Cancer Research; Ontario Genomics Institute; Movember Foundation","keywords":"Non-negative matrix factorization; Computer science; Matrix (chemical analysis); Matrix decomposition; Computational biology; Biology; Mathematics; Physics; Chemistry","score_opus":0.044048035217136294,"score_gpt":0.30938569971251123,"score_spread":0.26533766449537494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3000659041","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016201313,0.00024237843,0.99676764,0.00020187958,0.000043686137,0.0000271091,0.00008807119,0.00016540772,0.0008437496],"genre_scores_gemma":[0.07034129,0.000768368,0.9242586,0.00020820124,0.00016877573,0.00026969746,0.0005364539,0.00030437286,0.0031441858],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986965,0.00055755686,0.000056350786,0.00025270352,0.00035043916,0.00008651086],"domain_scores_gemma":[0.99658054,0.0019664306,0.00034719642,0.00034832972,0.0006274074,0.00013022883],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003053607,0.0014086773,0.0009150195,0.0007842839,0.00048188807,0.0009956132,0.0010234577,0.0013574556,0.0043527395],"category_scores_gemma":[0.010389089,0.00047773428,0.0012512726,0.00086488103,0.0013887198,0.001337394,0.0012804875,0.0020531144,0.0025495065],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011784914,0.00008812379,0.00090362894,0.00073161523,0.00008642121,0.0003057685,0.00023637334,0.68007886,0.008995838,0.130224,0.017788822,0.16044265],"study_design_scores_gemma":[0.000010548646,0.00002155662,0.00015868811,0.00003817861,0.00000655494,0.000073969386,0.000017431295,0.95496386,0.0011833787,0.03922664,0.004287324,0.0000119024035],"about_ca_topic_score_codex":0.0031922418,"about_ca_topic_score_gemma":0.0039182,"teacher_disagreement_score":0.0043527395,"about_ca_system_score_codex":0.0009779045,"about_ca_system_score_gemma":0.0017594292,"threshold_uncertainty_score":0.016149223},"labels":[],"label_agreement":null},{"id":"W3003647270","doi":"10.1186/s12859-019-3190-x","title":"DeepECA: an end-to-end learning framework for protein contact prediction from a multiple sequence alignment","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Genetics; University of Tokyo; Japan Agency for Medical Research and Development","keywords":"End-to-end principle; Computational biology; Sequence (biology); Computer science; Sequence alignment; Multiple sequence alignment; DNA microarray; Artificial intelligence; Biology; Bioinformatics; Peptide sequence; Genetics; Gene","score_opus":0.022764288424854583,"score_gpt":0.258106808117291,"score_spread":0.23534251969243639,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3003647270","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020466637,0.00072616304,0.9717336,0.00034311033,0.00006883502,0.00007461318,0.00043560704,0.005012561,0.0011389772],"genre_scores_gemma":[0.41255662,0.0009017222,0.57531494,0.0006836376,0.00014959322,0.00040324355,0.002914806,0.00046347364,0.0066119703],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996804,0.000063646155,0.000017804774,0.00009665652,0.00009490506,0.000046638743],"domain_scores_gemma":[0.99947935,0.00019773822,0.000061697094,0.000052764677,0.00014909447,0.000059404178],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00095660234,0.001177897,0.00084263633,0.00081363093,0.0004601982,0.000783295,0.002313849,0.0015903647,0.0027793306],"category_scores_gemma":[0.0015767682,0.00049176894,0.0009418089,0.0006593984,0.0006056955,0.0015205822,0.0012740714,0.0025919483,0.00090138405],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002586274,0.00022586339,0.0019901462,0.00011625066,0.0001432867,0.00019806008,0.000074523414,0.7550104,0.0053791506,0.007844866,0.007257765,0.221501],"study_design_scores_gemma":[0.000004074623,0.000016687514,0.00004955346,0.0000033305237,0.0000031568989,0.0000072487287,0.0000023245505,0.9970499,0.0005692008,0.0019193368,0.00037233016,0.0000027008032],"about_ca_topic_score_codex":0.010385785,"about_ca_topic_score_gemma":0.01685542,"teacher_disagreement_score":0.010385785,"about_ca_system_score_codex":0.0011857654,"about_ca_system_score_gemma":0.0013609248,"threshold_uncertainty_score":0.020650685},"labels":[],"label_agreement":null},{"id":"W30089455","doi":"10.1186/s12859-018-2289-9","title":"A Position Between Two Curves site specific installation","year":2003,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Conservation Techniques and Studies","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Fondation Brain Canada; Canadian Institute for Advanced Research","keywords":"Exhibition; Microphone; Loudspeaker; Noise (video); Space (punctuation); Position (finance); Point (geometry); Acoustics; Scale (ratio); Sound (geography); Computer science; Visual arts; Physics; Art; Mathematics; Artificial intelligence; Geometry","score_opus":0.07189833449293616,"score_gpt":0.25813552594355377,"score_spread":0.18623719145061762,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W30089455","genre_codex":"software","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006921549,0.00028788124,0.31137648,0.0013526912,0.0034678231,0.00060150225,0.029160202,0.5106187,0.13621323],"genre_scores_gemma":[0.07429208,0.00054218044,0.40953517,0.0025336796,0.00087793154,0.0011002261,0.06804055,0.15649699,0.2865812],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992637,0.00010537581,0.000057722456,0.00020973054,0.0002496431,0.000113780305],"domain_scores_gemma":[0.995887,0.0009079364,0.00014041348,0.0013999852,0.0011922104,0.0004725299],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012263282,0.0014223076,0.0009805219,0.0018545055,0.0014300641,0.0021612183,0.0019326371,0.0019047736,0.4074681],"category_scores_gemma":[0.006782543,0.0013872405,0.0009522675,0.0018816111,0.00048573076,0.0022563527,0.0026723973,0.0027993133,0.25384492],"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":[0.001065564,0.00015569793,0.0016177852,0.00046468232,0.000028595896,0.0004789544,0.00036342329,0.0010490159,0.022478338,0.0117687965,0.74093723,0.2195919],"study_design_scores_gemma":[0.00013083148,0.00010874525,0.0016435576,0.00009247785,0.000023717163,0.0003627252,0.00009223686,0.0052123005,0.018137809,0.0060656937,0.9680568,0.00007312838],"about_ca_topic_score_codex":0.001734232,"about_ca_topic_score_gemma":0.001483569,"teacher_disagreement_score":0.4074681,"about_ca_system_score_codex":0.00055528275,"about_ca_system_score_gemma":0.00072558667,"threshold_uncertainty_score":0.8451748},"labels":[],"label_agreement":null},{"id":"W3010830252","doi":"10.1186/s12859-020-3346-8","title":"Ensemble disease gene prediction by clinical sample-based networks","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"China Scholarship Council; Natural Sciences and Engineering Research Council of Canada; Natural Science Foundation of Shaanxi Province; National Natural Science Foundation of China","keywords":"DNA microarray; Computational biology; Ensemble learning; Computer science; Disease; Artificial intelligence; Gene; Bioinformatics; Genetics; Biology; Medicine; Gene expression; Pathology","score_opus":0.024874482279030368,"score_gpt":0.2560171676417269,"score_spread":0.23114268536269653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3010830252","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39893022,0.00260203,0.5917646,0.0009165258,0.00011280659,0.00019264483,0.0016506317,0.0014743325,0.0023561362],"genre_scores_gemma":[0.918578,0.0005752753,0.07704517,0.00017499669,0.00011615013,0.00009634089,0.0026448243,0.000043123677,0.0007261229],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99923134,0.00021598156,0.000045293444,0.0002747261,0.00017040392,0.00006226084],"domain_scores_gemma":[0.99713886,0.0016914635,0.0003433188,0.00023342951,0.00046161868,0.00013145647],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017405305,0.0011840487,0.0009275639,0.002122633,0.00037436638,0.00066571723,0.0008159143,0.00085407414,0.00077789696],"category_scores_gemma":[0.00454362,0.0003246475,0.00091423426,0.0010744362,0.00035308278,0.0010247183,0.00066578196,0.000913612,0.00026620794],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005286461,0.0002669101,0.09446438,0.00011972181,0.0005295155,0.0005805621,0.00009920404,0.67914385,0.0044191503,0.0012500534,0.003588224,0.21500984],"study_design_scores_gemma":[0.000009039968,0.000034999848,0.002907171,0.000009407414,0.000057230005,0.00010133678,0.000012088786,0.9937582,0.0009567031,0.0017770579,0.0003700289,0.0000067139113],"about_ca_topic_score_codex":0.005265638,"about_ca_topic_score_gemma":0.0065082028,"teacher_disagreement_score":0.005265638,"about_ca_system_score_codex":0.0007299734,"about_ca_system_score_gemma":0.00064361596,"threshold_uncertainty_score":0.010470033},"labels":[],"label_agreement":null},{"id":"W3011481967","doi":"10.1186/s12859-020-3397-x","title":"CNV Radar: an improved method for somatic copy number alteration characterization in oncology","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Cancer Research; University of Calgary","funders":"Janssen Research and Development","keywords":"Copy-number variation; Concordance; Loss of heterozygosity; Copy number analysis; Oncology; Biology; Medicine; Bioinformatics; Genetics; Allele; Gene; Genome","score_opus":0.021740245374512534,"score_gpt":0.31035138363434267,"score_spread":0.28861113825983015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011481967","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029240612,0.0017794506,0.87147087,0.0003684956,0.0003250418,0.00061815267,0.009880206,0.08266971,0.0036474627],"genre_scores_gemma":[0.087376215,0.000506317,0.8965873,0.00048480646,0.0001919094,0.0013885825,0.006271092,0.00397108,0.0032227417],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962025,0.0009121737,0.00035783852,0.0010502728,0.001322547,0.00015459073],"domain_scores_gemma":[0.9946138,0.0028322546,0.0009170455,0.00065528415,0.00082122337,0.00016043473],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00457903,0.0015165319,0.0011222109,0.006680917,0.0005030979,0.0013466503,0.0014869453,0.00142545,0.0116042895],"category_scores_gemma":[0.015529354,0.000890066,0.0013453945,0.002321828,0.00047347008,0.0013698981,0.0020172861,0.0012425896,0.0045448476],"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":[0.0015556806,0.00020495607,0.02951906,0.0012607739,0.00084260455,0.0007965639,0.0004947775,0.011320343,0.1316306,0.0068003046,0.053665712,0.76190865],"study_design_scores_gemma":[0.0007376411,0.0007053038,0.06955174,0.00038960399,0.00062332326,0.007113455,0.00019385823,0.60763144,0.16642763,0.02017323,0.12581599,0.0006368283],"about_ca_topic_score_codex":0.0017348421,"about_ca_topic_score_gemma":0.0033786509,"teacher_disagreement_score":0.0116042895,"about_ca_system_score_codex":0.0007195622,"about_ca_system_score_gemma":0.0011388926,"threshold_uncertainty_score":0.038820207},"labels":[],"label_agreement":null},{"id":"W3012154856","doi":"10.1186/s12859-020-3426-9","title":"PESM: predicting the essentiality of miRNAs based on gradient boosting machines and sequences","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"MicroRNA in disease regulation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"National Natural Science Foundation of China","keywords":"Boosting (machine learning); Support vector machine; Computer science; Bayes' theorem; microRNA; Machine learning; Gradient boosting; Naive Bayes classifier; Artificial intelligence; Computational biology; DNA microarray; Data mining; Biology; Bayesian probability; Random forest; Gene; Genetics; Gene expression","score_opus":0.019176273843448458,"score_gpt":0.24489331344234425,"score_spread":0.22571703959889577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3012154856","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11301765,0.0017624012,0.8805976,0.0005108275,0.0001952994,0.00015234815,0.0003909034,0.002082161,0.0012907542],"genre_scores_gemma":[0.7164783,0.0005875509,0.27888352,0.00033810257,0.00017990729,0.00022656556,0.0011043262,0.00013075421,0.0020710158],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99912053,0.00030816454,0.00006229973,0.00019026213,0.00022159352,0.00009720484],"domain_scores_gemma":[0.9986206,0.0008309553,0.00013361232,0.00007507463,0.00027325496,0.00006660194],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002365398,0.00096063013,0.0013075237,0.0011852471,0.00042585394,0.00056347443,0.00091300067,0.0010126183,0.0010938232],"category_scores_gemma":[0.0034029102,0.00041718432,0.0013299906,0.00057424547,0.00036744802,0.0006631662,0.0005651138,0.0011127366,0.0004850495],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00066831225,0.00040135978,0.020128764,0.0002873812,0.0004240858,0.0003144951,0.00008061534,0.5805111,0.013198202,0.0036342298,0.007163539,0.373188],"study_design_scores_gemma":[0.00001615525,0.00007072641,0.00094697694,0.000007827136,0.00002703241,0.00005288688,0.000003825155,0.99479103,0.0019105704,0.0016337337,0.0005317594,0.000007446558],"about_ca_topic_score_codex":0.0014261391,"about_ca_topic_score_gemma":0.0012185675,"teacher_disagreement_score":0.002365398,"about_ca_system_score_codex":0.000415127,"about_ca_system_score_gemma":0.0011064105,"threshold_uncertainty_score":0.012509584},"labels":[],"label_agreement":null},{"id":"W3012532670","doi":"10.1186/s12859-020-3345-9","title":"Prediction of tumor location in prostate cancer tissue using a machine learning system on gene expression data","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada; University of Windsor","keywords":"Laterality; Prostate cancer; Prostate; Gene; Human leukocyte antigen; Computational biology; DNA microarray; Cancer; Gene expression; Biology; Artificial intelligence; Computer science; Genetics; Neuroscience; Antigen","score_opus":0.041854032633337535,"score_gpt":0.2834448822248406,"score_spread":0.24159084959150307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3012532670","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8213515,0.0007088062,0.1720782,0.0003669795,0.00007296484,0.00018955444,0.0019938294,0.0019392573,0.0012988889],"genre_scores_gemma":[0.93589044,0.00016276562,0.06144033,0.000060394905,0.000036964782,0.0001868204,0.0015979907,0.000019100818,0.00060528103],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995993,0.00008942199,0.000036637517,0.0001570856,0.000068523004,0.000049123293],"domain_scores_gemma":[0.9991335,0.0005358743,0.00009112704,0.000041902622,0.00016541293,0.000032207154],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080017396,0.0006006574,0.0006561473,0.0015592864,0.0002634186,0.00066516607,0.00038093698,0.0005929371,0.00085153925],"category_scores_gemma":[0.0016439869,0.00012343789,0.0005580154,0.000877743,0.00018967381,0.00029805847,0.00024862375,0.0004137738,0.0005018179],"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":[0.0013331405,0.0011504615,0.20752417,0.00033399597,0.00037564564,0.0005340707,0.00016977257,0.15004946,0.07435388,0.0003545728,0.002643934,0.56117684],"study_design_scores_gemma":[0.000020562851,0.00028843305,0.039945185,0.000020947928,0.000064398075,0.00016692682,0.00006073485,0.946643,0.011768268,0.00051235285,0.00048914424,0.000020012036],"about_ca_topic_score_codex":0.001753363,"about_ca_topic_score_gemma":0.0014963982,"teacher_disagreement_score":0.001753363,"about_ca_system_score_codex":0.00048168734,"about_ca_system_score_gemma":0.00044094093,"threshold_uncertainty_score":0.0042318106},"labels":[],"label_agreement":null},{"id":"W3012879287","doi":"10.1186/s12859-020-3368-2","title":"GenEpi: gene-based epistasis discovery using machine learning","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; University of California, San Diego; Genentech; National Institutes of Health; H. Lundbeck A/S; Servier; Nanjing University of Aeronautics and Astronautics; National Natural Science Foundation of China; Eisai; U.S. National Library of Medicine; IXICO; Northern California Institute for Research and Education; Ministry of Science and Technology, Taiwan; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; University of Southern California; Scheme for Promotion of Academic and Research Collaboration; Novartis Pharmaceuticals Corporation; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; Foundation for the National Institutes of Health; Alzheimer's Disease Neuroimaging Initiative; National Center for Advancing Translational Sciences; Meso Scale Diagnostics; Alzheimer's Association; National Science Foundation","keywords":"Epistasis; Genome-wide association study; Computational biology; Computer science; Machine learning; Biology; Artificial intelligence; Genetics; Gene; Single-nucleotide polymorphism; Genotype","score_opus":0.0393174571091678,"score_gpt":0.26343535917751904,"score_spread":0.22411790206835125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3012879287","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0113845775,0.00029320287,0.9532869,0.00031726382,0.00007187959,0.00015223253,0.0023787662,0.031115767,0.0009994624],"genre_scores_gemma":[0.1388542,0.00037544614,0.84939706,0.0004021309,0.00007090415,0.0012212171,0.0054105693,0.0024668796,0.0018015333],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993025,0.0003171944,0.00002958612,0.00016019674,0.00014364436,0.00004690886],"domain_scores_gemma":[0.99794406,0.0016113826,0.0001240258,0.00015035975,0.000102128695,0.000068078465],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018780814,0.0015733442,0.0014549264,0.0012024215,0.0005008426,0.0009105678,0.0023605027,0.0009981628,0.006806249],"category_scores_gemma":[0.0065331403,0.0006945606,0.0021431248,0.0010070029,0.0005252005,0.0007368044,0.0012273717,0.0019005239,0.001794294],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011305476,0.0006759527,0.022175074,0.0015932636,0.002064394,0.0011239131,0.00039854864,0.51714903,0.013374213,0.044588957,0.06577872,0.3299474],"study_design_scores_gemma":[0.00009877297,0.000054381664,0.00072458625,0.000013401703,0.00006857023,0.000093626484,0.000008350514,0.9805818,0.0012827356,0.013180423,0.0038722223,0.00002108971],"about_ca_topic_score_codex":0.002504042,"about_ca_topic_score_gemma":0.003034179,"teacher_disagreement_score":0.006806249,"about_ca_system_score_codex":0.0004558783,"about_ca_system_score_gemma":0.0018009886,"threshold_uncertainty_score":0.022769213},"labels":[],"label_agreement":null},{"id":"W3014189804","doi":"10.1186/s12859-020-3415-z","title":"Visualizing metabolic network dynamics through time-series metabolomic data","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"National Institutes of Health; Novo Nordisk; National Institute of General Medical Sciences; Landspítali Háskólasjúkrahús; Háskóli Íslands; National Center for Advancing Translational Sciences; Danmarks Tekniske Universitet; Eberhard Karls Universität Tübingen; Novo Nordisk Fonden; Google; Deutsches Zentrum für Infektionsforschung; Deutsche Forschungsgemeinschaft","keywords":"Visualization; Metabolic network; Metabolomics; Computer science; Context (archaeology); Metabolome; Data visualization; Big data; Data science; Data mining; Computational biology; Bioinformatics; Biology","score_opus":0.039005607178237194,"score_gpt":0.2777569274503506,"score_spread":0.23875132027211338,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3014189804","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19292593,0.0042172302,0.5802449,0.0058331853,0.001964974,0.0005604952,0.1440092,0.046272717,0.023971425],"genre_scores_gemma":[0.40093118,0.0041035903,0.5256743,0.0009281347,0.00076156337,0.0007178005,0.051869,0.0031736817,0.011840773],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998419,0.00004061691,0.000012934145,0.00003480021,0.000052314095,0.000017259636],"domain_scores_gemma":[0.9987476,0.0007236352,0.00013707839,0.00008764093,0.0002085608,0.000095495016],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005232562,0.0006369429,0.00044631216,0.0020754575,0.00034570097,0.0012484988,0.00077721226,0.0008826883,0.038695768],"category_scores_gemma":[0.0022059944,0.00024083337,0.00069645164,0.0014685497,0.00016775301,0.000733734,0.0007501309,0.00076152605,0.0021158082],"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":[0.0023798114,0.0003527777,0.020628171,0.004817652,0.00058257056,0.0025436769,0.0017669855,0.055527665,0.3464206,0.021075567,0.25460643,0.28929806],"study_design_scores_gemma":[0.00020985419,0.0004737779,0.048132412,0.0007408331,0.0002738068,0.0015468388,0.0010389773,0.5054174,0.12789379,0.027190477,0.2867134,0.00036841023],"about_ca_topic_score_codex":0.0027790808,"about_ca_topic_score_gemma":0.0035554036,"teacher_disagreement_score":0.038695768,"about_ca_system_score_codex":0.0004608883,"about_ca_system_score_gemma":0.00073870376,"threshold_uncertainty_score":0.12945026},"labels":[],"label_agreement":null},{"id":"W3020323696","doi":"10.1186/s12859-019-3311-6","title":"TooT-T: discrimination of transport proteins from non-transport proteins","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; King Saud University; Saudi Arabian Cultural Bureau; Genome Canada","keywords":"Computational biology; Classifier (UML); Membrane protein; Membrane transport protein; Protein function prediction; Computer science; Function (biology); Protein sequencing; Transport protein; Protein function; Artificial intelligence; Machine learning; Membrane; Bioinformatics; Chemistry; Biology; Peptide sequence; Biochemistry; Genetics; Gene","score_opus":0.014126327398125518,"score_gpt":0.2362567035197294,"score_spread":0.22213037612160388,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3020323696","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5816207,0.0046092714,0.38587782,0.0012906365,0.001119881,0.0005415518,0.004491885,0.008968371,0.011479848],"genre_scores_gemma":[0.891838,0.00077668467,0.09370402,0.00038714334,0.00030178454,0.00022394922,0.008233196,0.00021433552,0.004320861],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99876535,0.00019535152,0.000096730364,0.00037838615,0.00037805468,0.00018617723],"domain_scores_gemma":[0.9983145,0.00059295545,0.00016328465,0.00015021244,0.0005785058,0.00020057023],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015523097,0.0012935522,0.001146664,0.0022103756,0.00071544416,0.0012736886,0.0012803643,0.0017621131,0.001596717],"category_scores_gemma":[0.0026191156,0.00017553054,0.0019066709,0.0010620514,0.0002688294,0.001104141,0.0009934509,0.0014040237,0.0014715442],"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":[0.0015889389,0.0010642826,0.06729449,0.00050627044,0.00074401824,0.00094113685,0.00014389976,0.104084834,0.06538628,0.0023597893,0.03358662,0.72229946],"study_design_scores_gemma":[0.000031391024,0.00053733203,0.007947557,0.000043070602,0.00017147823,0.0007708433,0.00007720988,0.9653769,0.018687628,0.0022505363,0.0040576393,0.000048366775],"about_ca_topic_score_codex":0.0032716105,"about_ca_topic_score_gemma":0.0029315269,"teacher_disagreement_score":0.0032716105,"about_ca_system_score_codex":0.0006207577,"about_ca_system_score_gemma":0.0010994907,"threshold_uncertainty_score":0.008209527},"labels":[],"label_agreement":null},{"id":"W3021761165","doi":"10.1186/s12859-020-3441-x","title":"Intrinsic limitations in mainstream methods of identifying network motifs in biology","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Young Scientists Fund; Medical Research Council; National Health and Medical Research Council; National Natural Science Foundation of China; National Science Foundation","keywords":"Motif (music); Biological network; Mainstream; Spurious relationship; Computational biology; Data science; Network motif; Systems biology; Computer science; Gene regulatory network; Underpinning; Network analysis; Identification (biology); Synthetic biology; Biology; Machine learning; Genetics; Gene","score_opus":0.06509519079156656,"score_gpt":0.3180088046397023,"score_spread":0.25291361384813577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3021761165","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0051531936,0.005462485,0.98147064,0.0053044762,0.0002572744,0.000091038186,0.00016815795,0.00047608616,0.0016167136],"genre_scores_gemma":[0.17045367,0.009818309,0.8128196,0.002247922,0.0014867168,0.0008984423,0.00044330742,0.00056287705,0.0012691932],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9239603,0.04789705,0.0036066493,0.007951055,0.01594688,0.0006380893],"domain_scores_gemma":[0.46727073,0.48762777,0.00632538,0.023813425,0.013734124,0.0012286269],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.101847775,0.0020696968,0.0026540994,0.004631384,0.0018156698,0.0060283253,0.0073433896,0.003822161,0.0024898306],"category_scores_gemma":[0.3215012,0.0017601807,0.001763254,0.003879983,0.011926821,0.011152971,0.0066721793,0.010065431,0.002687134],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005101954,0.00025352658,0.015662476,0.004808383,0.001059656,0.00022842028,0.0023042068,0.061167523,0.005489419,0.500247,0.010776187,0.39749306],"study_design_scores_gemma":[0.00005344797,0.00013332647,0.0019867877,0.0007093814,0.00008015085,0.000461034,0.00031270704,0.18499206,0.0021421271,0.7980178,0.011005609,0.000105571555],"about_ca_topic_score_codex":0.0021309035,"about_ca_topic_score_gemma":0.0018238273,"teacher_disagreement_score":0.101847775,"about_ca_system_score_codex":0.0023905777,"about_ca_system_score_gemma":0.0027299398,"threshold_uncertainty_score":0.53862894},"labels":[],"label_agreement":null},{"id":"W3027464055","doi":"10.1186/s12859-020-3494-x","title":"MEPHAS: an interactive graphical user interface for medical and pharmaceutical statistical analysis with R and Shiny","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Data Analysis with R","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Genetics; Chinese Government Scholarship; China Scholarship Council","keywords":"Computer science; Graphical user interface; Visualization; Interface (matter); Analytics; Workstation; User interface; Scatter plot; OS X; Data visualization; Statistical analysis; Data mining; Software; Programming language; Machine learning; Operating system; Statistics","score_opus":0.029111670027291998,"score_gpt":0.333294396465094,"score_spread":0.30418272643780203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3027464055","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002847713,0.0012577652,0.49663818,0.0014571934,0.00072390743,0.00082522136,0.049334902,0.43782178,0.009093369],"genre_scores_gemma":[0.035524443,0.0015527363,0.74440354,0.0028167374,0.0005769723,0.0062394,0.035519283,0.15923278,0.014134228],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956995,0.0018372623,0.0005158637,0.0006831614,0.0010213892,0.00024278207],"domain_scores_gemma":[0.9661539,0.02654508,0.0014619022,0.002092916,0.0030246226,0.0007216279],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009095216,0.002890767,0.0018302317,0.0030966734,0.00052218523,0.0028436887,0.003804646,0.0017822447,0.21274324],"category_scores_gemma":[0.04745369,0.0017005014,0.002367768,0.0021006055,0.0010017405,0.0035044127,0.0040025776,0.0028771139,0.07501019],"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":[0.0011970898,0.00009099457,0.0019018318,0.004634239,0.0005628115,0.0007190362,0.00071744877,0.004025514,0.0070529925,0.015540981,0.7897412,0.17381594],"study_design_scores_gemma":[0.0014344368,0.0003066569,0.0066500786,0.0019770607,0.00039139026,0.00164186,0.00021468701,0.05340423,0.015982412,0.060204066,0.85722506,0.00056816696],"about_ca_topic_score_codex":0.0013969743,"about_ca_topic_score_gemma":0.0019999852,"teacher_disagreement_score":0.21274324,"about_ca_system_score_codex":0.00061714713,"about_ca_system_score_gemma":0.0026423777,"threshold_uncertainty_score":0.71169704},"labels":[],"label_agreement":null},{"id":"W3028589227","doi":"10.1186/s12859-020-3535-5","title":"RintC: fast and accuracy-aware decomposition of distributions of RNA secondary structures with extended logsumexp","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Core Research for Evolutional Science and Technology; Ministry of Education, Culture, Sports, Science and Technology; Japan Society for the Promotion of Science; Institute of Genetics; Artificial Intelligence Research Center; National Institute of Advanced Industrial Science and Technology","keywords":"Computation; Stability (learning theory); Computer science; Constraint (computer-aided design); RNA; Numerical analysis; Algorithm; Decomposition; Computational complexity theory; Statistical physics; Bioinformatics; Biological system; Mathematics; Biology; Physics; Ecology; Machine learning; Genetics","score_opus":0.01177219424403008,"score_gpt":0.24373674197201275,"score_spread":0.23196454772798267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3028589227","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013114164,0.00011803342,0.97917205,0.00009986176,0.00006178269,0.000048602775,0.00018314652,0.005851452,0.001350924],"genre_scores_gemma":[0.18895276,0.00017544563,0.8049512,0.00020691106,0.00007869495,0.00037839828,0.0011623192,0.001693809,0.0024003834],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995339,0.00010009502,0.000031325697,0.000064199274,0.00022815233,0.000042366937],"domain_scores_gemma":[0.9983084,0.00071318017,0.00014963161,0.0002614848,0.00047543348,0.000091912516],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010840411,0.0006542017,0.0004983071,0.0007828443,0.00045178886,0.0012050294,0.0015548117,0.0009272723,0.0043987744],"category_scores_gemma":[0.0049144123,0.0003664304,0.0006358539,0.000598233,0.0005776197,0.0011780732,0.000980365,0.001391983,0.00160686],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004241159,0.00021570368,0.0052058334,0.0005213947,0.00010329386,0.00043584334,0.0002980146,0.5237046,0.03439619,0.031176507,0.021054124,0.38246438],"study_design_scores_gemma":[0.000009298828,0.00000990654,0.00012441112,0.0000058159403,0.0000022605118,0.00002284393,0.0000054730613,0.99482995,0.0020276033,0.002007017,0.0009495331,0.000005951624],"about_ca_topic_score_codex":0.0027416602,"about_ca_topic_score_gemma":0.0035707806,"teacher_disagreement_score":0.0043987744,"about_ca_system_score_codex":0.00069360377,"about_ca_system_score_gemma":0.0013800458,"threshold_uncertainty_score":0.014715314},"labels":[],"label_agreement":null},{"id":"W3030951244","doi":"10.1186/s12859-020-03549-8","title":"BEAVR: a browser-based tool for the exploration and visualization of RNA-seq data","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Children’s Health Research Institute; London Health Sciences Centre; Western University","funders":"Canadian Institutes of Health Research; Institute of Cancer Research; London Health Sciences Centre","keywords":"Computer science; Visualization; Table (database); Documentation; Cluster analysis; Data mining; Data visualization; Unix; RNA-Seq; Data science; Software; Information retrieval; Machine learning; Programming language; Biology; Transcriptome","score_opus":0.09356307070348382,"score_gpt":0.2861941582142696,"score_spread":0.19263108751078575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3030951244","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022334808,0.002096163,0.27758983,0.0009503788,0.0006694655,0.00061277585,0.08290921,0.62495965,0.007979006],"genre_scores_gemma":[0.020049028,0.0033626787,0.57541966,0.0028061594,0.00035182358,0.004226248,0.18301864,0.19220555,0.018560315],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99724776,0.0006927454,0.00030167936,0.0005577549,0.00093166204,0.00026836878],"domain_scores_gemma":[0.99369556,0.0035672176,0.0004203466,0.00061264215,0.0011768412,0.00052738644],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0051834835,0.004239157,0.002432377,0.0048343902,0.0010902274,0.0033806458,0.0043824404,0.0027421543,0.091113426],"category_scores_gemma":[0.0120519735,0.002153044,0.003110689,0.002373089,0.0008154604,0.0039504096,0.0047995606,0.004477313,0.061340265],"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":[0.0008580663,0.00015013723,0.001943579,0.0035813474,0.0004181058,0.0009076848,0.0009330296,0.0019419477,0.030487329,0.004632306,0.86125606,0.09289043],"study_design_scores_gemma":[0.0006606786,0.00020542194,0.0055213063,0.001464765,0.00024379107,0.0018959753,0.0003192488,0.03413346,0.037846465,0.020820035,0.8962299,0.00065892306],"about_ca_topic_score_codex":0.0047024833,"about_ca_topic_score_gemma":0.006377739,"teacher_disagreement_score":0.091113426,"about_ca_system_score_codex":0.0008116478,"about_ca_system_score_gemma":0.0022959372,"threshold_uncertainty_score":0.30480474},"labels":[],"label_agreement":null},{"id":"W3037659634","doi":"10.1186/s12859-020-03577-4","title":"NASQAR: a web-based platform for high-throughput sequencing data analysis and visualization","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"York University; New York University Abu Dhabi","keywords":"Computer science; Variety (cybernetics); Visualization; Toolbox; Source code; Software; World Wide Web; Data science; Data mining; Programming language; Artificial intelligence","score_opus":0.05769829710894775,"score_gpt":0.2836874729498316,"score_spread":0.22598917584088385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037659634","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002568584,0.0009809937,0.30152923,0.0010504227,0.00094500405,0.0007270675,0.08212614,0.6031671,0.006905416],"genre_scores_gemma":[0.025097866,0.0016218772,0.65800464,0.0023627044,0.0004372352,0.0052360804,0.18865278,0.11054226,0.008044617],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99444747,0.0010378113,0.0006477404,0.0010505215,0.0024227696,0.00039367177],"domain_scores_gemma":[0.9932789,0.0022580654,0.00086495583,0.00092821347,0.0018725966,0.00079715624],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007917266,0.0040863696,0.0028813877,0.0046322984,0.0020510012,0.005307392,0.008783454,0.0027982274,0.065331884],"category_scores_gemma":[0.012225262,0.0021427823,0.0034323025,0.003777636,0.0010488684,0.0040108133,0.0053890795,0.00722502,0.06098272],"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":[0.0014422775,0.00021182472,0.0019240858,0.0027103662,0.00055813516,0.00076764484,0.0007177746,0.007730637,0.041674025,0.007636235,0.86224115,0.072385795],"study_design_scores_gemma":[0.0016213479,0.0003309067,0.0060964925,0.0010331622,0.00027813367,0.0010835169,0.00032792165,0.15635407,0.051927708,0.058378354,0.7215502,0.0010181359],"about_ca_topic_score_codex":0.0046199216,"about_ca_topic_score_gemma":0.0046886937,"teacher_disagreement_score":0.065331884,"about_ca_system_score_codex":0.0013759683,"about_ca_system_score_gemma":0.0039357473,"threshold_uncertainty_score":0.21855688},"labels":[],"label_agreement":null},{"id":"W3040929481","doi":"10.1186/s12859-023-05509-4","title":"Cross-study analyses of microbial abundance using generalized common factor methods","year":2023,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Nova Scotia Health Research Foundation","keywords":"Metagenomics; Interpretability; Computer science; Leverage (statistics); Microbiome; Bootstrapping (finance); Abundance (ecology); Covariance; Computational biology; Projection (relational algebra); Data mining; Machine learning; Data science; Biology; Ecology; Bioinformatics; Statistics; Mathematics; Algorithm; Genetics; Econometrics","score_opus":0.14838727491041914,"score_gpt":0.47929714693268616,"score_spread":0.330909872022267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3040929481","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04187347,0.0003783057,0.9559697,0.00015173623,0.00006076581,0.0001773511,0.0003227711,0.00087832136,0.00018756089],"genre_scores_gemma":[0.47406277,0.00027765884,0.52108604,0.0002013679,0.00018595412,0.00077983155,0.0022644647,0.00041967793,0.00072227285],"study_design_codex":"design_other","study_design_gemma":"meta_analysis","domain_scores_codex":[0.9827032,0.011183046,0.0007271011,0.0038976918,0.0010596814,0.00042916523],"domain_scores_gemma":[0.9345138,0.049343944,0.003422747,0.008715494,0.0030035954,0.0010003633],"candidate_categories":["metaepi_broad"],"consensus_categories":[],"category_scores_codex":[0.030969303,0.002125125,0.0024368847,0.0043085506,0.0014778627,0.0020386297,0.0031614345,0.0020474615,0.0027369342],"category_scores_gemma":[0.058221392,0.00088293396,0.008216875,0.0030248438,0.002263815,0.0016752142,0.002925733,0.0024970982,0.00059589726],"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":[0.0021328279,0.00087396085,0.123032905,0.0008350355,0.01715909,0.0012663213,0.0017443091,0.3339221,0.017598523,0.02278062,0.004713526,0.47394085],"study_design_scores_gemma":[0.00011877813,0.0006006724,0.013647442,0.00006616625,0.0006585171,0.00025494053,0.00023850458,0.9420342,0.0028338558,0.03672391,0.0027106695,0.00011240927],"about_ca_topic_score_codex":0.005541047,"about_ca_topic_score_gemma":0.005559286,"teacher_disagreement_score":0.9975631,"about_ca_system_score_codex":0.00091804395,"about_ca_system_score_gemma":0.0017196817,"threshold_uncertainty_score":0.16378331},"labels":[],"label_agreement":null},{"id":"W3041251855","doi":"10.1186/s12859-020-03595-2","title":"Efficient implied alignment","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Topological and Geometric Data Analysis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Robert J. Kleberg, Jr. and Helen C. Kleberg Foundation; Defense Sciences Office, DARPA; Defense Advanced Research Projects Agency; McGill University","keywords":"Algorithm; Tree traversal; Artificial intelligence; Computer science","score_opus":0.03399497211501743,"score_gpt":0.23570747319662025,"score_spread":0.20171250108160282,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3041251855","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01679986,0.0002506387,0.9624642,0.00035168757,0.00010746373,0.00014612504,0.0024058619,0.010102431,0.007371692],"genre_scores_gemma":[0.11856355,0.00022664151,0.861575,0.00019327801,0.00009937522,0.00027096193,0.012225658,0.0018263621,0.005019185],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977842,0.00042150455,0.00019712518,0.0006647051,0.0007511795,0.00018134443],"domain_scores_gemma":[0.99519473,0.0015549537,0.00041631554,0.0019501556,0.00076727115,0.00011656782],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010156168,0.0017048467,0.001064013,0.0015016127,0.0013218398,0.0022093619,0.0032233114,0.0015561662,0.026592076],"category_scores_gemma":[0.010197371,0.0007277161,0.0014245734,0.0033910675,0.00094730937,0.005323482,0.0034294492,0.0021140974,0.011131814],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013352903,0.00037828606,0.0029217983,0.0014452621,0.000092976734,0.0006137212,0.0006153507,0.054909438,0.04375671,0.14258936,0.05114232,0.70019954],"study_design_scores_gemma":[0.00018706548,0.0002631444,0.0013611984,0.00012668884,0.00009551537,0.0010327629,0.0002589354,0.58493054,0.042206664,0.3042632,0.06517833,0.00009596257],"about_ca_topic_score_codex":0.0007918254,"about_ca_topic_score_gemma":0.0016290622,"teacher_disagreement_score":0.026592076,"about_ca_system_score_codex":0.0010753425,"about_ca_system_score_gemma":0.0015033645,"threshold_uncertainty_score":0.08895934},"labels":[],"label_agreement":null},{"id":"W3047407562","doi":"10.1186/s12859-020-03697-x","title":"GPU accelerated adaptive banded event alignment for rapid comparative nanopore signal analysis","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":143,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Centre Hospitalier Universitaire Sainte-Justine; University of Toronto; Ontario Institute for Cancer Research","funders":"University of Peradeniya; Government of Ontario; Government of Canada; Ontario Institute for Cancer Research; Genome Canada; Ontario Genomics; Innopolis University; University of New South Wales; Nvidia","keywords":"Computer science; Parallel computing; Overhead (engineering); Nanopore sequencing; Software; General-purpose computing on graphics processing units; Computational science; DNA