{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":946,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":946,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12","author_layer_release":"2026-06-26"},"query_hash":"122d1dfedb94","filters":{"venue":"Bioinformatics"}},"results":[{"id":"W2133360663","doi":"10.1093/bioinformatics/btq166","title":"Picante: R tools for integrating phylogenies and ecology","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Ecology and Vegetation Dynamics Studies","field":"Environmental Science","cited_by":6383,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Gordon and Betty Moore Foundation; Chinese Academy of Sciences; National Science Foundation","keywords":"R package; Phylogenetic tree; Trait; Phylogenetic diversity; Set (abstract data type); License; Open source; Diversity (politics); Software package; Computer science; Software; Biology; Data science; Ecology; Evolutionary biology; Sociology; Programming language; Anthropology","authors":[{"name":"Steven W. Kembel","is_ca":true},{"name":"Peter D. Cowan","is_ca":true},{"name":"Matthew R. Helmus","is_ca":true},{"name":"William K. Cornwell","is_ca":true},{"name":"Hélène Morlon","is_ca":true},{"name":"David D. Ackerly","is_ca":true},{"name":"Simon P. Blomberg","is_ca":true},{"name":"Campbell O. Webb","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01060361882652631,"gpt":0.2363869733498922,"spread":0.2257833545233659,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007217632,0.003864489,0.004106394,0.005318498,0.001168773,0.003609285,0.006948134,0.001258601,0.05849132],"category_scores_gemma":[0.0272369,0.003178302,0.003711821,0.004425957,0.00115187,0.003895859,0.004695412,0.005781225,0.04842932],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007787551,"about_ca_system_score_gemma":0.002179768,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003470822,"about_ca_topic_score_gemma":0.002641517,"domain_scores_codex":[0.9958678,0.001750622,0.0004539026,0.0008722167,0.0008422117,0.0002133506],"domain_scores_gemma":[0.9901716,0.005888269,0.0009589636,0.001627017,0.0009681456,0.000386094],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0008800777,0.0001072997,0.006233744,0.005344821,0.002937778,0.0007120353,0.0009184983,0.02038072,0.00713798,0.03320583,0.7608152,0.161326],"study_design_scores_gemma":[0.0005660763,0.0001375634,0.007926461,0.0007962855,0.0009731015,0.001340822,0.0001392394,0.09050055,0.007998968,0.111419,0.7777919,0.0004099987],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.00234217,0.001521919,0.6555651,0.0006567493,0.0003631524,0.0002899596,0.0914204,0.2422951,0.005545377],"genre_scores_gemma":[0.02562981,0.00138505,0.6811977,0.0008589585,0.0002654141,0.002692265,0.1391075,0.1428167,0.006046737],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.05849132,"threshold_uncertainty_score":0.1956729,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2153109441","doi":"10.1093/bioinformatics/btu494","title":"STAMP: statistical analysis of taxonomic and functional profiles","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4314,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"","keywords":"Python (programming language); Computer science; Graphical user interface; Software; R package; Exploratory data analysis; Statistical analysis; Data mining; Source code; Software package; Information retrieval; Programming language; Statistics; Mathematics","authors":[{"name":"Donovan H. Parks","is_ca":true},{"name":"Gene W. Tyson","is_ca":true},{"name":"Philip Hugenholtz","is_ca":true},{"name":"Robert G. Beiko","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3681394256237464,"gpt":0.471576120107807,"spread":0.1034366944840607,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02003762,0.001520003,0.00316289,0.008829535,0.001355737,0.00373493,0.003355234,0.001419373,0.114391],"category_scores_gemma":[0.1416755,0.0007712414,0.003383039,0.01024328,0.002401869,0.003468786,0.003236532,0.004096156,0.02314666],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001356342,"about_ca_system_score_gemma":0.004611631,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001631333,"about_ca_topic_score_gemma":0.001969012,"domain_scores_codex":[0.9778321,0.007996794,0.002514683,0.004227796,0.006488256,0.0009402781],"domain_scores_gemma":[0.8872508,0.07546181,0.01239239,0.0139541,0.008773975,0.00216699],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.003820785,0.0004108643,0.04352606,0.009883556,0.002933931,0.000636265,0.001527806,0.01179755,0.009364958,0.02861386,0.4903833,0.397101],"study_design_scores_gemma":[0.001012193,0.002144739,0.1019799,0.003091398,0.002652654,0.001835426,0.001111036,0.1113656,0.01733536,0.1754192,0.5812758,0.0007767494],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02292874,0.001501718,0.6190777,0.002430947,0.001956389,0.002813897,0.2913143,0.04659692,0.01137938],"genre_scores_gemma":[0.1696749,0.001153528,0.6179495,0.001759301,0.001247934,0.02187442,0.1485705,0.02501386,0.01275602],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.114391,"threshold_uncertainty_score":0.382676,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2130706354","doi":"10.1093/bioinformatics/bth092","title":"TANDEM: matching proteins with tandem mass spectra","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":2606,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"Canadian Institutes of Health Research; University of Chicago","keywords":"Tandem; Matching (statistics); Tandem repeat; Tandem mass spectrometry; Computer science; Computational biology; Chemistry; Biology; Genetics; Mass spectrometry; Chromatography; Mathematics; Genome; Statistics; Materials science","authors":[{"name":"Robertson Craig","is_ca":true},{"name":"Ronald