{"meta":{"query_hash":"d9fbe9c57fec","filters":{"venue":"Computer applications in the biosciences"},"cohort_total":19,"direct_labels_cover":0,"predictions_cover":19,"exported":19,"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/d9fbe9c57fec","api":"https://metacan.xera.ac/api/v1/cohort?venue=Computer+applications+in+the+biosciences"},"results":[{"id":"W2096149709","doi":"10.1093/bioinformatics/bti1037","title":"Reversal distance for partially ordered genomes","year":2005,"lang":"en","type":"article","venue":"Computer applications in the biosciences","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Genome; Position (finance); Chromosome; Computer science; Representation (politics); Order (exchange); Gene; Mutation; Genetics; Computational biology; Biology; Algorithm","score_opus":0.014496985183509515,"score_gpt":0.27133429649502283,"score_spread":0.2568373113115133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096149709","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07748479,0.001390144,0.9173352,0.0022032273,0.00010316981,0.0010418409,0.000024694624,0.000015725174,0.0004012216],"genre_scores_gemma":[0.9251399,0.00012518081,0.07307196,0.00045973883,0.0005482941,0.00042839747,0.000049113933,0.0000059975214,0.00017141984],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993659,0.00002069285,0.00011856325,0.00025247387,0.000087158296,0.00015516499],"domain_scores_gemma":[0.99960196,0.000020221687,0.00004054664,0.00028527554,0.00003149695,0.000020493555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024484773,0.00007053955,0.00005444142,0.000026301384,0.00012915776,0.000044298165,0.00057400984,0.00002963359,0.0000023879584],"category_scores_gemma":[0.0000050211706,0.000050232637,0.000034877077,0.00017824199,0.00011804232,0.0000045178135,0.000057713558,0.000024373652,0.000005978916],"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":[0.000069126974,0.0012923183,0.028919587,0.00009310161,0.000090808055,8.1985576e-7,0.0033873457,0.0065757614,0.18382594,0.032230977,0.034022648,0.70949155],"study_design_scores_gemma":[0.00023281139,0.000093832474,0.0044442043,0.0000024874666,0.0000060396956,0.0000020552518,0.00011893387,0.0041493904,0.004370305,0.00050123624,0.985938,0.00014070449],"about_ca_topic_score_codex":0.000001754161,"about_ca_topic_score_gemma":0.00004612869,"teacher_disagreement_score":0.9519153,"about_ca_system_score_codex":0.000009264976,"about_ca_system_score_gemma":0.000029917106,"threshold_uncertainty_score":0.20484275},"labels":[],"label_agreement":null},{"id":"W2099398646","doi":"10.1093/bioinformatics/bti170","title":"BIAS: Bioinformatics Integrated Application Software","year":2004,"lang":"en","type":"article","venue":"Computer applications in the biosciences","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Software; Object (grammar); Data mining; Relational database; Bioinformatics; Data science; Software engineering; Artificial intelligence; Programming language; Biology","score_opus":0.013024605203504892,"score_gpt":0.24295220211584717,"score_spread":0.22992759691234227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099398646","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049349215,0.00014117586,0.9493681,0.00028577982,0.00007288201,0.0004635899,0.000011469717,0.00002043187,0.00028731098],"genre_scores_gemma":[0.87099004,0.00008523864,0.12712783,0.0011521123,0.00020002954,0.00021526302,0.00020387332,0.0000069676908,0.000018650946],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99925154,0.000017725019,0.0002552872,0.00017912147,0.00012234328,0.00017400621],"domain_scores_gemma":[0.9993637,0.00002003517,0.000100181824,0.00043839918,0.00004461158,0.000033025],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003521589,0.000109384455,0.00007509383,0.000059312526,0.00017505341,0.00008424817,0.0007512162,0.00007654867,9.563033e-7],"category_scores_gemma":[0.000009626289,0.000071164824,0.00004146829,0.00046925838,0.00018549741,0.00000999885,0.000100496676,0.000082928666,0.000022352244],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034240704,0.0010221174,0.01402106,0.00013904668,0.00006881813,9.2764736e-7,0.0072316583,0.0505727,0.009758146,0.07646255,0.009578618,0.8311101],"study_design_scores_gemma":[0.002587136,0.00104683,0.023829233,0.00012577201,0.000059818172,0.00014958422,0.005368883,0.11545319,0.018802237,0.06630053,0.7642174,0.0020594303],"about_ca_topic_score_codex":0.000021907907,"about_ca_topic_score_gemma":0.000046630405,"teacher_disagreement_score":0.82905066,"about_ca_system_score_codex":0.000018132812,"about_ca_system_score_gemma":0.00007560769,"threshold_uncertainty_score":0.29020175},"labels":[],"label_agreement":null},{"id":"W2103184043","doi":"10.1093/bioinformatics/bti321","title":"MtbRegList, a database dedicated to the analysis of transcriptional regulation in Mycobacterium tuberculosis","year":2005,"lang":"en","type":"article","venue":"Computer applications in the biosciences","topic":"Tuberculosis Research and Epidemiology","field":"Medicine","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":"Université de Sherbrooke","funders":"Fonds Québécois de la Recherche sur la Nature et les Technologies; U.S. National Library of Medicine; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Mycobacterium tuberculosis; Tuberculosis; Database; Computational biology; Biology; Computer