sequencing; Graphics; DNA","score_opus":0.07105467821933206,"score_gpt":0.2832542641391247,"score_spread":0.21219958591979263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3047407562","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07983527,0.0007823813,0.891042,0.00037884663,0.00020492739,0.00013325548,0.0019802772,0.021921191,0.0037218686],"genre_scores_gemma":[0.12242119,0.0001814632,0.87168044,0.00014475624,0.000027009368,0.00022318123,0.002355716,0.0016291935,0.0013370647],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99933845,0.00016358499,0.000045807265,0.00019274988,0.00019827133,0.00006109502],"domain_scores_gemma":[0.99894387,0.00047925522,0.000103334925,0.00015650663,0.0002436433,0.000073416726],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011666745,0.0008233599,0.0006659558,0.0008433818,0.00064589723,0.0011208812,0.0014277106,0.00092304515,0.0065183197],"category_scores_gemma":[0.0032620945,0.000519364,0.0008583046,0.0009526019,0.0004526441,0.0007333705,0.0008949447,0.0014307628,0.0017197455],"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":[0.0019970855,0.00032163344,0.010063124,0.0008646812,0.00063218275,0.0006047081,0.00071780017,0.08613509,0.4102331,0.01568498,0.032940526,0.43980518],"study_design_scores_gemma":[0.00012471066,0.00016766712,0.0045423806,0.0000392302,0.00006568757,0.00030218298,0.000077593315,0.8807869,0.08062589,0.0092130955,0.023974178,0.00008054606],"about_ca_topic_score_codex":0.004074485,"about_ca_topic_score_gemma":0.007116888,"teacher_disagreement_score":0.0065183197,"about_ca_system_score_codex":0.0010073348,"about_ca_system_score_gemma":0.0010560895,"threshold_uncertainty_score":0.021806002},"labels":[],"label_agreement":null},{"id":"W3049762379","doi":"10.1186/s12859-020-03704-1","title":"Evaluation of variant calling tools for large plant genome re-sequencing","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Wheat and Barley Genetics and Pathology","field":"Agricultural and Biological Sciences","cited_by":54,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan; Agriculture and Agri-Food Canada","funders":"Agriculture and Agri-Food Canada; Genome Canada","keywords":"Concordance; Biology; Genetics; Germplasm; Genotyping; Genome; Computational biology; 1000 Genomes Project; SNP genotyping; Reference genome; Single-nucleotide polymorphism; Genotype; Gene","score_opus":0.16774170175173803,"score_gpt":0.2719729421515648,"score_spread":0.10423124039982679,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3049762379","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5189023,0.004057463,0.41397265,0.0005655353,0.0004038169,0.0007573488,0.005208147,0.053726677,0.002406069],"genre_scores_gemma":[0.3860506,0.0007923533,0.58600366,0.0003198115,0.000059151218,0.00076692016,0.019713081,0.0050681406,0.0012262177],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9924684,0.0025162122,0.00074643333,0.0020618471,0.0018094453,0.00039765929],"domain_scores_gemma":[0.9838808,0.010665368,0.000838601,0.0015793804,0.0025001785,0.00053562474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01765507,0.0020428863,0.0009863009,0.0020231053,0.0010451254,0.0016317687,0.002765324,0.0014983809,0.0020718647],"category_scores_gemma":[0.028200915,0.0006465264,0.0017346464,0.0016934074,0.0006176476,0.0016920142,0.0019297814,0.0018386163,0.0012421323],"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":[0.007297924,0.0010628569,0.06275789,0.0034154516,0.0045396932,0.001387542,0.0022573906,0.09922638,0.17787442,0.005689264,0.02348569,0.61100554],"study_design_scores_gemma":[0.00055261725,0.002297585,0.052592266,0.00027697175,0.0009819716,0.001998103,0.00054106215,0.7446658,0.17298318,0.0054937406,0.017155902,0.00046078584],"about_ca_topic_score_codex":0.0022613732,"about_ca_topic_score_gemma":0.0027315826,"teacher_disagreement_score":0.01765507,"about_ca_system_score_codex":0.00070031825,"about_ca_system_score_gemma":0.0010801187,"threshold_uncertainty_score":0.09337008},"labels":[],"label_agreement":null},{"id":"W3081286367","doi":"10.1186/s12859-021-03997-w","title":"geneRFinder: gene finding in distinct metagenomic data complexities","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"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":"Vale Canada Limited","keywords":"Metagenomics; Benchmark (surveying); McNemar's test; Gene prediction; Computational biology; Gene Annotation; Computer science; Data mining; Annotation; Biology; Gene; Machine learning; Artificial intelligence; Statistics; Genetics; Genome; Mathematics; Geography","score_opus":0.08674744853583267,"score_gpt":0.28577810191656,"score_spread":0.19903065338072734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3081286367","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10724439,0.0023622883,0.62622905,0.0012972999,0.00039396808,0.000347025,0.030862033,0.2284723,0.0027916653],"genre_scores_gemma":[0.29061952,0.0006257326,0.6603079,0.0006750437,0.00017998186,0.00067640276,0.039982405,0.005087381,0.0018456102],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980457,0.00041379553,0.00017939342,0.0006269967,0.0005874228,0.0001467036],"domain_scores_gemma":[0.99352866,0.0047416924,0.00050882896,0.00060803734,0.0003965058,0.00021623538],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042713764,0.0019145857,0.001210947,0.0041823313,0.0008248259,0.0019246077,0.0027268766,0.0016839869,0.0069234096],"category_scores_gemma":[0.016027018,0.000713992,0.0016850894,0.002546718,0.000835878,0.0030374336,0.0020335403,0.0018777935,0.002422317],"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":[0.003876469,0.0005515772,0.08699232,0.0031153758,0.0012491886,0.001564728,0.00069798675,0.11714917,0.03711923,0.011253027,0.12720303,0.60922796],"study_design_scores_gemma":[0.00024216634,0.00040860017,0.0075187846,0.00020600623,0.00018035292,0.000999536,0.00021876654,0.90208864,0.035459865,0.02415501,0.02838032,0.00014203216],"about_ca_topic_score_codex":0.0015746302,"about_ca_topic_score_gemma":0.0028790915,"teacher_disagreement_score":0.0069234096,"about_ca_system_score_codex":0.00086225977,"about_ca_system_score_gemma":0.0016751178,"threshold_uncertainty_score":0.023161113},"labels":[],"label_agreement":null},{"id":"W3088926825","doi":"10.1186/s12859-020-03729-6","title":"Theoretical characterisation of strand cross-correlation in ChIP-seq","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","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":"Institute of Genetics; Canon Medical Systems Corporation","keywords":"Chip; Correlation; Cross-correlation; Consistency (knowledge bases); Metric (unit); Independence (probability theory); Noise (video); Measure (data warehouse); Correlation coefficient; Sensitivity (control systems); Computer science; Algorithm; Mathematics; Statistics; Data mining; Telecommunications; Engineering; Artificial intelligence; Electronic engineering","score_opus":0.009160658078495428,"score_gpt":0.23414556913504603,"score_spread":0.2249849110565506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3088926825","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06571997,0.00037556168,0.9304551,0.00011335991,0.00002794313,0.00006090462,0.00021138001,0.0005774079,0.0024583216],"genre_scores_gemma":[0.83050185,0.00081436336,0.16529141,0.00025978053,0.000039656043,0.0005480632,0.0007400734,0.00035925847,0.0014454669],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985348,0.00032926054,0.000059456583,0.000423969,0.000538916,0.00011364777],"domain_scores_gemma":[0.99277556,0.005431635,0.00047594172,0.00046331648,0.0007078683,0.00014569616],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036387343,0.00078771246,0.00047956363,0.0011536012,0.0004122786,0.0007641055,0.0014101348,0.0010370289,0.0015769453],"category_scores_gemma":[0.011816861,0.0005836861,0.0008106661,0.0007958255,0.0013082449,0.0013494003,0.0007761876,0.0010646613,0.0005099244],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011586973,0.000055631237,0.008730376,0.0003899743,0.000080115686,0.0004342321,0.0002513636,0.8743013,0.040959798,0.05444203,0.000904991,0.019334234],"study_design_scores_gemma":[0.0000028889474,0.000026178323,0.001044742,0.000016538292,0.000009017674,0.00011337506,0.000012514368,0.9814519,0.008405392,0.008273863,0.0006264836,0.000017015207],"about_ca_topic_score_codex":0.0019148781,"about_ca_topic_score_gemma":0.0011000376,"teacher_disagreement_score":0.0036387343,"about_ca_system_score_codex":0.0015232009,"about_ca_system_score_gemma":0.0011810147,"threshold_uncertainty_score":0.019243658},"labels":[],"label_agreement":null},{"id":"W3091870415","doi":"10.1186/s12859-020-03747-4","title":"Application of OU processes to modelling temporal dynamics of the human microbiome, and calculating optimal sampling schemes","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Microbiome; Stability (learning theory); Computer science; Dynamics (music); Series (stratigraphy); Biology; Machine learning; Bioinformatics; Psychology","score_opus":0.03374253322409365,"score_gpt":0.28624995014285887,"score_spread":0.2525074169187652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3091870415","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037026986,0.0004938956,0.9607735,0.00039650372,0.00004279974,0.0000954146,0.00006704478,0.000123803,0.0009800215],"genre_scores_gemma":[0.5243285,0.0008767723,0.4712216,0.00015329398,0.00012367601,0.0005519036,0.00023397623,0.00013882254,0.0023714644],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988181,0.0006633183,0.00007093738,0.0001892925,0.00017132577,0.00008691397],"domain_scores_gemma":[0.9852879,0.012674363,0.00077465555,0.00033161146,0.0006779347,0.0002535478],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0066113803,0.00079033803,0.0010865512,0.0019431611,0.00079854537,0.0014087699,0.0017610957,0.0023229094,0.0023773161],"category_scores_gemma":[0.030358832,0.0009182002,0.0013396421,0.0012291875,0.0014546459,0.0019077783,0.0019565737,0.001710685,0.00025138396],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017655933,0.000018176896,0.0014801683,0.000031615295,0.000020356925,0.000030843898,0.00005469347,0.97798,0.00020092464,0.013031868,0.00012096021,0.007012735],"study_design_scores_gemma":[0.0000018410332,0.000003732527,0.00006183373,0.0000042634356,0.0000016953697,0.0000037201173,0.000004951156,0.99596786,0.00004668015,0.0038110171,0.00009027557,0.0000021964458],"about_ca_topic_score_codex":0.022166569,"about_ca_topic_score_gemma":0.011147319,"teacher_disagreement_score":0.022166569,"about_ca_system_score_codex":0.002631719,"about_ca_system_score_gemma":0.0023713873,"threshold_uncertainty_score":0.04407513},"labels":[],"label_agreement":null},{"id":"W3092695394","doi":"10.1186/s12859-020-03794-x","title":"Implementation of homology based and non-homology based computational methods for the identification and annotation of orphan enzymes: using Mycobacterium tuberculosis H37Rv as a case study","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","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":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Council of Scientific and Industrial Research, India","keywords":"In silico; Computational biology; Sequence alignment; Annotation; Biology; Genome; Homology (biology); Context (archaeology); Genetics; Mycobacterium tuberculosis; Homology modeling; Bioinformatics; Gene; Peptide sequence; Tuberculosis; Enzyme; Medicine","score_opus":0.027311041487814994,"score_gpt":0.37450429355805614,"score_spread":0.34719325207024115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092695394","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.444209,0.00016231278,0.54287416,0.00025772085,0.000048532354,0.0005086921,0.0005352356,0.008934677,0.002469674],"genre_scores_gemma":[0.397981,0.00010912303,0.59933573,0.000058824917,0.000008668008,0.00038183038,0.001077376,0.0003515658,0.0006957854],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99936074,0.00017130443,0.00006427514,0.00017941116,0.00015943547,0.000064789885],"domain_scores_gemma":[0.99856913,0.00073257793,0.000088248366,0.00022533657,0.00029484037,0.000089863875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016796069,0.00074690924,0.000614696,0.0006905658,0.0007501209,0.0008981421,0.0020135774,0.001345492,0.0018337728],"category_scores_gemma":[0.0035119338,0.00045965915,0.00087636954,0.0006358572,0.00045436682,0.0010833658,0.0010888661,0.00072847167,0.00045895754],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027700919,0.0025249037,0.0366145,0.001124467,0.0004588011,0.0037792611,0.0016005092,0.4348004,0.18732306,0.016116332,0.0038913074,0.30899635],"study_design_scores_gemma":[0.000090437214,0.00017378134,0.0019489862,0.000012933392,0.00003424089,0.00014540262,0.00010518511,0.9609657,0.032971423,0.0017681496,0.001753672,0.000030076173],"about_ca_topic_score_codex":0.0033639465,"about_ca_topic_score_gemma":0.0028864092,"teacher_disagreement_score":0.0033639465,"about_ca_system_score_codex":0.0006650663,"about_ca_system_score_gemma":0.0013063512,"threshold_uncertainty_score":0.008882761},"labels":[],"label_agreement":null},{"id":"W3093072871","doi":"10.1186/s12859-020-03779-w","title":"RepAHR: an improved approach for de novo repeat identification by assembly of the high-frequency reads","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Higher Education Discipline Innovation Project; King Abdullah University of Science and Technology; National Natural Science Foundation of China","keywords":"Sequence assembly; Hybrid genome assembly; Identification (biology); Genome; Computational biology; Reference genome; Computer science; DNA sequencing; DNA microarray; Biology; Genetics; DNA; Gene","score_opus":0.01856362151659104,"score_gpt":0.23638895082227057,"score_spread":0.21782532930567952,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3093072871","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019113125,0.0009773272,0.9438519,0.00010598821,0.00018939994,0.000282066,0.0009320627,0.03346435,0.0010838102],"genre_scores_gemma":[0.037837878,0.0002695951,0.9556333,0.00018922456,0.000079593265,0.00016011552,0.002588404,0.0011974933,0.0020444158],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996716,0.00039206306,0.00026609318,0.0009589131,0.0014631372,0.00020372715],"domain_scores_gemma":[0.9968796,0.00097133906,0.00044141457,0.0007726463,0.00078450056,0.00015058962],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031791679,0.0020989648,0.0015501309,0.0030385256,0.00086539786,0.0014956674,0.002900196,0.0015077371,0.004659909],"category_scores_gemma":[0.0038144577,0.0011210921,0.0024915778,0.0018478761,0.000596351,0.002079201,0.0022211105,0.001833223,0.003454321],"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":[0.0012262783,0.00045027467,0.008088717,0.0018131246,0.0007891,0.0010945016,0.0005932289,0.015203665,0.27510265,0.0042305347,0.014899534,0.6765084],"study_design_scores_gemma":[0.00031554324,0.0010305335,0.011906691,0.00012108861,0.00050002174,0.00297614,0.000282099,0.5702339,0.347279,0.0053870436,0.059508163,0.00045984276],"about_ca_topic_score_codex":0.0020504382,"about_ca_topic_score_gemma":0.0033925246,"teacher_disagreement_score":0.004659909,"about_ca_system_score_codex":0.00048051865,"about_ca_system_score_gemma":0.0010926448,"threshold_uncertainty_score":0.016813219},"labels":[],"label_agreement":null},{"id":"W3093280245","doi":"10.1186/s12859-020-03754-5","title":"LDkit: a parallel computing toolkit for linkage disequilibrium analysis","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Genetics and Developmental Biology, Chinese Academy of Sciences; Chinese Academy of Sciences; Institute of Genetics; National Natural Science Foundation of China","keywords":"Linkage disequilibrium; Graphical user interface; Computer science; Software; Linkage (software); Disequilibrium; Population; Interface (matter); Plot (graphics); Block (permutation group theory); Data mining; Biology; Genetics; Programming language; Single-nucleotide polymorphism; Operating system; Gene; Mathematics; Statistics","score_opus":0.03288581403397207,"score_gpt":0.28002338812433314,"score_spread":0.24713757409036108,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3093280245","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004352603,0.0011447776,0.5826539,0.00053991785,0.0004171338,0.00048025546,0.02100916,0.38475844,0.0046438742],"genre_scores_gemma":[0.051614914,0.0010701643,0.8422699,0.0007244769,0.0002062816,0.0035853311,0.041641206,0.05319935,0.005688361],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99520266,0.0015186281,0.00080895575,0.0010743001,0.0010123975,0.00038293935],"domain_scores_gemma":[0.9954928,0.00184959,0.00044088293,0.00089791114,0.0009474652,0.00037130315],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044779736,0.0023039214,0.0024792855,0.0024669373,0.0015638986,0.0036553787,0.0048538,0.001112022,0.025150182],"category_scores_gemma":[0.01696028,0.002240674,0.0027094022,0.003135241,0.0009094346,0.0035566909,0.004791723,0.004337779,0.022541527],"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":[0.0028422396,0.00032699457,0.00839368,0.004691183,0.0016020527,0.0010959775,0.0014757725,0.023902738,0.020608358,0.028468424,0.50645894,0.40013367],"study_design_scores_gemma":[0.002500664,0.00031528427,0.0070314687,0.00074359705,0.0007244314,0.0013976279,0.0003605762,0.31711692,0.033747207,0.14042749,0.49486962,0.0007652824],"about_ca_topic_score_codex":0.0032301943,"about_ca_topic_score_gemma":0.002561055,"teacher_disagreement_score":0.025150182,"about_ca_system_score_codex":0.00092285476,"about_ca_system_score_gemma":0.003630056,"threshold_uncertainty_score":0.08413571},"labels":[],"label_agreement":null},{"id":"W3094445727","doi":"10.1186/s12859-020-03815-9","title":"MetaLAFFA: a flexible, end-to-end, distributed computing-compatible metagenomic functional annotation pipeline","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Canada","funders":"National Institute of Diabetes and Digestive and Kidney Diseases; National Institute of General Medical Sciences; University of Washington; National Institute on Aging; National Institutes of Health; Tel Aviv University; Israel Science Foundation","keywords":"Metagenomics; Computer science; Annotation; Pipeline (software); Personalization; Interoperability; Pipeline transport; Database; Data mining; World Wide Web; Operating system; Artificial intelligence; Engineering; Biology","score_opus":0.03207415185522694,"score_gpt":0.24420367441701127,"score_spread":0.21212952256178433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3094445727","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014414384,0.00072301336,0.46893045,0.0006171711,0.00039373225,0.00055374746,0.04001189,0.46815282,0.0062027485],"genre_scores_gemma":[0.06977396,0.0006917124,0.6952737,0.0019022883,0.00016942754,0.0025012575,0.15192221,0.06810835,0.009657112],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977708,0.00024710136,0.00018439913,0.0008826911,0.0006388013,0.00027627998],"domain_scores_gemma":[0.9982191,0.000465491,0.00024377785,0.0004086075,0.00041750862,0.00024540507],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032975932,0.00388895,0.0017587444,0.0032467658,0.0023942569,0.0033490113,0.004577661,0.0018929042,0.0128902225],"category_scores_gemma":[0.0049486407,0.0025127002,0.004077584,0.0017895041,0.0011864088,0.0033187633,0.0053249244,0.0046157637,0.020701181],"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":[0.004566208,0.0005371825,0.01270861,0.0040407763,0.0010943891,0.0022588056,0.0027058402,0.015138252,0.34493408,0.013441338,0.35694522,0.24162933],"study_design_scores_gemma":[0.00064048567,0.00050636736,0.012428003,0.0006446539,0.00048235265,0.0017397525,0.000544841,0.149722,0.29870328,0.03864772,0.4949085,0.0010321571],"about_ca_topic_score_codex":0.002439552,"about_ca_topic_score_gemma":0.002655992,"teacher_disagreement_score":0.0128902225,"about_ca_system_score_codex":0.0013534739,"about_ca_system_score_gemma":0.002666243,"threshold_uncertainty_score":0.043122053},"labels":[],"label_agreement":null},{"id":"W3100449126","doi":"10.1186/s12859-020-03837-3","title":"Speeding up the core algorithm for the dual calculation of minimal cut sets in large metabolic networks","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Microbial Metabolic Engineering and Bioproduction","field":"Biochemistry, Genetics and Molecular Biology","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Bundesministerium für Bildung und Forschung","keywords":"Computer science; Benchmark (surveying); Computation; Algorithm; Dimension (graph theory); Flexibility (engineering); Lemma (botany); Dual (grammatical number); Mathematical optimization; Theoretical computer science; Mathematics","score_opus":0.02615582391004195,"score_gpt":0.25906384041751035,"score_spread":0.2329080165074684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3100449126","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.057365336,0.00025355362,0.93397266,0.00030367298,0.000087760774,0.00013405422,0.0001665853,0.0015843279,0.006132038],"genre_scores_gemma":[0.42529038,0.000107090644,0.57078755,0.00020462509,0.00005354284,0.00027983848,0.00055420015,0.00036023598,0.002362491],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99943835,0.00017196184,0.000024880448,0.000094286115,0.00015355885,0.00011690099],"domain_scores_gemma":[0.99774677,0.0013839419,0.00014836864,0.00021449318,0.0003542467,0.00015225168],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013334246,0.0011823508,0.0012977917,0.00084614236,0.0006130329,0.0013760914,0.0015619938,0.0012372148,0.0057848217],"category_scores_gemma":[0.0047465446,0.00050021976,0.0009217397,0.00066940405,0.0007628956,0.0012472746,0.0020199788,0.0020979613,0.0009295431],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028881233,0.0001925094,0.000979423,0.00015559646,0.000037152782,0.00008501891,0.000082915314,0.8868843,0.003685213,0.020728076,0.0028733278,0.084007695],"study_design_scores_gemma":[0.00001481553,0.0000156696,0.00003921783,0.0000048969555,0.000003106979,0.0000073065316,0.000008651371,0.9945261,0.00055352726,0.0045621605,0.00026244056,0.0000020815353],"about_ca_topic_score_codex":0.0038627984,"about_ca_topic_score_gemma":0.004354616,"teacher_disagreement_score":0.0057848217,"about_ca_system_score_codex":0.0010948714,"about_ca_system_score_gemma":0.002139908,"threshold_uncertainty_score":0.019352138},"labels":[],"label_agreement":null},{"id":"W3101058692","doi":"10.1186/s12859-020-03734-9","title":"MADA: a web service for analysing DNA methylation array data","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Epigenetics and DNA Methylation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"National Key Research and Development Program of China; Higher Education Discipline Innovation Project; National Natural Science Foundation of China","keywords":"DNA methylation; Methylation; Workflow; Bioconductor; Computer science; Computational biology; Visualization; Bioinformatics; Data mining; Biology; Database; Genetics; Gene; Gene expression","score_opus":0.08744543724510032,"score_gpt":0.3051757837573827,"score_spread":0.21773034651228237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3101058692","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003312565,0.0003686452,0.12973157,0.00045874613,0.00015608945,0.00044092681,0.03737884,0.8254987,0.0026538544],"genre_scores_gemma":[0.07429006,0.0012976703,0.56512916,0.003401563,0.00040712618,0.005381267,0.2128404,0.12060887,0.016643904],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984212,0.0003245025,0.00020941906,0.000346326,0.0005168531,0.00018163525],"domain_scores_gemma":[0.9960556,0.0018356666,0.0003830821,0.0006836052,0.00052531203,0.00051675853],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032040896,0.0031778975,0.0020482964,0.0046897484,0.0011473687,0.0028643121,0.0034578883,0.002190756,0.057719357],"category_scores_gemma":[0.007454883,0.0014584416,0.003025966,0.0025017385,0.0006058828,0.0024353408,0.0045609325,0.0025468245,0.04504056],"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":[0.005154503,0.00055665866,0.014766864,0.004141479,0.0013583082,0.0020740074,0.0009497327,0.0067199185,0.0934415,0.007235111,0.5659943,0.2976076],"study_design_scores_gemma":[0.0017002622,0.00033211272,0.023561208,0.00060788874,0.00041981475,0.0024456051,0.00039056755,0.1555548,0.09594305,0.022766294,0.69539243,0.00088595494],"about_ca_topic_score_codex":0.0045029134,"about_ca_topic_score_gemma":0.004312937,"teacher_disagreement_score":0.057719357,"about_ca_system_score_codex":0.0017004489,"about_ca_system_score_gemma":0.0021690147,"threshold_uncertainty_score":0.19309044},"labels":[],"label_agreement":null},{"id":"W3107863713","doi":"10.1186/s12859-020-03768-z","title":"MADloy: robust detection of mosaic loss of chromosome Y from genotype-array-intensity data","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomic variations and chromosomal abnormalities","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"European Regional Development Fund; Ministerio de Economía y Competitividad; Centres de Recerca de Catalunya; Institució Catalana de Recerca i Estudis Avançats; Agencia Estatal de Investigación; Ministerio de Ciencia, Innovación y Universidades; Ministère de l'Économie, de l’Innovation et des Exportations du Québec","keywords":"Biology; Chromosome; Software; Population; Replicate; Computational biology; SNP array; Genotype; Computer science; Data mining; Genetics; Statistics; Gene; Single-nucleotide polymorphism; Medicine; Mathematics","score_opus":0.03455742967135808,"score_gpt":0.22143668606563424,"score_spread":0.18687925639427616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3107863713","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07516352,0.0012354949,0.76895326,0.0005953805,0.00026124777,0.00039807218,0.027845439,0.12311355,0.0024340418],"genre_scores_gemma":[0.2291347,0.00038867226,0.7259063,0.0011935167,0.00016798177,0.0020066025,0.026583448,0.01101394,0.0036047923],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9964227,0.0010003429,0.00025073768,0.0011602034,0.0009664462,0.00019956227],"domain_scores_gemma":[0.991967,0.005016866,0.0012808286,0.0011119343,0.00042897044,0.00019436516],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008276003,0.0016833079,0.001699273,0.0030326925,0.000624337,0.002234576,0.0024143895,0.0012670712,0.0069687767],"category_scores_gemma":[0.02232862,0.0010089037,0.002055929,0.0015601076,0.000650164,0.00095142913,0.0032844814,0.0013945053,0.0023799038],"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":[0.0035411185,0.00038516143,0.19701144,0.0041363803,0.0048701484,0.0013876739,0.0020521178,0.073718056,0.15054779,0.011306471,0.12285778,0.42818585],"study_design_scores_gemma":[0.0007593032,0.000533438,0.10808129,0.00028556082,0.0006382777,0.0014904751,0.00027860547,0.67702955,0.11074976,0.020092273,0.07944012,0.0006214579],"about_ca_topic_score_codex":0.002565462,"about_ca_topic_score_gemma":0.005789599,"teacher_disagreement_score":0.008276003,"about_ca_system_score_codex":0.0006644733,"about_ca_system_score_gemma":0.0012091479,"threshold_uncertainty_score":0.043768227},"labels":[],"label_agreement":null},{"id":"W3111170609","doi":"10.1186/s12859-020-03919-2","title":"PyClone-VI: scalable inference of clonal population structures using whole genome data","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":140,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"Michael Smith Health Research BC","keywords":"Deconvolution; Computer science; Inference; Scalability; Software; Population; Computational biology; Bayesian probability; Genome; Data mining; Biology; Artificial intelligence; Algorithm; Genetics; Gene; Database","score_opus":0.056188144556107995,"score_gpt":0.29457957920893857,"score_spread":0.23839143465283058,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3111170609","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016089097,0.0006850199,0.9208664,0.00042867835,0.00015017403,0.0001698277,0.0068417466,0.0533709,0.0013982076],"genre_scores_gemma":[0.11124743,0.0004308636,0.85861176,0.0005358253,0.00015517599,0.00060495705,0.015638016,0.010075803,0.0027001214],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989986,0.00031641917,0.000053989246,0.00031011298,0.00025241383,0.00006848496],"domain_scores_gemma":[0.99596125,0.0026038869,0.00025801748,0.0005522097,0.00040336922,0.00022129534],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041211727,0.0014443645,0.0016711727,0.001612788,0.001016367,0.0024130244,0.0039522788,0.0019287345,0.0119395],"category_scores_gemma":[0.01731097,0.001573372,0.0025877147,0.0014354679,0.0009753974,0.0016109714,0.0023941887,0.0031728304,0.004872367],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013526857,0.0003039008,0.03236539,0.0019139248,0.0025948356,0.001032079,0.0009723249,0.4245451,0.0308012,0.02796244,0.12266286,0.35349324],"study_design_scores_gemma":[0.0001821726,0.00005508693,0.0023306487,0.000054015785,0.00007401024,0.000292786,0.00005171203,0.960693,0.004621709,0.021621676,0.009971089,0.000052193223],"about_ca_topic_score_codex":0.009232974,"about_ca_topic_score_gemma":0.01476681,"teacher_disagreement_score":0.0119395,"about_ca_system_score_codex":0.0011079652,"about_ca_system_score_gemma":0.0031441643,"threshold_uncertainty_score":0.03994161},"labels":[],"label_agreement":null},{"id":"W3113308471","doi":"10.1186/s12859-020-03930-7","title":"Inter-protein residue covariation information unravels physically interacting protein dimers","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Coevolution; Computer science; Protein–protein interaction; Computational biology; Surface protein; Protein sequencing; Mutual information; Artificial intelligence; Support vector machine; Feature vector; Biology; Machine learning; Theoretical computer science; Genetics; Gene; Evolutionary biology; Peptide sequence","score_opus":0.010862866212746536,"score_gpt":0.22999357294230885,"score_spread":0.2191307067295623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3113308471","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9058749,0.0005263198,0.09158585,0.000079151774,0.000007726894,0.00002062058,0.00018670646,0.00039063187,0.001328007],"genre_scores_gemma":[0.98284,0.00008073201,0.016602444,0.0000115407,0.000005800704,0.000010539681,0.00026067224,0.000029324425,0.00015883279],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995104,0.00009617202,0.000035404013,0.00016920104,0.00014108546,0.000047744095],"domain_scores_gemma":[0.99899274,0.00033646505,0.00030505247,0.00012900656,0.00014702737,0.00008956363],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007396096,0.0005193848,0.0005317633,0.0017113286,0.0004732449,0.0006405605,0.0004939919,0.00054305466,0.0011073147],"category_scores_gemma":[0.0018952306,0.0002009735,0.00060886174,0.0011015792,0.00036856646,0.0009942207,0.0006460361,0.00054312195,0.00044241917],"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":[0.0016586632,0.00060073024,0.30783233,0.00060908747,0.00069605006,0.0010896,0.000749871,0.1759246,0.26353687,0.0046964833,0.0017531543,0.24085256],"study_design_scores_gemma":[0.000009380876,0.0001259285,0.06604619,0.00002422933,0.00010120174,0.00047013586,0.00018827803,0.9061706,0.02216671,0.003643009,0.0010222993,0.0000320186],"about_ca_topic_score_codex":0.000968385,"about_ca_topic_score_gemma":0.0011374906,"teacher_disagreement_score":0.0017113286,"about_ca_system_score_codex":0.00033557205,"about_ca_system_score_gemma":0.00039734054,"threshold_uncertainty_score":0.0039114356},"labels":[],"label_agreement":null},{"id":"W3116132399","doi":"10.1186/s12859-020-03848-0","title":"Deep learning detection of informative features in tau PET for Alzheimer’s disease classification","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":96,"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":"Servier; National Cancer Institute; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; U.S. National Library of Medicine; IXICO; H. Lundbeck A/S; Eisai; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; University of Southern California; Eli Lilly and Company; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Bristol-Myers Squibb; National Institute on Aging; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Entorhinal cortex; Positron emission tomography; Temporal lobe; Neuroscience; Alzheimer's disease; Neuroimaging; Medicine; Dementia; Artificial intelligence; Voxel; Deep learning; Temporal cortex; Psychology; Disease; Pathology; Hippocampus; Computer science","score_opus":0.047600836721933486,"score_gpt":0.3236986725723198,"score_spread":0.27609783585038633,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3116132399","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30582973,0.0023911798,0.6854052,0.0007729132,0.00011301993,0.00017645088,0.0008759056,0.0025843505,0.0018512408],"genre_scores_gemma":[0.9100198,0.00045732834,0.08673583,0.00019030758,0.000052899955,0.000107451306,0.0011099596,0.000049626047,0.0012766963],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996524,0.00008079071,0.00002465188,0.00009457515,0.00007410761,0.00007344127],"domain_scores_gemma":[0.999423,0.00024544436,0.00008522216,0.000057588466,0.00015520294,0.000033504894],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012981232,0.0010951568,0.0007087036,0.0010725065,0.0002694568,0.00061073084,0.0008348111,0.0010703207,0.00077649567],"category_scores_gemma":[0.0024394754,0.00036489186,0.0010266218,0.00069387845,0.00038831125,0.0005712258,0.00064357795,0.0010816215,0.00036361936],"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":[0.0003759561,0.00041452542,0.014700124,0.00017412363,0.00029229157,0.00034245328,0.00009380563,0.44863087,0.032897793,0.0018998838,0.005179698,0.49499846],"study_design_scores_gemma":[0.000006513973,0.00003696158,0.0013285097,0.0000099197005,0.000019869176,0.000039357146,0.000005388955,0.9934344,0.003655299,0.0012034641,0.000253944,0.0000063272296],"about_ca_topic_score_codex":0.008084101,"about_ca_topic_score_gemma":0.006376633,"teacher_disagreement_score":0.008084101,"about_ca_system_score_codex":0.0009348823,"about_ca_system_score_gemma":0.0010214959,"threshold_uncertainty_score":0.016074061},"labels":[],"label_agreement":null},{"id":"W3116224340","doi":"10.1186/s12859-020-03891-x","title":"Integrative approach for detecting membrane proteins","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; King Saud University; Saudi Arabian Cultural Bureau; Genome Canada","keywords":"Transmembrane protein; Membrane topology; Membrane protein; Computer science; Topology (electrical circuits); Integral membrane protein; Transmembrane domain; Computational biology; Feature (linguistics); Artificial intelligence; Data mining; Bioinformatics; Pattern recognition (psychology); Machine learning; Membrane; Biology; Mathematics; Biochemistry","score_opus":0.02162475551480415,"score_gpt":0.257806208504307,"score_spread":0.23618145298950288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3116224340","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19072874,0.002440973,0.7950236,0.00021722684,0.00008899426,0.0003730778,0.0013176209,0.004585458,0.0052242912],"genre_scores_gemma":[0.48343644,0.0008080934,0.5101289,0.00017613119,0.00007594412,0.0002365728,0.0030385123,0.00021327227,0.0018861399],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987087,0.00019835056,0.00007997863,0.0003593109,0.00055066205,0.000102987055],"domain_scores_gemma":[0.99860746,0.00034596375,0.0001932641,0.00015573092,0.00060538156,0.00009230729],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013432885,0.0015577327,0.001086897,0.0039157276,0.0004487656,0.0009346923,0.0011349071,0.00079941755,0.0019929744],"category_scores_gemma":[0.002247817,0.0002658792,0.001202654,0.0020534298,0.00036424387,0.0010190567,0.0014820294,0.000798381,0.0015529683],"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":[0.0005887205,0.0005300668,0.02755121,0.0009370455,0.00073897996,0.0008561321,0.0003475212,0.022403372,0.31536487,0.00391223,0.0046509667,0.62211895],"study_design_scores_gemma":[0.000051901363,0.000644824,0.03855185,0.00010120314,0.0008148215,0.0032314002,0.00048513897,0.7576883,0.17737894,0.009196294,0.0117047345,0.00015063255],"about_ca_topic_score_codex":0.0009605194,"about_ca_topic_score_gemma":0.0012989696,"teacher_disagreement_score":0.0039157276,"about_ca_system_score_codex":0.00043212037,"about_ca_system_score_gemma":0.0005936411,"threshold_uncertainty_score":0.007104099},"labels":[],"label_agreement":null},{"id":"W3116851193","doi":"10.1186/s12859-020-03877-9","title":"Effect of APOE ε4 on multimodal brain connectomic traits: a persistent homology study","year":2020,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; University of California, San Diego; Genentech; Fundamental Research Funds for the Central Universities; National Institutes of Health; Servier; National Natural Science Foundation of China; Eisai; H. Lundbeck A/S; IXICO; Natural Science Foundation of Heilongjiang Province; Harbin Engineering University; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; University of Pennsylvania; University of Southern California; Novartis Pharmaceuticals Corporation; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Apolipoprotein E; Neuroimaging; Connectome; Functional magnetic resonance imaging; Neuroscience; Discriminative model; Diffusion MRI; Imaging genetics; Artificial intelligence; Computer science; Computational biology; Medicine; Machine learning; Magnetic resonance imaging; Disease; Biology; Functional connectivity; Pathology","score_opus":0.0443465359365428,"score_gpt":0.2805188398877967,"score_spread":0.23617230395125388,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3116851193","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9678027,0.00016580432,0.031353902,0.00016341584,0.00000496985,0.000015204855,0.00014550207,0.00004617944,0.00030224322],"genre_scores_gemma":[0.99486285,0.000051118088,0.0047890064,0.000020959664,0.000008593112,0.00001105581,0.00013475724,0.000013822098,0.00010780425],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99945885,0.0002539177,0.000021538262,0.0001597956,0.00006223346,0.00004363722],"domain_scores_gemma":[0.995261,0.0030357228,0.00079518755,0.00053028535,0.00016826442,0.00020962604],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020036774,0.00045136808,0.00038900637,0.00093195646,0.0003198482,0.00044935802,0.00045198956,0.000489848,0.0015347236],"category_scores_gemma":[0.0063745272,0.00015120304,0.0007590222,0.0005424654,0.0007849049,0.00068399403,0.0009493211,0.00061967503,0.00009781945],"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":[0.0052445205,0.0010638228,0.5923249,0.0003144858,0.0037021164,0.0032596919,0.0013325942,0.08788679,0.105090156,0.009149541,0.0014177953,0.18921357],"study_design_scores_gemma":[0.00013229568,0.000917458,0.5182277,0.000041704145,0.0012646016,0.0018901164,0.00036593943,0.44133386,0.014956773,0.019932376,0.00086202327,0.00007510806],"about_ca_topic_score_codex":0.0020994332,"about_ca_topic_score_gemma":0.0018782297,"teacher_disagreement_score":0.0020994332,"about_ca_system_score_codex":0.00031223157,"about_ca_system_score_gemma":0.00029059438,"threshold_uncertainty_score":0.010596633},"labels":[],"label_agreement":null},{"id":"W3118322235","doi":"10.1186/s12859-021-04179-4","title":"GWENA: gene co-expression networks analysis and extended modules characterization in a single Bioconductor package","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":66,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre hospitalier universitaire de Québec; Université Laval","funders":"","keywords":"Bioconductor; Gene co-expression network; Computational biology; Phenotype; DNA microarray; Gene; Gene regulatory network; Biology; Gene expression; Gene expression profiling; Computer science; Systems biology; Pipeline (software); Expression (computer science); Biological network; Topology (electrical