C. Beavis","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01073187936705139,"gpt":0.2430020231674446,"spread":0.2322701438003932,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002460954,0.002085019,0.0008498613,0.003344375,0.0008748036,0.002004483,0.002573315,0.001688751,0.02797272],"category_scores_gemma":[0.006881369,0.001029844,0.001107301,0.003376147,0.0004179529,0.003296229,0.003057791,0.001133955,0.02535267],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003906845,"about_ca_system_score_gemma":0.0006964377,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005225064,"about_ca_topic_score_gemma":0.0005285595,"domain_scores_codex":[0.998332,0.0002028726,0.0002400052,0.0004909745,0.0005950766,0.0001391441],"domain_scores_gemma":[0.9982005,0.0005406424,0.0003336982,0.0004448204,0.0003258485,0.0001544846],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003792768,0.0004185851,0.0103151,0.002788774,0.0006592931,0.001832328,0.0004467374,0.004502228,0.11863,0.01600228,0.4053324,0.4352795],"study_design_scores_gemma":[0.0007285708,0.0005401066,0.0122113,0.0003223288,0.0004067168,0.007221999,0.0002661837,0.08118228,0.2956946,0.05065971,0.5503711,0.0003951704],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02611585,0.001628124,0.6271328,0.000838981,0.0008390458,0.0007290201,0.04551481,0.2853704,0.01183101],"genre_scores_gemma":[0.08771034,0.001183666,0.7995979,0.001263774,0.0004385813,0.001115353,0.0802474,0.01558687,0.01285613],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02797272,"threshold_uncertainty_score":0.0935781,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2162792752","doi":"10.1093/bioinformatics/btq249","title":"PSORTb 3.0: improved protein subcellular localization prediction with refined localization subcategories and predictive capabilities for all prokaryotes","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2574,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Simon Fraser University; Michael Smith Health Research BC; Cystic Fibrosis Foundation","keywords":"Proteome; Protein subcellular localization prediction; Archaea; Computer science; Subcellular localization; Precision and recall; Computational biology; Interface (matter); Proteomics; Software; Metagenomics; Biology; Bioinformatics; Data mining; Artificial intelligence; Bacteria; Cytoplasm; Genetics; Gene; Programming language","authors":[{"name":"Nancy Yu","is_ca":true},{"name":"James Wagner","is_ca":true},{"name":"Matthew R. Laird","is_ca":true},{"name":"Gabor Melli","is_ca":true},{"name":"Sébastien Rey","is_ca":true},{"name":"Raymond Lo","is_ca":true},{"name":"Phuong Dao","is_ca":true},{"name":"S. Cenk Şahinalp","is_ca":true},{"name":"Martin Ester","is_ca":true},{"name":"Leonard J. Foster","is_ca":true},{"name":"Fiona S. L. Brinkman","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.004537457218943714,"gpt":0.2113114192828754,"spread":0.2067739620639316,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00230192,0.002018392,0.001519675,0.001095361,0.000555147,0.001442636,0.00143963,0.0006951142,0.004834733],"category_scores_gemma":[0.005074054,0.000781537,0.00153168,0.001200974,0.0002976581,0.001218013,0.001456018,0.001624487,0.004395199],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005243601,"about_ca_system_score_gemma":0.001009831,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003062548,"about_ca_topic_score_gemma":0.004309738,"domain_scores_codex":[0.9991978,0.000168045,0.00007287906,0.0002385616,0.0002548622,0.00006780422],"domain_scores_gemma":[0.9984868,0.000557114,0.0001998914,0.0002085026,0.0004101473,0.000137578],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.007678094,0.0007391932,0.0608428,0.00285007,0.001412427,0.001081672,0.0004568542,0.1062439,0.3123614,0.00339053,0.169241,0.3337022],"study_design_scores_gemma":[0.0005461889,0.0004893991,0.01969438,0.0001385185,0.0004012526,0.0009964992,0.00007256969,0.8062905,0.1322566,0.003538151,0.0353558,0.0002200911],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2500788,0.001873041,0.5257825,0.001338273,0.0002125625,0.0003313535,0.03199696,0.1845153,0.003871135],"genre_scores_gemma":[0.2771847,0.0006646733,0.6211372,0.0004525877,0.00008731647,0.0005964051,0.08416393,0.0111011,0.004612062],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004834733,"threshold_uncertainty_score":0.01617384,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2117368100","doi":"10.1093/bioinformatics/btm538","title":"GEIGER: investigating evolutionary radiations","year":2007,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Evolution and Paleontology Studies","field":"Earth and Planetary Sciences","cited_by":2550,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"","keywords":"Geiger counter; Computer science; Software; R package; Software package; Theoretical computer science; Programming language; Physics; Nuclear physics","authors":[{"name":"Luke J. Harmon","is_ca":true},{"name":"Jason T. Weir","is_ca":true},{"name":"Chad D. Brock","is_ca":true},{"name":"Richard E. Glor","is_ca":true},{"name":"Wendell Challenger","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02611603997804895,"gpt":0.2387691718893873,"spread":0.2126531319113383,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004623245,0.001527672,0.001948651,0.003934299,0.0009803431,0.003034047,0.002776403,0.0009794761,0.03940324],"category_scores_gemma":[0.02407165,0.0008283965,0.002731988,0.005227723,0.0008422281,0.003170904,0.003553863,0.001836439,0.01267474],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005028278,"about_ca_system_score_gemma":0.001030794,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003108944,"about_ca_topic_score_gemma":0.002384169,"domain_scores_codex":[0.9976826,0.0009859222,0.0001375546,0.0007129417,0.0003574936,0.0001233696],"domain_scores_gemma":[0.9899704,0.007634013,0.0005462202,0.001044768,0.0004658366,0.0003388939],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006179842,0.00007539913,0.04845784,0.004473963,0.003766964,0.001191572,0.002705436,0.05477133,0.01171349,0.09505615,0.4648423,0.3123275],"study_design_scores_gemma":[0.0003485105,0.0003171639,0.05528801,0.0007747906,0.002226094,0.002589105,0.0006432634,0.146173,0.01033953,0.2313622,0.5494975,0.0004407086],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04308348,0.006278309,0.7401037,0.003074546,0.0009251061,0.0002465697,0.103089,0.07044161,0.03275763],"genre_scores_gemma":[0.2742343,0.003626561,0.5862485,0.001199292,0.0004419023,0.001631461,0.07909901,0.03974891,0.01377],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03940324,"threshold_uncertainty_score":0.1318169,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2951158909","doi":"10.1093/bioinformatics/btw777","title":"Scater: pre-processing, quality control, normalization