science; Medicine","score_opus":0.034468796006127594,"score_gpt":0.3397371658698042,"score_spread":0.30526836986367656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103184043","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8733548,0.00028603277,0.059745822,0.065202005,0.00004208635,0.0009997207,0.00007507416,0.000019847499,0.00027461833],"genre_scores_gemma":[0.9916072,0.00007738944,0.0058370787,0.0019639682,0.00012578104,0.00022790924,0.00014437681,0.000002715988,0.000013612832],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986045,0.000193858,0.00037252138,0.0002962922,0.00031750937,0.00021533534],"domain_scores_gemma":[0.99897563,0.00032603487,0.00005776464,0.0005016293,0.00007095685,0.00006797612],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001390833,0.000083778024,0.00021890223,0.00057653396,0.00009422103,0.000019021052,0.0005187095,0.00004124226,0.000038616705],"category_scores_gemma":[0.00006694492,0.000045552366,0.00008623504,0.003895821,0.00024278258,0.00009009358,0.000055397635,0.0001302856,0.000012365731],"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":[0.0003108788,0.0033718518,0.64999455,0.00013504169,0.00067164225,0.0000041633075,0.011964015,0.034507375,0.09005664,0.03992225,0.020772945,0.14828864],"study_design_scores_gemma":[0.00014074074,0.000040927862,0.90327275,0.000013958556,0.00008619097,0.000004029448,0.0001194076,0.078491166,0.00024323785,0.00007961858,0.017457712,0.000050275878],"about_ca_topic_score_codex":0.00027313994,"about_ca_topic_score_gemma":0.00088535796,"teacher_disagreement_score":0.2532782,"about_ca_system_score_codex":0.0000560976,"about_ca_system_score_gemma":0.000056648332,"threshold_uncertainty_score":0.1871813},"labels":[],"label_agreement":null},{"id":"W2107500667","doi":"10.1093/bioinformatics/bti397","title":"A robust neural networks approach for spatial and intensity-dependent normalization of cDNA microarray data","year":2005,"lang":"en","type":"article","venue":"Computer applications in the biosciences","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":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Normalization (sociology); Sampling bias; Computer science; Microarray; Computational biology; Pattern recognition (psychology); Biology; Biological system; Statistics; Sample size determination; Artificial intelligence; Mathematics; Gene expression; Gene; Genetics","score_opus":0.04246975923685588,"score_gpt":0.2754001957445745,"score_spread":0.23293043650771866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107500667","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03681192,0.0003239201,0.9621029,0.00028807536,0.000047683247,0.0003686033,0.00001336425,0.0000037892273,0.0000397501],"genre_scores_gemma":[0.97527796,0.00006736567,0.02384873,0.0002118577,0.00023735267,0.000077943296,0.0002638343,0.000003083179,0.000011845776],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99937034,0.000029031251,0.00014258747,0.0003000561,0.000072129544,0.00008584443],"domain_scores_gemma":[0.9994227,0.0000118850785,0.00007890789,0.00042048373,0.000048021215,0.00001794486],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028378228,0.000060323873,0.000060777056,0.000035738227,0.00009229792,0.000031777723,0.000567134,0.000042308766,4.5529555e-7],"category_scores_gemma":[0.000006381622,0.0000425589,0.000014585875,0.0001336419,0.00012392359,0.000009244536,0.0001537684,0.00003134271,7.667787e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016910583,0.0010513832,0.035278697,0.00010951765,0.000039561583,9.446277e-8,0.0014504818,0.1675111,0.3135206,0.0024689313,0.013709252,0.46469125],"study_design_scores_gemma":[0.00022612594,0.00006250352,0.008867825,0.0000035221585,0.000009087417,0.0000054565594,0.0002253476,0.97067565,0.009448414,0.000024062727,0.010353765,0.00009821821],"about_ca_topic_score_codex":0.000010529785,"about_ca_topic_score_gemma":0.000023009157,"teacher_disagreement_score":0.9384661,"about_ca_system_score_codex":0.000004010404,"about_ca_system_score_gemma":0.000016760774,"threshold_uncertainty_score":0.17355014},"labels":[],"label_agreement":null},{"id":"W2108149347","doi":"10.1093/bioinformatics/bti330","title":"Recoverable one-dimensional encoding of three-dimensional protein structures","year":2005,"lang":"en","type":"article","venue":"Computer applications in the biosciences","topic":"Protein Structure and Dynamics","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":"Institute of Genetics; Ministry of Education, Culture, Sports, Science and Technology","keywords":"Protein structure; Protein secondary structure; Sequence (biology); Protein structure prediction; Computer science; Protein tertiary structure; Set (abstract data type); Structural bioinformatics; Structural motif; Biological system; Algorithm; Crystallography; Biology; Chemistry; Genetics","score_opus":0.013849647384956375,"score_gpt":0.25164552140407603,"score_spread":0.23779587401911967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2108149347","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95887095,0.00043600425,0.03939516,0.00039209356,0.000057477017,0.00051525433,0.000015077537,0.000008253595,0.00030971857],"genre_scores_gemma":[0.9368061,0.0000044110775,0.062630534,0.0002475121,0.00020086854,0.000059659076,0.000025047668,0.0000038064302,0.000022099757],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99917907,0.000033716682,0.00018595073,0.0002655334,0.00019415029,0.00014157344],"domain_scores_gemma":[0.99950755,0.000023609684,0.00008589,0.00031129256,0.000048448113,0.000023198238],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002418996,0.0000919797,0.00008791536,0.000050026934,0.00013444753,0.000022393786,0.0005050365,0.00006408588,0.0000071569766],"category_scores_gemma":[0.000009709639,0.000063179185,0.000041604046,0.00021311404,0.00018877497,0.000008471884,0.00012414569,0.00007103891,0.0000018362041],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042029584,0.0002663061,0.0050721173,0.00003068064,0.000031168805,4.920113e-7,0.00016713301,0.020796346,0.900361,0.03654314,0.00091671594,0.03577286],"study_design_scores_gemma":[0.0012753953,0.0008073999,0.06447357,0.00011055114,0.00004079296,0.00009410836,0.00009766373,0.065665916,0.7237163,0.10018615,0.04241393,0.0011181732],"about_ca_topic_score_codex":0.000020384396,"about_ca_topic_score_gemma":0.00007479432,"teacher_disagreement_score":0.17664467,"about_ca_system_score_codex":0.000009418554,"about_ca_system_score_gemma":0.00006570566,"threshold_uncertainty_score":0.25763726},"labels":[],"label_agreement":null},{"id":"W2108926360","doi":"10.1093/bioinformatics/bti1050","title":"Search