circuits); Genetics; Mathematics","score_opus":0.012078021885891105,"score_gpt":0.23056987602147563,"score_spread":0.21849185413558453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3118322235","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009446666,0.0015959189,0.43873936,0.0007284656,0.0008255636,0.00063033914,0.08868184,0.4559742,0.003377631],"genre_scores_gemma":[0.070316136,0.0019977412,0.61655015,0.0012868247,0.0003383092,0.012839288,0.17831156,0.10996308,0.008396967],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99658763,0.0010290077,0.00032265732,0.0012644338,0.00054036884,0.00025595032],"domain_scores_gemma":[0.99312216,0.0034289397,0.0008153943,0.0013072344,0.0009869353,0.00033940046],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0076467707,0.006175614,0.004314946,0.0049792733,0.0010796253,0.0034677102,0.006018676,0.0016528732,0.035576385],"category_scores_gemma":[0.019956805,0.002238315,0.0050896765,0.0043476936,0.001241805,0.0023082923,0.004858872,0.004294524,0.02844892],"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":[0.0038689733,0.00040121816,0.016636504,0.0149295395,0.008112733,0.0018637473,0.0019469288,0.031519417,0.023134377,0.032569144,0.70897347,0.15604404],"study_design_scores_gemma":[0.0015575188,0.0007835476,0.025473295,0.0018594752,0.0034092802,0.001925675,0.0003955398,0.24010316,0.033466894,0.10186061,0.5883792,0.0007858728],"about_ca_topic_score_codex":0.0029773193,"about_ca_topic_score_gemma":0.002671251,"teacher_disagreement_score":0.035576385,"about_ca_system_score_codex":0.00092234096,"about_ca_system_score_gemma":0.004185804,"threshold_uncertainty_score":0.1190148},"labels":[],"label_agreement":null},{"id":"W3118344282","doi":"10.1186/s12859-020-03770-5","title":"SPServer: split-statistical potentials for the analysis of protein structures and protein–protein interactions","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Children's Hospital; University of British Columbia","funders":"European Regional Development Fund; Instituto de Salud Carlos III; Generalitat de Catalunya; Agència de Gestió d'Ajuts Universitaris i de Recerca; Ministerio de Asuntos Económicos y Transformación Digital, Gobierno de España; Ministerio de Ciencia e Innovación","keywords":"Web server; Computer science; Protein structure prediction; Protein structure; Protein–protein interaction; Data mining; Amino acid residue; Computational biology; Protein tertiary structure; Bioinformatics; Database; Biology; Peptide sequence; The Internet; Biochemistry; World Wide Web","score_opus":0.012084555805854883,"score_gpt":0.2718247820414553,"score_spread":0.25974022623560045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3118344282","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01721751,0.0015060889,0.73127735,0.0005307349,0.00024334423,0.0002230545,0.021768257,0.22010036,0.007133283],"genre_scores_gemma":[0.1981695,0.002260008,0.6709805,0.00050758047,0.00027762444,0.0015759892,0.06614121,0.050388195,0.009699388],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989875,0.0002023178,0.000060995273,0.00017879906,0.00048352414,0.00008688769],"domain_scores_gemma":[0.9986192,0.0007083974,0.00012413456,0.00019164554,0.00021766232,0.0001389646],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001724743,0.002570192,0.0017610791,0.002158194,0.00070559484,0.0023094139,0.0035517938,0.0017848518,0.027815487],"category_scores_gemma":[0.0050013373,0.0009362271,0.002045871,0.0019514341,0.00064998865,0.0023634015,0.0027567754,0.0020828797,0.016054083],"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":[0.0016064702,0.0004402904,0.006955904,0.0033460539,0.0009456894,0.0012380459,0.0006234087,0.115740895,0.043648686,0.058522142,0.35911137,0.40782103],"study_design_scores_gemma":[0.00030078655,0.00019689358,0.0035031138,0.00019789528,0.00012361656,0.0006234898,0.00007268464,0.8266294,0.018919544,0.073390126,0.07584478,0.00019767553],"about_ca_topic_score_codex":0.0017103823,"about_ca_topic_score_gemma":0.0015934084,"teacher_disagreement_score":0.027815487,"about_ca_system_score_codex":0.0007225,"about_ca_system_score_gemma":0.0013821871,"threshold_uncertainty_score":0.09305209},"labels":[],"label_agreement":null},{"id":"W3124892619","doi":"10.1186/s12859-020-03950-3","title":"SNF-NN: computational method to predict drug-disease interactions using similarity network fusion and neural networks","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Machine learning; Artificial intelligence; Computer science; Artificial neural network; Similarity (geometry); Drug repositioning; Robustness (evolution); Drug discovery; Drug development; Deep learning; Drug; Data mining; Bioinformatics; Medicine; Biology; Pharmacology","score_opus":0.039244372198190415,"score_gpt":0.33385737926637127,"score_spread":0.29461300706818083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3124892619","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07058806,0.002238531,0.91926587,0.0006378444,0.00015358215,0.00018192419,0.00066621625,0.0033422168,0.0029257948],"genre_scores_gemma":[0.7067503,0.0006803439,0.28783074,0.0003407525,0.00012385906,0.0003177182,0.0013649241,0.00010561563,0.0024857104],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994344,0.00013982758,0.000046371486,0.00013399057,0.00018193977,0.00006345507],"domain_scores_gemma":[0.9990403,0.0004977543,0.00012419661,0.00005806524,0.00022392775,0.000055691035],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017733139,0.00102475,0.0013864223,0.0017774819,0.00047049733,0.0006310672,0.0014143558,0.0016997117,0.00235566],"category_scores_gemma":[0.0032491803,0.00038017094,0.0012075049,0.0011371765,0.0004451783,0.0010084853,0.0007430143,0.0011116777,0.0005041247],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016298599,0.00013655717,0.0035968893,0.000097970486,0.00017443954,0.00010533859,0.000024596246,0.83792704,0.0011146066,0.002162188,0.0029538348,0.15154354],"study_design_scores_gemma":[0.0000039788233,0.000010939256,0.000094763105,0.000002605507,0.0000057359293,0.00001161656,0.0000012755576,0.99902415,0.00017468874,0.0005616078,0.00010642225,0.0000022686138],"about_ca_topic_score_codex":0.014399981,"about_ca_topic_score_gemma":0.011652736,"teacher_disagreement_score":0.014399981,"about_ca_system_score_codex":0.0012992746,"about_ca_system_score_gemma":0.0018207228,"threshold_uncertainty_score":0.028632343},"labels":[],"label_agreement":null},{"id":"W3129593819","doi":"10.1186/s12859-020-03927-2","title":"WACS: improving ChIP-seq peak calling by optimally weighting controls","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"Compute Canada","keywords":"Chromatin immunoprecipitation; Chip; Computer science; Noise (video); Weighting; DNA microarray; Bioconductor; Computational biology; Data mining; Genetics; Biology; Artificial intelligence; Telecommunications; Gene; Medicine","score_opus":0.005878323693093789,"score_gpt":0.20453734792653197,"score_spread":0.19865902423343818,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3129593819","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013442718,0.0003672892,0.95608765,0.00013443564,0.00013910286,0.00013507795,0.0003496302,0.028841402,0.0005026361],"genre_scores_gemma":[0.0615694,0.00017230032,0.92903614,0.0003913641,0.00008002652,0.00040704588,0.0021670125,0.0048021707,0.0013746142],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960043,0.00091400696,0.00024459173,0.0012387157,0.0013380001,0.0002604336],"domain_scores_gemma":[0.992504,0.0035613417,0.00059826707,0.0013814294,0.0016571328,0.00029779188],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0058406587,0.0035471169,0.0014859948,0.0025847221,0.00096092356,0.0021639224,0.0047111595,0.0016359307,0.0045592785],"category_scores_gemma":[0.015728153,0.0011310865,0.002226854,0.001830434,0.0012904474,0.0015524537,0.0023343284,0.0036615229,0.0032666808],"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":[0.001435443,0.00054402277,0.00976428,0.0006987176,0.00061980274,0.00025561027,0.00039185947,0.13950388,0.15254623,0.0077661616,0.02349037,0.6629837],"study_design_scores_gemma":[0.00014840682,0.00015077324,0.0014460232,0.000026610365,0.00009032398,0.000121600904,0.000038899278,0.92623687,0.058641553,0.0052890913,0.0076913484,0.00011844939],"about_ca_topic_score_codex":0.00618067,"about_ca_topic_score_gemma":0.0073015545,"teacher_disagreement_score":0.00618067,"about_ca_system_score_codex":0.0011251785,"about_ca_system_score_gemma":0.0024725806,"threshold_uncertainty_score":0.030888736},"labels":[],"label_agreement":null},{"id":"W3137414883","doi":"10.1186/s12859-021-04055-1","title":"Juxtapose: a gene-embedding approach for comparing co-expression networks","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Similarity (geometry); Set (abstract data type); Computer science; Biological network; Expression (computer science); Embedding; Cosine similarity; DNA microarray; Computational biology; Gene regulatory network; Gene; Artificial intelligence; Data mining; Gene expression; Theoretical computer science; Biology; Pattern recognition (psychology); Genetics","score_opus":0.024842362712033446,"score_gpt":0.2742495784601811,"score_spread":0.24940721574814767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3137414883","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041113652,0.00044826668,0.9517233,0.00014024769,0.000075388874,0.00014397023,0.0016002652,0.0036156266,0.0011392758],"genre_scores_gemma":[0.2495004,0.0002795319,0.74512357,0.00009997094,0.000057141817,0.00043333077,0.0029764518,0.00064517226,0.0008844405],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99895346,0.00026806848,0.000071082715,0.00039939996,0.00026016854,0.00004771394],"domain_scores_gemma":[0.9962549,0.0020397857,0.00062063645,0.00059852493,0.000334943,0.000151181],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015961826,0.0011288614,0.000722792,0.005342536,0.00066097354,0.0013866633,0.001255655,0.0010269197,0.003848888],"category_scores_gemma":[0.00696811,0.00045844374,0.0014165754,0.0031881023,0.0010279763,0.0020360337,0.0020373361,0.0012365698,0.00079872384],"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":[0.0012575324,0.00046501844,0.028095044,0.0018238125,0.0012802621,0.0008273044,0.0017125463,0.14026493,0.11777704,0.058966324,0.009547877,0.63798225],"study_design_scores_gemma":[0.00008016624,0.00048683252,0.011148912,0.00011981299,0.00024512137,0.0009504114,0.0006699676,0.79856837,0.036533177,0.13219108,0.018866055,0.0001401015],"about_ca_topic_score_codex":0.000926237,"about_ca_topic_score_gemma":0.0018101447,"teacher_disagreement_score":0.005342536,"about_ca_system_score_codex":0.0006066247,"about_ca_system_score_gemma":0.0006467094,"threshold_uncertainty_score":0.012875795},"labels":[],"label_agreement":null},{"id":"W3146187752","doi":"10.1186/s12859-021-04018-6","title":"Reliable genomic strategies for species classification of plant genetic resources","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Newfoundland and Labrador; Ministerie van Landbouw, Natuur en Voedselkwaliteit","keywords":"Naive Bayes classifier; Classifier (UML); Documentation; Computer science; Data mining; Random forest; Variety (cybernetics); Bayes' theorem; Machine learning; Artificial intelligence; Support vector machine; Bayesian probability","score_opus":0.028445124261018858,"score_gpt":0.2325085918689675,"score_spread":0.20406346760794863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3146187752","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1384938,0.0018663718,0.8368928,0.0010706465,0.00014575789,0.0004939979,0.011068745,0.005783788,0.004184106],"genre_scores_gemma":[0.23117138,0.00033004672,0.7541202,0.00016084059,0.00006159557,0.00025485872,0.012945757,0.0004917283,0.00046365088],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99406093,0.0022915087,0.0006116622,0.0015130384,0.0012506072,0.00027217774],"domain_scores_gemma":[0.97001183,0.013366235,0.0040980363,0.0054741255,0.006263093,0.0007866462],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011487079,0.0010294174,0.0012154978,0.006084551,0.0010307609,0.003330581,0.0020026946,0.0011636956,0.002669359],"category_scores_gemma":[0.039122578,0.0005145945,0.0012136168,0.0050951247,0.00109689,0.003948029,0.0019213752,0.0017754727,0.002612292],"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":[0.00087413314,0.00049860164,0.097493395,0.0024484477,0.00046979,0.0005232252,0.002403063,0.030744128,0.08848181,0.017729936,0.011689015,0.74664444],"study_design_scores_gemma":[0.00021747626,0.0006457947,0.16231145,0.001415226,0.0006786389,0.001366642,0.0033611248,0.53227484,0.09531514,0.1328314,0.06919388,0.00038831373],"about_ca_topic_score_codex":0.0024543935,"about_ca_topic_score_gemma":0.004414554,"teacher_disagreement_score":0.011487079,"about_ca_system_score_codex":0.0014087893,"about_ca_system_score_gemma":0.0020328446,"threshold_uncertainty_score":0.060750246},"labels":[],"label_agreement":null},{"id":"W3153503836","doi":"10.1186/s12859-021-04117-4","title":"MAPS: machine-assisted phenotype scoring enables rapid functional assessment of genetic variants by high-content microscopy","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Canadian Institutes of Health Research","keywords":"Workflow; Computer science; Leverage (statistics); Deep learning; Artificial intelligence; Machine learning; PTEN; Software; Computational biology; Bioinformatics; Biology; Genetics; Database","score_opus":0.019422379557617022,"score_gpt":0.26188649321732815,"score_spread":0.24246411365971113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3153503836","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045227557,0.00045112858,0.7450861,0.00068007485,0.00020657157,0.00014989726,0.005258535,0.19949824,0.0034419731],"genre_scores_gemma":[0.3811749,0.00077438337,0.59395534,0.0005787752,0.00009224818,0.00054900796,0.0078684,0.010742695,0.0042642457],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99941826,0.00008473364,0.000035811787,0.0001199519,0.0002869161,0.000054309596],"domain_scores_gemma":[0.99893326,0.00043461,0.00013422566,0.0002203427,0.00017218618,0.000105442974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011825113,0.0010345279,0.0005207887,0.0015034383,0.00032967245,0.0012315102,0.0017872324,0.0010434615,0.0050220317],"category_scores_gemma":[0.0027450884,0.0006551351,0.0010690291,0.00045960394,0.00060433976,0.001277559,0.0021189093,0.0013099449,0.0018280465],"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":[0.0014358304,0.0002957308,0.023297861,0.0013987183,0.0010138381,0.0018321804,0.0008411325,0.089487344,0.27596506,0.020923892,0.17397465,0.4095338],"study_design_scores_gemma":[0.00012764063,0.00013804574,0.011329005,0.00011924768,0.000101934944,0.0010055928,0.00011392983,0.7133915,0.19305834,0.020670634,0.059666023,0.00027807106],"about_ca_topic_score_codex":0.0020753113,"about_ca_topic_score_gemma":0.0030787005,"teacher_disagreement_score":0.0050220317,"about_ca_system_score_codex":0.00070660457,"about_ca_system_score_gemma":0.0008276319,"threshold_uncertainty_score":0.016800344},"labels":[],"label_agreement":null},{"id":"W3157357664","doi":"10.1186/s12859-022-04693-z","title":"Evaluation of statistical approaches for association testing in noisy drug screening data","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Université du Québec à Montréal; Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"Syöpäjärjestöt; Academy of Finland; European Commission","keywords":"Concordance; False positive paradox; Computer science; Statistical hypothesis testing; Pearson product-moment correlation coefficient; Data mining; Spearman's rank correlation coefficient; Correlation; Rank correlation; Statistics; Parametric statistics; Noise (video); Machine learning; Medicine; Artificial intelligence; Mathematics; Internal medicine","score_opus":0.8876184499002661,"score_gpt":0.574548024450978,"score_spread":0.3130704254492881,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3157357664","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07754961,0.0016041459,0.91632557,0.0011725861,0.000111693415,0.000376104,0.0006067977,0.0009785591,0.0012749154],"genre_scores_gemma":[0.5509893,0.0005759415,0.44550395,0.00039356432,0.00014755728,0.0007320016,0.0009812721,0.0002804801,0.0003959064],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.945641,0.041177902,0.0029314833,0.003305331,0.0064383927,0.0005059076],"domain_scores_gemma":[0.52388084,0.43953148,0.01268885,0.014177504,0.0080725765,0.0016488744],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0842928,0.0012946855,0.0014713977,0.0036369509,0.00074754056,0.0027158363,0.0029139705,0.00196076,0.0017922199],"category_scores_gemma":[0.2885305,0.00053975737,0.0019219603,0.003344857,0.0028023536,0.002098802,0.0029026305,0.003058228,0.00036671522],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020939002,0.0003837986,0.05572323,0.0011997304,0.0024603107,0.0004584479,0.0005055437,0.6594512,0.0028523519,0.04186037,0.0033903478,0.22962075],"study_design_scores_gemma":[0.00013211941,0.0005329041,0.0043950845,0.00008940731,0.00014432683,0.00023542956,0.00007722799,0.9548671,0.0020078495,0.03651796,0.0009621573,0.000038459508],"about_ca_topic_score_codex":0.0021023643,"about_ca_topic_score_gemma":0.0015464054,"teacher_disagreement_score":0.0842928,"about_ca_system_score_codex":0.0019534642,"about_ca_system_score_gemma":0.00378433,"threshold_uncertainty_score":0.44578826},"labels":[],"label_agreement":null},{"id":"W3159624973","doi":"10.1186/s12859-021-04138-z","title":"Dynamic model updating (DMU) approach for statistical learning model building with missing data","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto; Princess Margaret Cancer Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Prostate Cancer Canada","keywords":"Missing data; Categorical variable; Data mining; Imputation (statistics); Computer science; Cluster analysis; Closeness; Statistical model; Bayesian probability; Machine learning; Artificial intelligence; Mathematics","score_opus":0.14795907018902008,"score_gpt":0.39605897055970263,"score_spread":0.24809990037068255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3159624973","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020131024,0.00047241003,0.9964032,0.00024806464,0.00004228607,0.000049458973,0.00010963799,0.0003494126,0.0003123382],"genre_scores_gemma":[0.19016217,0.0012255795,0.8028681,0.0006843036,0.00034035422,0.0011785396,0.001379967,0.0003242573,0.0018367099],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9923396,0.005276808,0.0003556369,0.0010637906,0.00071980734,0.00024430142],"domain_scores_gemma":[0.9796569,0.016776726,0.00094937504,0.0011066612,0.0012216949,0.0002886993],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010199861,0.0015956705,0.0030580056,0.002257555,0.0010221389,0.0020722235,0.0043137684,0.0020544366,0.0029674259],"category_scores_gemma":[0.027879445,0.0013708737,0.0028955953,0.0024661266,0.0010757073,0.0017658604,0.0031196377,0.0042150156,0.0008396507],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020046298,0.00014934754,0.0041711754,0.00057848665,0.0009634132,0.0002733419,0.0004063421,0.7068472,0.0008093618,0.04867849,0.0046189157,0.23230347],"study_design_scores_gemma":[0.000023005117,0.000045100805,0.00020918642,0.00003707048,0.00006295421,0.00004767644,0.000022598919,0.9703658,0.00035111065,0.026295507,0.0025216474,0.000018300761],"about_ca_topic_score_codex":0.00822877,"about_ca_topic_score_gemma":0.008570992,"teacher_disagreement_score":0.010199861,"about_ca_system_score_codex":0.0016468859,"about_ca_system_score_gemma":0.0029974196,"threshold_uncertainty_score":0.05394268},"labels":[],"label_agreement":null},{"id":"W3162362563","doi":"10.1186/s12859-020-03873-z","title":"Identifying cell types from single-cell data based on similarities and dissimilarities between cells","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Wuhan Institute of Technology; China Scholarship Council; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Cluster analysis; Spectral clustering; Dimensionality reduction; Computer science; Categorical variable; Pattern recognition (psychology); Hierarchical clustering; Data mining; Similarity (geometry); Cell type; Clustering high-dimensional data; Artificial intelligence; Computational biology; Mathematics; Biology; Cell; Genetics; Machine learning","score_opus":0.06198245153201891,"score_gpt":0.250350994032811,"score_spread":0.1883685425007921,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3162362563","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31105036,0.001966209,0.679277,0.0004407206,0.00020614223,0.00022879161,0.0028682095,0.0013930289,0.0025696259],"genre_scores_gemma":[0.6734645,0.0012220861,0.3200477,0.00016520149,0.000117197924,0.00023319863,0.0038975584,0.00013717802,0.00071543606],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991886,0.00008809922,0.000083884996,0.00025072155,0.00032785162,0.000060875278],"domain_scores_gemma":[0.9971644,0.00110316,0.00047942137,0.00035689154,0.000741061,0.0001550449],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013350168,0.00058985635,0.0009728896,0.0035128852,0.00048139616,0.0015311802,0.0007802288,0.00088769884,0.0013095795],"category_scores_gemma":[0.00425703,0.00022432437,0.00087281194,0.0026728876,0.00080656,0.001358579,0.00076977874,0.000904851,0.0011210323],"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":[0.00095970655,0.00033735583,0.14124854,0.002082947,0.00045934768,0.00066563714,0.0010716474,0.10427257,0.3549686,0.008647054,0.006287517,0.37899914],"study_design_scores_gemma":[0.0000421875,0.00017177251,0.09020073,0.00017452863,0.0002863517,0.00087186217,0.0010762481,0.7409818,0.12842022,0.026113898,0.011428351,0.00023194743],"about_ca_topic_score_codex":0.001713204,"about_ca_topic_score_gemma":0.0025467093,"teacher_disagreement_score":0.0035128852,"about_ca_system_score_codex":0.000580231,"about_ca_system_score_gemma":0.00068198494,"threshold_uncertainty_score":0.0070602894},"labels":[],"label_agreement":null},{"id":"W3163273456","doi":"10.1186/s12859-021-04180-x","title":"Profile hidden Markov model sequence analysis can help remove putative pseudogenes from DNA barcoding and metabarcoding datasets","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Environmental DNA in Biodiversity Studies","field":"Environmental Science","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Government of Canada; Ontario Genomics; Genome Canada","keywords":"Pseudogene; Barcode; Amplicon; Computational biology; DNA barcoding; Biology; Gene; Sequence analysis; Genetics; DNA sequencing; Coding region; Genome; Computer science; Polymerase chain reaction; Evolutionary biology","score_opus":0.037522168001210686,"score_gpt":0.24711458856696852,"score_spread":0.20959242056575783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3163273456","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15413201,0.00063678017,0.81500953,0.000918312,0.00015330267,0.00026728582,0.0071467245,0.020469174,0.0012668221],"genre_scores_gemma":[0.37268594,0.00035474106,0.60775435,0.0005715351,0.0000691914,0.0005827061,0.015261029,0.001957587,0.0007629059],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998752,0.0005341624,0.00011174081,0.00035233446,0.00017991407,0.00006973834],"domain_scores_gemma":[0.99098164,0.006825097,0.00070907135,0.0006065301,0.0006693972,0.00020832101],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005667446,0.0013250698,0.0009488731,0.00147805,0.0009623322,0.0014545317,0.0014011967,0.001692629,0.0022672887],"category_scores_gemma":[0.018625287,0.0007071768,0.0024721657,0.0013480393,0.00050314085,0.0018230347,0.001080077,0.0026780064,0.0015017892],"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":[0.0022835948,0.00079109456,0.091752,0.0022692059,0.0024929934,0.0008935857,0.0012662379,0.63044447,0.05627846,0.011206574,0.015750073,0.1845717],"study_design_scores_gemma":[0.000048610575,0.0000789099,0.0030852095,0.000050655875,0.00009479462,0.000069076246,0.000063374086,0.9782296,0.0071333605,0.009075781,0.0020313514,0.000039230865],"about_ca_topic_score_codex":0.0061363527,"about_ca_topic_score_gemma":0.015552319,"teacher_disagreement_score":0.0061363527,"about_ca_system_score_codex":0.001506391,"about_ca_system_score_gemma":0.0023366238,"threshold_uncertainty_score":0.029972672},"labels":[],"label_agreement":null},{"id":"W3164474166","doi":"10.1186/s12859-021-04209-1","title":"SMILE: systems metabolomics using interpretable learning and evolution","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; Queen's University","funders":"Queen's University; National Research Council Canada; Compute Canada","keywords":"Interpretability; Metabolomics; Machine learning; Computer science; Artificial intelligence; Visualization; Mechanism (biology); Process (computing); Interface (matter); Disease; Data science; Big data; Bioinformatics; Data mining; Biology; Medicine","score_opus":0.013210388016453174,"score_gpt":0.24776902086803762,"score_spread":0.23455863285158446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3164474166","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008774272,0.00016171334,0.9878215,0.0003927742,0.00003607858,0.000046881498,0.00018118565,0.0017348266,0.00085070374],"genre_scores_gemma":[0.2469358,0.00044561902,0.7492349,0.00027815104,0.00010597025,0.00045028102,0.0009049317,0.00051326375,0.0011310141],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99924517,0.00037308567,0.00003685368,0.0001281658,0.00018124592,0.000035551482],"domain_scores_gemma":[0.9981248,0.0012837758,0.00019119185,0.00017401495,0.00016569803,0.000060496663],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00195691,0.001041385,0.00076318794,0.0008419778,0.0004643883,0.0011133585,0.0013788837,0.001151195,0.0023348117],"category_scores_gemma":[0.0051370296,0.00032194995,0.0019065775,0.0006029667,0.0011399206,0.0011042525,0.0015649742,0.0019468229,0.0005435515],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013046844,0.000121777775,0.004675444,0.00043216528,0.00027726486,0.0003545144,0.00023416289,0.781134,0.00864693,0.088243686,0.003202079,0.11254751],"study_design_scores_gemma":[0.000009104378,0.000022915658,0.00021423567,0.0000107570095,0.000010464283,0.00003079093,0.00000617192,0.9743825,0.0008956409,0.02313298,0.0012761761,0.000008307128],"about_ca_topic_score_codex":0.0012825284,"about_ca_topic_score_gemma":0.0010296386,"teacher_disagreement_score":0.0023348117,"about_ca_system_score_codex":0.0007100953,"about_ca_system_score_gemma":0.00084690016,"threshold_uncertainty_score":0.010349274},"labels":[],"label_agreement":null},{"id":"W3165113039","doi":"10.1186/s12859-021-04042-6","title":"PIGNON: a protein–protein interaction-guided functional enrichment analysis for quantitative proteomics","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; Government of Ontario; Compute Canada","keywords":"Proteomics; Computational biology; Interaction network; Cluster analysis; Biology; DNA microarray; Annotation; Gene ontology; Quantitative proteomics; Bioinformatics; Computer science; Gene expression; Gene; Genetics; Artificial intelligence","score_opus":0.036280038192337966,"score_gpt":0.2814574738628821,"score_spread":0.24517743567054415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3165113039","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012012005,0.00031393106,0.9792859,0.00012792028,0.000051774008,0.000105960484,0.00065373094,0.0069112773,0.0005374685],"genre_scores_gemma":[0.13415267,0.00041970843,0.8585671,0.0003411792,0.00006605047,0.0005773358,0.0029823452,0.0014462647,0.0014472576],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990563,0.0003124047,0.000027949283,0.00021333776,0.0003343371,0.00005574549],"domain_scores_gemma":[0.99843615,0.0009834288,0.0001619543,0.00017642889,0.00016974608,0.00007228181],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020316136,0.0017460529,0.0013022616,0.002083865,0.00048386495,0.0010633705,0.0017164832,0.0009865594,0.0023046483],"category_scores_gemma":[0.0030981458,0.00062324514,0.0024622902,0.0011842139,0.0009101571,0.00063695625,0.0011987865,0.0018779017,0.0008667504],"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":[0.0012710544,0.0008540547,0.011502963,0.0024879668,0.0020623205,0.001254722,0.00028778712,0.269176,0.3076761,0.037890643,0.023850827,0.34168547],"study_design_scores_gemma":[0.000058564205,0.00014666186,0.0022071651,0.00002365479,0.00010539255,0.00022935879,0.000018956147,0.95752877,0.017820785,0.015466683,0.0063417074,0.00005226508],"about_ca_topic_score_codex":0.0014591049,"about_ca_topic_score_gemma":0.0023211155,"teacher_disagreement_score":0.0023046483,"about_ca_system_score_codex":0.000843054,"about_ca_system_score_gemma":0.001112937,"threshold_uncertainty_score":0.010744333},"labels":[],"label_agreement":null},{"id":"W3165409583","doi":"10.1186/s12859-021-04215-3","title":"Uncovering the roles of microRNAs/lncRNAs in characterising breast cancer subtypes and prognosis","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Cancer-related molecular mechanisms research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"BC Cancer Agency; National Natural Science Foundation of China; Cancer Research UK","keywords":"Subtyping; Breast cancer; microRNA; Oncology; Cancer; Computational biology; Bioinformatics; Biology; Medicine; Internal medicine; Gene; Computer science; Genetics","score_opus":0.010208272530979449,"score_gpt":0.2552147196282357,"score_spread":0.24500644709725627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3165409583","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88060915,0.02471851,0.06760159,0.0017875138,0.00020781302,0.00031766325,0.01917002,0.0007195801,0.0048681037],"genre_scores_gemma":[0.9434171,0.00231316,0.04004159,0.00039438697,0.00010515446,0.00021904933,0.01290809,0.00014377681,0.00045770593],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9946613,0.002310713,0.0005896868,0.0013463586,0.0008586212,0.00023341335],"domain_scores_gemma":[0.98173195,0.012404148,0.0025354389,0.0013513566,0.0016346662,0.00034240144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00908105,0.00076653046,0.00094223116,0.002832278,0.0005594701,0.001675711,0.00072298583,0.00067677716,0.0013779058],"category_scores_gemma":[0.01955045,0.00023624796,0.0018597523,0.0027785643,0.00051595893,0.0009513126,0.00096339727,0.00094665575,0.0007696798],"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":[0.00068592414,0.00012437768,0.87632245,0.0011534918,0.0017703575,0.000081407925,0.00026471223,0.0081699835,0.0073014013,0.0005387745,0.0025948691,0.10099229],"study_design_scores_gemma":[0.00014424232,0.00066681387,0.845453,0.00091968547,0.0039630323,0.0011465359,0.0010808253,0.093260966,0.020530628,0.009924773,0.022733692,0.00017576509],"about_ca_topic_score_codex":0.0029228618,"about_ca_topic_score_gemma":0.005499123,"teacher_disagreement_score":0.00908105,"about_ca_system_score_codex":0.00067162944,"about_ca_system_score_gemma":0.0014958833,"threshold_uncertainty_score":0.048025787},"labels":[],"label_agreement":null},{"id":"W3173187119","doi":"10.1186/s12859-021-04267-5","title":"Pheniqs 2.0: accurate, high-performance Bayesian decoding and confidence estimation for combinatorial barcode indexing","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":54,"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; New York University Abu Dhabi; New York University","keywords":"Barcode; Computer science; Decoding methods; Probabilistic logic; Benchmark (surveying); Data mining; Algorithm; Artificial intelligence","score_opus":0.016237025944968002,"score_gpt":0.25120736955113604,"score_spread":0.23497034360616803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3173187119","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005089582,0.00017418382,0.9079888,0.00020601308,0.00008521673,0.00010863439,0.0026389048,0.08255499,0.0011537579],"genre_scores_gemma":[0.07372917,0.00028127374,0.8968164,0.00060422195,0.00010567208,0.00085054163,0.007898635,0.017156845,0.0025572171],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99568886,0.0010105838,0.00033718615,0.0008351194,0.0018978394,0.00023038438],"domain_scores_gemma":[0.98969555,0.006050094,0.0011496976,0.0010100834,0.0016813537,0.00041314677],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008935501,0.002785753,0.0022160755,0.002511148,0.0011189737,0.003497271,0.0048112613,0.0024720714,0.016584551],"category_scores_gemma":[0.03032473,0.0022844328,0.0018993465,0.00141816,0.0018227736,0.002573065,0.0034760947,0.0044726245,0.00948359],"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":[0.0022454278,0.00045530836,0.023539659,0.002757724,0.001147807,0.0010386263,0.0013278299,0.2447567,0.09259439,0.06819089,0.14696291,0.41498274],"study_design_scores_gemma":[0.00019534925,0.00012198173,0.0015728686,0.00012408903,0.000071306466,0.00029321393,0.000051825173,0.88692254,0.05665662,0.030414702,0.023333177,0.00024241064],"about_ca_topic_score_codex":0.004396586,"about_ca_topic_score_gemma":0.005291025,"teacher_disagreement_score":0.016584551,"about_ca_system_score_codex":0.0019440091,"about_ca_system_score_gemma":0.005096795,"threshold_uncertainty_score":0.055480838},"labels":[],"label_agreement":null},{"id":"W3176962018","doi":"10.1186/s12859-021-04230-4","title":"StrongestPath: a Cytoscape application for protein–protein interaction analysis","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Institute for Research in Fundamental Sciences","keywords":"Protein–protein interaction; Computer science; Computational biology; Network analysis; Interaction network; DNA microarray; Graphical user interface; Bioinformatics; Set (abstract data type); Biology; Database; Gene; Genetics; Gene expression; Engineering","score_opus":0.01255292378503829,"score_gpt":0.2511388889712844,"score_spread":0.2385859651862461,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3176962018","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008590657,0.001966017,0.35199702,0.0012784202,0.0006086215,0.000805902,0.113707,0.50858086,0.012465608],"genre_scores_gemma":[0.0841134,0.004141509,0.60412765,0.00278564,0.00047948284,0.0057147434,0.22478552,0.055548042,0.018303927],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99900913,0.00016426714,0.000068471185,0.0002237948,0.00044897714,0.000085372216],"domain_scores_gemma":[0.9976592,0.0014260072,0.00017055722,0.00021694785,0.0002869108,0.00024039856],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015071724,0.0023050506,0.0011823514,0.004872776,0.0013464951,0.0015693696,0.00420408,0.0016226819,0.05250968],"category_scores_gemma":[0.00452476,0.0013619588,0.0014586527,0.0024910127,0.00047813726,0.0021603454,0.0026247606,0.0028775681,0.016891483],"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":[0.0009134239,0.0002811608,0.003939777,0.006483663,0.00103636,0.0013721542,0.00045657367,0.010591033,0.03689836,0.012545238,0.7672497,0.15823257],"study_design_scores_gemma":[0.0008506944,0.00019289202,0.008683239,0.000661578,0.00037037866,0.001968268,0.00014217732,0.12125501,0.08387462,0.052556697,0.7289657,0.0004786989],"about_ca_topic_score_codex":0.0031658616,"about_ca_topic_score_gemma":0.0053529735,"teacher_disagreement_score":0.05250968,"about_ca_system_score_codex":0.00079360994,"about_ca_system_score_gemma":0.0025011124,"threshold_uncertainty_score":0.1756624},"labels":[],"label_agreement":null},{"id":"W3191052428","doi":"10.1186/1471-2105-12-s9-s5","title":"Fractionation statistics","year":2011,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Biology; Genome; Gene; Gene duplication; Genetics; Chromosome; Function (biology); Copy-number variation; Computational biology; Binomial distribution; Gene dosage; Statistics; Mathematics; Gene expression","score_opus":0.0331666259512709,"score_gpt":0.236926421764829,"score_spread":0.2037597958135581,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3191052428","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04447858,0.0018112463,0.8871961,0.0013254103,0.0006815416,0.0012227674,0.03073483,0.013851337,0.018698119],"genre_scores_gemma":[0.48463368,0.0013166924,0.4062737,0.00174229,0.0009994686,0.004044603,0.06962121,0.0051593333,0.026209002],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9911493,0.002913641,0.00067957,0.0028290625,0.0019056287,0.0005227187],"domain_scores_gemma":[0.9639776,0.021871023,0.0018798199,0.008756688,0.0029974247,0.00051747233],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010583093,0.001186306,0.0021725707,0.0029453742,0.001223355,0.0025170639,0.0037104702,0.0022761498,0.040893942],"category_scores_gemma":[0.051366333,0.0006098906,0.001965157,0.0033447295,0.0020465935,0.0028003731,0.0018170523,0.0030968795,0.016497448],"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":[0.0022275022,0.0004217742,0.058106754,0.0019970227,0.0008871641,0.000949059,0.00063954835,0.1247562,0.008582648,0.21023236,0.14483196,0.44636804],"study_design_scores_gemma":[0.00045049805,0.00080964237,0.018238254,0.00040229745,0.00034740518,0.0015955291,0.0003727796,0.47911325,0.012452507,0.34371686,0.14227165,0.00022934507],"about_ca_topic_score_codex":0.0023940965,"about_ca_topic_score_gemma":0.0020781653,"teacher_disagreement_score":0.040893942,"about_ca_system_score_codex":0.001822974,"about_ca_system_score_gemma":0.0023651472,"threshold_uncertainty_score":0.13680387},"labels":[],"label_agreement":null},{"id":"W3197024050","doi":"10.1186/s12859-021-04337-8","title":"A globally diverse reference alignment and panel for imputation of mitochondrial DNA variants","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Mitochondrial Function and Pathology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; JPB Foundation; F. Hoffmann-La Roche; University of Southern California; Eli Lilly and Company; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Bristol-Myers Squibb; National Institute on Aging; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Haplogroup; Imputation (statistics); 1000 Genomes Project; Mitochondrial DNA; Biology; Computational biology; Missing data; Genetics; Genome; Genotyping; DNA microarray; Reference genome; Hypervariable region; Single-nucleotide polymorphism; Genotype; Computer science; Haplotype; Gene","score_opus":0.03677071907624388,"score_gpt":0.26635807950817375,"score_spread":0.22958736043192987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3197024050","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06599731,0.0013910792,0.8635905,0.0005403527,0.00042891403,0.00060645357,0.051640738,0.011855629,0.003949051],"genre_scores_gemma":[0.080433,0.00035443367,0.7825933,0.0004013047,0.000115849085,0.0014460002,0.13006034,0.002287463,0.0023083251],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9891271,0.0034557602,0.0010930467,0.0040737083,0.0017854436,0.00046497546],"domain_scores_gemma":[0.98126674,0.004091831,0.0018355293,0.005194227,0.007087822,0.0005238587],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014997382,0.0018500799,0.002200273,0.0063329837,0.0019251353,0.0019930606,0.0032927666,0.0021609098,0.007320079],"category_scores_gemma":[0.03719002,0.0011623866,0.0024984991,0.0082748495,0.0005615505,0.0011501105,0.0030571497,0.002781954,0.009003369],"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":[0.002695406,0.00066085526,0.107652195,0.0019791927,0.0024303915,0.0018159305,0.0024062712,0.056320705,0.12325014,0.012922271,0.13997343,0.54789317],"study_design_scores_gemma":[0.0012734265,0.0016792112,0.19232033,0.001222135,0.0025590935,0.0041159275,0.0011038565,0.2860104,0.12567262,0.026675865,0.35669783,0.00066929037],"about_ca_topic_score_codex":0.0058055976,"about_ca_topic_score_gemma":0.011697088,"teacher_disagreement_score":0.014997382,"about_ca_system_score_codex":0.0010293424,"about_ca_system_score_gemma":0.003511358,"threshold_uncertainty_score":0.07931465},"labels":[],"label_agreement":null},{"id":"W3203875161","doi":"10.1186/s12859-021-04398-9","title":"On the robustness of generalization of drug–drug interaction models","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; Université Laval","funders":"Mitacs; Compute Canada; Nvidia","keywords":"Computer science; Machine learning; Robustness (evolution); Generalizability theory; Artificial intelligence; Benchmarking; Multi-task learning; Generalization; Task (project management); Data mining","score_opus":0.04704167203536014,"score_gpt":0.2900567858064442,"score_spread":0.24301511377108403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3203875161","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47081482,0.0076979618,0.49888176,0.008907474,0.00043691494,0.0003681657,0.0017272322,0.0024692796,0.008696409],"genre_scores_gemma":[0.9735517,0.0009836085,0.021791711,0.00079455355,0.00018607377,0.00013677239,0.0012897627,0.00019034745,0.0010755386],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99373335,0.0037635271,0.0004230083,0.0010964584,0.00063032383,0.0003533285],"domain_scores_gemma":[0.9041899,0.07801457,0.005234302,0.008601779,0.0028571177,0.001102343],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.029203238,0.0026837934,0.0018277072,0.0021321601,0.0008955004,0.0019086319,0.0026211566,0.0028243326,0.0016357282],"category_scores_gemma":[0.09312745,0.0010145449,0.002415997,0.0009505176,0.0029573177,0.00299153,0.004201789,0.004534874,0.0004956937],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002635912,0.00007789542,0.0063800327,0.00010675673,0.0002518042,0.000075189004,0.00007333226,0.9748293,0.0005318431,0.0037097365,0.0009983982,0.01270211],"study_design_scores_gemma":[0.000021929061,0.000112376576,0.0012431588,0.000048354366,0.000037261092,0.00003436567,0.000015486277,0.9869779,0.0003872155,0.010860473,0.0002466862,0.0000149971665],"about_ca_topic_score_codex":0.0136542665,"about_ca_topic_score_gemma":0.005920685,"teacher_disagreement_score":0.029203238,"about_ca_system_score_codex":0.002549081,"about_ca_system_score_gemma":0.0017247398,"threshold_uncertainty_score":0.15444332},"labels":[],"label_agreement":null},{"id":"W3208925084","doi":"10.1186/s12859-021-04451-7","title":"LongStitch: high-quality genome assembly correction and scaffolding using long reads","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":81,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"National Human Genome Research Institute; National Institutes of Health; Genome British Columbia; Genome Canada","keywords":"Scaffold; Sequence assembly; Computational biology; DNA microarray; Genome; Computer science; Quality (philosophy); Biology; Genetics; Programming language; Gene; Transcriptome","score_opus":0.033476493123443814,"score_gpt":0.27870488512566594,"score_spread":0.24522839200222213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3208925084","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.053083472,0.0012883154,0.77765423,0.0003711985,0.00041000778,0.00053818745,0.010471713,0.15284604,0.003336878],"genre_scores_gemma":[0.086551175,0.0005147288,0.8714593,0.00037594725,0.000101649704,0.0006347354,0.02553689,0.011012642,0.0038129643],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99786204,0.00023885627,0.00016194672,0.0007347912,0.00083970354,0.00016276797],"domain_scores_gemma":[0.9957415,0.001466677,0.0006844746,0.0010181873,0.00085143466,0.00023779945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033758297,0.0019201621,0.0011319078,0.0014263414,0.0012390458,0.0016594714,0.0025145498,0.0011159425,0.0072006704],"category_scores_gemma":[0.00610427,0.0012408237,0.0017812543,0.0013532573,0.00091921294,0.0015743026,0.0024024793,0.0028251505,0.0054854206],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015947386,0.00032967012,0.009243317,0.0026738206,0.0006427459,0.001077096,0.0011137344,0.026217854,0.44802037,0.0064245784,0.07360039,0.4290616],"study_design_scores_gemma":[0.00035898728,0.0007001132,0.008558298,0.00031187397,0.00022633534,0.0010628798,0.00023358011,0.16148128,0.6937752,0.0063950387,0.12640378,0.0004925876],"about_ca_topic_score_codex":0.002441679,"about_ca_topic_score_gemma":0.004116893,"teacher_disagreement_score":0.0072006704,"about_ca_system_score_codex":0.00091801863,"about_ca_system_score_gemma":0.0020471925,"threshold_uncertainty_score":0.024088621},"labels":[],"label_agreement":null},{"id":"W3209044105","doi":"10.1186/s12859-021-04420-0","title":"Improve hot region prediction by analyzing different machine learning algorithms","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Computational Drug Discovery Methods","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":"Simon Fraser University","funders":"Wuhan University of Science and Technology; Wuhan University; China Scholarship Council; National Natural Science Foundation of China","keywords":"Computer science; Naive Bayes classifier; Machine learning; Artificial intelligence; Random forest; Hot spot (computer programming); Support vector machine; Cluster analysis; Algorithm; Bayes' theorem; Precision and recall; Measure (data warehouse); Data mining; Pattern recognition (psychology); Bayesian probability","score_opus":0.023246946459827913,"score_gpt":0.26319112687879803,"score_spread":0.23994418041897012,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209044105","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28938892,0.004239985,0.695158,0.0004304936,0.00022191358,0.00028677587,0.0007966726,0.006616955,0.0028602397],"genre_scores_gemma":[0.68970454,0.00080784207,0.30546978,0.00024741061,0.00012750605,0.00017073992,0.002078436,0.00021674826,0.0011770882],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99819165,0.00038393913,0.00017749332,0.00046218673,0.00058770896,0.00019693916],"domain_scores_gemma":[0.9967319,0.0017422618,0.0003040795,0.00021167847,0.0009257522,0.00008444828],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025669204,0.0013399561,0.001636053,0.004995615,0.0007466399,0.0011577636,0.0011051638,0.0012694648,0.0010643926],"category_scores_gemma":[0.00496685,0.00028572872,0.0016352407,0.0028730526,0.00034548255,0.0012999524,0.0004792045,0.00080109824,0.000615747],"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":[0.0006552128,0.0006919291,0.04364516,0.00045170423,0.0005459021,0.0002662389,0.000111372836,0.36007112,0.012589237,0.0015129193,0.005725421,0.57373375],"study_design_scores_gemma":[0.000019594778,0.0000718859,0.0032780955,0.000015799973,0.00007534361,0.00006258177,0.000016831997,0.9901674,0.004422512,0.0012995788,0.00055560056,0.000014801567],"about_ca_topic_score_codex":0.006413334,"about_ca_topic_score_gemma":0.0037775806,"teacher_disagreement_score":0.006413334,"about_ca_system_score_codex":0.0008248998,"about_ca_system_score_gemma":0.00110084,"threshold_uncertainty_score":0.0135753155},"labels":[],"label_agreement":null},{"id":"W3216980854","doi":"10.1186/s12859-021-04484-y","title":"A multitask transfer learning framework for the prediction of virus-human protein–protein interactions","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute for Catastrophic Loss Reduction; Gottfried Wilhelm Leibniz Universität Hannover; Niedersächsische Ministerium für Wissenschaft und Kultur","keywords":"Transfer of learning; Computer science; Computational biology; Protein–protein interaction; Multi-task learning; Artificial intelligence; Machine learning; Biology; Task (project management); Genetics; Engineering","score_opus":0.020319157096883683,"score_gpt":0.26183476274924095,"score_spread":0.24151560565235727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3216980854","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09267411,0.0030365316,0.89277846,0.0018405152,0.00022352165,0.00014582693,0.0013773357,0.0045223143,0.0034013188],"genre_scores_gemma":[0.8530899,0.0008027143,0.1328427,0.00090111326,0.0003352614,0.00044009706,0.003392373,0.00030052336,0.007895338],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99931884,0.00025333435,0.00003123008,0.00019050743,0.00010471181,0.00010146646],"domain_scores_gemma":[0.998553,0.0008283419,0.00011956241,0.00011571336,0.00023787761,0.00014566301],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020244045,0.0012172938,0.0011983447,0.0011208332,0.00061045354,0.0009037614,0.0024167704,0.0021180897,0.0035765893],"category_scores_gemma":[0.0031944758,0.000481663,0.0015090699,0.0010561963,0.00074063794,0.0015374868,0.0016461515,0.0022567722,0.0015346229],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033868002,0.00040113236,0.0033336335,0.00019752856,0.00023022905,0.00027862104,0.000119511795,0.8309173,0.0028138573,0.0054920795,0.009383591,0.14649384],"study_design_scores_gemma":[0.000007438118,0.000020886795,0.00012982464,0.0000036012837,0.0000055480205,0.000009379431,0.000004902966,0.9953831,0.00015859853,0.004050187,0.00022277102,0.0000037369439],"about_ca_topic_score_codex":0.007974803,"about_ca_topic_score_gemma":0.0072098905,"teacher_disagreement_score":0.007974803,"about_ca_system_score_codex":0.0012773265,"about_ca_system_score_gemma":0.0012526207,"threshold_uncertainty_score":0.015856743},"labels":[],"label_agreement":null},{"id":"W3216989434","doi":"10.1186/s12859-021-04371-6","title":"Randomized quantile residuals for diagnosing zero-inflated generalized linear mixed models with applications to microbiome count data","year":2021,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University; Public Health Ontario; University of Toronto; University of Saskatchewan","funders":"","keywords":"Count data; Statistics; Overdispersion; Nominal level; Generalized linear mixed model; Quantile; Type I and type II errors; Generalized linear model; Quasi-likelihood; Computer science; Mathematics; False discovery rate; Poisson distribution; Confidence interval; Biology","score_opus":0.05691195805946668,"score_gpt":0.3233291252895891,"score_spread":0.26641716723012243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3216989434","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009508276,0.00042385297,0.98769605,0.0002016491,0.000050961156,0.000099956815,0.00018367085,0.0016161401,0.00021950995],"genre_scores_gemma":[0.18377098,0.00037296396,0.81293374,0.0003405855,0.00009962817,0.0004973144,0.0008011098,0.00069312396,0.00049047236],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98391736,0.012480411,0.0006785785,0.0014971022,0.0011164026,0.00031021817],"domain_scores_gemma":[0.91793495,0.0690435,0.0051277475,0.0039101606,0.0033911646,0.00059255556],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02844568,0.0016292802,0.0018900955,0.0023229935,0.0007469239,0.0014754266,0.0032887394,0.0019740683,0.0039426177],"category_scores_gemma":[0.10021678,0.0006514641,0.0030662185,0.0019229668,0.0022480965,0.0017107804,0.002542632,0.0035418842,0.0009812944],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007925771,0.00024269703,0.027588014,0.0012898259,0.00089525734,0.0008459003,0.0008644024,0.6241372,0.006328858,0.07931241,0.0049534724,0.25274932],"study_design_scores_gemma":[0.000077895595,0.00022395272,0.0017198453,0.00008637812,0.000077980476,0.0001226066,0.00011166194,0.96133035,0.001919877,0.031602856,0.0026630156,0.000063536834],"about_ca_topic_score_codex":0.0067724097,"about_ca_topic_score_gemma":0.0060756127,"teacher_disagreement_score":0.02844568,"about_ca_system_score_codex":0.0011852515,"about_ca_system_score_gemma":0.0026498858,"threshold_uncertainty_score":0.15043694},"labels":[],"label_agreement":null},{"id":"W37286963","doi":"10.1186/s12859-023-05340-x","title":"Una experiencia de adecuación al EEES desde el área de Educación Plástica-Visual en el C.E.S. Cardenal Spínola","year":2006,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Technology in Education and Healthcare","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Humanities; Art","score_opus":0.017456639588664145,"score_gpt":0.39521756619012327,"score_spread":0.3777609266014591,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W37286963","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6880428,0.010475232,0.027144877,0.052354936,0.0024321664,0.0001640091,0.00053058786,0.0008651649,0.21799017],"genre_scores_gemma":[0.8491287,0.006115787,0.021219673,0.0041591395,0.00034201675,0.000117290874,0.00021261329,0.00026976012,0.11843509],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975547,0.0014069015,0.000045920053,0.0003009772,0.00044519533,0.0002463449],"domain_scores_gemma":[0.9955853,0.002148211,0.0002497331,0.0004700558,0.00081229664,0.0007344367],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041124984,0.0005194779,0.00028202924,0.0008204835,0.0024362886,0.002560682,0.00081011094,0.0013729621,0.015349665],"category_scores_gemma":[0.010367912,0.00018158977,0.0004705153,0.000464165,0.00218653,0.0014423089,0.0031778158,0.0015365097,0.0021943757],"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":[0.0008587813,0.0009138414,0.04620834,0.00057614536,0.000043167838,0.0045081535,0.07885608,0.0011428646,0.011857596,0.027801806,0.054224595,0.77300864],"study_design_scores_gemma":[0.000054743134,0.0006267261,0.062026966,0.0010133032,0.00007569141,0.0035939384,0.07768076,0.0014159527,0.009561409,0.009182201,0.834633,0.00013538917],"about_ca_topic_score_codex":0.015227428,"about_ca_topic_score_gemma":0.024824515,"teacher_disagreement_score":0.015349665,"about_ca_system_score_codex":0.001709167,"about_ca_system_score_gemma":0.0020374786,"threshold_uncertainty_score":0.0513497},"labels":[],"label_agreement":null},{"id":"W4205780876","doi":"10.1186/s12859-021-04521-w","title":"Aristotle: stratified causal discovery for omics data","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Medical Research Council; Genome Canada; Alfred P. Sloan Foundation","keywords":"Omics; Causal inference; Data science; Computer science; Data mining; Bioinformatics; Computational biology; Medicine; Biology","score_opus":0.09495989527245134,"score_gpt":0.2949676792731858,"score_spread":0.20000778400073443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205780876","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021179684,0.00066198065,0.99395037,0.0006120011,0.000056063738,0.00019634116,0.0008069637,0.0012925797,0.00030566106],"genre_scores_gemma":[0.07720226,0.0006567034,0.9172873,0.0006505572,0.00014772383,0.0007873928,0.0024334472,0.00019722703,0.00063741725],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9828666,0.011986314,0.00078222924,0.0018926662,0.0022217876,0.00025045482],"domain_scores_gemma":[0.9112954,0.07909517,0.0023517793,0.00440831,0.0020625503,0.00078685617],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027965,0.001551449,0.0021815028,0.004867385,0.001918916,0.002735092,0.0027923738,0.0023651663,0.005366601],"category_scores_gemma":[0.081491664,0.0010806472,0.004133489,0.0034167254,0.002172148,0.0027923975,0.0038528827,0.003929255,0.0012257642],"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":[0.0016164684,0.00028527263,0.022836033,0.0032337154,0.0032130058,0.0016935186,0.0011245958,0.2218315,0.0032108387,0.2180936,0.033589747,0.48927173],"study_design_scores_gemma":[0.00024051551,0.000118455166,0.0014220837,0.00020937683,0.00022182846,0.00037109834,0.000069924885,0.5220498,0.0014804603,0.4618579,0.011903198,0.000055473305],"about_ca_topic_score_codex":0.0036462708,"about_ca_topic_score_gemma":0.006275133,"teacher_disagreement_score":0.027965,"about_ca_system_score_codex":0.0013588797,"about_ca_system_score_gemma":0.00575251,"threshold_uncertainty_score":0.1478948},"labels":[],"label_agreement":null},{"id":"W4206795002","doi":"10.1186/s12859-022-04559-4","title":"Topology preserving stratification of tissue neoplasticity using Deep Neural Maps and microRNA signatures","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Topological and Geometric Data Analysis","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 British Columbia; Queen's University","funders":"Southeastern Ontario Academic Medical Organization; Natural Sciences and Engineering Research Council of Canada","keywords":"microRNA; Computational biology; Artificial intelligence; Cluster analysis; Cancer; DNA microarray; Deep learning; Biology; Artificial neural network; Machine learning; Computer science; Bioinformatics; Gene expression; Gene; Genetics","score_opus":0.02635764017547924,"score_gpt":0.257129791685578,"score_spread":0.23077215151009875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206795002","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3263538,0.00036710277,0.66913265,0.00037175237,0.000031510608,0.00007393996,0.00038248498,0.0013427022,0.001944147],"genre_scores_gemma":[0.9268988,0.00012562747,0.07076993,0.00008024608,0.000019599727,0.00006083122,0.0005374022,0.00005619094,0.0014514581],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997944,0.000052518753,0.000011199176,0.000057756806,0.000045958237,0.000038075294],"domain_scores_gemma":[0.99953306,0.00017200423,0.000104928215,0.00005003547,0.0001020593,0.00003787754],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053771463,0.00066131854,0.0003968556,0.001109975,0.0002836442,0.0008512707,0.00074327143,0.0006052921,0.0006322065],"category_scores_gemma":[0.0014773913,0.00024951165,0.00068031636,0.0004932668,0.0005143436,0.000671337,0.00080667995,0.0007323009,0.00023222648],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029393798,0.00013270554,0.011371987,0.00007390297,0.000095275966,0.0001797699,0.00015813415,0.7540747,0.023489477,0.0060684644,0.0012863973,0.20277525],"study_design_scores_gemma":[0.000002042473,0.000017857095,0.00072176685,0.0000038193734,0.0000050585354,0.000020209478,0.000009225944,0.99397355,0.0027577807,0.0023560445,0.00012710481,0.0000055283153],"about_ca_topic_score_codex":0.003923215,"about_ca_topic_score_gemma":0.004659608,"teacher_disagreement_score":0.003923215,"about_ca_system_score_codex":0.0010018655,"about_ca_system_score_gemma":0.00061432936,"threshold_uncertainty_score":0.007800758},"labels":[],"label_agreement":null},{"id":"W4207000820","doi":"10.1186/s12859-022-04571-8","title":"Epigenetic landscape of drug responses revealed through large-scale ChIP-seq data analyses","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Degradation and Inhibitors","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Bioscience Database Center; Japan Science and Technology Agency; Japan Society for the Promotion of Science; Institute of Genetics; Precursory Research for Embryonic Science and Technology; Kyoto University; Japan Agency for Medical Research and Development","keywords":"Epigenetics; Drug discovery; Computational biology; Transcriptome; Biology; DNA microarray; Drug; Disease; Histone; Bioinformatics; Gene; Genetics; Gene expression; Pharmacology; Medicine","score_opus":0.05363702471057392,"score_gpt":0.3247655073235028,"score_spread":0.2711284826129289,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4207000820","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85880315,0.00089830323,0.11593513,0.0002582996,0.0000329911,0.00016628606,0.021303456,0.0012153637,0.0013870691],"genre_scores_gemma":[0.9158495,0.00048443067,0.06609031,0.00020749541,0.00002198902,0.00022567362,0.016606577,0.00011490961,0.0003991164],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99967074,0.0000478609,0.000025028017,0.00015129236,0.00007358009,0.000031619464],"domain_scores_gemma":[0.99900925,0.0005516226,0.00016154055,0.00010336169,0.00012483326,0.00004944958],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009024901,0.00038769303,0.00046310236,0.0007137304,0.00027661986,0.00058127695,0.00038448174,0.00030829135,0.0011271052],"category_scores_gemma":[0.0011300036,0.00020252065,0.00076401606,0.00073996244,0.00032464936,0.00025958457,0.00033287832,0.0004968404,0.00024666567],"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":[0.000590898,0.00021685018,0.119611666,0.001038842,0.00088204566,0.00042404985,0.00019859477,0.087213755,0.75116026,0.002148695,0.0019379512,0.03457641],"study_design_scores_gemma":[0.00006510151,0.00031254924,0.25356212,0.00004837984,0.0005861201,0.00041863014,0.00030851076,0.43625972,0.29437926,0.005939035,0.007995121,0.00012540712],"about_ca_topic_score_codex":0.001834424,"about_ca_topic_score_gemma":0.0046276245,"teacher_disagreement_score":0.001834424,"about_ca_system_score_codex":0.00052017556,"about_ca_system_score_gemma":0.0007656516,"threshold_uncertainty_score":0.0047729015},"labels":[],"label_agreement":null},{"id":"W4207037095","doi":"10.1186/s12859-022-04568-3","title":"Iam hiQ—a novel pair of accuracy indices for imputed genotypes","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; Princess Margaret Cancer Centre; Sinai Health System; Lunenfeld-Tanenbaum Research Institute; Public Health Ontario; University of Toronto","funders":"University of Texas MD Anderson Cancer Center; National Institutes of Health; Deutsches Zentrum für Lungenforschung; Clalit Health Services; Radboud Universitair Medisch Centrum; Universität Salzburg; Umeå Universitet; Markey Cancer Center, University of Kentucky; Georg-August-Universität Göttingen; Lunds Universitet; Skånes universitetssjukhus; Radboud Universiteit; Newcastle University; National Cancer Institute; Universität Heidelberg; University of Liverpool; Vanderbilt University Medical Center; Huntsman Cancer Institute; Universidad de Oviedo; BC Cancer Agency; Vanderbilt University; Moffitt Cancer Center; Dartmouth College; Washington State University; Fred Hutchinson Cancer Research Center; World Health Organization","keywords":"Imputation (statistics); Computer science; Data mining; Software; Computational biology; Machine learning; Biology; Missing data","score_opus":0.025590839880014423,"score_gpt":0.2752904179259309,"score_spread":0.24969957804591647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4207037095","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034690637,0.0017699515,0.9515046,0.0007807203,0.00024977545,0.00028240745,0.0036262507,0.0045810365,0.0025146455],"genre_scores_gemma":[0.33405766,0.00043780316,0.65405136,0.0008619508,0.0004964254,0.0010158503,0.006060794,0.0016405733,0.0013775949],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9822848,0.007440592,0.001536345,0.002739748,0.0053003677,0.00069807994],"domain_scores_gemma":[0.8973329,0.068614736,0.011569497,0.01141286,0.00973226,0.0013377476],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024618298,0.0017128763,0.0023353193,0.009583338,0.0009773802,0.0053140377,0.0040523973,0.003051491,0.0031752835],"category_scores_gemma":[0.12544046,0.0008824866,0.002454125,0.006830425,0.0016078653,0.0041790935,0.0036711153,0.004306027,0.001653107],"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":[0.0015755167,0.00041712887,0.3501575,0.0009500027,0.0027278739,0.00032923112,0.0008144804,0.06225213,0.0066960063,0.025948897,0.025002865,0.52312833],"study_design_scores_gemma":[0.00028940826,0.0010233419,0.14524242,0.0005314532,0.00081085664,0.0019372621,0.00036550456,0.74123615,0.013129428,0.070342936,0.024458854,0.00063233316],"about_ca_topic_score_codex":0.0018118713,"about_ca_topic_score_gemma":0.0015143349,"teacher_disagreement_score":0.024618298,"about_ca_system_score_codex":0.0020089727,"about_ca_system_score_gemma":0.0015467404,"threshold_uncertainty_score":0.13019556},"labels":[],"label_agreement":null},{"id":"W4220730260","doi":"10.1186/s12859-022-04631-z","title":"LANDMark: an ensemble approach to the supervised selection of biomarkers in high-throughput sequencing data","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McMaster University; University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada; Ontario Genomics; Genome Canada","keywords":"Selection (genetic algorithm); Computational biology; Throughput; Computer science; DNA microarray; Landmark; DNA sequencing; Biology; Machine learning; Artificial intelligence; Genetics; DNA; Gene","score_opus":0.039024028273366214,"score_gpt":0.25847034451258344,"score_spread":0.21944631623921723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220730260","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.050612494,0.0007921815,0.94134706,0.0003864074,0.0001078019,0.00022269413,0.0006880771,0.0051175654,0.0007257417],"genre_scores_gemma":[0.43596298,0.00043577098,0.5561117,0.0005839006,0.00032691643,0.00053390657,0.003924966,0.0004041554,0.0017157081],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99703324,0.0013291487,0.00017754892,0.00070026546,0.00052278925,0.00023686794],"domain_scores_gemma":[0.9927267,0.004227828,0.00048184136,0.00064533413,0.0015432545,0.00037496278],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006904227,0.0017646278,0.002492379,0.0028995671,0.0010207045,0.0013046284,0.0028402873,0.0019754732,0.0010776443],"category_scores_gemma":[0.010815377,0.00062384957,0.0021590784,0.0020803488,0.00064627745,0.001624049,0.001741724,0.0026863497,0.00074886106],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00066988054,0.00037902108,0.018381424,0.00027025773,0.0010585297,0.00040881083,0.0002840608,0.49044842,0.006694364,0.0028642104,0.009213336,0.46932775],"study_design_scores_gemma":[0.000017942733,0.00009966043,0.0005597424,0.000012601941,0.000052711286,0.000036685407,0.000024233748,0.9943317,0.0010302687,0.0032232031,0.0005976502,0.000013485257],"about_ca_topic_score_codex":0.0060118306,"about_ca_topic_score_gemma":0.009955106,"teacher_disagreement_score":0.006904227,"about_ca_system_score_codex":0.0009509669,"about_ca_system_score_gemma":0.0014957037,"threshold_uncertainty_score":0.036513507},"labels":[],"label_agreement":null},{"id":"W4220798428","doi":"10.1186/s12859-022-04649-3","title":"LPMX: a pure rootless composable container system","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Japan Society for the Promotion of Science; Institute of Genetics; University of Tokyo","keywords":"Container (type theory); Computer science; Composability; Host (biology); Operating system; Distributed computing; Pipeline (software); Cache; Virtualization; File system; Cloud computing; Engineering","score_opus":0.011376411945248294,"score_gpt":0.20942865192418297,"score_spread":0.19805223997893467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220798428","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016520532,0.0006099718,0.5570341,0.00042964952,0.00035334154,0.00045746772,0.0014168575,0.41358626,0.009591898],"genre_scores_gemma":[0.2237755,0.0010228646,0.63952625,0.001436953,0.00025621903,0.0011302764,0.017046735,0.08251436,0.03329088],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99777395,0.00026566148,0.00023750757,0.000601514,0.0008481586,0.0002731775],"domain_scores_gemma":[0.9968112,0.00056658953,0.00027075465,0.0014237628,0.0004344737,0.00049316575],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025027927,0.0017218867,0.000942132,0.00095038046,0.0009388537,0.0030807806,0.005275438,0.0014930705,0.014883402],"category_scores_gemma":[0.0067879,0.0014635803,0.0018782152,0.0005576172,0.0015530147,0.0066207,0.008529034,0.003023221,0.012151285],"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":[0.005155657,0.0007314658,0.012698667,0.0023212153,0.00054397905,0.0035835607,0.004296616,0.01914922,0.19214462,0.075256914,0.25488886,0.42922923],"study_design_scores_gemma":[0.00068007025,0.00092306215,0.0066169566,0.00036025877,0.0003792002,0.0019875048,0.00044146852,0.17745365,0.17721358,0.035416875,0.5978339,0.00069336797],"about_ca_topic_score_codex":0.001639909,"about_ca_topic_score_gemma":0.00092468417,"teacher_disagreement_score":0.014883402,"about_ca_system_score_codex":0.0009641236,"about_ca_system_score_gemma":0.0016270006,"threshold_uncertainty_score":0.049789906},"labels":[],"label_agreement":null},{"id":"W4221090405","doi":"10.1186/s12859-022-04636-8","title":"The Xenopus phenotype ontology: bridging model organism phenotype data to human health and development","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute of Child Health and Human Development; National Human Genome Research Institute; National Institutes of Health","keywords":"Ontology; Open Biomedical Ontologies; Computer science; Ontology-based data integration; Interoperability; Process ontology; Phenotype; Computational biology; Biology; Suggested Upper Merged Ontology; Bioinformatics; Information retrieval; World Wide Web; Semantic Web; Genetics; Gene","score_opus":0.07694043601688808,"score_gpt":0.31537138656195013,"score_spread":0.23843095054506205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221090405","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015757648,0.0009967863,0.9139767,0.004509814,0.0003991935,0.00060860306,0.021237474,0.01221425,0.030299557],"genre_scores_gemma":[0.10193569,0.0028601515,0.8472241,0.0015983763,0.0001502135,0.00090886495,0.034670852,0.0032796585,0.0073721376],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984515,0.0004227312,0.00033024565,0.00027665967,0.0004394051,0.00007936932],"domain_scores_gemma":[0.99672544,0.0012243566,0.0004565635,0.00092020055,0.00048343217,0.00018985037],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034935027,0.0006083588,0.00044044942,0.0022123768,0.000856262,0.0022249732,0.0014803882,0.000883883,0.0043044044],"category_scores_gemma":[0.004999762,0.00045144832,0.0013066852,0.0019882803,0.0014857484,0.0040825717,0.002236216,0.0014432542,0.0014974425],"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":[0.0003537546,0.00014927903,0.012665457,0.003121314,0.00020984869,0.0015365989,0.0040573045,0.009229808,0.03166692,0.60239923,0.09586968,0.23874077],"study_design_scores_gemma":[0.000048802645,0.00006999722,0.007621306,0.0011140807,0.00013050827,0.0014319457,0.0009546669,0.014323514,0.017520469,0.10675348,0.84992564,0.000105619896],"about_ca_topic_score_codex":0.009337616,"about_ca_topic_score_gemma":0.010364395,"teacher_disagreement_score":0.009337616,"about_ca_system_score_codex":0.0018122457,"about_ca_system_score_gemma":0.0038495134,"threshold_uncertainty_score":0.01856649},"labels":[],"label_agreement":null},{"id":"W4223431254","doi":"10.1186/s12859-022-04669-z","title":"Identification of multimodal brain imaging association via a parameter decomposition based sparse multi-view canonical correlation analysis method","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Aging; Key Research and Development Projects of Shaanxi Province; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; H. Lundbeck A/S; Servier; National Institutes of Health; Natural Science Foundation of Shaanxi Province; National Natural Science Foundation of China; Eisai; Genentech; IXICO; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; China Postdoctoral Science Foundation; F. Hoffmann-La Roche; University of Southern California; Eli Lilly and Company; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Bristol-Myers Squibb; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Canonical correlation; Computer science; Modality (human–computer interaction); Neuroimaging; Artificial intelligence; Identification (biology); Pattern recognition (psychology); Correlation; Feature (linguistics); Feature selection; Association (psychology); Machine learning; Data mining; Mathematics; Neuroscience","score_opus":0.03446274984406474,"score_gpt":0.32011182714199315,"score_spread":0.28564907729792843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4223431254","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010163782,0.00014850832,0.98873377,0.0000905091,0.000022956483,0.000039611452,0.00008519987,0.0002602031,0.00045539186],"genre_scores_gemma":[0.32655936,0.00062914676,0.66857564,0.0001690281,0.00013172072,0.00038956592,0.0012906952,0.00027337816,0.0019814076],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989619,0.0003509869,0.000048879316,0.00027923987,0.00026710003,0.000091964095],"domain_scores_gemma":[0.998432,0.0005596474,0.00016164147,0.00018483536,0.0005697219,0.000092095186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013503253,0.0011654883,0.0010249136,0.001699858,0.0005327866,0.0011342284,0.0008393164,0.0008478824,0.002028141],"category_scores_gemma":[0.0047390917,0.00040171956,0.0015780425,0.0017207675,0.0007484833,0.00097473356,0.0010878822,0.0013068153,0.00073906814],"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":[0.00028836733,0.00022436748,0.00906477,0.0003928923,0.00053839956,0.0005188563,0.00043429036,0.33536395,0.041072246,0.039012063,0.015407014,0.55768275],"study_design_scores_gemma":[0.0000072198404,0.00002851812,0.001095104,0.000012061314,0.000037739424,0.00011554477,0.000029086026,0.98921037,0.0023836975,0.005358946,0.0016955459,0.000026133433],"about_ca_topic_score_codex":0.0051111192,"about_ca_topic_score_gemma":0.005660217,"teacher_disagreement_score":0.0051111192,"about_ca_system_score_codex":0.00043980917,"about_ca_system_score_gemma":0.0019364505,"threshold_uncertainty_score":0.010162771},"labels":[],"label_agreement":null},{"id":"W4223988818","doi":"10.1186/s12859-022-04667-1","title":"Deep clustering of small molecules at large-scale via variational autoencoder embedding and K-means","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"CancerCare Manitoba; University of Manitoba","funders":"Canadian Institutes of Health Research","keywords":"Cluster analysis; Autoencoder; Computer science; Pattern recognition (psychology); Artificial intelligence; Feature (linguistics); Principal component analysis; Cluster (spacecraft); Embedding; Similarity (geometry); Biological system; Data mining; Deep learning; Biology","score_opus":0.011832895892648772,"score_gpt":0.2411205728047431,"score_spread":0.22928767691209434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4223988818","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019163013,0.00015469319,0.97930235,0.00014855745,0.00001872967,0.000026430253,0.000045597146,0.0004274631,0.00071301823],"genre_scores_gemma":[0.48143426,0.0002962524,0.514147,0.0001539862,0.00005033251,0.00017946071,0.00041512467,0.00026893217,0.0030545744],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99967074,0.000094429444,0.000016706012,0.00008795423,0.00009268429,0.0000375363],"domain_scores_gemma":[0.99909997,0.00040860553,0.00012240234,0.00010666748,0.00020742953,0.000054880282],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008973761,0.0009911517,0.0009836522,0.00077960565,0.0005492849,0.0008057231,0.0014900706,0.0012120088,0.0011954631],"category_scores_gemma":[0.0021093434,0.00069006917,0.0014765222,0.0006738771,0.0010942349,0.0012057027,0.00088384264,0.0016227722,0.00036106838],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016354907,0.000012090513,0.0001859692,0.000021112366,0.000024616236,0.000013636539,0.000025275473,0.9831306,0.0014134258,0.004031209,0.00029273363,0.010832979],"study_design_scores_gemma":[6.747546e-7,0.0000013299225,0.000016752825,6.2143994e-7,6.8547587e-7,9.935054e-7,0.0000011411036,0.9988362,0.00013080722,0.000969656,0.000039956125,0.0000012080973],"about_ca_topic_score_codex":0.01457088,"about_ca_topic_score_gemma":0.012009794,"teacher_disagreement_score":0.01457088,"about_ca_system_score_codex":0.0018491424,"about_ca_system_score_gemma":0.0014860725,"threshold_uncertainty_score":0.028972149},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W4225364091","doi":"10.1186/s12859-021-04536-3","title":"vCOMBAT: a novel tool to create and visualize a computational model of bacterial antibiotic target-binding","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bacterial Genetics and Biotechnology","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":"Polytechnique Montréal","funders":"Norges Forskningsråd; National Center for Advancing Translational Sciences; Universitetet i Tromsø; European Molecular Biology Organization; Bill and Melinda Gates Foundation","keywords":"Antibiotics; Dosing; Antibiotic resistance; Computer science; Rifampicin; Computational biology; Bacteria; Biochemical engineering; Biology; Microbiology; Pharmacology; Engineering","score_opus":0.01690757740222136,"score_gpt":0.24422808697473308,"score_spread":0.2273205095725117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225364091","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02060489,0.00078195205,0.79975045,0.0014031096,0.0005360186,0.00041546542,0.017602555,0.14591323,0.012992376],"genre_scores_gemma":[0.23320387,0.0018715145,0.6852,0.0016177242,0.00021254932,0.003127756,0.03527719,0.029737866,0.009751535],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99955803,0.00011709085,0.000038825594,0.00007292877,0.00015485677,0.000058147765],"domain_scores_gemma":[0.9977221,0.0016887761,0.00010946404,0.00013167819,0.00018249862,0.00016551022],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013594481,0.0020241134,0.001315567,0.0011326785,0.0010032003,0.0022003057,0.0039217486,0.0025577608,0.025111023],"category_scores_gemma":[0.0042330986,0.0010099814,0.002400696,0.00085432077,0.0008770943,0.00161772,0.0023935135,0.0024566583,0.0037590996],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010734516,0.00055181485,0.0074151987,0.0026817292,0.00074766245,0.0017214294,0.0009527006,0.6397299,0.015210248,0.056368724,0.177648,0.095899165],"study_design_scores_gemma":[0.00031251422,0.000053567568,0.00052585785,0.00010970438,0.00005491995,0.00019316305,0.00004882418,0.92497885,0.003373249,0.016416613,0.053851545,0.00008128339],"about_ca_topic_score_codex":0.009171359,"about_ca_topic_score_gemma":0.011396259,"teacher_disagreement_score":0.025111023,"about_ca_system_score_codex":0.0011106769,"about_ca_system_score_gemma":0.002252519,"threshold_uncertainty_score":0.0840047},"labels":[],"label_agreement":null},{"id":"W4225376695","doi":"10.1186/s12859-022-04673-3","title":"KnotAli: informed energy minimization through the use of evolutionary information","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pseudoknot; Multiple sequence alignment; Computer science; Structural alignment; Sequence alignment; Energy minimization; Nucleic acid structure; Sequence (biology); Nucleic acid secondary structure; Quality Score; Data mining; Computational biology; Bioinformatics; Artificial intelligence; RNA; Biology; Genetics; Physics","score_opus":0.030252200067816076,"score_gpt":0.22977132947826795,"score_spread":0.19951912941045188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225376695","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.068279654,0.00067642995,0.9149738,0.00018616466,0.00009130019,0.00015922944,0.0003976665,0.011857363,0.0033783347],"genre_scores_gemma":[0.28285897,0.00024118155,0.71052766,0.00020774589,0.000041896903,0.00042427253,0.00123519,0.0020848482,0.002378222],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994542,0.00017969441,0.000026483904,0.00012376085,0.00016340327,0.000052509648],"domain_scores_gemma":[0.99888486,0.0006613227,0.00010853695,0.00015594688,0.00012662767,0.00006280606],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012671563,0.0012452631,0.0011770854,0.001158142,0.0007962411,0.0009317114,0.0028393986,0.0014824161,0.003881028],"category_scores_gemma":[0.0040857736,0.0008188573,0.00094665703,0.0009388143,0.00068044115,0.0013296441,0.001673138,0.0016422747,0.0011435029],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005663319,0.00016381645,0.0028779763,0.00033294284,0.00026659912,0.00022392719,0.0001789592,0.78715605,0.012911504,0.011425429,0.0069314167,0.17696503],"study_design_scores_gemma":[0.000032816417,0.000037467664,0.00018981162,0.000008196605,0.000014423197,0.000034357246,0.000011483,0.9942683,0.0016647554,0.002872033,0.00085245026,0.000013910301],"about_ca_topic_score_codex":0.0037600012,"about_ca_topic_score_gemma":0.0057806685,"teacher_disagreement_score":0.003881028,"about_ca_system_score_codex":0.00073065615,"about_ca_system_score_gemma":0.0013646556,"threshold_uncertainty_score":0.012983382},"labels":[],"label_agreement":null},{"id":"W4225684933","doi":"10.1186/s12859-022-04647-5","title":"Supervised promoter recognition: a benchmark framework","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Benchmark (surveying); Benchmarking; Machine learning; Deep learning; Computer science; Artificial intelligence; Promoter; DNA microarray; Computational biology; Process (computing); Data