and visualization of single-cell RNA-seq data in R","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2053,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Health and Medical Research Council; Medical Research Council Canada; Cancer Research UK; Medical Research Council; European Molecular Biology Laboratory","keywords":"Normalization (sociology); Visualization; Computer science; RNA-Seq; Software; Computational biology; Data mining; Biology; Transcriptome; Genetics; Gene expression; Programming language; Gene","authors":[{"name":"Davis J. McCarthy","is_ca":false},{"name":"Kieran R. Campbell","is_ca":false},{"name":"Aaron T. L. Lun","is_ca":false},{"name":"Quin F. Wills","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02825178629128504,"gpt":0.2756035259650396,"spread":0.2473517396737545,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01727693,0.005536002,0.003980031,0.003879452,0.001371604,0.005043797,0.006485344,0.001611955,0.07292074],"category_scores_gemma":[0.04427633,0.003365837,0.004440603,0.00402553,0.002286256,0.003350705,0.004754945,0.006467659,0.1001481],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001605492,"about_ca_system_score_gemma":0.0055069,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003248139,"about_ca_topic_score_gemma":0.003884663,"domain_scores_codex":[0.9899714,0.004147922,0.001054319,0.002048617,0.002266414,0.0005112851],"domain_scores_gemma":[0.9737304,0.01545737,0.002410709,0.004150456,0.003387571,0.0008634308],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001429542,0.000121654,0.004153517,0.007584841,0.001567009,0.0008429956,0.001195539,0.0125019,0.02401558,0.01566656,0.8387011,0.09221973],"study_design_scores_gemma":[0.001333371,0.0004453198,0.01032792,0.001743761,0.0009644742,0.001899536,0.000367484,0.1091213,0.06892585,0.07460879,0.7292371,0.001025078],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.00243659,0.00064404,0.4882271,0.0006781429,0.0004245353,0.0005747952,0.05291079,0.4501919,0.003912014],"genre_scores_gemma":[0.02155606,0.001030255,0.6868539,0.00104578,0.0001987267,0.004950191,0.06234115,0.2152335,0.006790331],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.07292074,"threshold_uncertainty_score":0.2439442,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2145562754","doi":"10.1093/bioinformatics/btu462","title":"ASTRAL: genome-scale coalescent-based species tree estimation","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1422,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Howard Hughes Medical Institute; University of Alberta; National Science Foundation","keywords":"Coalescent theory; Tree (set theory); Genome; Population; Computational biology; Concatenation (mathematics); Scale (ratio); Computer science; Biology; Data mining; Theoretical computer science; Gene; Geography; Mathematics; Genetics; Phylogenetic tree; Cartography; Combinatorics","authors":[{"name":"Siavash Mirarab","is_ca":false},{"name":"Rezwana Reaz","is_ca":false},{"name":"Md. Shamsuzzoha Bayzid","is_ca":false},{"name":"Théo Zimmermann","is_ca":false},{"name":"M. Shel Swenson","is_ca":false},{"name":"Tandy Warnow","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01075530619077333,"gpt":0.2132245282185999,"spread":0.2024692220278266,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00550135,0.002338636,0.00246913,0.00399511,0.001714523,0.00321694,0.005564189,0.002199987,0.01357712],"category_scores_gemma":[0.0315985,0.001729334,0.002899111,0.004429435,0.001308508,0.003372876,0.003364747,0.004335139,0.01202752],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009563185,"about_ca_system_score_gemma":0.002306886,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005382918,"about_ca_topic_score_gemma":0.009631455,"domain_scores_codex":[0.9972934,0.0009869606,0.0001616391,0.0008354881,0.0006046239,0.0001177664],"domain_scores_gemma":[0.9905221,0.005895558,0.0007694204,0.001470607,0.0009094292,0.0004328752],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002016774,0.0003774372,0.0325236,0.005514559,0.003622492,0.001266206,0.001809861,0.239388,0.02787967,0.04191267,0.4110504,0.2326383],"study_design_scores_gemma":[0.0009903616,0.0001971808,0.007878468,0.0003542046,0.0006020186,0.00104928,0.0002501792,0.8245521,0.0111755,0.06756886,0.08505779,0.0003240574],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03422132,0.002412352,0.759843,0.001326481,0.0005967966,0.0004244235,0.06839023,0.1276307,0.005154725],"genre_scores_gemma":[0.1126971,0.001031257,0.7370113,0.0009168837,0.0003096093,0.001221187,0.1213849,0.02279304,0.002634685],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01357712,"threshold_uncertainty_score":0.04542005,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2104398544","doi":"10.1093/bioinformatics/btp368","title":"PhyloBayes 3: a Bayesian software package for phylogenetic reconstruction and molecular dating","year":2009,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1351,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"Université de Montréal; Agence Nationale de la Recherche","keywords":"Phylogenetic tree; Bayesian probability; Variety (cybernetics); Molecular clock; Probabilistic logic; Computer science; Software; Software package; Computational biology; Phylogenetics; Parametric statistics; Evolutionary biology; Biology; Data mining; Artificial intelligence; Genetics; Mathematics; Statistics; Programming language; Gene","authors":[{"name":"Nicolas Lartillot","is_ca":true},{"name":"Thomas Lepage","is_ca":true},{"name":"Samuel