for folding nuclei in native protein structures","year":2005,"lang":"en","type":"article","venue":"Computer applications in the biosciences","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Executable; Computer science; Protein folding; Folding (DSP implementation); Simple (philosophy); Algorithm; Graph; Theoretical computer science; Topology (electrical circuits); Physics; Mathematics; Combinatorics; Engineering","score_opus":0.014176281649470424,"score_gpt":0.296746002949353,"score_spread":0.28256972129988256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2108926360","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8214436,0.00021063718,0.17649049,0.00052731787,0.00002795414,0.0010654062,0.000011578499,0.0000063778684,0.00021665104],"genre_scores_gemma":[0.960841,0.000008567871,0.03839782,0.00021882248,0.00020484606,0.00029417302,0.000015958645,0.0000039094457,0.000014896978],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99934083,0.000034713772,0.000119443874,0.00025226153,0.00009380748,0.00015895425],"domain_scores_gemma":[0.9996895,0.000023942435,0.0000308203,0.00021011978,0.000029075163,0.00001652736],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027420907,0.00007376099,0.00005960177,0.00006266978,0.000113229304,0.000042963904,0.0005461828,0.000051578787,9.1103135e-7],"category_scores_gemma":[0.000008210748,0.000050352886,0.000027523318,0.00025170684,0.00012920625,0.0000064538417,0.000081651044,0.000059576967,6.063651e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007015953,0.00030965207,0.014456487,0.00007141736,0.000025182004,8.350718e-7,0.0037587709,0.009881844,0.45154488,0.24847744,0.00074714125,0.2706562],"study_design_scores_gemma":[0.001871816,0.000762179,0.06600282,0.000058256992,0.000014084302,0.000025492078,0.00181174,0.07761411,0.6443381,0.06446171,0.1419542,0.0010855237],"about_ca_topic_score_codex":0.00001026207,"about_ca_topic_score_gemma":0.000059975104,"teacher_disagreement_score":0.26957065,"about_ca_system_score_codex":0.000014792496,"about_ca_system_score_gemma":0.000038322676,"threshold_uncertainty_score":0.2053331},"labels":[],"label_agreement":null},{"id":"W2114368649","doi":"10.1093/bioinformatics/bti1045","title":"GenXHC: a probabilistic generative model for cross-hybridization compensation in high-density genome-wide microarray data","year":2005,"lang":"en","type":"article","venue":"Computer applications in the biosciences","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Generative model; Computer science; Probabilistic logic; Generative grammar; Genome; Compensation (psychology); Computational biology; Statistical model; Microarray; Data mining; Artificial intelligence; Biology; Genetics; Gene; Gene expression","score_opus":0.04346260838480358,"score_gpt":0.31504882174478693,"score_spread":0.27158621335998334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114368649","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3822097,0.00010050254,0.61627084,0.0006303068,0.00003952845,0.00068282796,0.000039396782,0.00000674528,0.000020168096],"genre_scores_gemma":[0.95653695,0.00004759501,0.041356638,0.0005919743,0.00021675878,0.00036027946,0.00082743686,0.000006296738,0.0000560663],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988448,0.00006793327,0.00025375624,0.0005540453,0.00012369189,0.00015579171],"domain_scores_gemma":[0.9990366,0.000037317404,0.000108716165,0.0006978556,0.00009294049,0.000026570891],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005293801,0.00010606095,0.00008843435,0.00007843462,0.00018942203,0.00009868706,0.00088887673,0.000060020822,0.0000012900919],"category_scores_gemma":[0.000031719082,0.0000823168,0.000022310564,0.0003140318,0.00015770929,0.000023702787,0.00014245139,0.000051490762,0.0000024887597],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007834867,0.00080213376,0.02207671,0.000054931203,0.00001616581,1.8897586e-7,0.0022497429,0.41006196,0.52724195,0.006708571,0.005572909,0.025136411],"study_design_scores_gemma":[0.00050779944,0.000052075644,0.07807157,0.000007800623,0.000008081193,0.000002151013,0.00010087127,0.88131225,0.02074239,0.0020299174,0.01692748,0.00023758781],"about_ca_topic_score_codex":0.000011911447,"about_ca_topic_score_gemma":0.0002294039,"teacher_disagreement_score":0.5749142,"about_ca_system_score_codex":0.000038927956,"about_ca_system_score_gemma":0.0001085443,"threshold_uncertainty_score":0.3356782},"labels":[],"label_agreement":null},{"id":"W2117003089","doi":"10.1093/bioinformatics/bti280","title":"Computational identification of human mitochondrial proteins based on homology to yeast mitochondrially targeted proteins","year":2005,"lang":"en","type":"article","venue":"Computer applications in the biosciences","topic":"Machine Learning in Bioinformatics","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":"Hospital for Sick Children","funders":"Canadian Institutes of Health Research; Hospital for Sick Children","keywords":"Biology; Human genome; Computational biology; Saccharomyces cerevisiae; Homology (biology); Genetics; Human