mining; Biology; Gene; Genetics","score_opus":0.013961049832787028,"score_gpt":0.22111594216789052,"score_spread":0.20715489233510348,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225684933","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2580641,0.010090641,0.67029643,0.001968391,0.0005629401,0.00067429995,0.026164869,0.01773223,0.014446037],"genre_scores_gemma":[0.53372055,0.0021776045,0.36925596,0.0005742721,0.00019627747,0.0009704359,0.086950816,0.00076182664,0.00539226],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971288,0.0008358092,0.00018669578,0.00095952424,0.0006733844,0.00021577142],"domain_scores_gemma":[0.9953055,0.0017513548,0.00036401648,0.00092722854,0.0013957174,0.00025616324],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004612034,0.0018120861,0.0009971362,0.0017523525,0.00068851555,0.0014983118,0.0040336233,0.0023868696,0.0020020695],"category_scores_gemma":[0.009323547,0.00040184098,0.0012977041,0.0019205405,0.0011203986,0.0017756765,0.0015504379,0.0018236863,0.0012239792],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00078132737,0.0007232826,0.008226456,0.00109252,0.00027101376,0.0002863635,0.000089046465,0.7653422,0.010764532,0.011785984,0.02482179,0.17581555],"study_design_scores_gemma":[0.000058150545,0.0002959469,0.0013684818,0.00005758461,0.000033987526,0.00014854658,0.00004496136,0.96435356,0.015254033,0.01224089,0.0061123814,0.00003147502],"about_ca_topic_score_codex":0.009114623,"about_ca_topic_score_gemma":0.008162782,"teacher_disagreement_score":0.009114623,"about_ca_system_score_codex":0.0018975919,"about_ca_system_score_gemma":0.002170242,"threshold_uncertainty_score":0.024391055},"labels":[],"label_agreement":null},{"id":"W4226144949","doi":"10.1186/s12859-022-04662-6","title":"Computationally repurposing drugs for breast cancer subtypes using a network-based approach","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","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":"Windsor Clinical Research; University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada; University of Windsor","keywords":"Drug repositioning; Repurposing; Drug discovery; Computational biology; Drug; In silico; Disease; Drug development; DNA microarray; Interaction network; Bioinformatics; Computer science; Biology; Medicine; Pharmacology; Gene; Genetics","score_opus":0.04285852233238176,"score_gpt":0.30537347045572055,"score_spread":0.2625149481233388,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226144949","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22424515,0.0017189161,0.7515003,0.0029430492,0.00015205395,0.00042247365,0.0030924957,0.002831612,0.013093908],"genre_scores_gemma":[0.77191174,0.000807438,0.21615264,0.0005892882,0.00013035882,0.00053583074,0.0036714822,0.00017116364,0.006030011],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99980325,0.000058757007,0.0000133213025,0.000048336617,0.000040867577,0.000035425397],"domain_scores_gemma":[0.9988689,0.000906008,0.0000725114,0.000035635123,0.000070743845,0.000046236823],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050296314,0.00088790513,0.0009390174,0.0013675479,0.00046245588,0.0009331902,0.0009834985,0.001422628,0.0057788845],"category_scores_gemma":[0.002327479,0.0005993011,0.0014020256,0.0010581168,0.0003170614,0.0007342558,0.0006635478,0.00089592714,0.00048724897],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007472495,0.00004550123,0.0012422225,0.00006408556,0.000057286175,0.00011407284,0.000012023808,0.9804648,0.0005487659,0.0016238972,0.0008288714,0.014923762],"study_design_scores_gemma":[0.0000080745895,0.000007840886,0.00009750859,0.0000022785548,0.000012080334,0.000013689791,0.000003964101,0.99826115,0.00011719292,0.0012487941,0.0002257684,0.000001671479],"about_ca_topic_score_codex":0.017293513,"about_ca_topic_score_gemma":0.023893615,"teacher_disagreement_score":0.017293513,"about_ca_system_score_codex":0.001189796,"about_ca_system_score_gemma":0.001605161,"threshold_uncertainty_score":0.03438568},"labels":[],"label_agreement":null},{"id":"W4237234846","doi":"10.1186/1471-2105-3-15","title":"Erratum to: The Comparative RNA Web (CRW) Site: an online database of comparative sequence and structure information for ribosomal, intron, and other RNAs: Correction","year":2002,"lang":"en","type":"erratum","venue":"BMC Bioinformatics","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","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":"University of Waterloo; Dalhousie University","funders":"National Science Foundation","keywords":"Intron; Computational biology; Biology; Ribosomal RNA; Web site; Sequence (biology); RNA; Genetics; Sequence database; Database; World Wide Web; Computer science; Gene; The Internet","score_opus":0.05235440435453029,"score_gpt":0.2973078417660093,"score_spread":0.24495343741147899,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4237234846","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002980775,0.00096892955,0.0019681223,0.027184384,0.96314955,0.000040051065,0.0028346912,0.0012227676,0.0023333568],"genre_scores_gemma":[0.02152787,0.010179346,0.028329449,0.12282512,0.22303757,0.0006213472,0.025632128,0.010728967,0.55711824],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962974,0.000515857,0.0007292383,0.00043402103,0.0016831463,0.00034027154],"domain_scores_gemma":[0.97003126,0.00520953,0.0016210135,0.0021464191,0.019399928,0.0015918798],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028291498,0.0030064862,0.0027688844,0.0055121067,0.003591503,0.0040315758,0.003644127,0.0050383336,0.08555275],"category_scores_gemma":[0.04311307,0.0018603445,0.0018278691,0.004028646,0.0016186037,0.0020441446,0.0018300071,0.009442683,0.06539718],"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":[0.00006544959,0.000014868737,0.00006320066,0.0001704336,0.000014172864,0.00016670398,0.000012137384,0.000057248013,0.000105105595,0.00031301653,0.9931224,0.0058952263],"study_design_scores_gemma":[0.00009232556,0.00005600448,0.0011108363,0.00038003697,0.000089632,0.0008479549,0.00009196175,0.00060523563,0.0010834519,0.0013018477,0.9942719,0.00006886088],"about_ca_topic_score_codex":0.01563198,"about_ca_topic_score_gemma":0.018968815,"teacher_disagreement_score":0.08555275,"about_ca_system_score_codex":0.003198832,"about_ca_system_score_gemma":0.0049335826,"threshold_uncertainty_score":0.2862025},"labels":[],"label_agreement":null},{"id":"W4281817583","doi":"10.1186/s12859-022-04751-6","title":"CoQUAD: a COVID-19 question answering dataset system, facilitating research, benchmarking, and practice","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Topic Modeling","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Public Health Ontario","funders":"Institute of Health Services and Policy Research; Canadian Institutes of Health Research","keywords":"Benchmarking; Coronavirus disease 2019 (COVID-19); 2019-20 coronavirus outbreak; Data science; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Computer science; Computational biology; Information retrieval; Biology; Virology; Medicine; Business","score_opus":0.12784802972864218,"score_gpt":0.3884872227123956,"score_spread":0.26063919298375343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281817583","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035070743,0.0057313326,0.068453096,0.004244152,0.0011104889,0.0052360995,0.7471319,0.11501745,0.018004721],"genre_scores_gemma":[0.023559693,0.0004982368,0.09231154,0.0011611052,0.00016240362,0.0027087517,0.8754614,0.0011567347,0.0029802267],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99193066,0.0025323178,0.0013470384,0.0018341609,0.0019516649,0.00040413986],"domain_scores_gemma":[0.9882428,0.0042016394,0.0011158742,0.002614662,0.0028881163,0.00093686406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0086199185,0.0029120771,0.0012492738,0.008067946,0.0016976738,0.0028152259,0.0047256546,0.0037536712,0.013236554],"category_scores_gemma":[0.025953213,0.00059207814,0.0017792865,0.004995091,0.0009141659,0.0055985195,0.0060588624,0.0028141527,0.011804751],"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":[0.0012139123,0.00081483094,0.008541645,0.0042738267,0.00026426345,0.0004569204,0.0009345002,0.0036369823,0.009874526,0.006015397,0.8282717,0.13570167],"study_design_scores_gemma":[0.0012409724,0.001012741,0.024866536,0.00083878747,0.00020847496,0.00088273175,0.0015207351,0.08225365,0.02562059,0.014067866,0.8470841,0.0004028225],"about_ca_topic_score_codex":0.015389197,"about_ca_topic_score_gemma":0.022310983,"teacher_disagreement_score":0.015389197,"about_ca_system_score_codex":0.0030436693,"about_ca_system_score_gemma":0.004086695,"threshold_uncertainty_score":0.045587063},"labels":[],"label_agreement":null},{"id":"W4283267624","doi":"10.1186/s12859-022-04790-z","title":"RResolver: efficient short-read repeat resolution within ABySS","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"National Human Genome Research Institute; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; Genome British Columbia; Canada's Michael Smith Genome Sciences Centre; Genome Canada","keywords":"Computational biology; DNA microarray; Resolution (logic); Computer science; Biology; Genetics; Programming language; Gene; Gene expression","score_opus":0.01872862315502454,"score_gpt":0.23430197223895327,"score_spread":0.21557334908392872,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283267624","genre_codex":"software","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028830223,0.002424929,0.41772857,0.0004179492,0.0004372203,0.00053877576,0.0054258294,0.5385799,0.005616606],"genre_scores_gemma":[0.044913907,0.00070400897,0.9044097,0.00044086165,0.00007765435,0.0006038578,0.01266922,0.032512806,0.0036679236],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974923,0.00036262308,0.00021093439,0.0010046533,0.0006939707,0.00023546876],"domain_scores_gemma":[0.9983625,0.00071991305,0.00025328796,0.00024255033,0.00028707334,0.00013470303],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036250646,0.0037521059,0.0020662546,0.0014476597,0.0013905386,0.0035835786,0.0033112231,0.0018000493,0.01513566],"category_scores_gemma":[0.006054081,0.0019662348,0.0026838675,0.0011995484,0.0009023185,0.0026175242,0.0021877622,0.0030616233,0.016007284],"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":[0.004698494,0.0007376237,0.00952674,0.0044199256,0.0011970053,0.0013909771,0.0024511884,0.044447068,0.17878008,0.016236598,0.18110712,0.5550072],"study_design_scores_gemma":[0.0012818679,0.0009533126,0.0055806013,0.0007175491,0.00032156357,0.0013059872,0.0006449528,0.490971,0.22737497,0.021896362,0.24821398,0.00073783705],"about_ca_topic_score_codex":0.0041743037,"about_ca_topic_score_gemma":0.0049698395,"teacher_disagreement_score":0.01513566,"about_ca_system_score_codex":0.0011316442,"about_ca_system_score_gemma":0.002470386,"threshold_uncertainty_score":0.050633788},"labels":[],"label_agreement":null},{"id":"W4283365300","doi":"10.1186/s12859-022-04804-w","title":"SAPFIR: A webserver for the identification of alternative protein features","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"RNA Research and Splicing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; Université de Sherbrooke","keywords":"Alternative splicing; Biology; RNA splicing; Computational biology; Gene; Genetics; Human genome; DNA microarray; Gene isoform; Genome; Gene expression; RNA","score_opus":0.020927017190322375,"score_gpt":0.2846299926362194,"score_spread":0.26370297544589705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283365300","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015714206,0.0015690522,0.06418366,0.0004537441,0.0002677282,0.00034798417,0.2059515,0.7043029,0.007209316],"genre_scores_gemma":[0.09036427,0.0019871166,0.19377086,0.0010794599,0.00020588025,0.002160136,0.63575304,0.06635482,0.008324457],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985794,0.00021147502,0.00016641343,0.00039637825,0.00048063492,0.0001657087],"domain_scores_gemma":[0.99710685,0.0012665213,0.00036471742,0.00052889687,0.00036320233,0.0003698417],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003066332,0.0053310725,0.002420338,0.0058414643,0.001046321,0.0027741124,0.0039048567,0.0021851552,0.050162584],"category_scores_gemma":[0.0051479707,0.0014973782,0.0021602025,0.0035407988,0.0006276246,0.0042516203,0.0042818217,0.0030710716,0.0455175],"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":[0.0061756666,0.00044806785,0.008858619,0.0052957623,0.0008421664,0.002286804,0.00064990873,0.0027266932,0.0548795,0.0064310543,0.788726,0.12267983],"study_design_scores_gemma":[0.0025811656,0.0011674403,0.03241246,0.001398525,0.0006384387,0.006804121,0.0006560292,0.15361764,0.12887107,0.04053622,0.63031,0.0010069169],"about_ca_topic_score_codex":0.0010932737,"about_ca_topic_score_gemma":0.0014960726,"teacher_disagreement_score":0.050162584,"about_ca_system_score_codex":0.0008579436,"about_ca_system_score_gemma":0.0014959702,"threshold_uncertainty_score":0.16781056},"labels":[],"label_agreement":null},{"id":"W4287959313","doi":"10.1186/s12859-022-04840-6","title":"Pan-cancer integrative analysis of whole-genome De novo somatic point mutations reveals 17 cancer types","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Simon Fraser University","funders":"","keywords":"Cancer; Somatic cell; Genetics; Biology; Point mutation; DNA microarray; Genome; Computational biology; Mutation; Gene; Gene expression","score_opus":0.013698067476509522,"score_gpt":0.27714162343285337,"score_spread":0.26344355595634383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4287959313","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9734493,0.001240521,0.012764576,0.00012390195,0.000014225972,0.00008189582,0.010055003,0.00081828336,0.0014521851],"genre_scores_gemma":[0.95654273,0.00060865795,0.01941728,0.000102135215,0.000008068777,0.00007547516,0.02227811,0.0001564262,0.00081107696],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9996427,0.000028319368,0.00002276185,0.00017084237,0.00008036652,0.000054984506],"domain_scores_gemma":[0.99965,0.00010752297,0.00008515157,0.00005497788,0.000061965984,0.000040353156],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000538367,0.00051056565,0.000577682,0.0017550639,0.00045535868,0.00062615715,0.0003669983,0.00035305167,0.0013538116],"category_scores_gemma":[0.0007076484,0.00020047247,0.0009998322,0.0014650634,0.00019296608,0.00019199707,0.0005470044,0.00043638848,0.00037349536],"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":[0.0010371094,0.0001829101,0.5344209,0.00040249547,0.0011383827,0.00093124463,0.00019925834,0.006310049,0.34372216,0.0006127568,0.0024849973,0.108557716],"study_design_scores_gemma":[0.000047808728,0.00023221681,0.9093934,0.000027899137,0.0007247339,0.001867509,0.00016913994,0.030454775,0.050076198,0.00094594725,0.0060279844,0.000032288342],"about_ca_topic_score_codex":0.0033801477,"about_ca_topic_score_gemma":0.007682488,"teacher_disagreement_score":0.0033801477,"about_ca_system_score_codex":0.00042124192,"about_ca_system_score_gemma":0.0005161955,"threshold_uncertainty_score":0.00672096},"labels":[],"label_agreement":null},{"id":"W4292171780","doi":"10.1186/s12859-022-04878-6","title":"Semi-supervised COVID-19 CT image segmentation using deep generative models","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"CancerCare Manitoba; University of Manitoba","funders":"","keywords":"Artificial intelligence; Segmentation; Computer science; Deep learning; Autoencoder; Pattern recognition (psychology); Generative model; Image segmentation; Convolutional neural network; Ground truth; Scale-space segmentation; Segmentation-based object categorization; Generative grammar","score_opus":0.08687116947554052,"score_gpt":0.34736270832576854,"score_spread":0.260491538850228,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292171780","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045641575,0.00038697873,0.94919837,0.00061261293,0.00004818006,0.000100598656,0.00033076288,0.002083038,0.001597924],"genre_scores_gemma":[0.768577,0.00033854682,0.22360091,0.0005142401,0.00009047036,0.00014324013,0.0017614153,0.00046433628,0.0045100073],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994092,0.00018691068,0.000029857378,0.00018793756,0.00012210313,0.00006399445],"domain_scores_gemma":[0.9983814,0.00090534263,0.00019106326,0.00021848094,0.00020008329,0.00010372674],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015181227,0.00076567126,0.0007862816,0.0007542712,0.0003416284,0.0013767863,0.0017315568,0.0016572049,0.001703358],"category_scores_gemma":[0.0034548563,0.000741171,0.0017154186,0.0004576297,0.0009529096,0.0011014411,0.0011270484,0.0019273675,0.00061460485],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017517728,0.0000669801,0.0023386693,0.00006515124,0.00009532284,0.0001110827,0.00008539111,0.92105746,0.004092144,0.005319889,0.0017730114,0.06481983],"study_design_scores_gemma":[0.0000036878587,0.000009369985,0.00014474722,0.0000045478696,0.0000037445518,0.000028325088,0.000003055334,0.99679524,0.00075336924,0.0020647468,0.00018440885,0.0000048750812],"about_ca_topic_score_codex":0.007761065,"about_ca_topic_score_gemma":0.01088817,"teacher_disagreement_score":0.007761065,"about_ca_system_score_codex":0.0016500863,"about_ca_system_score_gemma":0.0013912573,"threshold_uncertainty_score":0.015431762},"labels":[],"label_agreement":null},{"id":"W4292729083","doi":"10.1186/s12859-022-04882-w","title":"Learning to detect boundary information for brain image segmentation","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"National Natural Science Foundation of China; National Science Foundation","keywords":"Segmentation; Computer science; Boundary (topology); Artificial intelligence; Image segmentation; Pattern recognition (psychology); Sørensen–Dice coefficient; Computer vision; Context (archaeology); Scale-space segmentation; Mathematics; Biology","score_opus":0.015227836235929859,"score_gpt":0.2715470974248548,"score_spread":0.2563192611889249,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292729083","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028113121,0.0007442149,0.9677182,0.00023203813,0.000046156565,0.00007598763,0.00007266283,0.001597718,0.0013998428],"genre_scores_gemma":[0.58480066,0.00077018404,0.40906444,0.00041401436,0.000090687776,0.00025016928,0.0005030766,0.00024499273,0.0038617768],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996673,0.000052765234,0.000016916392,0.00013705263,0.00007363102,0.000052308995],"domain_scores_gemma":[0.9994728,0.00021760253,0.00008925937,0.000052947813,0.00012544579,0.00004201006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008364198,0.0008483014,0.0008549034,0.00090622716,0.00041186597,0.0007139359,0.0015145283,0.0016809433,0.0019219375],"category_scores_gemma":[0.0022532383,0.0005047183,0.000881896,0.00056312437,0.0009413908,0.0019477116,0.0011232953,0.0012741273,0.0010293032],"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":[0.00033926417,0.0002352869,0.00332585,0.0002152923,0.00010394902,0.0002303405,0.00022498709,0.34021816,0.06025396,0.009743982,0.004430432,0.58067846],"study_design_scores_gemma":[0.000005515068,0.00005650118,0.0003897284,0.000014491494,0.000018428656,0.00006685741,0.000013834237,0.98625565,0.007828105,0.004640924,0.0007015195,0.000008378127],"about_ca_topic_score_codex":0.0038830636,"about_ca_topic_score_gemma":0.004280456,"teacher_disagreement_score":0.0038830636,"about_ca_system_score_codex":0.0010032057,"about_ca_system_score_gemma":0.000923588,"threshold_uncertainty_score":0.0077209473},"labels":[],"label_agreement":null},{"id":"W4297475198","doi":"10.1186/s12859-022-04933-2","title":"Identifying health related occupations of Twitter users through word embedding and deep neural networks","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Social Media in Health Education","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University; Lakehead University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Lakehead University","keywords":"Computer science; Word embedding; Artificial neural network; Embedding; Artificial intelligence; Word (group theory); Encoder; Recurrent neural network; Transformer; Deep learning; Recall; Social media; Construct (python library); Machine learning; Precision and recall; F1 score; Natural language processing; Information retrieval; World Wide Web","score_opus":0.1478485987947585,"score_gpt":0.41606809107234716,"score_spread":0.2682194922775887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297475198","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8480353,0.0018025774,0.13411775,0.0013442801,0.00028990133,0.00017651897,0.004850935,0.0032978947,0.00608483],"genre_scores_gemma":[0.9469604,0.00041776543,0.044161554,0.00013857837,0.00008626119,0.00008063202,0.0043926565,0.000032031814,0.003730215],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99965763,0.00009780755,0.000032970172,0.00009587737,0.00006204245,0.00005353925],"domain_scores_gemma":[0.99916553,0.00040936348,0.00014927726,0.00008259959,0.00015077008,0.000042528274],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046047286,0.0010417695,0.00036366913,0.0014848468,0.00022762643,0.0005461643,0.0004168913,0.00072467764,0.0012942369],"category_scores_gemma":[0.0018870815,0.00018923124,0.00048755846,0.0009914072,0.0002202434,0.0010537634,0.0005920296,0.0006676768,0.00086430553],"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":[0.0010962712,0.0012439861,0.07797335,0.000476303,0.00030741098,0.0004962263,0.00044196277,0.10276586,0.018778034,0.0011684145,0.011248349,0.7840039],"study_design_scores_gemma":[0.0000118518265,0.000117419506,0.01143113,0.000028608523,0.000034216122,0.00008416455,0.00014717413,0.9797707,0.005917305,0.0015956828,0.00084427395,0.000017437545],"about_ca_topic_score_codex":0.0074347495,"about_ca_topic_score_gemma":0.012681047,"teacher_disagreement_score":0.0074347495,"about_ca_system_score_codex":0.0005196765,"about_ca_system_score_gemma":0.00029828618,"threshold_uncertainty_score":0.014782965},"labels":[],"label_agreement":null},{"id":"W4297997542","doi":"10.1186/s12859-022-04946-x","title":"Deep multiview learning to identify imaging-driven subtypes in mild cognitive impairment","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Aging; National Institutes of Health; Genentech; U.S. National Library of Medicine; IXICO; Directorate for Computer and Information Science and Engineering; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; University of Southern California; Novartis Pharmaceuticals Corporation; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; Foundation for the National Institutes of Health; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Alzheimer's Association; Canadian Institutes of Health Research; National Science Foundation","keywords":"Artificial intelligence; Neuroimaging; Discriminative model; Cluster analysis; Computer science; Canonical correlation; Feature learning; Imaging genetics; Pattern recognition (psychology); Modality (human–computer interaction); Unsupervised learning; Dimensionality reduction; Deep learning; Machine learning; Psychology; Neuroscience","score_opus":0.02594478998113494,"score_gpt":0.34339418836680774,"score_spread":0.3174493983856728,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297997542","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.50241387,0.0014188845,0.4922414,0.0005727418,0.0000934187,0.00011196044,0.0009543617,0.00096022146,0.001233117],"genre_scores_gemma":[0.9609657,0.00018939313,0.036010407,0.0001585241,0.000047428144,0.00006461937,0.0014294605,0.00006379203,0.0010706],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995491,0.0001373215,0.000022096237,0.00014958257,0.00005314846,0.00008873383],"domain_scores_gemma":[0.9991509,0.0003402418,0.00013264826,0.00010206738,0.00018029139,0.00009383592],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013631457,0.00092864543,0.00081755687,0.0008734504,0.00025183544,0.00059440936,0.0008579322,0.00063891825,0.0010043504],"category_scores_gemma":[0.0029483458,0.00028967686,0.0013313796,0.00055186264,0.00048409222,0.0006626229,0.0010140452,0.0012809865,0.00027606366],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015669377,0.00062488695,0.075989656,0.0002465621,0.0006935885,0.000374541,0.00066267943,0.4672671,0.01663137,0.006461116,0.009187712,0.4202939],"study_design_scores_gemma":[0.000013186595,0.00007511042,0.0048335106,0.000014350134,0.000032529064,0.00004542796,0.00004696701,0.9893713,0.0012317674,0.004036953,0.00028473878,0.000014150606],"about_ca_topic_score_codex":0.0074189003,"about_ca_topic_score_gemma":0.0070112613,"teacher_disagreement_score":0.0074189003,"about_ca_system_score_codex":0.0008191488,"about_ca_system_score_gemma":0.00074912264,"threshold_uncertainty_score":0.014751434},"labels":[],"label_agreement":null},{"id":"W4303423564","doi":"10.1186/s12859-022-04972-9","title":"Comparative transcriptomics analysis pipeline for the meta-analysis of phylogenetically divergent datasets (CoRMAP)","year":2022,"lang":"en","type":"review","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Compute Canada; Morris Animal Foundation","keywords":"Computational biology; Biology; RNA-Seq; Pipeline (software); De novo transcriptome assembly; DNA microarray; Metadata; Transcriptome; Gene; Gene expression; Computer science; Genetics; World Wide Web","score_opus":0.23312561210069377,"score_gpt":0.3716177139744434,"score_spread":0.1384921018737496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4303423564","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008149323,0.0017768015,0.62448454,0.0006890183,0.00041361444,0.0011775646,0.16087924,0.19925034,0.0031795672],"genre_scores_gemma":[0.029632434,0.00087237905,0.7428586,0.00073379895,0.00011181562,0.006058739,0.19736215,0.0213546,0.0010154808],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99531156,0.00120796,0.0004955666,0.0017576821,0.0008817432,0.00034549623],"domain_scores_gemma":[0.9949226,0.002319311,0.0006841345,0.0009962929,0.0007335052,0.0003442333],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014597469,0.004503473,0.0030391382,0.006665707,0.0021283035,0.003942389,0.004536833,0.00187176,0.013510581],"category_scores_gemma":[0.015187708,0.0022015707,0.0060299113,0.0060786917,0.001031886,0.0027203306,0.0051548453,0.0053469418,0.0079245325],"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":[0.0067984257,0.0007616341,0.022418534,0.029165585,0.012170171,0.0030365048,0.0055297744,0.030160785,0.23637271,0.041095946,0.34712702,0.2653628],"study_design_scores_gemma":[0.0018718465,0.0011245795,0.04594859,0.002642345,0.0041613216,0.0025795011,0.0012091262,0.15148582,0.10603917,0.104328595,0.5774694,0.0011398476],"about_ca_topic_score_codex":0.0026802528,"about_ca_topic_score_gemma":0.0035714912,"teacher_disagreement_score":0.014597469,"about_ca_system_score_codex":0.0014800077,"about_ca_system_score_gemma":0.005767283,"threshold_uncertainty_score":0.07719976},"labels":[],"label_agreement":null},{"id":"W4308436127","doi":"10.1186/s12859-022-04812-w","title":"A novel method for drug-target interaction prediction based on graph transformers model","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Children's Hospital","funders":"","keywords":"Drug target; Drug; Computer science; Graph; Transformer; Interaction network; Artificial intelligence; Theoretical computer science; Pharmacology; Engineering; Medicine; Biology; Voltage","score_opus":0.04043657864088868,"score_gpt":0.3149732236917865,"score_spread":0.2745366450508978,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308436127","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0064494363,0.0001645392,0.98855674,0.00014246472,0.000037948677,0.00009002146,0.00036158017,0.0024443325,0.0017529036],"genre_scores_gemma":[0.39520475,0.00084517244,0.5906885,0.00025190125,0.00009824721,0.00038353162,0.0034453976,0.00070190954,0.008380609],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995018,0.00008017798,0.000030503725,0.00015919967,0.00018340115,0.000044948287],"domain_scores_gemma":[0.9993573,0.00026392908,0.000056474066,0.00008368819,0.00019556425,0.000043064854],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045327254,0.0011585905,0.00087529083,0.0025857782,0.0005290121,0.00085680356,0.0014841371,0.00083951553,0.0051264325],"category_scores_gemma":[0.0020968835,0.00046499536,0.0015075943,0.0016674211,0.00039084395,0.0023086085,0.0009220717,0.00094476267,0.0013477106],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002698224,0.00016997095,0.0053822543,0.0003015735,0.00015104878,0.00042375445,0.0001165148,0.52266526,0.010346237,0.025239091,0.013891002,0.42104346],"study_design_scores_gemma":[0.00001078566,0.000016722452,0.00017416589,0.000004962064,0.000019252986,0.00006015741,0.000009496768,0.9922019,0.0011742242,0.0050999187,0.0012212371,0.00000717331],"about_ca_topic_score_codex":0.013326051,"about_ca_topic_score_gemma":0.0126279155,"teacher_disagreement_score":0.013326051,"about_ca_system_score_codex":0.0010296293,"about_ca_system_score_gemma":0.0017619309,"threshold_uncertainty_score":0.026496947},"labels":[],"label_agreement":null},{"id":"W4311134061","doi":"10.1186/s12859-022-04582-5","title":"Boosting tissue-specific prediction of active cis-regulatory regions through deep learning and Bayesian optimization techniques","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Charité – Universitätsmedizin Berlin; Berlin Institute of Health; Università degli Studi di Milano","keywords":"Artificial intelligence; Machine learning; Bayesian optimization; Deep learning; Computer science; Enhancer; Computational biology; Convolutional neural network; Epigenomics; Artificial neural network; Biology; DNA methylation; Transcription factor; Genetics","score_opus":0.009196831369433146,"score_gpt":0.2200819021844075,"score_spread":0.21088507081497437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311134061","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07182902,0.0007465105,0.92396295,0.00049560436,0.000050607163,0.000049311297,0.00024441877,0.0015966297,0.0010249797],"genre_scores_gemma":[0.7329732,0.00041074655,0.26023528,0.0006904112,0.00010712246,0.0002471853,0.0015326722,0.00036940002,0.0034339312],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993807,0.00023668255,0.000029408113,0.00016972625,0.00010241676,0.00008102219],"domain_scores_gemma":[0.997308,0.0019957412,0.00017608875,0.00010906731,0.00031720623,0.00009389932],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021527524,0.0014252531,0.0011987146,0.00082437095,0.00026204763,0.0007065079,0.0014281818,0.0014375452,0.0014797498],"category_scores_gemma":[0.00467061,0.00070912344,0.0010308969,0.00046261132,0.0006903615,0.00072992616,0.0010220088,0.0023521427,0.0005946182],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018616898,0.00010832816,0.001497457,0.000057513065,0.00007228016,0.000045538207,0.000028937207,0.94357294,0.0044742045,0.001446773,0.0010287804,0.047481027],"study_design_scores_gemma":[0.0000040462,0.000008420012,0.00007617398,0.0000029033972,0.0000040047016,0.000003973533,0.0000010599335,0.99854195,0.0005494788,0.0007505909,0.000055145396,0.000002259439],"about_ca_topic_score_codex":0.008016945,"about_ca_topic_score_gemma":0.0085907355,"teacher_disagreement_score":0.008016945,"about_ca_system_score_codex":0.0011213201,"about_ca_system_score_gemma":0.001280243,"threshold_uncertainty_score":0.015940547},"labels":[],"label_agreement":null},{"id":"W4311481079","doi":"10.1186/s12859-022-05059-1","title":"Development of an image classification pipeline for atherosclerotic plaques assessment using supervised machine learning","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Spectroscopy Techniques in Biomedical and Chemical Research","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":"Carleton University","funders":"National Research Council Canada; Natural Sciences and Engineering Research Council of Canada; Carleton University","keywords":"Artificial intelligence; Thresholding; Segmentation; Computer science; Pattern recognition (psychology); Feature selection; Pipeline (software); Support vector machine; Image segmentation; Preprocessor; Image processing; Classifier (UML); Image (mathematics)","score_opus":0.05393710765054982,"score_gpt":0.3645234978491708,"score_spread":0.310586390198621,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311481079","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0135818925,0.0000898342,0.97081435,0.000099542514,0.000029528666,0.00036563692,0.00032984157,0.014007082,0.00068230793],"genre_scores_gemma":[0.09604725,0.00007591238,0.90009034,0.00007365375,0.000026524984,0.0006371338,0.001224422,0.00028739832,0.0015374003],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99870074,0.00019731434,0.00011536728,0.0004428925,0.00041032778,0.00013327968],"domain_scores_gemma":[0.99772865,0.0005319457,0.00020568477,0.00021922088,0.0012255703,0.00008907421],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019917209,0.0016167131,0.0011644579,0.0023765813,0.000679623,0.0012666133,0.0019714537,0.001304347,0.0037520686],"category_scores_gemma":[0.0032728193,0.00056747574,0.0013851264,0.0009996655,0.0004502454,0.0011409845,0.00080919976,0.0014296644,0.003701176],"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":[0.0002592299,0.0005090859,0.003972867,0.00024947332,0.0001290884,0.00016798722,0.00016484587,0.045696817,0.049364388,0.0019364026,0.006605693,0.8909441],"study_design_scores_gemma":[0.000018348657,0.00013234615,0.0017344152,0.000024394645,0.00003061648,0.00007376141,0.000034471588,0.9481258,0.04405557,0.0023794698,0.003360309,0.000030525574],"about_ca_topic_score_codex":0.0037803503,"about_ca_topic_score_gemma":0.0030696136,"teacher_disagreement_score":0.0037803503,"about_ca_system_score_codex":0.00094845047,"about_ca_system_score_gemma":0.0018014191,"threshold_uncertainty_score":0.012551963},"labels":[],"label_agreement":null},{"id":"W4319748040","doi":"10.1186/s12859-023-05141-2","title":"Model performance and interpretability of semi-supervised generative adversarial networks to predict oncogenic variants with unlabeled data","year":2023,"lang":"en","type":"review","venue":"BMC Bioinformatics","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"National Institute of General Medical Sciences; Intellectual and Developmental Disabilities Research Center; National Institutes of Health; Eunice Kennedy Shriver National Institute of Child Health and Human Development; University of Pennsylvania","keywords":"Interpretability; Leverage (statistics); Computer science; Machine learning; Artificial intelligence; Annotation; Labeled data; Data mining","score_opus":0.06189355387424046,"score_gpt":0.30034539051275455,"score_spread":0.2384518366385141,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319748040","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4141837,0.0016758124,0.5718705,0.002589468,0.0002642976,0.0002522253,0.00093358266,0.001810618,0.0064198747],"genre_scores_gemma":[0.9646501,0.0002017831,0.03104602,0.00040492963,0.00006300474,0.00012392164,0.0010766205,0.00007331408,0.0023602922],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987262,0.0006798915,0.000056363,0.0002768892,0.00015513718,0.000105619365],"domain_scores_gemma":[0.9883128,0.009687765,0.000498568,0.00046526775,0.0007980547,0.0002375057],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005759823,0.0017720197,0.000918054,0.0008306867,0.00054405304,0.0009224144,0.0014830685,0.0013051248,0.0015935942],"category_scores_gemma":[0.012159168,0.00042245374,0.0009464343,0.00032203374,0.0014505003,0.0012137844,0.0012768547,0.002263567,0.00037682822],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001016911,0.00004053295,0.0019773664,0.000025415113,0.000032573644,0.000033337707,0.000029026327,0.9857755,0.00031231667,0.00165043,0.00059190445,0.009429965],"study_design_scores_gemma":[0.0000021341714,0.000008741928,0.000087501154,0.000003462411,0.0000025613206,0.000004028682,0.0000019575816,0.9988488,0.0001255764,0.0008881826,0.000024897001,0.0000022520155],"about_ca_topic_score_codex":0.009646139,"about_ca_topic_score_gemma":0.008145578,"teacher_disagreement_score":0.009646139,"about_ca_system_score_codex":0.0016716699,"about_ca_system_score_gemma":0.0011851861,"threshold_uncertainty_score":0.030461192},"labels":[],"label_agreement":null},{"id":"W4321002108","doi":"10.1186/s12859-023-05168-5","title":"petiteFinder: an automated computer vision tool to compute Petite colony frequencies in baker’s yeast","year":2023,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto; Simons Foundation","keywords":"Biology; Yeast; Computer science; Artificial intelligence; Object detection; Object (grammar); Computational biology; Pattern recognition (psychology); Genetics","score_opus":0.012276469586557724,"score_gpt":0.2896800436631122,"score_spread":0.27740357407655447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321002108","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12525402,0.0007667864,0.72341627,0.0004001579,0.0001374423,0.00020277043,0.0059164097,0.14053205,0.0033740618],"genre_scores_gemma":[0.36657867,0.00027963868,0.61407804,0.00036866925,0.000035461522,0.0003585475,0.011481221,0.0029884675,0.0038312639],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9996306,0.00003393943,0.000024665971,0.00013089614,0.00013761404,0.000042216994],"domain_scores_gemma":[0.99934477,0.00027816813,0.000093102964,0.00007252139,0.00015897363,0.000052491378],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051796343,0.0013545178,0.00054437434,0.0014456229,0.0002803363,0.001005266,0.0022737246,0.0011219206,0.005371116],"category_scores_gemma":[0.002427368,0.0005193316,0.00076908554,0.0006343141,0.00030053983,0.0010488789,0.0009868668,0.001135629,0.0019030973],"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":[0.0013273746,0.00054409954,0.012327286,0.0007845063,0.00030116912,0.0006621823,0.00023670642,0.19921112,0.09139631,0.004898855,0.074622765,0.61368763],"study_design_scores_gemma":[0.000046069832,0.000085859334,0.0019365806,0.000020365393,0.000014756265,0.00014534412,0.00003770887,0.9565049,0.03241963,0.0030590757,0.005695342,0.00003440151],"about_ca_topic_score_codex":0.0067942617,"about_ca_topic_score_gemma":0.008579363,"teacher_disagreement_score":0.0067942617,"about_ca_system_score_codex":0.0010498086,"about_ca_system_score_gemma":0.0006935361,"threshold_uncertainty_score":0.017968178},"labels":[],"label_agreement":null},{"id":"W4353020774","doi":"10.1186/s12859-023-05227-x","title":"PWN: enhanced random walk on a warped network for disease target prioritization","year":2023,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Stantec (Canada)","funders":"","keywords":"Prioritization; Computer science; Random walk; Computational biology; Biology; Mathematics; Statistics; Engineering; Process management","score_opus":0.012019183507147879,"score_gpt":0.24452672842898954,"score_spread":0.23250754492184167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353020774","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034738023,0.00025610556,0.9616755,0.00025786326,0.00008908907,0.00014091805,0.00020461556,0.0016945562,0.0009432912],"genre_scores_gemma":[0.40372524,0.00026542335,0.5913663,0.0002614038,0.00008905796,0.00036538148,0.00092166604,0.0003001433,0.0027054225],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994991,0.00017022264,0.000024569481,0.00014521612,0.00011679264,0.00004409834],"domain_scores_gemma":[0.99837565,0.0009953418,0.00015738994,0.00016008587,0.00021151357,0.000100048],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011200384,0.0011127277,0.0008254396,0.0014261493,0.00049463083,0.0006079496,0.0012483698,0.001094202,0.0024287687],"category_scores_gemma":[0.0047318735,0.00044272127,0.00066994014,0.0009100383,0.00051900424,0.0013996823,0.001101642,0.0010660386,0.0005555842],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022302868,0.00010475918,0.001771219,0.00014572861,0.00010359795,0.00015451293,0.00008391618,0.85634977,0.008403548,0.0074356543,0.0028846164,0.122339696],"study_design_scores_gemma":[0.000008068895,0.000017808128,0.0000947735,0.0000023926973,0.000004150838,0.000017100383,0.0000034738289,0.99674404,0.0007044715,0.0021346656,0.0002653273,0.0000036248546],"about_ca_topic_score_codex":0.004150037,"about_ca_topic_score_gemma":0.0057072006,"teacher_disagreement_score":0.004150037,"about_ca_system_score_codex":0.0006978139,"about_ca_system_score_gemma":0.00085740915,"threshold_uncertainty_score":0.008251727},"labels":[],"label_agreement":null},{"id":"W4360826396","doi":"10.1186/s12859-023-05226-y","title":"Complete