Blanquart","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.00846319551486009,"gpt":0.2270831567231505,"spread":0.2186199612082904,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01128569,0.002770547,0.004648385,0.006939837,0.002341575,0.003655264,0.008340739,0.002785211,0.09652954],"category_scores_gemma":[0.03115795,0.004313133,0.003691697,0.005651732,0.001298932,0.004282515,0.005267262,0.007039936,0.04365171],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001339509,"about_ca_system_score_gemma":0.004381103,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006404255,"about_ca_topic_score_gemma":0.006465327,"domain_scores_codex":[0.9965062,0.001531597,0.0004235253,0.0005728948,0.0007789499,0.0001868656],"domain_scores_gemma":[0.9888626,0.007554643,0.0008469202,0.001132242,0.0011105,0.0004931038],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00138021,0.0002338983,0.006386233,0.00648504,0.002231708,0.001334196,0.001062546,0.04537771,0.01111893,0.06758165,0.5296698,0.3271381],"study_design_scores_gemma":[0.001008712,0.0001543724,0.005640521,0.001223001,0.0007813083,0.002097492,0.0002033838,0.2649069,0.009332702,0.1725497,0.5413842,0.0007176481],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.001610212,0.0006378241,0.8839901,0.0004607292,0.000242236,0.0002332217,0.02905582,0.08027506,0.003494851],"genre_scores_gemma":[0.01581696,0.0006085421,0.9105462,0.000383413,0.0001594499,0.001932601,0.02832343,0.03904361,0.003185763],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.09652954,"threshold_uncertainty_score":0.3229235,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2140028978","doi":"10.1093/bioinformatics/btq429","title":"Datamonkey 2010: a suite of phylogenetic analysis tools for evolutionary biology","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1235,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"AIDS Vancouver","funders":"National Institute of Allergy and Infectious Diseases; Canadian Institutes of Health Research","keywords":"Suite; Phylogenetic tree; Biology; Identification (biology); Documentation; Selection (genetic algorithm); Computer science; Evolutionary biology; Computational biology; Data science; Machine learning; Genetics; Gene; Ecology; Geography; Programming language","authors":[{"name":"Wayne Delport","is_ca":true},{"name":"Art F. Y. Poon","is_ca":true},{"name":"Simon D. W. Frost","is_ca":true},{"name":"Sergei L. Kosakovsky Pond","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01890285606913534,"gpt":0.2598102866946762,"spread":0.2409074306255408,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01141195,0.00388639,0.004115955,0.006185757,0.00219729,0.005240904,0.009641999,0.002112593,0.08203473],"category_scores_gemma":[0.03026619,0.004187778,0.004028806,0.007773633,0.001591745,0.009692608,0.008088112,0.008636242,0.05216614],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001584009,"about_ca_system_score_gemma":0.005468432,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004073719,"about_ca_topic_score_gemma":0.004658511,"domain_scores_codex":[0.9955656,0.001390361,0.0007311962,0.0008286668,0.001070036,0.0004141187],"domain_scores_gemma":[0.986852,0.007336787,0.001028849,0.00229237,0.001355557,0.001134421],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001791992,0.0001960557,0.003588306,0.005497076,0.0007872539,0.0007824228,0.001130055,0.003139121,0.007329491,0.01807872,0.8748193,0.08286019],"study_design_scores_gemma":[0.00134768,0.0001422783,0.00589846,0.001482976,0.0003730043,0.001093658,0.0003532002,0.0214602,0.01198023,0.06144589,0.8938604,0.0005620357],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"software","genre_gemma":"software","genre_scores_codex":[0.003778575,0.0015306,0.2505885,0.001601077,0.001081201,0.001072793,0.3466547,0.3836215,0.01007099],"genre_scores_gemma":[0.02202664,0.002158186,0.4254444,0.002009623,0.0003198241,0.004721412,0.3627568,0.1732988,0.007264383],"genre_candidate":"software","genre_consensus":"software","teacher_disagreement_score":0.08203473,"threshold_uncertainty_score":0.2744336,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2154518589","doi":"10.1093/bioinformatics/btu181","title":"geiger v2.0: an expanded suite of methods for fitting macroevolutionary models to phylogenetic trees","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Evolution and Paleontology Studies","field":"Earth and Planetary Sciences","cited_by":1222,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Geiger counter; Computer science; Source code; R package; Phylogenetic tree; Suite; Scope (computer science); Code (set theory); Data mining; Data science; Biology; Set (abstract data type); Programming language; Genetics; Physics; Geography","authors":[{"name":"Matthew W. Pennell","is_ca":false},{"name":"Jonathan M. Eastman","is_ca":false},{"name":"Graham J. Slater","is_ca":false},{"name":"Joseph W. Brown","is_ca":false},{"name":"Josef C. Uyeda","is_ca":false},{"name":"Richard G. FitzJohn","is_ca":false},{"name":"Michael E. Alfaro","is_ca":false},{"name":"Luke J. Harmon","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06591234001703411,"gpt":0.3228357091837009,"spread":0.2569233691666668,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008890259,0.004873794,0.003678935,0.005338884,0.001761308,0.003550969,0.007712415,0.002816166,0.05650549],"category_scores_gemma":[0.03033641,0.003871606,0.00695231,0.004257701,0.001083591,0.003303923,0.005129053,0.006761065,0.04635177],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001036789,"about_ca_system_score_gemma":0.002877613,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004434432,"about_ca_topic_score_gemma":0.007304109,"domain_scores_codex":[0.9969922,0.001378086,0.000316641,0.0006325529,0.0004939442,0.0001865157],"domain_scores_gemma":[0.9905576,0.00698856,0.0005490779,0.001118855,0.0005877671,0.0001981333],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000561489,0.0001680267,0.01079552,0.004648806,0.003669274,0.001286878,0.001489794,0.1142331,0.0107161,0.02919447,0.5847337,0.2385028],"study_design_scores_gemma":[0.0004502577,0.0001983881,0.00722422,0.0008087683,0.0008758333,0.002166772,0.000210216,0.4508587,0.009643701,0.0969108,0.4300638,0.0005885188],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005276646,0.001498507,0.787264,0.0005369735,0.0003907423,0.0003424676,0.03946099,0.1608753,0.004354485],"genre_scores_gemma":[0.0219149,0.001068294,0.8013595,0.0005681629,0.0001475403,0.002028944,0.05111682,0.1174411,0.004354846],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.05650549,"threshold_uncertainty_score":0.1890297,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2157748357","doi":"10.1093/bioinformatics/bti054","title":"Circular genome visualization and exploration using CGView","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1122,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Genome Prairie; Genome Canada","keywords":"Scalable Vector Graphics; Visualization; Computer science; Java