proteins; Gene; Genome; Human mitochondrial genetics; Mitochondrion; UniGene; Expressed sequence tag","score_opus":0.008637087028099883,"score_gpt":0.2773267700318632,"score_spread":0.2686896830037633,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117003089","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26480561,0.000013377761,0.73112553,0.0014585401,0.00014408698,0.0020243067,0.00004002636,0.000021479735,0.00036705518],"genre_scores_gemma":[0.8750894,5.1147305e-7,0.12346433,0.0004856781,0.00036392268,0.00040587693,0.00014641417,0.000006905703,0.00003698076],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99872226,0.00011740673,0.0004125753,0.00030556764,0.00027934386,0.00016282292],"domain_scores_gemma":[0.9991548,0.000035133035,0.00019978627,0.00047000975,0.00010091841,0.000039375514],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000349312,0.00012284247,0.00011072051,0.00016238088,0.00018775075,0.000051996765,0.000842194,0.0000763003,0.0000058330356],"category_scores_gemma":[0.000051421426,0.00009483609,0.00005195672,0.00042344708,0.00019974467,0.000008643574,0.000081692866,0.000097354416,0.000018316543],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000634388,0.00096013525,0.002019543,0.000047435085,0.000016097307,2.9167788e-7,0.0011920746,0.31204507,0.66271394,0.00950203,0.0027660702,0.0086739],"study_design_scores_gemma":[0.0026735796,0.0036650242,0.093410976,0.00009881986,0.000039177547,0.000021084148,0.00032848355,0.53288895,0.29377565,0.0024920502,0.06940371,0.0012025295],"about_ca_topic_score_codex":0.000010464669,"about_ca_topic_score_gemma":0.000026505235,"teacher_disagreement_score":0.61028373,"about_ca_system_score_codex":0.000019187022,"about_ca_system_score_gemma":0.000087157125,"threshold_uncertainty_score":0.38673034},"labels":[],"label_agreement":null},{"id":"W2120815702","doi":"10.1093/bioinformatics/bti1040","title":"ExonHunter: a comprehensive approach to gene finding","year":2005,"lang":"en","type":"article","venue":"Computer applications in the biosciences","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Annotation; Hidden Markov model; Gene prediction; Probabilistic logic; Set (abstract data type); Sequence (biology); Markov chain; Extension (predicate logic); Data mining; Artificial intelligence; Machine learning; Gene; Genome; Genetics; Biology","score_opus":0.02161260978141782,"score_gpt":0.26534300760899315,"score_spread":0.24373039782757533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120815702","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23676339,0.0003139538,0.7584493,0.00060824235,0.00008227594,0.0006138367,0.000008882598,0.000011410558,0.0031486922],"genre_scores_gemma":[0.91011333,0.000026812311,0.08720454,0.0020579263,0.00039821508,0.00012229195,0.000030363992,0.0000038320527,0.000042696633],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99933946,0.00002179816,0.00015519433,0.00022203889,0.00009074963,0.00017076524],"domain_scores_gemma":[0.9995515,0.0000146001985,0.000040348805,0.00033099315,0.000024065528,0.00003853587],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017670673,0.00008540764,0.00006747269,0.000049683837,0.00014339911,0.000067628076,0.00067482056,0.000043397893,9.2995396e-7],"category_scores_gemma":[0.0000016035186,0.00005905487,0.000033278433,0.00026336816,0.00008650836,0.0000045669635,0.00015897558,0.000052935407,0.000016406579],"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":[0.000051015337,0.0015894354,0.0045881066,0.000080974554,0.000092109585,9.265168e-7,0.014213597,0.092097685,0.15992132,0.040175576,0.07363579,0.61355346],"study_design_scores_gemma":[0.00041220183,0.0002067157,0.013735722,0.000012910436,0.000010976054,0.00005119868,0.0010983377,0.06666889,0.008390477,0.0006943238,0.90818864,0.00052961207],"about_ca_topic_score_codex":0.000002618248,"about_ca_topic_score_gemma":0.0000041342046,"teacher_disagreement_score":0.8345528,"about_ca_system_score_codex":0.0000092683695,"about_ca_system_score_gemma":0.000018914501,"threshold_uncertainty_score":0.24081877},"labels":[],"label_agreement":null},{"id":"W2121105117","doi":"10.1093/bioinformatics/bti406","title":"Modularized learning of genetic interaction networks from biological annotations and mRNA expression data","year":2005,"lang":"en","type":"article","venue":"Computer applications in the biosciences","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":59,"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":"Expression (computer science); Computer science; Messenger RNA; Computational biology; Annotation; Artificial intelligence; Biology; Genetics; Gene; Programming language","score_opus":0.02539486015560128,"score_gpt":0.27828838538913875,"score_spread":0.2528935252335375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121105117","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44698662,0.000569954,0.55208635,0.00011759841,0.000037989787,0.00014330607,0.000009510952,0.000004082688,0.000044602933],"genre_scores_gemma":[0.95592,0.00033264476,0.043204833,0.00011247829,0.00021178476,0.000019343142,0.00019337484,0.0000021530554,0.0000034032792],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993918,0.000053391166,0.00019310114,0.00021643829,0.0000566468,0.00008865037],"domain_scores_gemma":[0.99946815,0.000053390257,0.00009772218,0.0003424054,0.000018824641,0.000019517596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021244625,0.0000641241,0.00006797441,0.000026372252,0.00011386938,0.000037328726,0.0005041048,0.000060513667,0.000002000181],"category_scores_gemma":[0.000008361762,0.000042401796,0.00001504638,0.000117797485,0.00014156799,0.000011000857,0.00026407992,0.00007995635,7.9226976e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055224715,0.0004147773,0.050252378,0.000015459786,0.00004358987,3.697526e-7,0.0018801945,0.14369951,0.14923334,0.0015008138,0.0026475927,0.65025675],"study_design_scores_gemma":[0.00020489885,0.00008159496,0.0367886,0.000013896181,0.0000073429032,0.000004262779,0.00032620426,0.9394178,0.0011229048,0.00048447598,0.021426322,0.000121701356],"about_ca_topic_score_codex":0.000011379511,"about_ca_topic_score_gemma":0.000010264993,"teacher_disagreement_score":0.7957183,"about_ca_system_score_codex":0.0000029985638,"about_ca_system_score_gemma":0.0000106096995,"threshold_uncertainty_score":0.17290951},"labels":[],"label_agreement":null},{"id":"W2121194346","doi":"10.1093/bioinformatics/bti427","title":"NodMutDB: a database for genes and mutants involved in symbiosis","year":2005,"lang":"en","type":"article","venue":"Computer applications in the biosciences","topic":"Legume Nitrogen Fixing Symbiosis","field":"Agricultural and Biological Sciences","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 Waterloo","funders":"","keywords":"Functional genomics; Mutant; Gene; Computational biology; Function (biology); Biology; Schema (genetic algorithms); Symbiosis; Genomics; Database; Computer science; Genetics; Genome; Information retrieval","score_opus":0.028458525071656963,"score_gpt":0.25355197669410756,"score_spread":0.2250934516224506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121194346","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99548763,0.0005144281,0.00023502791,0.0029715095,0.000034994893,0.000639781,0.000054217227,0.000027669661,0.000034736222],"genre_scores_gemma":[0.9917539,0.000047585912,0.00704738,0.0006300703,0.00018261746,0.00030667745,0.000025252368,6.506557e-7,0.0000058834526],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9990262,0.000051441188,0.0001947626,0.00036409224,0.00013632244,0.00022720377],"domain_scores_gemma":[0.9993812,0.00039398074,0.000053554548,0.000108696,0.000025062,0.000037530153],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000508713,0.00010325182,0.00010681387,0.000035938887,0.00021695471,0.00010512696,0.0006849131,0.000042533873,0.0000059297536],"category_scores_gemma":[0.000013886827,0.000037682163,0.000031386597,0.000768777,0.00016790217,0.00017276444,0.000109251916,0.000058052596,0.0000057270204],"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":[0.000014066572,0.00064156315,0.21019287,0.000023765686,0.000008003003,9.2968395e-7,0.0011573745,0.0000050068857,0.34168497,0.0057348837,0.0007901278,0.43974644],"study_design_scores_gemma":[0.0009578142,0.0004156559,0.846499,0.00011025677,0.0000364859,0.00002394737,0.0026905336,0.01840216,0.07659052,0.00623338,0.046951253,0.0010889668],"about_ca_topic_score_codex":0.00012501008,"about_ca_topic_score_gemma":0.0011357502,"teacher_disagreement_score":0.63630617,"about_ca_system_score_codex":0.000020764237,"about_ca_system_score_gemma":0.0000087844555,"threshold_uncertainty_score":0.16686621},"labels":[],"label_agreement":null},{"id":"W2127325419","doi":"10.1093/bioinformatics/bti439","title":"pFind: a novel database-searching software system for automated peptide and protein identification via tandem mass spectrometry","year":2005,"lang":"en","type":"article","venue":"Computer applications in the biosciences","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":181,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Usability; Software; XML; Database; Tandem mass spectrometry; Proteomics; Identification (biology); Database search engine; Tandem mass tag; Data mining; Mass spectrometry; Information retrieval; Quantitative proteomics; Programming language; Operating system; Chemistry; Search engine; Chromatography; Biology","score_opus":0.01994045347924747,"score_gpt":0.2977135505692231,"score_spread":0.27777309708997566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127325419","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040917017,0.000071438524,0.95677346,0.0003884483,0.00001059525,0.0011753188,0.00009885269,0.00043626424,0.0001285992],"genre_scores_gemma":[0.44440582,0.0000063399816,0.55337656,0.00002745415,0.00011078741,0.0019681146,0.000055595145,0.000008906731,0.00004040328],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987743,0.000014364432,0.00031753333,0.00047098045,0.00019096749,0.0002318756],"domain_scores_gemma":[0.9990196,0.00016262913,0.00017314938,0.00054545456,0.000054064683,0.000045087723],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000527897,0.00013494659,0.000121676065,0.00011275682,0.00048710656,0.00016817957,0.0007846344,0.00005738823,0.0000025269546],"category_scores_gemma":[0.000017861246,0.00010620231,0.000035492914,0.00049063296,0.00016662208,0.00019700921,0.00010303238,0.00014208465,0.0000042077186],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000050052963,0.00019416121,0.0007010991,0.00021139083,0.000008925666,1.976033e-7,0.00032960842,0.00033055554,0.9520794,0.032227796,0.0002059554,0.013705904],"study_design_scores_gemma":[0.00065204815,0.00004653412,0.0016137498,0.00024073606,0.000033360353,0.000050657607,0.0008353201,0.6595482,0.30703732,0.009716451,0.019561362,0.0006642634],"about_ca_topic_score_codex":0.000013176151,"about_ca_topic_score_gemma":0.0000069015327,"teacher_disagreement_score":0.65921766,"about_ca_system_score_codex":0.00010236259,"about_ca_system_score_gemma":0.000033291202,"threshold_uncertainty_score":0.43308043},"labels":[],"label_agreement":null},{"id":"W2144014661","doi":"10.1093/bioinformatics/bti273","title":"Online Predicted Human Interaction Database","year":2005,"lang":"en","type":"article","venue":"Computer applications in the