sequence verification of plasmid DNA using the Oxford Nanopore Technologies’ MinION device","year":2023,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Nanopore and Nanochannel Transport Studies","field":"Engineering","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of British Columbia; Canada's Michael Smith Genome Sciences Centre","funders":"","keywords":"Minion; Plasmid; Nanopore sequencing; Sanger sequencing; Biology; DNA sequencing; Computational biology; Consensus sequence; Genetics; Sequence (biology); Computer science; DNA; Base sequence","score_opus":0.08525135470605225,"score_gpt":0.2667828808131616,"score_spread":0.18153152610710935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4360826396","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13581173,0.0018800914,0.8396779,0.00043311412,0.0002476074,0.00095036306,0.005092886,0.009297444,0.006608933],"genre_scores_gemma":[0.18679886,0.0018478938,0.7843681,0.00044056054,0.00006011664,0.0014455422,0.015135603,0.0013895128,0.008513845],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99669147,0.000621494,0.000330714,0.0007129182,0.0014420645,0.00020137825],"domain_scores_gemma":[0.9965842,0.0011581918,0.0004829234,0.0006700598,0.00089718826,0.00020744978],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002292751,0.0009760239,0.000810053,0.0010997453,0.0005841049,0.0007004794,0.0010365271,0.0010177483,0.005198339],"category_scores_gemma":[0.004321568,0.0006848622,0.00066335994,0.00047194975,0.0006375086,0.000959852,0.0010054959,0.0010932466,0.005140099],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016244297,0.000043822958,0.0010152216,0.00037624387,0.000028316012,0.00012907705,0.00015854536,0.0003712197,0.96495384,0.0012021263,0.0018931698,0.029665986],"study_design_scores_gemma":[0.000015845715,0.00017603765,0.0019382174,0.000051529852,0.000024735968,0.00063523976,0.00002779848,0.0039360384,0.9730592,0.00031376028,0.019786416,0.00003518531],"about_ca_topic_score_codex":0.00072618295,"about_ca_topic_score_gemma":0.001512772,"teacher_disagreement_score":0.005198339,"about_ca_system_score_codex":0.0005575356,"about_ca_system_score_gemma":0.0012253813,"threshold_uncertainty_score":0.017390132},"labels":[],"label_agreement":null},{"id":"W4366742336","doi":"10.1186/s12859-023-05264-6","title":"In-vitro validated methods for encoding digital data in deoxyribonucleic acid (DNA)","year":2023,"lang":"en","type":"review","venue":"BMC Bioinformatics","topic":"DNA and Biological Computing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia, Okanagan Campus; Kelowna General Hospital; University of British Columbia","funders":"Division of Electrical, Communications and Cyber Systems; Semiconductor Research Corporation; National Science Foundation","keywords":"DNA microarray; DNA; Computational biology; In vitro; Encoding (memory); Computer science; Digital polymerase chain reaction; Biology; Genetics; Gene; Polymerase chain reaction; Gene expression; Artificial intelligence","score_opus":0.2006860204091278,"score_gpt":0.43959385722058486,"score_spread":0.23890783681145705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366742336","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00040312487,0.9940388,0.0028662255,0.00017122409,0.0002824613,0.000026684163,0.000088295514,0.00003353318,0.0020897007],"genre_scores_gemma":[0.0016047403,0.99293375,0.003477586,0.00021419647,0.000118082346,0.0000487653,0.00020488574,0.0000127377,0.0013853555],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994311,0.000105041254,0.000068511865,0.00012834341,0.00022870502,0.000038220154],"domain_scores_gemma":[0.9987924,0.0007337284,0.0001118591,0.0000696703,0.0002513359,0.000040991523],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015497605,0.001146651,0.0014679381,0.002587647,0.00029438318,0.0011324806,0.0013127102,0.0011345525,0.0031331524],"category_scores_gemma":[0.0021703772,0.00048534243,0.00072919996,0.0021704433,0.00072985375,0.0015420957,0.0007560505,0.0017002474,0.0037736814],"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":[0.00008153712,0.00010983429,0.00021339543,0.034817696,0.00009629628,0.00014813333,0.000084145526,0.00060608436,0.020119725,0.009122302,0.01371575,0.92088515],"study_design_scores_gemma":[0.000012902397,0.00018533166,0.00048036457,0.0032329892,0.00016990211,0.0010192378,0.000060335067,0.00024214374,0.020143548,0.0018096726,0.9725937,0.000049920272],"about_ca_topic_score_codex":0.0007967342,"about_ca_topic_score_gemma":0.0008519848,"teacher_disagreement_score":0.0031331524,"about_ca_system_score_codex":0.00063924777,"about_ca_system_score_gemma":0.0011583886,"threshold_uncertainty_score":0.010481417},"labels":[],"label_agreement":null},{"id":"W4376872947","doi":"10.1186/s12859-023-05327-8","title":"CysPresso: a classification model utilizing deep learning protein representations to predict recombinant expression of cysteine-dense peptides","year":2023,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biochemical and Structural Characterization","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Critical Systems Labs; Sunnybrook Health Science Centre","funders":"H2020 Marie Skłodowska-Curie Actions; Medical Research Council; Alliance de recherche numérique du Canada; Natural Sciences and Engineering Research Council of Canada; University of Cambridge; UK Research and Innovation","keywords":"Artificial intelligence; Deep learning; Computer science; Computational biology; Machine learning; Concatenation (mathematics); Convolutional neural network; Chemical space; Support vector machine; Drug discovery; Chemistry; Biology; Biochemistry; Mathematics","score_opus":0.030178129362653336,"score_gpt":0.2728277365811366,"score_spread":0.24264960721848328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376872947","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6105384,0.0017463347,0.37655085,0.0010207334,0.00017553421,0.00017371234,0.002216783,0.0052353702,0.0023422558],"genre_scores_gemma":[0.9436466,0.0003755566,0.049481217,0.00025049932,0.000049133138,0.00017560033,0.003052229,0.00009009199,0.0028789802],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998542,0.000025249958,0.000009163296,0.000052554213,0.000024955643,0.000033888344],"domain_scores_gemma":[0.9996314,0.00017455521,0.000057173977,0.000023864864,0.000079452504,0.000033448025],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000688259,0.0011189134,0.0006527748,0.0007700862,0.00022133238,0.00069523946,0.00073343056,0.0010378783,0.0009983307],"category_scores_gemma":[0.00091995636,0.00026900787,0.0007337211,0.00032724347,0.00027027217,0.000641727,0.00044464652,0.0010960705,0.00035080078],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00061132625,0.00043472275,0.013192218,0.00009334178,0.00017705625,0.00017440901,0.000037539525,0.8380473,0.011989782,0.0013767992,0.0045294375,0.12933601],"study_design_scores_gemma":[0.0000035915286,0.000026621301,0.0002256432,0.000002329118,0.000004492422,0.0000072917114,0.0000018297259,0.9984976,0.0008650563,0.000267869,0.000095175936,0.0000025560605],"about_ca_topic_score_codex":0.0068022856,"about_ca_topic_score_gemma":0.005215005,"teacher_disagreement_score":0.0068022856,"about_ca_system_score_codex":0.0011001587,"about_ca_system_score_gemma":0.0008935367,"threshold_uncertainty_score":0.013525367},"labels":[],"label_agreement":null},{"id":"W4378903236","doi":"10.1186/s12859-023-05357-2","title":"Correction: Model performance and interpretability of semi-supervised generative adversarial networks to predict oncogenic variants with unlabeled data","year":2023,"lang":"en","type":"erratum","venue":"BMC Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","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":"Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"","keywords":"Interpretability; Generative grammar; Computer science; Artificial intelligence; Machine learning; DNA microarray; Generative adversarial network; Computational biology; Adversarial system; Data mining; Deep learning; Biology; Genetics; Gene","score_opus":0.0189577919662543,"score_gpt":0.2449546566504362,"score_spread":0.2259968646841819,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378903236","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04708895,0.002876209,0.85194945,0.015631016,0.037453145,0.00021576024,0.010932269,0.018884035,0.014969104],"genre_scores_gemma":[0.48428452,0.0010683974,0.4020712,0.0040271706,0.00324737,0.00025728432,0.019499762,0.007304444,0.07823979],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99650574,0.0012009843,0.0001954788,0.0009781176,0.0009784469,0.00014113929],"domain_scores_gemma":[0.9766847,0.015658004,0.00038735897,0.0035317857,0.0034521802,0.00028600602],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005800365,0.001683954,0.0010895125,0.0008460318,0.0010695715,0.002482332,0.0029756818,0.0028476706,0.021487648],"category_scores_gemma":[0.05970171,0.00051217317,0.000947936,0.0007090238,0.0014283173,0.0021741115,0.0022353246,0.0047974866,0.0065888073],"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":[0.0013090003,0.00013026796,0.005197752,0.0004898818,0.0003008017,0.0007584168,0.00022826485,0.20323259,0.005977566,0.019622857,0.4238768,0.33887583],"study_design_scores_gemma":[0.0001553362,0.00008111383,0.0013987512,0.00015626692,0.000071694805,0.0005840343,0.00006747119,0.9313949,0.015026811,0.026000977,0.024981195,0.000081581],"about_ca_topic_score_codex":0.008060745,"about_ca_topic_score_gemma":0.014508528,"teacher_disagreement_score":0.021487648,"about_ca_system_score_codex":0.0011887335,"about_ca_system_score_gemma":0.0017692804,"threshold_uncertainty_score":0.07188338},"labels":[],"label_agreement":null},{"id":"W4379197269","doi":"10.1186/s12859-023-05350-9","title":"An analysis of entity normalization evaluation biases in specialized domains","year":2023,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Topic Modeling","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":"Université de Montréal","funders":"","keywords":"Normalization (sociology); Computer science; Data science; Task (project management); Natural language processing; Field (mathematics); Information retrieval; Artificial intelligence; Mathematics","score_opus":0.08364742459170624,"score_gpt":0.3394736568482408,"score_spread":0.25582623225653456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379197269","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76299286,0.030737909,0.16640346,0.005215631,0.0011100721,0.0009924578,0.009217371,0.006625447,0.016704803],"genre_scores_gemma":[0.9261284,0.0014586364,0.052194897,0.0010351487,0.0002990049,0.0007129041,0.015124448,0.0013785661,0.0016680096],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9198045,0.051007845,0.007143087,0.009075655,0.011574699,0.0013941573],"domain_scores_gemma":[0.6308101,0.31106392,0.010063841,0.02025882,0.02647473,0.0013285861],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08764417,0.0016230714,0.0015005034,0.004514329,0.0017818096,0.0037995619,0.001868487,0.0018755766,0.0019607113],"category_scores_gemma":[0.24367984,0.00050048495,0.0010913346,0.005996631,0.0018642118,0.0048815426,0.0033800208,0.0019306632,0.001039725],"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":[0.0049888557,0.00087753835,0.23804381,0.0071172044,0.0032761986,0.0009899318,0.005114113,0.035360042,0.025200296,0.014644761,0.080027275,0.5843599],"study_design_scores_gemma":[0.0007856508,0.002082117,0.3624359,0.0036209363,0.0036076661,0.0051154657,0.004959687,0.3185002,0.13819997,0.05870578,0.10140431,0.00058231247],"about_ca_topic_score_codex":0.0027142896,"about_ca_topic_score_gemma":0.0032236117,"teacher_disagreement_score":0.08764417,"about_ca_system_score_codex":0.0021810543,"about_ca_system_score_gemma":0.0015958461,"threshold_uncertainty_score":0.46351218},"labels":[],"label_agreement":null},{"id":"W4379768536","doi":"10.1186/s12859-023-05340-x","title":"Rescuing biologically relevant consensus regions across replicated samples","year":2023,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada; Université Laval","keywords":"Computer science; Bioconductor; Computational biology; Scripting language; R package; Data mining; Biology; Genetics; Gene","score_opus":0.037743523144960406,"score_gpt":0.28342205504383733,"score_spread":0.24567853189887692,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379768536","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1819653,0.0022211925,0.748873,0.0004788348,0.0011853604,0.0007658533,0.028623197,0.03182168,0.004065578],"genre_scores_gemma":[0.25261325,0.00039683894,0.69958663,0.00077281316,0.00013603302,0.0023093557,0.03151827,0.010017349,0.002649523],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9915741,0.0014270707,0.00069631904,0.004388977,0.0014901998,0.000423238],"domain_scores_gemma":[0.98383397,0.0068592927,0.001155061,0.005126945,0.0026178334,0.00040687548],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010315586,0.002163099,0.0020714053,0.0022132695,0.0022473265,0.0018121843,0.0023800363,0.0020962937,0.00921159],"category_scores_gemma":[0.03017516,0.0012708094,0.0026882438,0.0021324046,0.0017957636,0.00070692383,0.002347228,0.0024904928,0.006378606],"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":[0.0024402947,0.00035443675,0.041077632,0.0060052145,0.0019296515,0.0014112941,0.002103823,0.014044145,0.79289824,0.005842916,0.018718354,0.11317399],"study_design_scores_gemma":[0.00041220334,0.0005885294,0.08303157,0.00042551363,0.0014929478,0.002077864,0.0007310358,0.10781341,0.7193094,0.015671235,0.0680999,0.00034636995],"about_ca_topic_score_codex":0.0037567483,"about_ca_topic_score_gemma":0.0073618097,"teacher_disagreement_score":0.010315586,"about_ca_system_score_codex":0.00095245434,"about_ca_system_score_gemma":0.0026181804,"threshold_uncertainty_score":0.05455464},"labels":[],"label_agreement":null},{"id":"W4381094396","doi":"10.1186/s12859-023-05377-y","title":"Covariance regression with random forests","year":2023,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; HEC Montréal; Fondation HEC","keywords":"Random forest; Covariance; Regression; Statistics; Regression analysis; Analysis of covariance; Computer science; Computational biology; Biology; Mathematics; Artificial intelligence","score_opus":0.10617106040966945,"score_gpt":0.3688357029765211,"score_spread":0.2626646425668516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381094396","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011214118,0.00031853263,0.99719244,0.00011065969,0.00006405011,0.00004465039,0.00020680716,0.00067677273,0.00026473854],"genre_scores_gemma":[0.06949038,0.000669823,0.9243352,0.0003674728,0.00032285205,0.0006599165,0.001645803,0.0006632934,0.0018453004],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9922989,0.0053758468,0.0002694134,0.0009917434,0.0008168497,0.00024721888],"domain_scores_gemma":[0.98800766,0.00890152,0.00080602145,0.0011457433,0.0009683199,0.0001708342],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012119941,0.0018345366,0.002291532,0.002144854,0.0007804601,0.0013708377,0.002716202,0.0019059505,0.00376972],"category_scores_gemma":[0.035713725,0.0011168678,0.0032380158,0.0023062867,0.0010064868,0.001827949,0.0020526913,0.00303243,0.0020247109],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027465323,0.00012424661,0.0063047684,0.0005799952,0.00097347086,0.0002636064,0.00014660423,0.5883134,0.002116022,0.07967507,0.016850332,0.30437788],"study_design_scores_gemma":[0.00005721991,0.00004216694,0.0006706837,0.000056607885,0.000066560395,0.00008832161,0.000013641718,0.9058589,0.0006844983,0.0857827,0.0066429325,0.000035818437],"about_ca_topic_score_codex":0.005991281,"about_ca_topic_score_gemma":0.007117212,"teacher_disagreement_score":0.012119941,"about_ca_system_score_codex":0.00068914477,"about_ca_system_score_gemma":0.0022674752,"threshold_uncertainty_score":0.06409711},"labels":[],"label_agreement":null},{"id":"W4382316216","doi":"10.1186/1471-2105-16-s19-s6","title":"Evolution of genes neighborhood within reconciled phylogenies: an ensemble approach","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Pacific Institute for the Mathematical Sciences; Simon Fraser University","funders":"Simon Fraser University; Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Evolutionary biology; Computer science; Gene; Computational biology; Biology; Genetics","score_opus":0.0365057201472548,"score_gpt":0.2460932431510488,"score_spread":0.20958752300379402,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382316216","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24555704,0.00064372626,0.75016785,0.00041671714,0.000035048874,0.000053096726,0.0004222775,0.00087230245,0.001831978],"genre_scores_gemma":[0.7829677,0.00033171306,0.21336389,0.00019219868,0.00007014901,0.0001491163,0.0016140832,0.00033031302,0.0009807716],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991586,0.00038705792,0.00003586034,0.00020989639,0.0001352163,0.000073349715],"domain_scores_gemma":[0.99549353,0.0029785458,0.00023945731,0.0007097555,0.00039817663,0.00018055494],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002710352,0.00052817096,0.0013781072,0.001953298,0.00087908504,0.0014529257,0.0024034556,0.0014210173,0.0021915087],"category_scores_gemma":[0.010253856,0.0006260611,0.0012415627,0.0012933483,0.000810947,0.0021427588,0.0018131955,0.0014873714,0.00039015544],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012773926,0.000056485474,0.008281053,0.000055044864,0.00020273651,0.000105545274,0.00017938999,0.91496503,0.001824144,0.015990451,0.0007769295,0.057435498],"study_design_scores_gemma":[0.0000069028943,0.000012500433,0.00047403484,0.000006115077,0.000014945672,0.000023154647,0.000019133224,0.9874113,0.00024494543,0.011478359,0.00030264698,0.000006035609],"about_ca_topic_score_codex":0.0026661314,"about_ca_topic_score_gemma":0.0048554493,"teacher_disagreement_score":0.002710352,"about_ca_system_score_codex":0.0008357606,"about_ca_system_score_gemma":0.0007381366,"threshold_uncertainty_score":0.014333904},"labels":[],"label_agreement":null},{"id":"W4382777287","doi":"10.1186/s12859-023-05394-x","title":"Neuroimaging feature extraction using a neural network classifier for imaging genetics","year":2023,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria; Simon Fraser University","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; Natural Sciences and Engineering Research Council of Canada; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; University of Southern California; Eli Lilly and Company; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Alzheimer Society; Bristol-Myers Squibb; National Institute on Aging; Alzheimer Society Research Program; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Neuroimaging; Artificial intelligence; Computer science; Imaging genetics; Machine learning; Artificial neural network; Classifier (UML); Feature selection; Pattern recognition (psychology); Bayesian probability; Pipeline (software); Biology; Neuroscience","score_opus":0.043862887520467526,"score_gpt":0.3193616961983528,"score_spread":0.2754988086778853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382777287","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026129706,0.00029874448,0.97031075,0.0005181397,0.000063394655,0.0001168103,0.00038970646,0.0012744794,0.0008983055],"genre_scores_gemma":[0.37535715,0.0002852679,0.61827165,0.00040052022,0.00019013652,0.00044072897,0.0015442439,0.00011993693,0.0033903762],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99933857,0.00013747731,0.000056562483,0.00021409088,0.00017678399,0.00007642241],"domain_scores_gemma":[0.99844354,0.0008473614,0.00015088299,0.0001202975,0.00039226605,0.000045614343],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014969477,0.0010073469,0.0009862464,0.0017890654,0.00047644778,0.0008932571,0.0012686985,0.0015754484,0.002332245],"category_scores_gemma":[0.004608076,0.00029887856,0.0013718741,0.001106984,0.00038171033,0.0008106453,0.0007371377,0.0016604958,0.0010689038],"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":[0.0003196522,0.00041994234,0.013286239,0.00014151903,0.00022393838,0.00046319934,0.000085000334,0.17282335,0.029094126,0.005438274,0.006849806,0.77085507],"study_design_scores_gemma":[0.000011508038,0.000035936,0.0019046773,0.00001298654,0.000031292086,0.00011333972,0.000009174141,0.9873524,0.0053323987,0.004311504,0.000870227,0.0000145905115],"about_ca_topic_score_codex":0.0055677383,"about_ca_topic_score_gemma":0.005145703,"teacher_disagreement_score":0.0055677383,"about_ca_system_score_codex":0.00096325,"about_ca_system_score_gemma":0.0011569081,"threshold_uncertainty_score":0.011070669},"labels":[],"label_agreement":null},{"id":"W4384663316","doi":"10.1186/s12859-023-05390-1","title":"IS-Seq: a bioinformatics pipeline for integration sites analysis with comprehensive abundance quantification methods","year":2023,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Virus-based gene therapy research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Infection and Immunity","funders":"University of Pennsylvania","keywords":"Pipeline (software); Computer science; Workflow; Data mining; Computational biology; Fragment (logic); Identifier; Process (computing); Pipeline transport; Biology; Database; Engineering; Algorithm","score_opus":0.08634068336102907,"score_gpt":0.39989763439967674,"score_spread":0.31355695103864767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384663316","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010749028,0.0010059931,0.8072339,0.0007514411,0.0003379106,0.00081839866,0.020286221,0.15592055,0.0028964614],"genre_scores_gemma":[0.052246563,0.0009406755,0.8795041,0.0012390703,0.00015898836,0.002740488,0.043437816,0.016820611,0.0029116864],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99707377,0.0005599408,0.0003239938,0.00088275695,0.0009284211,0.00023105094],"domain_scores_gemma":[0.99709976,0.0011919109,0.00040358258,0.00031653026,0.0007135984,0.00027464377],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005487062,0.0029933327,0.0020093685,0.002264905,0.0016052687,0.00329241,0.0028008178,0.0014059225,0.012434724],"category_scores_gemma":[0.007896507,0.0016602206,0.002616027,0.0016974936,0.0010462885,0.0017645982,0.002575603,0.0041880845,0.011020772],"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":[0.0039302763,0.00080924854,0.024753282,0.006536936,0.00183596,0.0014624859,0.0020282068,0.06825324,0.26050946,0.01903475,0.29132718,0.31951904],"study_design_scores_gemma":[0.0007731475,0.00065088033,0.012511887,0.00052361586,0.00040147523,0.0008199699,0.00040149473,0.57619435,0.19367579,0.03700278,0.17630503,0.00073960295],"about_ca_topic_score_codex":0.003205692,"about_ca_topic_score_gemma":0.004331858,"teacher_disagreement_score":0.012434724,"about_ca_system_score_codex":0.0013928077,"about_ca_system_score_gemma":0.003873098,"threshold_uncertainty_score":0.04159826},"labels":[],"label_agreement":null},{"id":"W4386031784","doi":"10.1186/s12859-023-05436-4","title":"BioLegato: a programmable, object-oriented graphic user interface","year":2023,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Genome Prairie; Genome Canada","keywords":"Computer science; Copying; Graphical user interface; Programming language; Software; Pipeline (software); Process (computing); User interface; Set (abstract data type); Simple (philosophy); Interface (matter); Usability; Software engineering; Field (mathematics); Source code; Debugger; Java; Human–computer interaction; Debugging; Operating system","score_opus":0.020662865741215973,"score_gpt":0.29314173950236094,"score_spread":0.272478873761145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386031784","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005321621,0.00047068959,0.65899557,0.0008034473,0.00035213036,0.0005626026,0.0043482073,0.31118688,0.017958885],"genre_scores_gemma":[0.065422356,0.0009306044,0.7936586,0.004304736,0.00032271066,0.0022919136,0.018090175,0.08617448,0.028804442],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989728,0.00015236378,0.000082712206,0.00023761656,0.00043500165,0.00011942393],"domain_scores_gemma":[0.9977034,0.00087258016,0.00019415698,0.00038111772,0.00049739727,0.0003514022],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022293897,0.0013305936,0.0006611736,0.0012022691,0.00044368897,0.0021200024,0.0035921754,0.0013897186,0.039172318],"category_scores_gemma":[0.006333362,0.0010183573,0.0010805252,0.00060213974,0.00090206665,0.0022401433,0.0028466769,0.0022486548,0.021512],"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":[0.0028595177,0.0004407858,0.005502516,0.0018064058,0.00019130882,0.001029499,0.0011765133,0.0032939394,0.09285279,0.030309353,0.49310932,0.36742797],"study_design_scores_gemma":[0.00063509995,0.0003378629,0.005304635,0.0003924859,0.00012998017,0.0011480007,0.00006905421,0.02785263,0.04218543,0.013216419,0.9084609,0.00026750466],"about_ca_topic_score_codex":0.0008531331,"about_ca_topic_score_gemma":0.0007972935,"teacher_disagreement_score":0.039172318,"about_ca_system_score_codex":0.00050663255,"about_ca_system_score_gemma":0.0009206044,"threshold_uncertainty_score":0.13104445},"labels":[],"label_agreement":null},{"id":"W4386890558","doi":"10.1186/s12859-023-05484-w","title":"Correspondence on NanoVar’s performance outlined by Jiang T. et al. in “Long-read sequencing settings for efficient structural variation detection based on comprehensive evaluation”","year":2023,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"Canada Research Chairs; National Research Foundation Singapore; Alliance de recherche numérique du Canada; National Research Foundation","keywords":"Benchmarking; Concordance; Recall; Variation (astronomy); Computer science; Structural variation; Computational biology; Statistics; Artificial intelligence; Bioinformatics; Biology; Psychology; Genetics; Mathematics; Cognitive psychology; Genome; Gene","score_opus":0.027046479786477628,"score_gpt":0.28870790108067085,"score_spread":0.26166142129419323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386890558","genre_codex":"methods","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.066115566,0.033388387,0.65094286,0.12633969,0.02710255,0.001010008,0.016251337,0.028118407,0.050731156],"genre_scores_gemma":[0.30646878,0.009181168,0.5178483,0.099631906,0.0047947466,0.003105912,0.020076586,0.010873562,0.028019024],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.96968776,0.013686582,0.002665215,0.0042845607,0.009012703,0.00066320045],"domain_scores_gemma":[0.9099733,0.054867182,0.0027456689,0.00834622,0.022916988,0.0011505854],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027860144,0.0015718746,0.00086975936,0.002285148,0.0017882404,0.0035670775,0.0029317706,0.004928636,0.006835975],"category_scores_gemma":[0.12137752,0.0010191381,0.0011644663,0.0018956023,0.0019181326,0.0027646022,0.0032438182,0.004638188,0.005553669],"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":[0.0012721863,0.00028511576,0.020678312,0.0026131861,0.00030591767,0.0005550411,0.002361771,0.012409711,0.03655492,0.03962982,0.5028549,0.3804791],"study_design_scores_gemma":[0.00024473478,0.001060466,0.021012554,0.001678947,0.00024397697,0.0017520933,0.0008269139,0.059047792,0.098635636,0.055846233,0.7588042,0.00084640423],"about_ca_topic_score_codex":0.006606966,"about_ca_topic_score_gemma":0.007536491,"teacher_disagreement_score":0.027860144,"about_ca_system_score_codex":0.0018919837,"about_ca_system_score_gemma":0.0039075767,"threshold_uncertainty_score":0.1473403},"labels":[],"label_agreement":null},{"id":"W4387495851","doi":"10.1186/s12859-023-05507-6","title":"Network-based prediction approach for cancer-specific driver missense mutations using a graph neural network","year":2023,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Genetics; Ministry of Education, Culture, Sports, Science and Technology","keywords":"Missense mutation; Artificial neural network; Computer science; Graph; Computational biology; DNA microarray; Artificial intelligence; Mutation; Biology; Gene; Machine learning; Genetics; Theoretical computer science","score_opus":0.03745443612303352,"score_gpt":0.2630600823418652,"score_spread":0.22560564621883167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387495851","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10766427,0.00086403475,0.88293,0.00071879616,0.00009517086,0.00014156892,0.0013376111,0.0032300374,0.0030186782],"genre_scores_gemma":[0.8133492,0.0005167462,0.17853236,0.00027148193,0.0000903775,0.00019224641,0.0026911492,0.00015929856,0.0041971123],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997495,0.000049763217,0.000013976479,0.000099889534,0.00005087195,0.000035973608],"domain_scores_gemma":[0.9993161,0.0003840018,0.00007857616,0.00003406538,0.0001500035,0.000037248057],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043704582,0.0010134841,0.0006608964,0.0021023604,0.000392365,0.00052170345,0.00096745597,0.0009243006,0.0030454176],"category_scores_gemma":[0.0015853196,0.00039303044,0.00092924334,0.00081583153,0.00026452699,0.00085851277,0.00045277204,0.00073698076,0.0005025654],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016202647,0.00010456227,0.007693218,0.000088861445,0.0001285943,0.00026017992,0.000028160808,0.8885367,0.0026318587,0.0026239066,0.0033652452,0.09437665],"study_design_scores_gemma":[0.0000033308538,0.0000072366556,0.0002666842,0.0000020409452,0.000010057022,0.000015327936,0.000002013082,0.99823254,0.00022988472,0.0011070558,0.00012161092,0.0000022097572],"about_ca_topic_score_codex":0.012644508,"about_ca_topic_score_gemma":0.014539507,"teacher_disagreement_score":0.012644508,"about_ca_system_score_codex":0.0009701586,"about_ca_system_score_gemma":0.00076873496,"threshold_uncertainty_score":0.025141776},"labels":[],"label_agreement":null},{"id":"W4387733089","doi":"10.1186/s12859-023-05502-x","title":"Artificial Intelligence based wrapper for high dimensional feature selection","year":2023,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto; Princess Margaret Cancer Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Prostate Cancer Canada","keywords":"Feature selection; Computer science; Feature (linguistics); Categorical variable; Data mining; Artificial intelligence; Set (abstract data type); Selection (genetic algorithm); Machine learning; Data set; Pattern recognition (psychology)","score_opus":0.03285917897682682,"score_gpt":0.28588844081041753,"score_spread":0.2530292618335907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387733089","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011600306,0.00018412062,0.98602897,0.00008925886,0.000033550852,0.000063270956,0.000081389786,0.0014316346,0.00048746768],"genre_scores_gemma":[0.2963873,0.00023233748,0.7002894,0.000260671,0.00009332397,0.00040926452,0.0008183351,0.00024969666,0.0012596429],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99796873,0.0006280902,0.00021173306,0.0004538631,0.0006201822,0.00011739984],"domain_scores_gemma":[0.9945695,0.0030801124,0.00047395602,0.0007770073,0.0009952452,0.00010409863],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032765719,0.0012999976,0.0015186714,0.0023278997,0.0006957929,0.0011529333,0.0014512173,0.0011428017,0.0017514685],"category_scores_gemma":[0.008522134,0.00049950316,0.0016468979,0.002323156,0.0007016098,0.0012248007,0.0012284261,0.0011762091,0.00096023345],"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":[0.00032480367,0.00024845914,0.005298266,0.00023635874,0.0004489041,0.00039450006,0.00012757932,0.47346547,0.0069090687,0.00948231,0.005466292,0.49759796],"study_design_scores_gemma":[0.000016796317,0.000070477334,0.00052571646,0.000012795498,0.000038329305,0.00009267305,0.000010162901,0.9873355,0.0033254663,0.00745342,0.0011076613,0.000010970811],"about_ca_topic_score_codex":0.0013328672,"about_ca_topic_score_gemma":0.000734026,"teacher_disagreement_score":0.0032765719,"about_ca_system_score_codex":0.0007230665,"about_ca_system_score_gemma":0.0008971475,"threshold_uncertainty_score":0.017328382},"labels":[],"label_agreement":null},{"id":"W4388501528","doi":"10.1186/s12859-023-05556-x","title":"A model-based clustering via mixture of hierarchical models with covariate adjustment for detecting differentially expressed genes from paired design","year":2023,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada; Sanofi","keywords":"Covariate; Cluster analysis; Confounding; False positive paradox; Hierarchical clustering; Computational biology; DNA microarray; Biology; Computer science; Gene; Data mining; Genetics; Machine learning; Gene expression; Statistics; Mathematics","score_opus":0.0628024944333424,"score_gpt":0.26320892573570503,"score_spread":0.20040643130236263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388501528","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0052743135,0.00008387643,0.99394614,0.000059415106,0.000019257866,0.00007246077,0.00010833661,0.00035747298,0.00007875517],"genre_scores_gemma":[0.12689708,0.00013891532,0.8694178,0.0001801635,0.000068806374,0.0007824203,0.0011753913,0.00022391089,0.0011155306],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9896116,0.0065844646,0.00033116978,0.00197749,0.0010845639,0.0004108459],"domain_scores_gemma":[0.9913634,0.0054541626,0.00062811695,0.0013130105,0.00096853817,0.00027275117],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011273337,0.0015330841,0.0022043525,0.0016594448,0.0012936181,0.0012453835,0.0032233698,0.0018807872,0.0018522163],"category_scores_gemma":[0.021287322,0.0010744025,0.0043985196,0.0023057614,0.0012764928,0.0013948984,0.0023623516,0.0026998753,0.0008289997],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018971949,0.00049784686,0.018556243,0.0005815881,0.0016733219,0.00040285467,0.0007476183,0.509875,0.026524456,0.053244684,0.005395413,0.38060382],"study_design_scores_gemma":[0.000078829704,0.00019003604,0.0021876497,0.00001238757,0.000119765435,0.000083876104,0.00002317777,0.97431153,0.0021669026,0.01913752,0.0016341412,0.00005421877],"about_ca_topic_score_codex":0.004761749,"about_ca_topic_score_gemma":0.0063614394,"teacher_disagreement_score":0.011273337,"about_ca_system_score_codex":0.0012549177,"about_ca_system_score_gemma":0.002339389,"threshold_uncertainty_score":0.059619844},"labels":[],"label_agreement":null},{"id":"W4388866605","doi":"10.1186/s12859-023-05570-z","title":"Image-centric compression of protein structures improves space savings","year":2023,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"DNA microarray; Computer science; Compression (physics); Image compression; Computational biology; Artificial intelligence; Computer graphics (images); Image (mathematics); Computer vision; Image processing; Biology; Genetics; Gene; Materials science; Gene expression; Composite material","score_opus":0.015107522464248383,"score_gpt":0.24591595228719174,"score_spread":0.23080842982294336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388866605","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43760732,0.0059567178,0.49517715,0.001912664,0.00038641057,0.00024337234,0.0037480837,0.036435593,0.018532729],"genre_scores_gemma":[0.6756203,0.002730502,0.30742458,0.00060174684,0.00018754113,0.00018273818,0.005901539,0.0017589345,0.0055920472],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99959785,0.000027857219,0.000024924368,0.000064510445,0.00023541308,0.000049443384],"domain_scores_gemma":[0.99907684,0.00028260655,0.00009234311,0.00022473674,0.00028685143,0.000036616693],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033420403,0.00091362506,0.00046935419,0.0011012204,0.00027693782,0.0008991213,0.0013727746,0.0007082104,0.004931974],"category_scores_gemma":[0.0019833304,0.00019026342,0.00033974185,0.001931051,0.00045928164,0.0014407735,0.0008533124,0.0006757714,0.0017301819],"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":[0.001120956,0.00030946368,0.00358696,0.00092657696,0.00009308179,0.00063928287,0.00037581,0.047559354,0.30744204,0.008873757,0.03376553,0.5953073],"study_design_scores_gemma":[0.000118051736,0.00033331334,0.003530037,0.00008653686,0.00007044736,0.0010779803,0.00012810546,0.3061678,0.65992564,0.0044055074,0.024094133,0.0000623345],"about_ca_topic_score_codex":0.001574176,"about_ca_topic_score_gemma":0.0011477655,"teacher_disagreement_score":0.004931974,"about_ca_system_score_codex":0.00058922457,"about_ca_system_score_gemma":0.0004683256,"threshold_uncertainty_score":0.016499162},"labels":[],"label_agreement":null},{"id":"W4389734944","doi":"10.1186/s12859-023-05596-3","title":"Performance analysis of conventional and AI-based variant callers using short and long reads","year":2023,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Government of Canada; Université Laval; Grain Farmers of Ontario; Génome Québec; Canadian Field Crop Research Alliance; Genome Canada","keywords":"DNA microarray; Computational biology; Computer science; Genetics; Biology; Bioinformatics; Gene; Gene expression","score_opus":0.021544958236113118,"score_gpt":0.2658458750186123,"score_spread":0.24430091678249916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389734944","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76680505,0.0039643818,0.20764345,0.00032191322,0.00030824033,0.0002352865,0.0033538544,0.014037519,0.0033302389],"genre_scores_gemma":[0.73025113,0.00047381833,0.2591899,0.00016805282,0.00006575604,0.0002315458,0.0077277357,0.00066824007,0.0012238987],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9911328,0.002118749,0.0010265817,0.0021381706,0.0031672295,0.00041641894],"domain_scores_gemma":[0.9695561,0.021948166,0.0015304647,0.0015648004,0.004798531,0.0006018666],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01016614,0.0012046886,0.00084074115,0.0027400206,0.000780925,0.0019300415,0.0023358492,0.0013740564,0.0013176504],"category_scores_gemma":[0.026436374,0.00032993278,0.0012087869,0.0025031797,0.00060736295,0.0017394098,0.0010605489,0.0011398265,0.00097641686],"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":[0.007938329,0.000711726,0.19011174,0.0021129264,0.0028541188,0.0006650086,0.0012544891,0.22073658,0.09980123,0.0044972305,0.0076571233,0.4616595],"study_design_scores_gemma":[0.00013230994,0.0008138652,0.035106428,0.0000775639,0.0003044869,0.00058757694,0.00029201905,0.8820757,0.075656466,0.0016685548,0.003055319,0.00022969172],"about_ca_topic_score_codex":0.007697828,"about_ca_topic_score_gemma":0.005787337,"teacher_disagreement_score":0.01016614,"about_ca_system_score_codex":0.001145564,"about_ca_system_score_gemma":0.0013292157,"threshold_uncertainty_score":0.053764343},"labels":[],"label_agreement":null},{"id":"W4391228942","doi":"10.1186/s12859-024-05659-z","title":"Anchor Clustering for million-scale immune repertoire sequencing data","year":2024,"lang":"en","type":"review","venue":"BMC Bioinformatics","topic":"Artificial Immune Systems Applications","field":"Engineering","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 Guelph","funders":"","keywords":"Repertoire; Cluster analysis; Computational biology; DNA microarray; Biology; Scale (ratio); Immune system; Data science; Computer science; Genetics; Bioinformatics; Gene; Geography; Artificial intelligence; Cartography; Gene