applet; Genome; Graphics; Documentation; Sample (material); World Wide Web; XML; Computer graphics; Computer graphics (images); Java; Information retrieval; Data mining; Biology; Programming language; Genetics","authors":[{"name":"Paul Stothard","is_ca":true},{"name":"David S. Wishart","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02948202242176128,"gpt":0.2626183593228257,"spread":0.2331363369010644,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008895539,0.0009208921,0.0006209763,0.002469907,0.0005700934,0.001468642,0.001489706,0.0006773979,0.08298483],"category_scores_gemma":[0.002154395,0.0004920316,0.0007810002,0.002307437,0.0002717742,0.001186678,0.001469515,0.001383883,0.01825194],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004298769,"about_ca_system_score_gemma":0.0008446745,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002530193,"about_ca_topic_score_gemma":0.002500612,"domain_scores_codex":[0.9996697,0.00005124192,0.00002093869,0.00008330706,0.0001299233,0.00004494147],"domain_scores_gemma":[0.9992056,0.0003098928,0.00005270266,0.0001232069,0.000210992,0.000097706],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001054783,0.0001534817,0.002858997,0.00169679,0.0001580185,0.000624767,0.0007361923,0.005571879,0.09714168,0.01473203,0.4728744,0.402397],"study_design_scores_gemma":[0.0003446296,0.0001151375,0.006838132,0.0004331246,0.00009498148,0.001257141,0.0002896643,0.08705574,0.1275545,0.01546941,0.7603028,0.0002446304],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.0121259,0.0009200104,0.6464301,0.001270121,0.0004288826,0.0002840069,0.0505713,0.25382,0.03414961],"genre_scores_gemma":[0.1108941,0.001801977,0.7065318,0.0006227009,0.0002142813,0.0010671,0.1004909,0.05187985,0.0264972],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.08298483,"threshold_uncertainty_score":0.2776119,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2909472027","doi":"10.1093/bioinformatics/bty1054","title":"DIABLO: an integrative approach for identifying key molecular drivers from multi-omics assays","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1056,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Prevention of Organ Failure; University of British Columbia","funders":"National Institute of Allergy and Infectious Diseases; National Health and Medical Research Council","keywords":"Bioconductor; Omics; Computer science; Computational biology; Benchmark (surveying); Identification (biology); Relevance (law); Data integration; Visualization; Data mining; Data science; Bioinformatics; Biology; Ecology; Cartography; Geography","authors":[{"name":"Amrit Singh","is_ca":true},{"name":"Casey P. Shannon","is_ca":true},{"name":"Benoît Gautier","is_ca":false},{"name":"Florian Rohart","is_ca":false},{"name":"Michaël Vacher","is_ca":false},{"name":"Scott J. Tebbutt","is_ca":true},{"name":"Kim‐Anh Lê Cao","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0158927330930595,"gpt":0.2508353458635373,"spread":0.2349426127704778,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006976734,0.00199008,0.001341732,0.004109098,0.0006357391,0.00277389,0.002782492,0.0007569416,0.005470053],"category_scores_gemma":[0.01089978,0.0008304259,0.002236223,0.002695648,0.0008207423,0.001704565,0.004033125,0.002234583,0.001597216],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001087848,"about_ca_system_score_gemma":0.002560625,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002578362,"about_ca_topic_score_gemma":0.005145956,"domain_scores_codex":[0.9984297,0.0005300827,0.0000767912,0.0004985304,0.0003867141,0.0000781725],"domain_scores_gemma":[0.9959786,0.002526325,0.0003618591,0.0004836219,0.0004070226,0.0002425011],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001741533,0.0006720619,0.0675237,0.004683438,0.004591292,0.0008095721,0.0008151769,0.2110687,0.08997278,0.05632981,0.06772384,0.4940681],"study_design_scores_gemma":[0.0002170507,0.00033437,0.01576924,0.0002352611,0.0006343159,0.000516492,0.0002170918,0.8499641,0.02255083,0.06585111,0.04348295,0.0002271318],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01272227,0.0007430803,0.9638133,0.0004445628,0.00008327961,0.0002187773,0.01039261,0.00970509,0.001876999],"genre_scores_gemma":[0.1033289,0.0007359275,0.8742003,0.0004782642,0.0001205715,0.0009810205,0.0171798,0.001818096,0.001157111],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006976734,"threshold_uncertainty_score":0.03689694,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2149202898","doi":"10.1093/bioinformatics/btq041","title":"Identifying biologically relevant differences between metagenomic communities","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Microbial Community Ecology and Physiology","field":"Environmental Science","cited_by":974,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"","keywords":"Metagenomics; Software; Biology; Ecology; Pairwise comparison; Computer science; Computational biology; Data science; Artificial intelligence","authors":[{"name":"Donovan H. Parks","is_ca":true},{"name":"Robert G. Beiko","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0448213979929792,"gpt":0.2558298542255986,"spread":0.2110084562326194,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00278559,0.0008472941,0.0006033208,0.002304643,0.0007788931,0.001682358,0.0009114254,0.0006448735,0.002307886],"category_scores_gemma":[0.009167531,0.0003203795,0.0007603079,0.002308449,0.001011149,0.001399454,0.001634277,0.0008992335,0.0007109637],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005080354,"about_ca_system_score_gemma":0.0009582945,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007908639,"about_ca_topic_score_gemma":0.0009745549,"domain_scores_codex":[0.9982646,0.0003505423,0.0001513697,0.0006499344,0.0004943896,0.00008927254],"domain_scores_gemma":[0.9931862,0.00361673,0.001397902,0.0006450276,0.0007684564,0.0003856009],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008595763,0.0002506323,0.1700083,0.003051725,0.0005579901,0.0004896257,0.0009511858,0.008311972,0.6674744,0.004149322,0.003024174,0.140871],"study_design_scores_gemma":[0.0001291785,0.000560475,0.4595034,0.000326163,0.0007190261,0.001934154,0.001067265,0.06594516,0.3995911,0.04908232,0.02089482,0.0002468018],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6664079,0.003784363,0.3003489,0.001885359,0.0001829167,0.0003531193,0.01909831,0.003878611,0.004060526],"genre_scores_gemma":[0.7531719,0.0009462367,0.2351084,0.000303782,0.0000954472,0.0002560527,0.0092302,0.0003575744,0.0005304589],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.00278559,"threshold_uncertainty_score":0.01473182,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2128591967","doi":"10.1093/bioinformatics/18.3.440","title":"PatternHunter: faster and more sensitive homology search","year":2002,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":863,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Bioinformatics Solutions (Canada)","funders":"","keywords":"Computer science; Java; Homology (biology); Genomics; MIT License; Computational biology; Computation; License; Biology; Bioinformatics; Data mining; Algorithm; Genome; Genetics; Operating system; Gene","authors":[{"name":"Bin Ma","is_ca":true},{"name":"John Tromp","is_ca":false},{"name":"Ming Li","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01569997354943418,"gpt":0.2324366666156915,"spread":0.2167366930662574,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002589194,0.001804202,0.001803046,0.002475907,0.0007260529,0.002285083,0.004231278,0.001864945,0.02422095],"category_scores_gemma":[0.008742313,0.001458435,0.001150891,0.003531544,0.0007448728,0.006533345,0.002874873,0.00252515,0.01386889],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006994978,"about_ca_system_score_gemma":0.0008581387,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001448689,"about_ca_topic_score_gemma":0.001239993,"domain_scores_codex":[0.9968233,0.0004431556,0.0002811415,0.001074928,0.001180503,0.0001969789],"domain_scores_gemma":[0.9952891,0.00199407,0.0004999339,0.001365484,0.0005805859,0.0002708641],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001902246,0.0003199568,0.003060652,0.001088748,0.0002525536,0.0007380217,0.0002898324,0.007305022,0.143637,0.01297818,0.1038861,0.7245418],"study_design_scores_gemma":[0.0010767,0.0005488943,0.004375508,0.000203727,0.0002282802,0.003768919,0.0001401783,0.3795803,0.3611255,0.04492577,0.2036527,0.0003735303],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0138689,0.0008828208,0.8430136,0.00060516,0.0002386149,0.0002750325,0.002723312,0.1346194,0.003773148],"genre_scores_gemma":[0.04977658,0.0004830402,0.92336,0.0005832842,0.0001426495,0.0004113441,0.007873977,0.01042836,0.006940819],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02422095,"threshold_uncertainty_score":0.08102715,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2809895957","doi":"10.1093/bioinformatics/bty528","title":"MetaboAnalystR: an R package for flexible and reproducible analysis of metabolomics data","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":802,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; McGill University; Chesapeake Research Consortium","keywords":"Computer science; Workflow; Flexibility (engineering); Interface (matter); Web server; Web application; World Wide Web; Database; Operating system; The Internet","authors":[{"name":"Jasmine Chong","is_ca":true},{"name":"Jianguo Xia","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.049798772644403,"gpt":0.3253653511141781,"spread":0.2755665784697751,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007509256,0.003429848,0.003025455,0.004037924,0.0008225412,0.004057615,0.004761435,0.001283114,0.04514894],"category_scores_gemma":[0.0339763,0.00175704,0.003151015,0.003766655,0.001021193,0.002390671,0.003547555,0.004081259,0.04036853],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007413148,"about_ca_system_score_gemma":0.00468978,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002962781,"about_ca_topic_score_gemma":0.003014597,"domain_scores_codex":[0.9962215,0.001485943,0.0004304807,0.0008142542,0.0008494192,0.0001983838],"domain_scores_gemma":[0.9863139,0.007062486,0.001897613,0.002236909,0.002036995,0.000452001],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001325201,0.0000861774,0.007384547,0.008780267,0.002848211,0.00089047,0.0005470171,0.01145996,0.01477024,0.01739397,0.8248138,0.1097002],"study_design_scores_gemma":[0.0007574585,0.0002834408,0.01123667,0.001285782,0.001246634,0.001795679,0.0001432401,0.07466522,0.03274335,0.05296761,0.8223073,0.0005677286],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.00388882,0.001803103,0.5410796,0.001231145,0.0005899334,0.0005935357,0.1302688,0.316434,0.004111165],"genre_scores_gemma":[0.03001412,0.001719148,0.688511,0.001066852,0.0003477087,0.003037296,0.1194645,0.1512522,0.004587213],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.04514894,"threshold_uncertainty_score":0.1510382,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2167540852","doi":"10.1093/bioinformatics/btq418","title":"MetPA: a web-based metabolomics tool for pathway analysis and visualization","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":785,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"National Institute for Nanotechnology; University of Alberta","funders":"","keywords":"Visualization; Computer science; Metabolomics; Context (archaeology); Data visualization; Zoom; Metabolic network; Metabolic pathway; Data mining; Computational biology; Bioinformatics; Biology","authors":[{"name":"Jianguo Xia","is_ca":true},{"name":"David S. Wishart","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.007518783320624244,"gpt":0.2492371449654704,"spread":0.2417183616448462,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001042333,0.002054604,0.001163528,0.003203974,0.0005787133,0.001782156,0.002573448,0.001171191,0.102701],"category_scores_gemma":[0.003394813,0.0007512244,0.001182148,0.003089796,0.0002563457,0.002034555,0.001940546,0.001488052,0.02879963],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004101188,"about_ca_system_score_gemma":0.001151453,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001579871,"about_ca_topic_score_gemma":0.001868482,"domain_scores_codex":[0.9995346,0.00008008111,0.00003985401,0.00008699075,0.0002118744,0.00004670021],"domain_scores_gemma":[0.9986069,0.0006358081,0.0001278344,0.0001766074,0.0003014636,0.0001514404],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001367546,0.0002090015,0.002829082,0.002891583,0.0002157134,0.0008376737,0.0003506871,0.008436637,0.04839533,0.007192343,0.6106194,0.316655],"study_design_scores_gemma":[0.001032899,0.0002593023,0.009390996,0.0006557769,0.0001592366,0.001879391,0.0001495092,0.1888181,0.06420174,0.02492726,0.7081254,0.000400465],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"software","genre_gemma":"software","genre_scores_codex":[0.006002584,0.0006659522,0.4220202,0.0006529419,0.0002112555,0.0002771031,0.0981672,0.4643772,0.007625584],"genre_scores_gemma":[0.06612741,0.001223024,0.6994635,0.000530631,0.0002637485,0.001929885,0.173502,0.04491902,0.01204082],"genre_candidate":"software","genre_consensus":"software","teacher_disagreement_score":0.102701,"threshold_uncertainty_score":0.3435691,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2107249189","doi":"10.1093/bioinformatics/btq430","title":"Cytoscape