biosciences","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":620,"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":"","keywords":"Drosophila melanogaster; Gene ontology; Computer science; Ontology; Visualization; Computational biology; Artificial intelligence; Biology; Gene; Gene expression; Genetics","score_opus":0.017661479102434197,"score_gpt":0.2957764760332367,"score_spread":0.2781149969308025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144014661","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73926896,0.0002333225,0.25739315,0.0010737287,0.00015976126,0.00050904125,0.00007031081,0.000022055061,0.0012696406],"genre_scores_gemma":[0.98733026,0.000038473027,0.0108885905,0.0006917875,0.00058260426,0.00003776597,0.0003892972,0.0000027661688,0.000038464048],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994933,0.000020452917,0.00015277806,0.00015536284,0.00007241977,0.00010569412],"domain_scores_gemma":[0.9995862,0.000010880948,0.00005244188,0.00030999264,0.00001929446,0.000021173464],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001828377,0.00006228572,0.000042288244,0.000035341218,0.00013445152,0.000043428026,0.00047067527,0.000034983135,0.000004066729],"category_scores_gemma":[0.0000022487545,0.000042421412,0.000021806614,0.00016153447,0.00009806691,0.000008312377,0.0001023024,0.00006566379,0.0000048120523],"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":[0.00004238245,0.0039177216,0.012614848,0.00007671369,0.00008179749,0.0000013803606,0.004040605,0.01263816,0.20062591,0.033460103,0.116097674,0.6164027],"study_design_scores_gemma":[0.00050942594,0.00025526667,0.021806644,0.000026223015,0.000015527163,0.000030395826,0.0007798728,0.10503834,0.00585267,0.0009407856,0.8643628,0.00038207383],"about_ca_topic_score_codex":0.000006714523,"about_ca_topic_score_gemma":0.00007765475,"teacher_disagreement_score":0.7482651,"about_ca_system_score_codex":0.000007354082,"about_ca_system_score_gemma":0.000015123834,"threshold_uncertainty_score":0.1729895},"labels":[],"label_agreement":null},{"id":"W2156336405","doi":"10.1093/bioinformatics/bti1041","title":"Multi-way clustering of microarray data using probabilistic sparse matrix factorization","year":2005,"lang":"en","type":"article","venue":"Computer applications in the biosciences","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":97,"is_retracted":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; University of Toronto; Microsoft","keywords":"Cluster analysis; Probabilistic logic; Computer science; Data mining; Sparse matrix; Non-negative matrix factorization; Noise (video); Hierarchical clustering; Matrix decomposition; Generative model; Matrix (chemical analysis); Algorithm; Artificial intelligence; Generative grammar; Eigenvalues and eigenvectors","score_opus":0.07690284190076663,"score_gpt":0.3453961809586526,"score_spread":0.26849333905788597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156336405","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14612775,0.00023914468,0.85306716,0.00012814759,0.00007860534,0.0003090916,0.000018111576,0.000005916729,0.000026076392],"genre_scores_gemma":[0.91784215,0.000037611117,0.08179219,0.000050992076,0.00014833604,0.0000255926,0.00007865622,0.0000038117419,0.000020653035],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999268,0.000047154208,0.0001858236,0.00030402205,0.00010069944,0.00009430664],"domain_scores_gemma":[0.9991813,0.000012266638,0.000104072904,0.0006446529,0.00003923272,0.000018491344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025223652,0.000068434485,0.000059184145,0.00005130272,0.00008895208,0.00003137938,0.0008499566,0.000041013744,0.000002187848],"category_scores_gemma":[0.000012270564,0.00004907874,0.000016863181,0.0002752618,0.000115927454,0.000011747614,0.0001801862,0.000032961536,0.0000013922707],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000036401602,0.00013525719,0.0021687674,0.000015280351,0.0000029434632,2.3797973e-8,0.0002557527,0.0093017435,0.978449,0.00012812582,0.00024621212,0.009293277],"study_design_scores_gemma":[0.00051651086,0.00007971248,0.026880734,0.000043262793,0.000022659815,0.000010731076,0.0006092904,0.7785661,0.10920319,0.00010809634,0.08361028,0.00034939838],"about_ca_topic_score_codex":0.000010130926,"about_ca_topic_score_gemma":0.00003157344,"teacher_disagreement_score":0.86924577,"about_ca_system_score_codex":0.000012215686,"about_ca_system_score_gemma":0.000045045163,"threshold_uncertainty_score":0.20013729},"labels":[],"label_agreement":null},{"id":"W2159605359","doi":"10.1093/bioinformatics/bti483","title":"Ensemble dependence model for classification and prediction of cancer and normal gene expression data","year":2005,"lang":"en","type":"article","venue":"Computer applications in the biosciences","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":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Ensemble forecasting; Ensemble learning; Computational biology; Cancer; Expression (computer science); Gene; Gene expression; Artificial intelligence; Genetics; Biology; Programming