expression","score_opus":0.14455506523277642,"score_gpt":0.3438470522205079,"score_spread":0.19929198698773146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391228942","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019000385,0.26174158,0.7034566,0.001671493,0.0009518083,0.00036449573,0.0035532168,0.002517187,0.006743187],"genre_scores_gemma":[0.113980755,0.16098526,0.70840687,0.0007145653,0.0007724327,0.00094016123,0.010601358,0.0008088982,0.002789633],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99821883,0.00039763917,0.000120266755,0.0004141607,0.0007834066,0.0000657299],"domain_scores_gemma":[0.9957644,0.0019877942,0.00043783887,0.0003939672,0.0012992471,0.00011684285],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030519902,0.00085573713,0.0015113682,0.0053653643,0.00046279255,0.0012981886,0.0022975535,0.0009860876,0.0018485792],"category_scores_gemma":[0.005808989,0.00046803127,0.0014940902,0.0073139486,0.00063134724,0.0011884397,0.0009507237,0.001436449,0.0018852458],"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":[0.00015965843,0.000074967604,0.004534538,0.0070298463,0.00079528376,0.00018747631,0.00023407736,0.032318484,0.009525524,0.012079606,0.018587388,0.9144731],"study_design_scores_gemma":[0.00009569192,0.00037703154,0.03390161,0.0032979446,0.00085203355,0.0026032126,0.00060060376,0.2633577,0.037493587,0.11978537,0.5372369,0.00039828313],"about_ca_topic_score_codex":0.0021110636,"about_ca_topic_score_gemma":0.0020183118,"teacher_disagreement_score":0.0053653643,"about_ca_system_score_codex":0.0009899018,"about_ca_system_score_gemma":0.0010382081,"threshold_uncertainty_score":0.0161407},"labels":[],"label_agreement":null},{"id":"W4391361452","doi":"10.1186/s12859-024-05643-7","title":"Learning self-supervised molecular representations for drug–drug interaction prediction","year":2024,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre hospitalier de l'Université Laval; Université Laval","funders":"Alliance de recherche numérique du Canada; Canadian Institute for Advanced Research; Nvidia","keywords":"Computer science; Machine learning; Artificial intelligence; Feature (linguistics); Chemical space; Feature vector; Feature learning; Labeled data; Process (computing); Drug discovery; Bioinformatics; Biology","score_opus":0.022251661039304493,"score_gpt":0.31483372901423423,"score_spread":0.29258206797492975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391361452","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0799835,0.0008865517,0.9154214,0.00036096218,0.00004487753,0.00008548433,0.0005140347,0.0015359565,0.0011672422],"genre_scores_gemma":[0.7948745,0.00051665015,0.20022461,0.00040445387,0.00009755941,0.00024375891,0.0019741193,0.00013508328,0.0015291548],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994924,0.00019043735,0.000024498888,0.00013665778,0.000113180206,0.00004275503],"domain_scores_gemma":[0.9986444,0.0007004345,0.00024586605,0.00020636617,0.00014605474,0.000056878733],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00096098904,0.00088673545,0.0010850597,0.0007263909,0.00019019122,0.0006282069,0.0013099636,0.0010345692,0.0010523284],"category_scores_gemma":[0.0028220357,0.00039268815,0.00093047123,0.00063655176,0.00070443616,0.0011685966,0.0008717435,0.0018465583,0.00041542386],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017647163,0.00020125728,0.0015069859,0.00014364567,0.00009054099,0.000059632126,0.00003031928,0.87360895,0.007302725,0.005980945,0.0019848535,0.10891367],"study_design_scores_gemma":[0.0000044894527,0.000026745478,0.000059536338,0.0000025125948,0.0000042115944,0.000006674704,0.0000016877308,0.9966878,0.0010100759,0.0020473164,0.00014632374,0.0000026922064],"about_ca_topic_score_codex":0.0011483413,"about_ca_topic_score_gemma":0.0020054441,"teacher_disagreement_score":0.0013099636,"about_ca_system_score_codex":0.000732145,"about_ca_system_score_gemma":0.00075613335,"threshold_uncertainty_score":0.005312085},"labels":[],"label_agreement":null},{"id":"W4391385457","doi":"10.1186/s12859-024-05660-6","title":"Multivariate pattern analysis: a method and software to reveal, quantify, and visualize predictive association patterns in multicollinear data","year":2024,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Institutes of Health; Universitetet i Bergen; National Center for Complementary and Integrative Health; Høgskulen på Vestlandet","keywords":"Covariate; Multivariate statistics; Statistics; Computer science; Regression analysis; Linear model; Partial least squares regression; Data mining; Multivariate analysis; Resampling; Linear regression; Variance (accounting); Contrast (vision); Ranking (information retrieval); Mathematics; Artificial intelligence","score_opus":0.031290639131473334,"score_gpt":0.34613156979160575,"score_spread":0.3148409306601324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391385457","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00209825,0.00030971394,0.960797,0.00039745498,0.00012050104,0.00017041375,0.004532484,0.030694623,0.00087959983],"genre_scores_gemma":[0.017938523,0.00053439854,0.96527314,0.00024505242,0.00011010104,0.0010532832,0.00511493,0.008787637,0.0009428773],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9954021,0.00199118,0.0004704841,0.0008881012,0.0010859157,0.00016219229],"domain_scores_gemma":[0.9809238,0.0123311905,0.0023090476,0.002300021,0.0017525912,0.0003833681],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008993155,0.0026172728,0.0017505409,0.0050982437,0.0010831165,0.0028586413,0.0031897542,0.0014720212,0.019484596],"category_scores_gemma":[0.038115446,0.0016859272,0.0034008229,0.0045592594,0.0013081415,0.0031057408,0.004329804,0.004074737,0.00711216],"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":[0.0008969987,0.00031358606,0.021622835,0.004858257,0.002272882,0.0008914546,0.001674576,0.030697167,0.030124087,0.06904245,0.24120939,0.59639627],"study_design_scores_gemma":[0.00042212434,0.00034320657,0.023450345,0.0012004005,0.0007291269,0.0023459618,0.0004250389,0.4455634,0.03520481,0.18089911,0.30874756,0.0006689135],"about_ca_topic_score_codex":0.0023032967,"about_ca_topic_score_gemma":0.0032560085,"teacher_disagreement_score":0.019484596,"about_ca_system_score_codex":0.00067457266,"about_ca_system_score_gemma":0.0033144746,"threshold_uncertainty_score":0.06518251},"labels":[],"label_agreement":null},{"id":"W4392190584","doi":"10.1186/s12859-024-05693-x","title":"GPAD: a natural language processing-based application to extract the gene-disease association discovery information from OMIM","year":2024,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Children's Hospital; University of Calgary","funders":"National Human Genome Research Institute; Canadian Institutes of Health Research; Genome British Columbia; Compute Canada; Genome Canada","keywords":"Computational biology; Disease; DNA microarray; Association (psychology); Gene; Natural (archaeology); Computer science; Biology; Data science; Bioinformatics; Genetics; Medicine; Gene expression; Psychology; Pathology","score_opus":0.006096063725336593,"score_gpt":0.25596481010590466,"score_spread":0.24986874638056808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392190584","genre_codex":"software","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008501188,0.00080701034,0.33503368,0.0017597618,0.00031012893,0.0012332342,0.18660247,0.4606575,0.005095144],"genre_scores_gemma":[0.052930053,0.0011182443,0.7093519,0.00215583,0.00025988615,0.0026542179,0.21210304,0.015509825,0.003917134],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977245,0.000496647,0.00050671474,0.00065258023,0.00053772266,0.00008190698],"domain_scores_gemma":[0.9919659,0.0058250264,0.00073016644,0.0006449177,0.0006055308,0.00022841584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030232985,0.0031149432,0.0009029394,0.0055722627,0.00079701014,0.0027862473,0.0020116398,0.0014429745,0.021368464],"category_scores_gemma":[0.013975318,0.0011358038,0.0028107397,0.0028502906,0.00088989135,0.002998192,0.004250119,0.0023492645,0.013663343],"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":[0.001708929,0.00047622717,0.013173853,0.0116891395,0.0011089728,0.0066949846,0.004165384,0.011830695,0.050425306,0.020551013,0.4619996,0.4161759],"study_design_scores_gemma":[0.0010276454,0.0005609373,0.015057307,0.0011204937,0.00046736666,0.005874367,0.0013205678,0.19557664,0.055036128,0.074202046,0.6491471,0.0006094698],"about_ca_topic_score_codex":0.0031216238,"about_ca_topic_score_gemma":0.0036623527,"teacher_disagreement_score":0.021368464,"about_ca_system_score_codex":0.0010564367,"about_ca_system_score_gemma":0.0022603816,"threshold_uncertainty_score":0.071484685},"labels":[],"label_agreement":null},{"id":"W4392517673","doi":"10.1186/s12859-024-05709-6","title":"DVA: predicting the functional impact of single nucleotide missense variants","year":2024,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Key Technologies Research and Development Program; National Key Research and Development Program of China; Key Research and Development Program of Heilongjiang","keywords":"Missense mutation; Computational biology; Single-nucleotide polymorphism; Robustness (evolution); DNA microarray; Biology; Genetics; Computer science; Mutation; Gene; Genotype","score_opus":0.017016408345376297,"score_gpt":0.2458707352147775,"score_spread":0.22885432686940121,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392517673","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5658536,0.010103653,0.3802603,0.0011890098,0.00038315816,0.0003527964,0.027514778,0.010775153,0.0035675545],"genre_scores_gemma":[0.86862427,0.0011090515,0.11400303,0.00023425311,0.00016936299,0.00016095238,0.014455534,0.00018184764,0.0010616917],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988921,0.00030226962,0.000104320214,0.00035927581,0.00027150675,0.000070521855],"domain_scores_gemma":[0.99534637,0.0033955385,0.000534847,0.0002489057,0.00030865497,0.00016564353],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017929494,0.0010139202,0.0009964718,0.003933017,0.0003899814,0.0008465415,0.000920044,0.0010845864,0.001410799],"category_scores_gemma":[0.0063810577,0.00027555405,0.0011770446,0.001548357,0.00034033784,0.00044920985,0.0006835913,0.0008685125,0.0005318616],"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":[0.0012028508,0.00042349863,0.37661812,0.0009878523,0.0016447357,0.001267518,0.00013440089,0.1819216,0.025935093,0.0033920351,0.021224672,0.38524762],"study_design_scores_gemma":[0.0001203377,0.0003047093,0.04774292,0.00006293821,0.00030068035,0.0013140439,0.0000497181,0.9292056,0.006983921,0.008211032,0.00563173,0.000072257215],"about_ca_topic_score_codex":0.005406121,"about_ca_topic_score_gemma":0.0068146507,"teacher_disagreement_score":0.005406121,"about_ca_system_score_codex":0.00050227495,"about_ca_system_score_gemma":0.0008457687,"threshold_uncertainty_score":0.01074928},"labels":[],"label_agreement":null},{"id":"W4392783992","doi":"10.1186/s12859-024-05661-5","title":"123VCF: an intuitive and efficient tool for filtering VCF files","year":2024,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Montreal Heart Institute","funders":"","keywords":"Computer science; Filter (signal processing); Annotation; Process (computing); Data mining; Flexibility (engineering); A priori and a posteriori; Identification (biology); Information retrieval; Artificial intelligence; Computer vision; Programming language","score_opus":0.012004658380433651,"score_gpt":0.25558263212881005,"score_spread":0.2435779737483764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392783992","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0062892493,0.00046410452,0.38081023,0.000280541,0.00026733387,0.00045533414,0.013933909,0.5937599,0.0037393752],"genre_scores_gemma":[0.079876386,0.0006031436,0.73576987,0.0011438326,0.00017650619,0.0018690468,0.047254026,0.12198453,0.0113227125],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977513,0.00026788763,0.0002562575,0.0005802664,0.00093089585,0.00021341883],"domain_scores_gemma":[0.9931606,0.004395163,0.0004443169,0.0007939273,0.00091903796,0.00028684488],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036061192,0.0025106154,0.0011213922,0.0039352933,0.0009851726,0.0026198481,0.0043454426,0.0022709148,0.037099138],"category_scores_gemma":[0.015543488,0.0011670025,0.001964783,0.001663704,0.0009175958,0.0027501893,0.0023176882,0.0017739123,0.015021434],"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":[0.0021065774,0.00033856006,0.008877353,0.0017305954,0.00033231676,0.0020256396,0.0009768911,0.007042009,0.044224057,0.010502225,0.41772667,0.50411713],"study_design_scores_gemma":[0.0010157117,0.0004646694,0.016033916,0.0010764374,0.00019805653,0.0050588124,0.0004286352,0.1929841,0.18944366,0.029810376,0.56224716,0.0012385069],"about_ca_topic_score_codex":0.0047817756,"about_ca_topic_score_gemma":0.0036979653,"teacher_disagreement_score":0.037099138,"about_ca_system_score_codex":0.0010604464,"about_ca_system_score_gemma":0.0017951124,"threshold_uncertainty_score":0.12410903},"labels":[],"label_agreement":null},{"id":"W4393044540","doi":"10.1186/s12859-024-05739-0","title":"Cell4D: a general purpose spatial stochastic simulator for cellular pathways","year":2024,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Monoclonal and Polyclonal Antibodies Research","field":"Medicine","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":"SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund; University of Toronto","keywords":"Computer science; Flexibility (engineering); Visualization; Biological data; Cluster analysis; Graphics; Variety (cybernetics); Human–computer interaction; Data mining; Machine learning; Bioinformatics; Artificial intelligence; Biology","score_opus":0.04667898820955073,"score_gpt":0.3110424190695676,"score_spread":0.26436343086001685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393044540","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09577922,0.00049403234,0.8582713,0.00095662137,0.00033540782,0.0003270004,0.0071778973,0.016426517,0.020231985],"genre_scores_gemma":[0.571928,0.0008100508,0.4047206,0.0004448586,0.000091063645,0.0014636042,0.006984073,0.0038565835,0.009701046],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997422,0.00007096213,0.00001842807,0.000037234175,0.0000983307,0.000032835702],"domain_scores_gemma":[0.99889475,0.0006703738,0.00006427477,0.00008837899,0.00016582871,0.00011630912],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008089696,0.00078783225,0.0007724524,0.0006174581,0.00058745005,0.0011652474,0.0023539853,0.0016041518,0.010246344],"category_scores_gemma":[0.0023700418,0.00053898006,0.0011760483,0.00053496024,0.00067018985,0.00064362766,0.0012970738,0.001380813,0.000958154],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000066743254,0.000044420456,0.0014713375,0.00010664971,0.000043806205,0.00009523239,0.000060976163,0.97604275,0.0021413623,0.011598213,0.0028440088,0.00548464],"study_design_scores_gemma":[0.000021542382,0.0000064240203,0.000043479227,0.000004133578,0.0000030648264,0.000007137518,0.0000046900186,0.9959104,0.0005025113,0.0013476072,0.0021438657,0.0000050857457],"about_ca_topic_score_codex":0.010877217,"about_ca_topic_score_gemma":0.007755474,"teacher_disagreement_score":0.010877217,"about_ca_system_score_codex":0.001235189,"about_ca_system_score_gemma":0.002119362,"threshold_uncertainty_score":0.03427744},"labels":[],"label_agreement":null},{"id":"W4393315502","doi":"10.1186/s12859-024-05759-w","title":"Feature-specific quantile normalization and feature-specific mean–variance normalization deliver robust bi-directional classification and feature selection performance between microarray and RNAseq data","year":2024,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Normalization (sociology); Feature selection; Computer science; Artificial intelligence; Data mining; Pattern recognition (psychology); Feature (linguistics); Model selection; Machine learning","score_opus":0.043403125535713044,"score_gpt":0.261369201763679,"score_spread":0.21796607622796596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393315502","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11583594,0.00026662883,0.8759746,0.00026653934,0.00007565716,0.00013199914,0.0008730629,0.004669467,0.0019061049],"genre_scores_gemma":[0.63323027,0.00016542878,0.3592677,0.00021947564,0.000049698396,0.0004464343,0.002898857,0.0010079544,0.002714152],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972395,0.00065538625,0.00013374604,0.0010397598,0.0007479951,0.00018367663],"domain_scores_gemma":[0.9965233,0.0014978235,0.0003871372,0.00074979465,0.00076843245,0.00007336151],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004844626,0.001027564,0.0007172567,0.00075210363,0.00040868018,0.0012083707,0.00093129516,0.0007262518,0.002457071],"category_scores_gemma":[0.012019772,0.00037138967,0.0013829008,0.00089772383,0.00075285905,0.0010583946,0.0010991733,0.0014990082,0.0014993693],"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":[0.0011676145,0.0004851515,0.03460205,0.00027347964,0.00044622488,0.00013664544,0.00029192574,0.10852822,0.22115573,0.0065487963,0.007826477,0.6185376],"study_design_scores_gemma":[0.000058883576,0.00033052484,0.039173834,0.000036139892,0.0001055893,0.00021160045,0.000087413304,0.7820003,0.16467115,0.0069063087,0.0062939054,0.00012427254],"about_ca_topic_score_codex":0.0024964856,"about_ca_topic_score_gemma":0.0031159918,"teacher_disagreement_score":0.004844626,"about_ca_system_score_codex":0.0010088264,"about_ca_system_score_gemma":0.0013013949,"threshold_uncertainty_score":0.025621116},"labels":[],"label_agreement":null},{"id":"W4395047680","doi":"10.1186/s12859-024-05768-9","title":"Mora: abundance aware metagenomic read re-assignment for disentangling similar strains","year":2024,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Scarborough Hospital; Canada Research Chairs; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Ministère de la Défense Nationale","keywords":"Metagenomics; Computer science; Genome; Computational biology; Workflow; Genomics; Biology; Data mining; Genetics; Gene","score_opus":0.03176217315068975,"score_gpt":0.2793249900307563,"score_spread":0.24756281688006654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395047680","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07770962,0.0020315128,0.85318,0.00046440386,0.0004355373,0.00035570425,0.0030938946,0.061051663,0.001677646],"genre_scores_gemma":[0.13514765,0.00018692062,0.8555893,0.00038800872,0.00012551242,0.0003854339,0.004273232,0.0025604782,0.0013434561],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978269,0.0004619885,0.00014028426,0.0008140945,0.0005755802,0.00018113475],"domain_scores_gemma":[0.9957889,0.0017370972,0.00068552984,0.00088777044,0.0005934229,0.0003072617],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034943875,0.002061193,0.0017587787,0.0031514452,0.0012219783,0.0016669268,0.0026171918,0.0021596702,0.0046191826],"category_scores_gemma":[0.010951352,0.0010633274,0.0026584868,0.0012833403,0.0008065704,0.0018318397,0.002913329,0.0024714754,0.0035764617],"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":[0.002436332,0.00074887724,0.03852069,0.0016296043,0.00178927,0.00064022746,0.00078411645,0.055280644,0.19882798,0.006060064,0.02861058,0.6646716],"study_design_scores_gemma":[0.00025610314,0.00055620493,0.0108408425,0.0001286232,0.00025862354,0.0007205752,0.00019326241,0.87304324,0.08072806,0.013286982,0.019805878,0.0001816329],"about_ca_topic_score_codex":0.0012820428,"about_ca_topic_score_gemma":0.0030455757,"teacher_disagreement_score":0.0046191826,"about_ca_system_score_codex":0.00075121474,"about_ca_system_score_gemma":0.0013816555,"threshold_uncertainty_score":0.0184803},"labels":[],"label_agreement":null},{"id":"W4399465136","doi":"10.1186/s12859-024-05822-6","title":"Integrating transformers and many-objective optimization for drug design","year":2024,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University; Thunder Bay Regional Research Institute; Brock University","funders":"National Research Council Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; DNA microarray; Computational biology; Drug; Biology; Pharmacology; Genetics","score_opus":0.029820889704763705,"score_gpt":0.2946029113881443,"score_spread":0.2647820216833806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399465136","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020391122,0.00031927158,0.9768599,0.00017639522,0.000017069724,0.000059656864,0.000020663472,0.0001553556,0.0020005761],"genre_scores_gemma":[0.6611891,0.0006066855,0.33618408,0.00013474883,0.000030655676,0.00017900637,0.000083249506,0.00009313327,0.0014993991],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99945325,0.0002869997,0.00002663009,0.000046118017,0.00015150831,0.000035404755],"domain_scores_gemma":[0.99892104,0.0007407081,0.00010819404,0.00007147133,0.00010988758,0.000048701993],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019411747,0.00091027503,0.00056311255,0.0008030453,0.00020756046,0.00066345325,0.00085569033,0.0006492467,0.0013620971],"category_scores_gemma":[0.0027507728,0.0003145441,0.0007226153,0.00065518566,0.00079989526,0.0011016179,0.0010470229,0.0010460987,0.00020687467],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003255645,0.000046636833,0.00040998848,0.00007512185,0.00003138846,0.000021445507,0.000016332144,0.9588314,0.0013046293,0.013864436,0.00014157423,0.025224356],"study_design_scores_gemma":[0.000006399219,0.000040328225,0.000037292317,0.000003995808,0.000006205637,0.000008170641,0.0000034978789,0.99479586,0.00040082887,0.004441973,0.00025306322,0.0000023525542],"about_ca_topic_score_codex":0.0015835643,"about_ca_topic_score_gemma":0.0015898176,"teacher_disagreement_score":0.0019411747,"about_ca_system_score_codex":0.0010077232,"about_ca_system_score_gemma":0.001074902,"threshold_uncertainty_score":0.010266006},"labels":[],"label_agreement":null},{"id":"W4400046055","doi":"10.1186/s12859-024-05847-x","title":"Can large language models understand molecules?","year":2024,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cheminformatics; Computer science; Embedding; Representation (politics); Artificial intelligence; Natural language processing; Field (mathematics); Property (philosophy); Machine learning; Bioinformatics; Biology; Mathematics","score_opus":0.01972382980271739,"score_gpt":0.27239039583762137,"score_spread":0.252666566034904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400046055","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02896388,0.004177298,0.9335309,0.017285513,0.0005248895,0.00010276235,0.0031213425,0.005372178,0.0069212015],"genre_scores_gemma":[0.6044142,0.005976825,0.3635186,0.005198875,0.00066010794,0.0005086666,0.007333449,0.0015758455,0.010813414],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992606,0.00040712318,0.000031053336,0.00015185085,0.00009694895,0.00005229684],"domain_scores_gemma":[0.99513054,0.0037947823,0.00020862775,0.0004736313,0.00028264508,0.000109670604],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019165804,0.0011210698,0.00088155153,0.0007499826,0.00034910714,0.0021612397,0.0014490671,0.0012678088,0.008480775],"category_scores_gemma":[0.014303808,0.00053124275,0.0014798999,0.00076316757,0.0009979407,0.0078038983,0.0013182178,0.0036791624,0.0045314054],"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":[0.0006142117,0.00024832,0.005258727,0.0014446263,0.00048067758,0.00041849827,0.0010287882,0.27602568,0.009174532,0.1710577,0.046764225,0.487484],"study_design_scores_gemma":[0.000036700898,0.000066678556,0.00040418666,0.00013928437,0.00004444711,0.00009469137,0.00014767474,0.71853393,0.0023700246,0.26524064,0.012887898,0.000033742712],"about_ca_topic_score_codex":0.0027234373,"about_ca_topic_score_gemma":0.003558038,"teacher_disagreement_score":0.008480775,"about_ca_system_score_codex":0.0008535755,"about_ca_system_score_gemma":0.0009863883,"threshold_uncertainty_score":0.028371036},"labels":[],"label_agreement":null},{"id":"W4400560580","doi":"10.1186/s12859-024-05853-z","title":"SimSpliceEvol2: alternative splicing-aware simulation of biological sequence evolution and transcript phylogenies","year":2024,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Université de Sherbrooke","keywords":"Biology; Tree (set theory); Computational biology; Web server; Phylogenetic tree; Documentation; Gene; Inference; DNA microarray; Computer science; Source code; Software; Sequence (biology); Phylogenetics; Genetics; The Internet; Gene expression; Programming language; World Wide Web; Artificial intelligence","score_opus":0.04176224017873746,"score_gpt":0.2843509021788098,"score_spread":0.24258866200007234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400560580","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12958391,0.001055677,0.7433129,0.0008214663,0.00060369435,0.00033572674,0.017711617,0.09016741,0.016407667],"genre_scores_gemma":[0.40387738,0.00097127067,0.5226655,0.0010385481,0.00019879911,0.0022171414,0.031908188,0.028851468,0.008271669],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999516,0.00016573905,0.0000277555,0.000120708086,0.0001118135,0.00005802102],"domain_scores_gemma":[0.99836224,0.0012061642,0.00006794707,0.0001311146,0.00012834562,0.0001042607],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015322391,0.0014119558,0.0012527335,0.0008087403,0.0008728735,0.0016267077,0.0036950572,0.0024204957,0.013177349],"category_scores_gemma":[0.003812494,0.0010718737,0.0022291224,0.000920732,0.0008773542,0.0010927186,0.0012138081,0.0024300548,0.0030713582],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006504501,0.0001593612,0.0061629824,0.00087307824,0.0004120723,0.00052417576,0.0005474503,0.89785886,0.010996442,0.02082878,0.030574357,0.030412009],"study_design_scores_gemma":[0.00010769755,0.000028535758,0.00024630196,0.000023554769,0.000025347574,0.000074270254,0.000026439478,0.9790203,0.0031487378,0.006950162,0.010319648,0.000029065683],"about_ca_topic_score_codex":0.005500375,"about_ca_topic_score_gemma":0.0063750744,"teacher_disagreement_score":0.013177349,"about_ca_system_score_codex":0.0010046221,"about_ca_system_score_gemma":0.0014881656,"threshold_uncertainty_score":0.044082582},"labels":[],"label_agreement":null},{"id":"W4400687503","doi":"10.1186/s12859-024-05858-8","title":"PyChelator: a Python-based Colab and web application for metal chelator calculations","year":2024,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Trace Elements in Health","field":"Nursing","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Deutsche Forschungsgemeinschaft","keywords":"Python (programming language); Computer science; World Wide Web; Web application; Computational biology; Bioinformatics; Operating system; Biology","score_opus":0.02432804058987388,"score_gpt":0.3225738479674255,"score_spread":0.29824580737755163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400687503","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006307577,0.0007635754,0.31177056,0.00045263648,0.0003989055,0.00047006394,0.017728949,0.6518964,0.010211299],"genre_scores_gemma":[0.062184185,0.0018232292,0.5725194,0.0023894943,0.0002764503,0.0037669449,0.056912515,0.27080327,0.029324487],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986216,0.00019891764,0.00014683501,0.0002933049,0.0005459851,0.00019350677],"domain_scores_gemma":[0.99804246,0.0007867715,0.00022119656,0.00024223822,0.0005346241,0.00017267796],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020119671,0.0028511335,0.0016706876,0.0017738136,0.0010640286,0.0022066378,0.005222979,0.0013675628,0.06105386],"category_scores_gemma":[0.007434908,0.0014367753,0.0018345027,0.0012331969,0.0008209641,0.0027194305,0.004125267,0.0029541391,0.036792256],"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":[0.0013689208,0.0003440452,0.005204977,0.0061943405,0.0005357106,0.0012835173,0.0010254917,0.013326537,0.02800141,0.013878868,0.6990717,0.22976446],"study_design_scores_gemma":[0.0005735105,0.00023259193,0.0043721474,0.00085601304,0.00020234413,0.001450126,0.0001883542,0.12635915,0.0792446,0.026213981,0.75973713,0.0005700039],"about_ca_topic_score_codex":0.0019857301,"about_ca_topic_score_gemma":0.0016983625,"teacher_disagreement_score":0.06105386,"about_ca_system_score_codex":0.000707101,"about_ca_system_score_gemma":0.0030894806,"threshold_uncertainty_score":0.20424551},"labels":[],"label_agreement":null},{"id":"W4400788779","doi":"10.1186/s12859-024-05865-9","title":"HEROIC: a platform for remote collection of electroencephalographic data using consumer-grade brain wearables","year":2024,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","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; McGill University; University Health Network","funders":"","keywords":"Computer science; Wearable computer; Neurocognitive; Scalability; Electroencephalography; Software; Human–computer interaction; Data collection; Data science; Inertial measurement unit; Technician; Protocol (science); Artificial intelligence; Embedded system; Database; Medicine; Cognition; Psychology; Neuroscience; Engineering","score_opus":0.11734397845058817,"score_gpt":0.334388231964429,"score_spread":0.21704425351384085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400788779","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04941677,0.0008678861,0.7988929,0.00053134264,0.00041552374,0.0017129179,0.0051670643,0.1332213,0.009774205],"genre_scores_gemma":[0.3517506,0.0017522292,0.59492195,0.0018190264,0.0003451334,0.0040990226,0.010145832,0.014968117,0.020198157],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999411,0.00008696656,0.000038539758,0.0001751433,0.00023335019,0.00005501592],"domain_scores_gemma":[0.99896216,0.00037490382,0.00010848749,0.00018406307,0.00021465104,0.0001557488],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011150085,0.0011226193,0.0006875926,0.00089894,0.00023065862,0.00071949733,0.0017608786,0.0005842591,0.011295522],"category_scores_gemma":[0.0032308393,0.0005269068,0.00057447207,0.00039929722,0.00056892337,0.0009689669,0.002152735,0.00085537485,0.0039816913],"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":[0.0050420105,0.0007658317,0.00987404,0.002459037,0.00057676126,0.0027291717,0.0020515623,0.0058534215,0.2639132,0.009863649,0.16328873,0.5335826],"study_design_scores_gemma":[0.0025216707,0.004415367,0.050447457,0.0010255774,0.0006893029,0.006905297,0.0006757946,0.17363529,0.34965503,0.025994256,0.3831348,0.00090015127],"about_ca_topic_score_codex":0.0006206069,"about_ca_topic_score_gemma":0.0010409158,"teacher_disagreement_score":0.011295522,"about_ca_system_score_codex":0.00027056865,"about_ca_system_score_gemma":0.0006951718,"threshold_uncertainty_score":0.03778732},"labels":[],"label_agreement":null},{"id":"W4401214408","doi":"10.1186/s12859-024-05861-z","title":"Hybrid fragment-SMILES tokenization for ADMET prediction in drug discovery","year":2024,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; Brock University","funders":"National Research Council Canada; Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation","keywords":"Lexical analysis; Computer science; In silico; Drug discovery; Computational biology; Transformer; Artificial intelligence; Machine learning; Bioinformatics; Biology; Genetics","score_opus":0.01916693910531592,"score_gpt":0.2797357114306657,"score_spread":0.2605687723253498,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401214408","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08912529,0.00062796584,0.9013015,0.00029974178,0.00006170332,0.00012125328,0.0007247642,0.006168356,0.00156936],"genre_scores_gemma":[0.82148904,0.0003545718,0.17315778,0.00023838993,0.000049017144,0.00017359188,0.0017540102,0.00028576606,0.0024977557],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99955875,0.00016084932,0.00003359443,0.000089639245,0.00010115204,0.000056003777],"domain_scores_gemma":[0.99836725,0.0010353123,0.00015068108,0.00018796089,0.00019071449,0.000068129935],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014893196,0.0007125926,0.0008688031,0.0007192776,0.00029254664,0.0005686236,0.0016756431,0.0005429762,0.0025275815],"category_scores_gemma":[0.004074098,0.0002770387,0.0006463985,0.0007237155,0.00052652124,0.0014299864,0.0009200685,0.001004315,0.0009551966],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018272597,0.0002386885,0.0049706106,0.0002979944,0.00012680817,0.00023721044,0.00010280938,0.70070887,0.01480643,0.01149815,0.003301789,0.2618833],"study_design_scores_gemma":[0.000015366626,0.00010060256,0.00014003171,0.0000052995147,0.000013801313,0.00003254632,0.000008360485,0.99078685,0.0060072676,0.0023750244,0.00050827884,0.000006538032],"about_ca_topic_score_codex":0.0036143558,"about_ca_topic_score_gemma":0.006242185,"teacher_disagreement_score":0.0036143558,"about_ca_system_score_codex":0.000937684,"about_ca_system_score_gemma":0.0015190048,"threshold_uncertainty_score":0.008455634},"labels":[],"label_agreement":null},{"id":"W4401728618","doi":"10.1186/s12859-024-05816-4","title":"Modeling relaxation experiments with a mechanistic model of gene expression","year":2024,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Laboratoire d'Excellence Ecofect; Agence Nationale de la Recherche; Université de Lyon; U.S. Department of Veterans Affairs","keywords":"DNA microarray; Computational biology; Relaxation (psychology); Population; Gene expression; Expression (computer science); Gene; Biology; Biological system; Computer science; Bioinformatics; Genetics; Neuroscience; Medicine","score_opus":0.021187813006774928,"score_gpt":0.24732616860079504,"score_spread":0.22613835559402012,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401728618","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19251357,0.00025404507,0.803653,0.0005416616,0.000047480542,0.00012943232,0.00059231964,0.00039396647,0.0018744469],"genre_scores_gemma":[0.8862898,0.00052893354,0.10730855,0.00022093422,0.000057985435,0.0006633949,0.00085978437,0.00007748653,0.0039930665],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996389,0.00010851058,0.000017155151,0.00013308643,0.000058610247,0.000043715983],"domain_scores_gemma":[0.99795926,0.001521317,0.00022838522,0.00013221856,0.00010022032,0.00005863158],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011828425,0.00053183653,0.0006420947,0.000553996,0.0002886345,0.0007803155,0.0014638382,0.0018718962,0.001535143],"category_scores_gemma":[0.0041852836,0.00051608926,0.0013788135,0.0005010453,0.0008432089,0.0009944726,0.0006762954,0.001539114,0.00030149636],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036219208,0.000034800294,0.0012461912,0.000051804196,0.000022197653,0.00005746892,0.000055883924,0.9827543,0.0059188437,0.00758741,0.000113052825,0.002121826],"study_design_scores_gemma":[0.0000053160147,0.000015113489,0.00029610295,0.0000019183353,0.000006622402,0.000015824773,0.000005366151,0.99618524,0.0005549278,0.0026852773,0.0002230605,0.000005185199],"about_ca_topic_score_codex":0.004221365,"about_ca_topic_score_gemma":0.0027032208,"teacher_disagreement_score":0.004221365,"about_ca_system_score_codex":0.0010851936,"about_ca_system_score_gemma":0.00079431554,"threshold_uncertainty_score":0.008393645},"labels":[],"label_agreement":null},{"id":"W4401914768","doi":"10.1186/s12859-024-05885-5","title":"HerpesDRG: a comprehensive resource for human herpesvirus antiviral drug resistance genotyping","year":2024,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Herpesvirus Infections 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":"Institute of Infection and Immunity","funders":"University College London Hospitals Biomedical Research Centre; Medical Research Council; University College London Hospitals NHS Foundation Trust; National Institute for Health and Care Research; UK Research and Innovation; Wellcome Trust","keywords":"Drug resistance; Genotyping; Sanger sequencing; Biology; Human herpesvirus 6; Annotation; Mutation; Computational biology; Genotype; Bioinformatics; Database; Genetics; Gene; Virus; Computer science; Viral disease; Herpesviridae","score_opus":0.0364832533639407,"score_gpt":0.3212147654646737,"score_spread":0.284731512100733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401914768","genre_codex":"dataset","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005264576,0.0063487976,0.026318494,0.0007997134,0.00024071005,0.00041234063,0.9270348,0.0262726,0.007308077],"genre_scores_gemma":[0.018335033,0.00446879,0.07342834,0.0011057402,0.00015317192,0.0010105327,0.892996,0.0057106568,0.0027917658],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970176,0.00087255775,0.000602739,0.0006960064,0.0006129195,0.00019821385],"domain_scores_gemma":[0.99112844,0.0042720665,0.0015132155,0.0013179613,0.001041356,0.00072690746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0051618437,0.0015768589,0.002672054,0.008531002,0.00079075503,0.0031953098,0.0029909215,0.0019054863,0.029711999],"category_scores_gemma":[0.023882821,0.001210457,0.0013775503,0.007902097,0.00044431345,0.0017678484,0.0040695868,0.0016336713,0.024905106],"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":[0.0015941012,0.00014011076,0.018958004,0.014181036,0.0010440854,0.000951364,0.0009211558,0.0033349276,0.010115696,0.0066633904,0.7746661,0.16743009],"study_design_scores_gemma":[0.0006694676,0.00016698522,0.0238505,0.0022288354,0.0007652409,0.0012735293,0.00031263957,0.004398531,0.006280963,0.012783595,0.9470591,0.00021063724],"about_ca_topic_score_codex":0.005391102,"about_ca_topic_score_gemma":0.008898544,"teacher_disagreement_score":0.029711999,"about_ca_system_score_codex":0.0008796054,"about_ca_system_score_gemma":0.0051139425,"threshold_uncertainty_score":0.09939653},"labels":[],"label_agreement":null},{"id":"W4401918821","doi":"10.1186/s12859-024-05776-9","title":"HBeeID: a molecular tool that identifies honey bee subspecies from different geographic populations","year":2024,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Insect and Arachnid Ecology and Behavior","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Animal and Plant Health Inspection Service; University of Illinois at Urbana-Champaign; Orta Doğu Teknik Üniversitesi; Office of International Science and Engineering; U.S. Department of Agriculture; Florida International University; Uppsala Universitet; National Science Foundation","keywords":"Subspecies; Honey bee; Biology; Pollinator; Linear discriminant analysis; Hierarchical clustering; Ecology; Cluster analysis; Artificial intelligence; Computer science; Pollen; Pollination","score_opus":0.02408205857244013,"score_gpt":0.2578502723451636,"score_spread":0.23376821377272347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401918821","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2930555,0.0011994505,0.5654582,0.00088680617,0.00027050753,0.00044278972,0.08056117,0.049935184,0.008190377],"genre_scores_gemma":[0.40569833,0.00030076792,0.53256726,0.00060888927,0.00008006049,0.0005841907,0.054235328,0.0015397965,0.004385259],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99953115,0.00008205037,0.000031692874,0.00020707483,0.00010769161,0.00004039271],"domain_scores_gemma":[0.9975479,0.0016144268,0.0003632322,0.00015449083,0.00017043331,0.00014942269],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011515608,0.00083419675,0.00065764895,0.0033512928,0.0006353054,0.0008406938,0.0008798108,0.00085663254,0.009110227],"category_scores_gemma":[0.005377613,0.00038336578,0.0007282281,0.0010868872,0.00026830143,0.00078929344,0.0014333616,0.0006897637,0.001842219],"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":[0.002235774,0.0006838294,0.28941935,0.001993618,0.00164124,0.0016839048,0.0013703072,0.029366028,0.0853706,0.00878417,0.08598813,0.49146312],"study_design_scores_gemma":[0.0007445802,0.00069474743,0.26551786,0.0005185234,0.000969696,0.0037535818,0.0008216724,0.50307053,0.06647422,0.029939344,0.12716237,0.0003328911],"about_ca_topic_score_codex":0.0018691043,"about_ca_topic_score_gemma":0.0042581824,"teacher_disagreement_score":0.009110227,"about_ca_system_score_codex":0.0003744515,"about_ca_system_score_gemma":0.00057219306,"threshold_uncertainty_score":0.030476809},"labels":[],"label_agreement":null},{"id":"W4401921714","doi":"10.1186/s12859-024-05882-8","title":"ARGV: 3D genome structure exploration using augmented