Web: an interactive web-based network browser","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":746,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"National Institutes of Health; National Institute of General Medical Sciences; Ontario Genomics Institute; Ontario Genomics; Genome Canada; University of Michigan; University of Toronto; Memorial Sloan-Kettering Cancer Center","keywords":"Computer science; JavaScript; World Wide Web; Web application; Web page; ActionScript; Visualization; Information retrieval; Data mining","authors":[{"name":"Christian Lopes","is_ca":true},{"name":"Max Franz","is_ca":true},{"name":"Farzana Kazi","is_ca":true},{"name":"Sylva L. Donaldson","is_ca":true},{"name":"Quaid Morris","is_ca":true},{"name":"Gary D. Bader","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.00650414083413331,"gpt":0.2293681171664229,"spread":0.2228639763322896,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00239934,0.001466849,0.001244099,0.004031501,0.0008207138,0.001918862,0.003700879,0.001725908,0.103213],"category_scores_gemma":[0.007214428,0.001538115,0.0009969021,0.0024196,0.0004119936,0.002509835,0.002864811,0.002962897,0.04761632],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005599039,"about_ca_system_score_gemma":0.002124987,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0026344,"about_ca_topic_score_gemma":0.004954963,"domain_scores_codex":[0.9988658,0.0002404739,0.0001171201,0.000205824,0.0004826071,0.00008816135],"domain_scores_gemma":[0.9969712,0.0013701,0.0001916388,0.0003756492,0.0005500006,0.0005413606],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005156388,0.0001566919,0.0009970167,0.001531401,0.0002504021,0.0005866541,0.0002969674,0.002581717,0.02672666,0.00746293,0.8582883,0.1006056],"study_design_scores_gemma":[0.0006612504,0.00007563692,0.002571031,0.000401007,0.0001357887,0.001039962,0.000088799,0.0477886,0.0393214,0.033129,0.8744833,0.0003041585],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"software","genre_gemma":"software","genre_scores_codex":[0.003371605,0.0008767695,0.3330193,0.00122458,0.0008432284,0.0006928087,0.1252453,0.5164189,0.01830751],"genre_scores_gemma":[0.03630448,0.001487086,0.5728893,0.001456655,0.0004208823,0.00408572,0.266106,0.08733428,0.02991556],"genre_candidate":"software","genre_consensus":"software","teacher_disagreement_score":0.103213,"threshold_uncertainty_score":0.345282,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2154202919","doi":"10.1093/bioinformatics/bti057","title":"PSORTb v.2.0: Expanded prediction of bacterial protein subcellular localization and insights gained from comparative proteome analysis","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":723,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Simon Fraser University; Michael Smith Health Research BC","keywords":"Proteome; Computer science; n-gram; Subsequence; Support vector machine; Computational biology; MIT License; Subcellular localization; Biology; Artificial intelligence; Software; Bioinformatics; Genetics; Mathematics; Programming language; Language model","authors":[{"name":"Jennifer L. Gardy","is_ca":true},{"name":"Matthew R. Laird","is_ca":false},{"name":"Fen‐Ling Chen","is_ca":false},{"name":"Sébastien Rey","is_ca":false},{"name":"Calum J. Walsh","is_ca":false},{"name":"Martin Ester","is_ca":false},{"name":"Fiona S. L. Brinkman","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01112130957213176,"gpt":0.2311252125935061,"spread":0.2200039030213743,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001166368,0.0009815398,0.0009439721,0.001478544,0.0002601959,0.000754475,0.0009998893,0.0004714882,0.005727987],"category_scores_gemma":[0.002935206,0.000483201,0.0006899817,0.001200774,0.000158103,0.0007130182,0.0007933745,0.0006167167,0.003732609],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002498478,"about_ca_system_score_gemma":0.0003918521,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000865289,"about_ca_topic_score_gemma":0.0009131095,"domain_scores_codex":[0.9997168,0.00006561656,0.000025593,0.00007838855,0.00009099415,0.0000225043],"domain_scores_gemma":[0.9993617,0.0003039629,0.00008923634,0.00008446423,0.000113477,0.00004710117],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004074526,0.0003218019,0.01593729,0.003199235,0.0004598754,0.001066672,0.0003615284,0.04210499,0.3341269,0.005094295,0.151509,0.4417439],"study_design_scores_gemma":[0.0005745821,0.0006620919,0.03235639,0.0003989735,0.0003264474,0.003753781,0.00008648938,0.6430902,0.1781543,0.009226647,0.1311671,0.0002029159],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1380973,0.002320569,0.6610056,0.000498088,0.0001391324,0.0002469906,0.03089832,0.1616791,0.005114842],"genre_scores_gemma":[0.1903609,0.001248868,0.7235301,0.0001860744,0.00006903095,0.0005025039,0.07147302,0.009394811,0.003234725],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005727987,"threshold_uncertainty_score":0,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2179127114","doi":"10.1093/bioinformatics/btv557","title":"Cytoscape.js: a graph theory library for visualisation and analysis","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":721,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"National Institute of General Medical Sciences; National Human Genome Research Institute; National Institutes of Health; National Institute for Health and Care