language","score_opus":0.06174760510571803,"score_gpt":0.32438642513740557,"score_spread":0.26263882003168754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159605359","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3056756,0.0011196955,0.6922686,0.00044052268,0.000028656099,0.0003635535,0.00007275536,0.000004488417,0.0000261298],"genre_scores_gemma":[0.9667563,0.0008220775,0.031862088,0.000087785316,0.000111626694,0.00024658392,0.000085466454,0.000002854276,0.000025231737],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999366,0.000018075634,0.00013823596,0.00031472574,0.00008807405,0.0000748913],"domain_scores_gemma":[0.9994646,0.000016666598,0.000080384714,0.0003763022,0.000040474326,0.000021575677],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000246378,0.0000563536,0.000048465605,0.000037080103,0.0001122105,0.000023302462,0.00036534452,0.000045253862,3.4671072e-7],"category_scores_gemma":[0.000006554603,0.000040375668,0.000008876611,0.00009827456,0.00011479639,0.000019647761,0.000116844414,0.000026045213,8.798455e-8],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009414029,0.000042093907,0.0031441653,0.000011121312,0.0000017584937,2.796216e-9,0.00017728972,0.0008115225,0.9407602,0.00033437705,0.0007206755,0.053987373],"study_design_scores_gemma":[0.0002720783,0.000050120434,0.033649143,0.000014425171,0.00001167622,0.0000024036167,0.0001815339,0.7682949,0.18801561,0.00037452418,0.009041795,0.00009182892],"about_ca_topic_score_codex":0.000004779697,"about_ca_topic_score_gemma":0.000026283411,"teacher_disagreement_score":0.76748335,"about_ca_system_score_codex":0.0000049283067,"about_ca_system_score_gemma":0.0000399128,"threshold_uncertainty_score":0.16464719},"labels":[],"label_agreement":null},{"id":"W2403880286","doi":"10.1093/bioinformatics/bts490","title":"ECCB 2012: The 11th European Conference on Computational Biology","year":2012,"lang":"en","type":"article","venue":"Computer applications in the biosciences","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"University at Buffalo; Swiss Institute of Bioinformatics; Schweizerische Akademie der Medizinischen Wissenschaften; Université de Genève; Eidgenössische Technische Hochschule Zürich; Universität Zürich; Branco Weiss Fellowship – Society in Science; Universität Basel; European Bioinformatics Institute; Universitätsspital Zürich; Microsoft Research","keywords":"Computer science; Computational biology; Biology","score_opus":0.04298584498611423,"score_gpt":0.32671621241327764,"score_spread":0.2837303674271634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2403880286","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2873871,0.0014017138,0.66362035,0.0115254875,0.00094943075,0.0017908891,0.00009193783,0.00004535747,0.03318772],"genre_scores_gemma":[0.99460626,0.0001237027,0.003378404,0.0012665142,0.00044253835,0.000038536033,0.000072618896,0.0000038137864,0.00006762553],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989661,0.0001851795,0.00018259388,0.00018007263,0.00020448466,0.00028154312],"domain_scores_gemma":[0.99937916,0.00009587029,0.00005815552,0.0003442611,0.000056196783,0.000066334775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010612551,0.000094943614,0.00006332375,0.000049750983,0.00024275768,0.00006526432,0.0010420242,0.000045550747,0.000009224178],"category_scores_gemma":[0.000026233782,0.000048231504,0.000037063626,0.0002222684,0.00069846807,0.000006955097,0.00020274216,0.00010772164,0.00008356563],"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":[0.00005771571,0.0023347395,0.04440832,0.00008202827,0.0001000647,0.0000011695545,0.007083193,0.0013682771,0.025300533,0.2774445,0.08932539,0.55249405],"study_design_scores_gemma":[0.0005666695,0.0008150817,0.19004555,0.000023534314,0.000015156215,0.000029521458,0.0014147778,0.014116712,0.0029890083,0.008868077,0.78057986,0.00053603895],"about_ca_topic_score_codex":0.0000047147028,"about_ca_topic_score_gemma":0.000004964215,"teacher_disagreement_score":0.7072191,"about_ca_system_score_codex":0.000006987778,"about_ca_system_score_gemma":0.00004794898,"threshold_uncertainty_score":0.25735345},"labels":[],"label_agreement":null},{"id":"W2509574344","doi":"10.1093/bioinformatics/btw481","title":"ECCB 2016: The 15th European Conference on Computational Biology","year":2016,"lang":"en","type":"editorial","venue":"Computer applications in the biosciences","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Cancer Research UK Cambridge Institute, University of Cambridge; RIKEN; Swiss Institute of Bioinformatics; Università di Bologna; Rigshospitalet; University of Oxford; Vrije Universiteit Amsterdam; Wageningen University and Research; Aalto-Yliopisto; Universiteit Utrecht; Univerzita Karlova v Praze; Centre National de la Recherche Scientifique; Cancer Research UK; University College London; Institut National de la Recherche Agronomique; University of Toronto; Technische Universität Dresden; Eidgenössische Technische Hochschule Zürich; Universiteit Leiden; Okinawa Institute of Science and Technology Graduate University; Universität des Saarlandes; University of Notre Dame; European Bioinformatics Institute; University of California, Santa Cruz; Vrije Universiteit Brussel; Massachusetts General Hospital","keywords":"Computational biology; Computer science; Biology; Data science","score_opus":0.013841547144270381,"score_gpt":0.29380388828160175,"score_spread":0.27996234113733137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2509574344","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023727068,0.0026426727,0.33911726,0.0075266873,0.6227795,0.0027741024,0.00265787,0.00006317041,0.020066075],"genre_scores_gemma":[0.13077803,0.0028829626,0.002722238,0.0021490986,0.85856545,0.00043926938,0.0019076028,0.000052425006,0.000502957],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99857384,0.00019948938,0.00024279639,0.00054395525,0.00021945203,0.00022048858],"domain_scores_gemma":[0.99841195,0.00059880473,0.00017188542,0.0006493858,0.00013305624,0.000034891207],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006254465,0.00019887753,0.00013332225,0.000058207494,0.00027148973,0.0001361765,0.0018927705,0.00016302994,0.000005222436],"category_scores_gemma":[0.000071849354,0.00010133843,0.000070606664,0.00015430535,0.00060134666,0.0000025031711,0.00030078433,0.00020117612,0.000055417997],"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":[0.0000065707627,0.000059284335,0.000039033835,0.000004440697,0.0000108299955,3.571391e-7,0.00007042964,0.00017928683,0.0002565887,0.008247491,0.9831763,0.007949388],"study_design_scores_gemma":[0.00014685588,0.00016286495,0.00026912274,0.000021786938,0.000007829338,0.000001162631,0.000021327112,0.00019945203,0.000058066096,0.0040384536,0.99490446,0.00016860774],"about_ca_topic_score_codex":0.000017839171,"about_ca_topic_score_gemma":0.000025514664,"teacher_disagreement_score":0.33639503,"about_ca_system_score_codex":0.000023127726,"about_ca_system_score_gemma":0.00031969137,"threshold_uncertainty_score":0.41324612},"labels":[],"label_agreement":null},{"id":"W2725970836","doi":"10.1093/bioinformatics/btx460","title":"Analysis