reality","year":2024,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Génome Québec; Genome Canada","keywords":"Genome; Visualization; Augmented reality; Computer science; Computational biology; Data visualization; Human–computer interaction; Biology; Genetics; Data mining; Gene","score_opus":0.02454012686021208,"score_gpt":0.26303558830816215,"score_spread":0.23849546144795006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401921714","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025452798,0.0017155388,0.7437234,0.00087793666,0.00032059444,0.00026195115,0.035944592,0.18185805,0.009845195],"genre_scores_gemma":[0.23314889,0.002251546,0.6700255,0.00086185907,0.00009925469,0.0010712057,0.06588057,0.01923936,0.00742172],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99938416,0.00010947514,0.000026191252,0.00013533584,0.00027026635,0.00007443468],"domain_scores_gemma":[0.999401,0.0002965125,0.000039443978,0.00010545995,0.00008542166,0.00007221392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009700171,0.0015807081,0.0010538192,0.0015720032,0.00054281065,0.0023095126,0.0022527045,0.0013515835,0.017244797],"category_scores_gemma":[0.0020517998,0.0009131978,0.001919209,0.00088973105,0.00038097057,0.0013340826,0.0036064684,0.0016723458,0.0043854937],"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":[0.002479075,0.000402154,0.006275847,0.0028684516,0.0010367252,0.0020370362,0.0025087725,0.08630743,0.13061771,0.024371998,0.31600252,0.42509225],"study_design_scores_gemma":[0.00070824055,0.00042839895,0.0076740533,0.00046983545,0.00024154803,0.0017114622,0.00081151264,0.50869715,0.07367466,0.035653736,0.36929694,0.0006324281],"about_ca_topic_score_codex":0.0036216443,"about_ca_topic_score_gemma":0.0055074613,"teacher_disagreement_score":0.017244797,"about_ca_system_score_codex":0.00038937683,"about_ca_system_score_gemma":0.0007271074,"threshold_uncertainty_score":0.057689548},"labels":[],"label_agreement":null},{"id":"W4402226771","doi":"10.1186/s12859-024-05912-5","title":"Answering open questions in biology using spatial genomics and structured methods","year":2024,"lang":"en","type":"review","venue":"BMC Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institutes of Health; National Cancer Institute; Center for Biomedical Informatics and Information Technology, National Cancer Institute; National Human Genome Research Institute; Canadian Institute for Advanced Research; Leona M. and Harry B. Helmsley Charitable Trust","keywords":"Data science; Context (archaeology); Computer science; Genomics; Biological data; Variety (cybernetics); Big data; Biology; Artificial intelligence; Bioinformatics; Data mining; Genome","score_opus":0.09727525832936341,"score_gpt":0.4270427508370241,"score_spread":0.3297674925076607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402226771","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000073357485,0.98849714,0.005818538,0.002798234,0.0006808891,0.000010823594,0.000028597966,0.000034876735,0.002057535],"genre_scores_gemma":[0.001029514,0.991156,0.0045389263,0.0014109873,0.00090945716,0.000032728887,0.000056593723,0.000018603083,0.0008472006],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989073,0.00038650894,0.000099090765,0.0001702556,0.00038000374,0.000056892728],"domain_scores_gemma":[0.9951925,0.0036996498,0.00014829736,0.00018490013,0.00062161335,0.00015294414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043446855,0.0013141574,0.0018766142,0.0038351368,0.0005861796,0.0020932108,0.0027508866,0.0032910926,0.0029665625],"category_scores_gemma":[0.0055806423,0.0006066857,0.0009753183,0.004156903,0.004872217,0.0056922217,0.0015931975,0.006664346,0.0030787515],"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":[0.000049483006,0.00007437452,0.0002429315,0.013080537,0.00015581057,0.00016706983,0.00023345345,0.0021897391,0.0009664812,0.17192292,0.060110897,0.7508063],"study_design_scores_gemma":[0.000017554185,0.000060645827,0.00040458344,0.0038460796,0.000050567647,0.00043009766,0.000111816444,0.0006815045,0.00044264135,0.0954398,0.8984637,0.00005099323],"about_ca_topic_score_codex":0.0027859015,"about_ca_topic_score_gemma":0.0025872507,"teacher_disagreement_score":0.0043446855,"about_ca_system_score_codex":0.0025806415,"about_ca_system_score_gemma":0.0026109384,"threshold_uncertainty_score":0.022977173},"labels":[],"label_agreement":null},{"id":"W4403039748","doi":"10.1186/s12859-024-05935-y","title":"ScRNAbox: empowering single-cell RNA sequencing on high performance computing systems","year":2024,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Neurological Institute and Hospital","funders":"Montreal Neurological Institute and Hospital; Fondation Brain Canada; McGill University; Canadian Institutes of Health Research; Québec Consortium for Drug Discovery; Michael J. Fox Foundation for Parkinson's Research","keywords":"Computer science; Scalability; Workstation; Pipeline (software); Workload; Distributed computing; Cluster analysis; Database; Operating system","score_opus":0.023389787648923927,"score_gpt":0.23039982112806542,"score_spread":0.2070100334791415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403039748","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039387736,0.0013731769,0.72450984,0.0013115667,0.0009520799,0.00062983873,0.008087956,0.21651359,0.007234261],"genre_scores_gemma":[0.12392184,0.001462899,0.8215655,0.0017268918,0.00033270338,0.0014187628,0.019816913,0.022898775,0.006855695],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99767536,0.00045782066,0.00014867698,0.0006538294,0.0008650598,0.00019922062],"domain_scores_gemma":[0.99689746,0.0012324993,0.0002182813,0.0006230186,0.0006231256,0.00040560972],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003747599,0.0012761932,0.0010466555,0.0009704531,0.0010723778,0.00217785,0.0024167912,0.0012370793,0.010872401],"category_scores_gemma":[0.006235884,0.0010810178,0.0013178191,0.0007143152,0.0008636552,0.002224701,0.0031160272,0.0022270945,0.00952698],"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":[0.0033860153,0.00036269278,0.008250381,0.0025293734,0.00055978954,0.0012747151,0.0013023991,0.020584024,0.51857495,0.01434809,0.1857825,0.24304514],"study_design_scores_gemma":[0.0005309976,0.0006489089,0.0063996413,0.00040891094,0.0001714771,0.00075443345,0.00030143902,0.26782107,0.44414672,0.027459485,0.25080407,0.00055284036],"about_ca_topic_score_codex":0.0011153149,"about_ca_topic_score_gemma":0.0024162198,"teacher_disagreement_score":0.010872401,"about_ca_system_score_codex":0.0006281811,"about_ca_system_score_gemma":0.0015040662,"threshold_uncertainty_score":0.036371768},"labels":[],"label_agreement":null},{"id":"W4404722864","doi":"10.1186/s12859-024-05941-0","title":"Plaseval: a framework for comparing and evaluating plasmid detection tools","year":2024,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University; Agriculture and Agri-Food Canada; University of Saskatchewan; Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Genome Canada","keywords":"DNA microarray; Plasmid; Computational biology; Computer science; Biology; Genetics; Gene; Gene expression","score_opus":0.06687434104668352,"score_gpt":0.3231134474966735,"score_spread":0.25623910644998993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404722864","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027254842,0.0022888898,0.8744433,0.00051386893,0.00023705242,0.0013853697,0.010747287,0.07977916,0.0033502567],"genre_scores_gemma":[0.09444084,0.0006512596,0.87288296,0.0002739314,0.00009040305,0.0019933674,0.023645908,0.0052500437,0.0007712176],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.98380196,0.005255927,0.0024783053,0.003059029,0.004723832,0.0006808509],"domain_scores_gemma":[0.9793632,0.011512922,0.0025437376,0.0031388358,0.0024799681,0.0009613336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01785909,0.004510771,0.0027858526,0.015038115,0.0015619143,0.008174785,0.0070760236,0.0036211712,0.004386129],"category_scores_gemma":[0.041811593,0.0018667475,0.006414242,0.0050923936,0.0024115464,0.0059100213,0.008397708,0.0031884264,0.0016636834],"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":[0.0033678694,0.0014382537,0.031455513,0.008480877,0.0041589835,0.0012317286,0.0018427379,0.34876975,0.023628071,0.06614407,0.045054365,0.46442774],"study_design_scores_gemma":[0.00045887253,0.0012272088,0.0065961895,0.0011438538,0.00059839647,0.00055823725,0.0006456377,0.8527797,0.01578755,0.06724209,0.05262086,0.0003414127],"about_ca_topic_score_codex":0.005124091,"about_ca_topic_score_gemma":0.006091398,"teacher_disagreement_score":0.01785909,"about_ca_system_score_codex":0.0032461055,"about_ca_system_score_gemma":0.003232082,"threshold_uncertainty_score":0.09444898},"labels":[],"label_agreement":null},{"id":"W4404976894","doi":"10.1186/s12859-024-05952-x","title":"Managing false positives during detection of pathogen sequences in shotgun metagenomics datasets","year":2024,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Salmonella and Campylobacter epidemiology","field":"Agricultural and Biological Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Food Inspection Agency; Carleton University","funders":"Alliance de recherche numérique du Canada; Ontario Ministry of Agriculture, Food and Rural Affairs; Canadian Food Inspection Agency","keywords":"False positive paradox; Metagenomics; Shotgun; Computational biology; Shotgun sequencing; DNA microarray; Biology; True positive rate; Computer science; Bioinformatics; Genetics; DNA sequencing; Gene; Artificial intelligence; Gene expression","score_opus":0.02605075273000819,"score_gpt":0.24427652744555386,"score_spread":0.21822577471554566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404976894","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45781898,0.0032210043,0.50294447,0.0013943465,0.00063521916,0.0010858238,0.006779969,0.024313968,0.001806283],"genre_scores_gemma":[0.44677824,0.00039032064,0.53704965,0.0012223786,0.000108787026,0.00085348386,0.011132989,0.0019537522,0.00051046594],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9833605,0.0060043978,0.002116289,0.00481848,0.0030217918,0.00067849946],"domain_scores_gemma":[0.9441187,0.041638214,0.0032131788,0.0050024353,0.005343195,0.0006843654],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03146903,0.0027538547,0.0019921986,0.0032793493,0.0027680881,0.0039759353,0.0033507515,0.0033133738,0.0009750429],"category_scores_gemma":[0.08337077,0.0015177369,0.0031431587,0.00222477,0.0016786205,0.0031619815,0.0027879886,0.003270067,0.0008897756],"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":[0.0039496035,0.0010631229,0.3333283,0.0071593765,0.006660068,0.004081142,0.0061576213,0.12531531,0.22627753,0.0057465686,0.022943206,0.25731823],"study_design_scores_gemma":[0.0003195923,0.00076127285,0.06322713,0.0005919988,0.0015448397,0.0021591221,0.0013602902,0.6753371,0.21405196,0.023237448,0.016993066,0.00041627476],"about_ca_topic_score_codex":0.003286755,"about_ca_topic_score_gemma":0.0081760185,"teacher_disagreement_score":0.03146903,"about_ca_system_score_codex":0.0013580059,"about_ca_system_score_gemma":0.0026271034,"threshold_uncertainty_score":0.16642612},"labels":[],"label_agreement":null},{"id":"W4406136011","doi":"10.1186/s12859-024-06030-y","title":"DFAST_QC: quality assessment and taxonomic identification tool for prokaryotic Genomes","year":2025,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Bioscience Database Center; Japan Society for the Promotion of Science; Ohsumi Frontier Science Foundation; Institute of Genetics; Japan Agency for Medical Research and Development","keywords":"Identification (biology); Computer science; Scalability; Genome; Biological classification; Data mining; Taxonomic rank; Data science; Biology; Database; Ecology","score_opus":0.030973555754661288,"score_gpt":0.31303070283876494,"score_spread":0.2820571470841037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406136011","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020072967,0.0008012902,0.5452579,0.0007305313,0.00039481663,0.0007861179,0.016063975,0.41382185,0.0020705366],"genre_scores_gemma":[0.10391126,0.00053357834,0.82050705,0.0008301202,0.00013195383,0.0019033942,0.0397713,0.030237863,0.0021736065],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9929229,0.0012856392,0.0009719611,0.0013396227,0.0029851382,0.00049459044],"domain_scores_gemma":[0.97488946,0.011850301,0.003579969,0.0023322157,0.0063913832,0.0009567301],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013569935,0.0035915219,0.0018484885,0.006353529,0.0022499948,0.0036828683,0.0049710535,0.0018577636,0.009422051],"category_scores_gemma":[0.04456711,0.001255488,0.0028753988,0.003313542,0.0016040198,0.003521944,0.0040500215,0.0033561669,0.0048271692],"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":[0.0048887394,0.00067852036,0.048109595,0.006286938,0.00083005195,0.001978134,0.003060668,0.021138618,0.094572015,0.012745094,0.3151009,0.49061075],"study_design_scores_gemma":[0.0014704111,0.00103961,0.022224098,0.00133211,0.0004539682,0.003180234,0.00078635954,0.44879046,0.22105129,0.019835103,0.27830967,0.0015267242],"about_ca_topic_score_codex":0.0052636005,"about_ca_topic_score_gemma":0.0041013467,"teacher_disagreement_score":0.013569935,"about_ca_system_score_codex":0.002317114,"about_ca_system_score_gemma":0.0048011467,"threshold_uncertainty_score":0.07176554},"labels":[],"label_agreement":null},{"id":"W4406677956","doi":"10.1186/s12859-024-06015-x","title":"A graph neural network approach for hierarchical mapping of breast cancer protein communities","year":2025,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Winnipeg; University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Breast cancer; Computational biology; Cluster analysis; Computer science; Hierarchical clustering; Machine learning; Artificial intelligence; Bioinformatics; Biology; Data mining; Cancer; Genetics","score_opus":0.01749997163686651,"score_gpt":0.24307157258260165,"score_spread":0.22557160094573514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406677956","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045593433,0.00038860706,0.95080185,0.00036029212,0.000037653648,0.000058760314,0.00037130652,0.0006441136,0.0017439255],"genre_scores_gemma":[0.6825538,0.00041522796,0.31095767,0.00028921312,0.00007610632,0.00021557896,0.0011798741,0.00013864863,0.0041739056],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99969125,0.00008104798,0.0000125448605,0.00011212912,0.00005657392,0.00004652481],"domain_scores_gemma":[0.99949837,0.00022650138,0.00008186768,0.000037784877,0.00011750221,0.000037965117],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044806115,0.00071814645,0.00046805138,0.0013540437,0.0004253772,0.00053808256,0.0010266526,0.00092431204,0.0014078465],"category_scores_gemma":[0.0016124224,0.0003452499,0.0008649539,0.00097161456,0.0004993463,0.00093738566,0.0007252535,0.0010109821,0.00030105404],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000080204525,0.000065805034,0.0023399987,0.00007839262,0.00007949965,0.00010204114,0.00009765615,0.9092977,0.005005799,0.01201563,0.001944428,0.06889283],"study_design_scores_gemma":[0.0000012038859,0.0000043983396,0.00012186929,0.0000018030464,0.000002739474,0.000005214169,0.000004409078,0.99587667,0.00016356743,0.0037130446,0.00010315823,0.0000018839731],"about_ca_topic_score_codex":0.01432723,"about_ca_topic_score_gemma":0.016698133,"teacher_disagreement_score":0.01432723,"about_ca_system_score_codex":0.001216527,"about_ca_system_score_gemma":0.0007385957,"threshold_uncertainty_score":0.028487682},"labels":[],"label_agreement":null},{"id":"W4407114045","doi":"10.1186/s12859-025-06050-2","title":"BioLake: an RNA expression analysis framework for prostate cancer biomarker powered by data lakehouse","year":2025,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gene expression and cancer classification","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":"Prostate Cancer Canada; University of Calgary","funders":"","keywords":"Upload; Computer science; Raw data; Scalability; Flexibility (engineering); Data science; Data pre-processing; Pipeline (software); Data mining; Workflow; Data warehouse; Database; World Wide Web","score_opus":0.04424208771644974,"score_gpt":0.352946851264794,"score_spread":0.3087047635483443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407114045","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038752863,0.00065754825,0.5863896,0.00081910193,0.00022570761,0.00057802885,0.031279847,0.37185493,0.0043200455],"genre_scores_gemma":[0.08307444,0.0012244447,0.7035417,0.0023666185,0.00020645093,0.003332761,0.1388619,0.05620665,0.011184959],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973308,0.0003322803,0.00028843695,0.0007017556,0.0011439518,0.0002027819],"domain_scores_gemma":[0.9969695,0.0010727777,0.0002813405,0.0008718951,0.00050557667,0.00029899512],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004284732,0.0020282422,0.001500122,0.0029825058,0.001086354,0.0037365295,0.0049191485,0.0012204633,0.017315682],"category_scores_gemma":[0.008798117,0.0016779405,0.003222904,0.002541099,0.0011555733,0.005517698,0.007396559,0.0028006288,0.009032269],"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":[0.004318623,0.00048783945,0.015198639,0.00400788,0.001179337,0.0024659135,0.0027292129,0.032794923,0.0725819,0.086059794,0.45379803,0.32437795],"study_design_scores_gemma":[0.00081812654,0.00035430674,0.009185676,0.000509868,0.00030062336,0.0011910093,0.00047903426,0.24535081,0.063432,0.116449386,0.5610933,0.0008359399],"about_ca_topic_score_codex":0.0059593734,"about_ca_topic_score_gemma":0.0100406315,"teacher_disagreement_score":0.017315682,"about_ca_system_score_codex":0.0013899059,"about_ca_system_score_gemma":0.0027802389,"threshold_uncertainty_score":0.057926714},"labels":[],"label_agreement":null},{"id":"W4407364035","doi":"10.1186/s12859-025-06051-1","title":"A hybrid machine learning framework for functional annotation of mitochondrial glutathione transport and metabolism proteins in cancers","year":2025,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Ferroptosis and cancer prognosis","field":"Medicine","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":"National Research Council Canada; University of Ottawa","funders":"National Research Council Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Computational biology; Context (archaeology); Biology; Annotation; Function (biology); Proteomics; Mitochondrion; Bioinformatics; Biochemistry; Gene; Genetics","score_opus":0.018564024742322795,"score_gpt":0.2678267071041971,"score_spread":0.2492626823618743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407364035","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01823735,0.0006303877,0.97726405,0.00038224118,0.00003154485,0.00005663823,0.00069995027,0.0019072802,0.00079056225],"genre_scores_gemma":[0.40545294,0.00048471236,0.5867069,0.000606533,0.0001570438,0.00040045448,0.0036550835,0.0002034851,0.0023328215],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99909174,0.0002679599,0.00006703541,0.0002637613,0.00022908898,0.000080474725],"domain_scores_gemma":[0.9989446,0.0004987516,0.00010212555,0.000106264386,0.00026479654,0.0000834027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018898337,0.00096765044,0.0010104814,0.0022584102,0.0005874612,0.0011677942,0.0017996046,0.001309196,0.0013185461],"category_scores_gemma":[0.0024663317,0.0003235546,0.0017034442,0.0014772275,0.0006182442,0.0010351755,0.0018462129,0.0010469077,0.000568713],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003675522,0.00033768037,0.008694075,0.0003198882,0.00036933663,0.00040634643,0.00020122177,0.61492395,0.013913521,0.021353502,0.0054093385,0.33370358],"study_design_scores_gemma":[0.000008286137,0.000026800015,0.00032979346,0.0000102467,0.00001860035,0.000033325054,0.000011327556,0.9904795,0.00069842854,0.0075145024,0.0008631484,0.000006008314],"about_ca_topic_score_codex":0.008467422,"about_ca_topic_score_gemma":0.009922416,"teacher_disagreement_score":0.008467422,"about_ca_system_score_codex":0.0013944302,"about_ca_system_score_gemma":0.0012388575,"threshold_uncertainty_score":0.016836286},"labels":[],"label_agreement":null},{"id":"W4407911294","doi":"10.1186/s12859-025-06082-8","title":"Bacterial network for precise plant stress detection and enhanced crop resilience","year":2025,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Molecular Communication and Nanonetworks","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Key Technologies Research and Development Program","keywords":"Resilience (materials science); Crop; Biology; Computer science; DNA microarray; Stress (linguistics); Computational biology; Biotechnology; Genetics; Agronomy; Gene; Gene expression; Materials science","score_opus":0.008203899709209869,"score_gpt":0.21601200935749648,"score_spread":0.2078081096482866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407911294","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71781456,0.002750865,0.26615384,0.0011240629,0.00022379638,0.00013304375,0.00068019144,0.0011290599,0.00999057],"genre_scores_gemma":[0.93495816,0.0010344664,0.060162533,0.00010526912,0.000009391772,0.00010888234,0.00037006123,0.000060871145,0.0031904664],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9999089,0.000020328604,0.0000035101618,0.000025879583,0.000022549295,0.000018828587],"domain_scores_gemma":[0.9999262,0.000020322752,0.000017974713,0.0000105025,0.000012554081,0.00001248038],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014606243,0.00026839197,0.0002899424,0.00017510427,0.00022788353,0.00039581794,0.00023097379,0.0004912012,0.0018204708],"category_scores_gemma":[0.00036446704,0.0001568142,0.00019495992,0.00015985903,0.00018153629,0.00058148446,0.00042470946,0.00038692262,0.00068326626],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015582815,0.00011864598,0.00222988,0.0003032032,0.000038159593,0.00008446205,0.000047265185,0.05356706,0.90451044,0.013053997,0.0010203187,0.02487076],"study_design_scores_gemma":[0.000036354617,0.00054229086,0.0033684531,0.00004515254,0.00005269763,0.00020969198,0.00012954438,0.5855804,0.37523678,0.008443348,0.026309194,0.000045997014],"about_ca_topic_score_codex":0.00094677304,"about_ca_topic_score_gemma":0.0015616578,"teacher_disagreement_score":0.0018204708,"about_ca_system_score_codex":0.0005034486,"about_ca_system_score_gemma":0.00031056668,"threshold_uncertainty_score":0.0060901046},"labels":[],"label_agreement":null},{"id":"W4408170149","doi":"10.1186/s12859-025-06091-7","title":"GoldPolish-target: targeted long-read genome assembly polishing","year":2025,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"Canadian Institutes of Health Research","keywords":"DNA microarray; Computational biology; Genome; Polishing; Sequence assembly; Biology; Computer science; Genetics; Engineering; Gene; Gene expression; Mechanical engineering","score_opus":0.011122698417002787,"score_gpt":0.24270969500747325,"score_spread":0.23158699659047047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408170149","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06494977,0.0013734951,0.8049518,0.0003125792,0.0002584376,0.0005286516,0.004767155,0.119008526,0.0038495858],"genre_scores_gemma":[0.12565875,0.0005354656,0.8442991,0.0006890997,0.00005845121,0.0005515311,0.011501403,0.011715102,0.0049911435],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986237,0.00014049727,0.00011420192,0.0005765648,0.0004339925,0.00011097144],"domain_scores_gemma":[0.99856156,0.00039924096,0.00029160082,0.00039520315,0.00023924242,0.000113098955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016529432,0.0016839812,0.00091182976,0.0009656703,0.0007259422,0.0013130909,0.0016662412,0.0010829902,0.005613176],"category_scores_gemma":[0.003624722,0.00089382235,0.0016897531,0.0007096126,0.00070002634,0.0010727175,0.0024160533,0.0018405705,0.0054692333],"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":[0.0013569831,0.00020742307,0.007978529,0.0020751636,0.00046001133,0.0006950642,0.0008326903,0.012622091,0.6731577,0.004847562,0.035815928,0.25995088],"study_design_scores_gemma":[0.0001544676,0.0005154054,0.0065701716,0.00013483984,0.00016637544,0.0012648036,0.00012373504,0.08398074,0.8201351,0.0044869543,0.08224021,0.0002271618],"about_ca_topic_score_codex":0.001754693,"about_ca_topic_score_gemma":0.0036047008,"teacher_disagreement_score":0.005613176,"about_ca_system_score_codex":0.0006165151,"about_ca_system_score_gemma":0.0012087396,"threshold_uncertainty_score":0.018777966},"labels":[],"label_agreement":null},{"id":"W4408209964","doi":"10.1186/s12859-025-06083-7","title":"Cross-validation for training and testing co-occurrence network inference algorithms","year":2025,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Inference; Computer science; Microbiome; Data mining; Machine learning; Consistency (knowledge bases); Interpretability; Artificial intelligence; Bioinformatics; Biology","score_opus":0.06368248566846932,"score_gpt":0.3683402510661587,"score_spread":0.3046577653976894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408209964","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09611472,0.003541237,0.88719285,0.00085135776,0.00064592145,0.0011944274,0.0019635055,0.0059491177,0.0025468871],"genre_scores_gemma":[0.55001044,0.0005178459,0.43670127,0.0008346255,0.00027909462,0.0019371179,0.007555506,0.00066357513,0.001500479],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.97577,0.015341706,0.002005843,0.0038877253,0.0021821873,0.0008125667],"domain_scores_gemma":[0.8685097,0.106502935,0.004106244,0.0077974736,0.011629731,0.0014539161],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04929051,0.004119533,0.0029533685,0.0048501026,0.0023601511,0.0021894951,0.0065969676,0.0051919883,0.005426879],"category_scores_gemma":[0.112041906,0.0012327202,0.0030715198,0.003103061,0.0025746357,0.0033968787,0.0031920688,0.007938452,0.0019948257],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00094505656,0.0008244389,0.02310989,0.0005443232,0.0010225868,0.00020277355,0.00019261318,0.8103911,0.0009647647,0.0044276216,0.009478285,0.14789653],"study_design_scores_gemma":[0.00004660943,0.00008293014,0.0006317353,0.000045118362,0.000029362074,0.000026754878,0.000026556392,0.9959253,0.00052186527,0.0022255117,0.00042592507,0.000012308211],"about_ca_topic_score_codex":0.01578156,"about_ca_topic_score_gemma":0.013042373,"teacher_disagreement_score":0.04929051,"about_ca_system_score_codex":0.0025675052,"about_ca_system_score_gemma":0.003943533,"threshold_uncertainty_score":0.26067626},"labels":[],"label_agreement":null},{"id":"W4408787684","doi":"10.1186/s12859-025-06103-6","title":"ChIPbinner: an R package for analyzing broad histone marks binned in uniform windows from ChIP-Seq or CUT&RUN/TAG data","year":2025,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill Genome Centre","funders":"National Cancer Institute; Fonds de Recherche du Québec - Santé; Canadian Institutes of Health Research; National Institutes of Health","keywords":"Computational biology; Chromatin; Chromatin immunoprecipitation; Histone; Biology; Computer science; Genome; DNA microarray; DNA sequencing; Epigenetics; Software; Principal component analysis; Genetics; DNA; Gene; Artificial intelligence; Gene expression","score_opus":0.025867122165030842,"score_gpt":0.2977455756890775,"score_spread":0.27187845352404666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408787684","genre_codex":"software","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":"software","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0044136066,0.0015906335,0.42842838,0.00053249556,0.0004184872,0.0004809508,0.108901195,0.45209324,0.0031411576],"genre_scores_gemma":[0.042466182,0.0018683937,0.5561395,0.0018731699,0.00022886787,0.0058737006,0.11491395,0.2704426,0.0061936104],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99665964,0.001184852,0.00029065704,0.0008635529,0.0007349095,0.00026639833],"domain_scores_gemma":[0.9904811,0.0063571036,0.0010455318,0.0010519234,0.00072950084,0.0003348821],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0059650172,0.0052271453,0.0037779287,0.0031466791,0.0008354445,0.0030429314,0.005550951,0.0017181662,0.051197585],"category_scores_gemma":[0.023829969,0.0025839661,0.0041687833,0.0023949496,0.0013679282,0.0019792807,0.0038710032,0.004406037,0.038833078],"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":[0.0022497473,0.00018211894,0.013041448,0.012233822,0.00565855,0.0013221458,0.0009812056,0.024882127,0.026017535,0.02169724,0.77362776,0.11810636],"study_design_scores_gemma":[0.0015982798,0.00050586445,0.017202308,0.0014611927,0.0022604885,0.0019009997,0.00024271343,0.1425909,0.051071633,0.062106647,0.71819216,0.0008668479],"about_ca_topic_score_codex":0.0039295964,"about_ca_topic_score_gemma":0.004701589,"teacher_disagreement_score":0.051197585,"about_ca_system_score_codex":0.0009506127,"about_ca_system_score_gemma":0.00408933,"threshold_uncertainty_score":0.171273},"labels":[],"label_agreement":null},{"id":"W4411136978","doi":"10.1186/s12859-025-06160-x","title":"SEQSIM: A novel bioinformatics tool for comparisons of promoter regions—a case study of calcium binding protein spermatid associated 1 (CABS1)","year":2025,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Spermatid; DNA microarray; Computational biology; Calcium-binding protein; Bioinformatics; Biology; Calcium; Genetics; Medicine; Gene; Gene expression; Internal medicine","score_opus":0.029866246856013905,"score_gpt":0.2836415420908401,"score_spread":0.25377529523482617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411136978","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15968826,0.0011085301,0.59408134,0.0007736776,0.00033221304,0.00044181535,0.040098097,0.19887924,0.004596809],"genre_scores_gemma":[0.21650031,0.00056781655,0.7123531,0.0004834115,0.0000619063,0.0010111238,0.053441305,0.013680733,0.0019002901],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988637,0.00024570271,0.00012752943,0.00037758905,0.00031304473,0.00007243479],"domain_scores_gemma":[0.9977424,0.0014770305,0.00022929879,0.00015558563,0.0002463884,0.0001492376],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027909481,0.0014295098,0.00091653544,0.0020173206,0.0009821234,0.0010068446,0.002137296,0.0010220634,0.006710347],"category_scores_gemma":[0.004926672,0.0006861786,0.0014062712,0.002035033,0.0006756303,0.001128417,0.0016972875,0.0013455015,0.0021276635],"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":[0.0050447853,0.0011327042,0.061391916,0.007861586,0.0016202022,0.0052974354,0.004977918,0.12280152,0.27969745,0.027963594,0.16459607,0.31761482],"study_design_scores_gemma":[0.0007090943,0.0005752416,0.014962094,0.00030625236,0.00029340005,0.0015411993,0.0010675341,0.7493488,0.087993205,0.025499543,0.11745206,0.00025151158],"about_ca_topic_score_codex":0.0022001665,"about_ca_topic_score_gemma":0.0043043084,"teacher_disagreement_score":0.006710347,"about_ca_system_score_codex":0.00069704826,"about_ca_system_score_gemma":0.0016190582,"threshold_uncertainty_score":0.02244836},"labels":[],"label_agreement":null},{"id":"W4412785840","doi":"10.1186/s12859-025-06229-7","title":"The BeeBiome data portal provides easy access to bee microbiome information","year":2025,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Insect and Pesticide Research","field":"Agricultural and Biological Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Agriculture and Agri-Food Canada; Université de Lausanne","keywords":"Metagenomics; Data science; Microbiome; Biology; World Wide Web; Honey bee; Resource (disambiguation); Computer science; Computational biology; Ecology; Bioinformatics; Gene","score_opus":0.06361257686676958,"score_gpt":0.3188988684488425,"score_spread":0.25528629158207294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412785840","genre_codex":"dataset","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019721796,0.00065091305,0.004067912,0.00035925585,0.00012688019,0.00009611998,0.9698453,0.018118082,0.004763372],"genre_scores_gemma":[0.0081164865,0.000571044,0.01406908,0.0003693677,0.000040273084,0.00029584326,0.9717953,0.0030573744,0.0016852083],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989976,0.00014378992,0.00015242309,0.00023484828,0.0003369588,0.00013438544],"domain_scores_gemma":[0.9972343,0.00084658014,0.00030138082,0.00069736876,0.0004649475,0.00045548243],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002038496,0.0014789659,0.0016577858,0.004283731,0.00075534766,0.0025232704,0.002158189,0.0023074567,0.061026804],"category_scores_gemma":[0.00857096,0.0009038097,0.0009998002,0.0048377616,0.00035021032,0.003602697,0.0052683013,0.0023018497,0.045258973],"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":[0.00095204666,0.00013543478,0.007715686,0.004160531,0.00027068635,0.00041506247,0.00041683682,0.0008268831,0.010146015,0.0035947994,0.9305591,0.040806737],"study_design_scores_gemma":[0.00030048413,0.000059447168,0.014706892,0.00071718777,0.00008581841,0.0002733391,0.0002680303,0.0021807163,0.0047254968,0.007626804,0.96892136,0.00013436931],"about_ca_topic_score_codex":0.0051041655,"about_ca_topic_score_gemma":0.010515434,"teacher_disagreement_score":0.061026804,"about_ca_system_score_codex":0.0007155276,"about_ca_system_score_gemma":0.0016917743,"threshold_uncertainty_score":0.20415503},"labels":[],"label_agreement":null},{"id":"W4413112863","doi":"10.1186/s12859-025-06243-9","title":"Winnow-KAN: single-cell RNA-seq location recovery with small-gene-set spatial transcriptomics","year":2025,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; McGill University","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada","keywords":"RNA-Seq; Transcriptome; Computational biology; Set (abstract data type); DNA microarray; Biology; Gene; Single-cell analysis; Gene expression; Genetics; Computer science; Cell","score_opus":0.01999084210850849,"score_gpt":0.21007172743887745,"score_spread":0.19008088533036896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413112863","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017210396,0.0003246176,0.97006184,0.00033384323,0.0001081071,0.000085349224,0.0006754413,0.010332489,0.0008679425],"genre_scores_gemma":[0.40027586,0.00043374905,0.5823833,0.0007592917,0.00008804783,0.00056926435,0.005344004,0.0012250249,0.008921478],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993044,0.00010943656,0.00003636664,0.00030344244,0.00017287255,0.000073480565],"domain_scores_gemma":[0.99898475,0.00044068208,0.00012519635,0.00023721502,0.0001375767,0.000074675634],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016437992,0.0017048345,0.001046814,0.00082586333,0.0006048137,0.0013885617,0.0031075221,0.0023771701,0.0035156256],"category_scores_gemma":[0.0044771936,0.00094096316,0.0011131575,0.0009235506,0.0011692914,0.0022245538,0.0027223793,0.0031517297,0.0021534069],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042818775,0.00019486257,0.0026685575,0.00028299636,0.00021324214,0.00026173782,0.00015666327,0.70334697,0.027077716,0.010811106,0.01048639,0.24407153],"study_design_scores_gemma":[0.0000076052866,0.000019721385,0.00012926687,0.0000045031743,0.0000056061185,0.000019046365,0.0000071400104,0.98877394,0.0052335695,0.0050690942,0.00071952003,0.0000110731335],"about_ca_topic_score_codex":0.0069588413,"about_ca_topic_score_gemma":0.009365879,"teacher_disagreement_score":0.0069588413,"about_ca_system_score_codex":0.0015536175,"about_ca_system_score_gemma":0.0021968735,"threshold_uncertainty_score":0.013836682},"labels":[],"label_agreement":null},{"id":"W4415995537","doi":"10.1186/s12859-025-06295-x","title":"Graph convolution network based on meta-paths and mutual information for drug-target interaction prediction","year":2025,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Science Foundation of Tianjin City","keywords":"Mutual information; Baseline (sea); Graph; Convolution (computer science); Graph theory; Interaction information","score_opus":0.0263901864289195,"score_gpt":0.2844000139566388,"score_spread":0.2580098275277193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415995537","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18747681,0.0015583036,0.80516005,0.0008180535,0.000060519444,0.000056416677,0.0006982404,0.001372524,0.0027990222],"genre_scores_gemma":[0.9295497,0.00045936526,0.06704658,0.00015562394,0.00003521603,0.0000706308,0.00073586067,0.000056941506,0.0018900728],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997634,0.000054306336,0.000013043667,0.00007180301,0.00005895656,0.00003842759],"domain_scores_gemma":[0.99925476,0.0003965881,0.00013845017,0.000060239057,0.000102734484,0.00004724873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006271211,0.0007584384,0.00066217466,0.0011735058,0.00032649338,0.0004850941,0.0009470323,0.0008332375,0.0012222624],"category_scores_gemma":[0.0023172386,0.00038950544,0.00079579366,0.00093040423,0.0005422051,0.0013103518,0.00078766636,0.0010198851,0.0002144761],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014402656,0.00007277329,0.005290229,0.00006821517,0.00010855522,0.00011250728,0.000043977634,0.90684175,0.0028851542,0.008692249,0.0015297263,0.07421084],"study_design_scores_gemma":[0.0000015171206,0.000008905208,0.00026033397,0.0000022376519,0.0000076891665,0.000009087241,0.0000014878009,0.99697256,0.00026002928,0.0023819918,0.00009174935,0.000002427878],"about_ca_topic_score_codex":0.011686102,"about_ca_topic_score_gemma":0.014768052,"teacher_disagreement_score":0.011686102,"about_ca_system_score_codex":0.0013232782,"about_ca_system_score_gemma":0.0010795385,"threshold_uncertainty_score":0.023236156},"labels":[],"label_agreement":null},{"id":"W4416612861","doi":"10.1186/s12859-025-06276-0","title":"CLEP-GAN: an innovative approach to subject-independent ECG reconstruction from PPG signals","year":2025,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"ECG Monitoring and Analysis","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; Fields Institute for Research in Mathematical Sciences; Canada Research Chairs","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Normal Sinus Rhythm; Sinus rhythm; RR interval; Pattern recognition (psychology); Atrial fibrillation; Electrocardiography","score_opus":0.028459659907360397,"score_gpt":0.2914696153237213,"score_spread":0.2630099554163609,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416612861","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0074499263,0.00049115013,0.9878996,0.0003000537,0.00007352123,0.00006336433,0.00031916922,0.0015908105,0.0018124018],"genre_scores_gemma":[0.42864946,0.001070659,0.5552327,0.0015093652,0.00032176488,0.00037633305,0.0035131057,0.0009337777,0.008392914],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995733,0.00016751101,0.000017255226,0.00010781248,0.00010339894,0.000030685584],"domain_scores_gemma":[0.9992163,0.00044848325,0.000054387503,0.00013882178,0.000097190336,0.000044683147],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010761895,0.0009900309,0.00065275433,0.00044873313,0.00015741705,0.00057519035,0.0014966191,0.0010011795,0.0022586489],"category_scores_gemma":[0.0027147736,0.00040814737,0.000885867,0.00037844718,0.00049734476,0.00057816855,0.0012474421,0.0019791564,0.00088061637],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024984343,0.00014024993,0.002190997,0.00021472579,0.00019653488,0.00042175374,0.000101869,0.7047236,0.017443763,0.009116987,0.016023314,0.2491764],"study_design_scores_gemma":[0.0000086367845,0.000028805456,0.00023972303,0.000012238303,0.000008733535,0.0001329953,0.000004851496,0.99237305,0.002123865,0.003260222,0.0017979477,0.000008815844],"about_ca_topic_score_codex":0.0014013428,"about_ca_topic_score_gemma":0.0026476446,"teacher_disagreement_score":0.0022586489,"about_ca_system_score_codex":0.00036925208,"about_ca_system_score_gemma":0.0005501193,"threshold_uncertainty_score":0.0075559616},"labels":[],"label_agreement":null}]}