and prediction of protein folding energy changes upon mutation by element specific persistent homology","year":2017,"lang":"en","type":"article","venue":"Computer applications in the biosciences","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":108,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Mutation; Homology modeling; Pearson product-moment correlation coefficient; Stability (learning theory); Mutation rate; Computational biology; Correlation coefficient; Computer science; Correlation; Persistent homology; Mutagenesis; Protein folding; Folding (DSP implementation); Mathematics; Protein design; Protein structure; Algorithm; Biology; Genetics; Machine learning; Statistics; Gene; Biochemistry; Engineering; Geometry","score_opus":0.010582423357981768,"score_gpt":0.24057174214454452,"score_spread":0.22998931878656276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2725970836","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68756044,0.00091862294,0.31084815,0.00028781415,0.000034077562,0.00024788166,0.000029988722,0.000003255611,0.00006978699],"genre_scores_gemma":[0.99680763,0.00018934085,0.002729579,0.00002949541,0.000056324192,0.00010412705,0.00006859339,0.0000017324279,0.000013165086],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994927,0.00003148776,0.00009958162,0.00021553542,0.00008068302,0.0000800194],"domain_scores_gemma":[0.99951506,0.0000065705794,0.00012280651,0.000314392,0.000026966194,0.000014223497],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001766416,0.000057289097,0.00007000916,0.000063972926,0.00021337281,0.000044963257,0.00033456628,0.00004147955,8.423242e-7],"category_scores_gemma":[0.00000366425,0.00004150221,0.000032927805,0.00011970761,0.00016888765,0.0000051418046,0.000086252134,0.000021337066,7.428086e-8],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000272436,0.00020531603,0.03186113,0.00003724729,0.00022297491,8.063146e-7,0.0007286545,0.0005779475,0.8083845,0.010250784,0.00044610313,0.14725734],"study_design_scores_gemma":[0.0014545848,0.0028790243,0.31428468,0.000053494703,0.00047563142,0.00004760309,0.0017520502,0.09357813,0.4908511,0.007781791,0.085952245,0.0008896677],"about_ca_topic_score_codex":0.00004893535,"about_ca_topic_score_gemma":0.00008719668,"teacher_disagreement_score":0.31753334,"about_ca_system_score_codex":0.0000063376788,"about_ca_system_score_gemma":0.000008488828,"threshold_uncertainty_score":0.1692411},"labels":[],"label_agreement":null},{"id":"W3108440423","doi":"10.1093/bioinformatics/btaa976","title":"Deep feature extraction of single-cell transcriptomes by generative adversarial network","year":2020,"lang":"en","type":"article","venue":"Computer applications in the biosciences","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Douglas Mental Health University Institute; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Computer science; Generative model; Generative grammar; Feature (linguistics); Source code; Embedding; Generative adversarial network; Raw data; Code (set theory); Artificial intelligence; Data mining; Machine learning; Deep learning","score_opus":0.016535428181128544,"score_gpt":0.23602699513096556,"score_spread":0.219491566949837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3108440423","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16878195,0.0015091349,0.8271095,0.0013889251,0.00026910592,0.00044263346,0.000021243424,0.0000141913915,0.00046328516],"genre_scores_gemma":[0.9864381,0.00008588042,0.011998742,0.00082225306,0.00052832795,0.000030289359,0.000070978866,0.0000060742273,0.000019369776],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992223,0.00006683136,0.00015602053,0.00028751395,0.00012576477,0.00014159677],"domain_scores_gemma":[0.9996604,0.000027083765,0.00007369287,0.0001662871,0.000034704382,0.000037861602],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011766394,0.00010529936,0.00010208931,0.000017065255,0.00011533682,0.000034737513,0.00046823916,0.00008334827,0.0000025953302],"category_scores_gemma":[0.000004108499,0.00007741167,0.000061120016,0.00032740092,0.00016972925,0.000008168206,0.00002489714,0.00008197199,0.0000011313139],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002500132,0.00016477749,0.0011117788,0.000010856213,0.000007090963,1.6161711e-7,0.0007132134,0.0019375585,0.9877474,0.0001446154,0.0056969025,0.0024406484],"study_design_scores_gemma":[0.0012084655,0.0012031615,0.0020709743,0.000015361571,0.000054112737,0.0000071360564,0.0008875421,0.02712739,0.7567224,0.00037046574,0.20978363,0.00054938084],"about_ca_topic_score_codex":0.000007948742,"about_ca_topic_score_gemma":0.000012960807,"teacher_disagreement_score":0.81765616,"about_ca_system_score_codex":0.0000059869967,"about_ca_system_score_gemma":0.00002629614,"threshold_uncertainty_score":0.31567562},"labels":[],"label_agreement":null}]}