Research","keywords":"Computer science; JavaScript; Visualization; Documentation; Source code; Graph; Programming language; Software; Web application; Graph drawing; World Wide Web; Information retrieval; Data mining; Theoretical computer science","authors":[{"name":"Max Franz","is_ca":true},{"name":"Christian Lopes","is_ca":true},{"name":"Gerardo Huck","is_ca":true},{"name":"Dong Yue","is_ca":true},{"name":"Onur Sumer","is_ca":true},{"name":"Gary D. Bader","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01456489344175985,"gpt":0.2430888264762435,"spread":0.2285239330344837,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002157151,0.002270444,0.002475877,0.007966056,0.001853979,0.003248377,0.005834302,0.00214844,0.1166176],"category_scores_gemma":[0.01175748,0.001931084,0.002208556,0.005228403,0.0007042358,0.004859248,0.003313399,0.005108802,0.07486907],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008841429,"about_ca_system_score_gemma":0.0029753,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004599222,"about_ca_topic_score_gemma":0.006510505,"domain_scores_codex":[0.9981738,0.0003106573,0.0001450608,0.0004234217,0.0008243325,0.0001226054],"domain_scores_gemma":[0.9956847,0.001850703,0.0003594435,0.0007326837,0.0009055817,0.000466995],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001945026,0.00009058722,0.0009369985,0.004390229,0.0004617902,0.0004767419,0.0004071753,0.004351578,0.0236933,0.01643884,0.8378126,0.1107455],"study_design_scores_gemma":[0.0002116896,0.0000483736,0.001620929,0.0005379099,0.0002077893,0.001049849,0.0001169198,0.0330052,0.03124544,0.07617369,0.8554478,0.0003343252],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.002608378,0.002314099,0.4342207,0.001769687,0.001196344,0.0004686712,0.1658959,0.3764921,0.01503428],"genre_scores_gemma":[0.03038781,0.00367309,0.5199459,0.002181588,0.0008733785,0.002309956,0.3047026,0.1160383,0.01988749],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.1166176,"threshold_uncertainty_score":0.3901247,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2148762636","doi":"10.1093/bioinformatics/bth436","title":"Modeling interactome: scale-free or geometric?","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":712,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Princess Margaret Cancer Centre; University Health Network; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Interactome; Geometric networks; Random graph; Network model; Scale (ratio); Complex network; Scale-free network; Measure (data warehouse); Artificial intelligence; Data mining; Theoretical computer science; Machine learning; Graph","authors":[{"name":"Nataša Pržulj","is_ca":true},{"name":"Derek G. Corneil","is_ca":true},{"name":"Igor Jurišica","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01418155438029658,"gpt":0.2415210846296265,"spread":0.2273395302493299,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003343709,0.001294793,0.001032052,0.001770457,0.000555291,0.001752062,0.002120481,0.001800849,0.001994269],"category_scores_gemma":[0.02089511,0.0005204027,0.0009270709,0.002118297,0.001921891,0.004661803,0.00141747,0.001188281,0.0005044465],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0015484,"about_ca_system_score_gemma":0.000640212,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002295923,"about_ca_topic_score_gemma":0.001737398,"domain_scores_codex":[0.9981802,0.0007176293,0.00006829351,0.0006196853,0.0003413601,0.0000729044],"domain_scores_gemma":[0.9908014,0.00589544,0.00143033,0.00109974,0.0004480252,0.0003250491],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001263079,0.00007855846,0.01803975,0.0008983798,0.0003334129,0.0003735192,0.0002903412,0.8114678,0.003596014,0.1314983,0.007212138,0.02608554],"study_design_scores_gemma":[0.00002954701,0.00005399605,0.003393871,0.00005881025,0.00007685247,0.0003844035,0.0000701317,0.7264813,0.001248594,0.26338,0.004784497,0.00003792038],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1853463,0.005657915,0.7888477,0.007543819,0.0002191124,0.0002798148,0.003110667,0.001906718,0.007087975],"genre_scores_gemma":[0.8705749,0.005504083,0.1162844,0.001119551,0.0003492406,0.0005822362,0.003136527,0.0004684779,0.001980601],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003343709,"threshold_uncertainty_score":0.01768345,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2138003801","doi":"10.1093/bioinformatics/bth351","title":"Protein complex prediction via cost-based clustering","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":668,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Ontario Institute for Cancer Research; University of Toronto","funders":"National Institute of General Medical Sciences; National Institutes of Health; University of Toronto","keywords":"Cluster analysis; Computer science; Scalability; Data mining; Partition (number theory); Identification (biology); Biological network; Protein function prediction; Caenorhabditis elegans; Computational biology; Protein function; Machine learning; Biology; Mathematics; Genetics","authors":[{"name":"Andrew D. King","is_ca":true},{"name":"Nataša Pržulj","is_ca":true},{"name":"Igor Jurišica","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01507396375421566,"gpt":0.2276197204721511,"spread":0.2125457567179354,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006912088,0.0006794339,0.0007234614,0.003370058,0.0004868096,0.000934415,0.001062503,0.0008368455,0.001317808],"category_scores_gemma":[0.004849113,0.0002929804,0.0005140748,0.001899463,0.0005343849,0.00103715,0.0005828492,0.0004833212,0.0005990249],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001249874,"about_ca_system_score_gemma":0.0009410035,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009970807,"about_ca_topic_score_gemma":0.0074321,"domain_scores_codex":[0.9992943,0.000141517,0.00004410314,0.0001760787,0.0003010722,0.00004294682],"domain_scores_gemma":[0.9978301,0.000843314,0.0002770473,0.0002530276,0.0007157106,0.00008085097],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002628526,0.000108506,0.01108711,0.0002625625,0.0001516413,0.0001320988,0.00008148745,0.7944101,0.0168751,0.01031392,0.00455302,0.1617616],"study_design_scores_gemma":[0.000005085113,0.00001125526,0.001048124,0.000003425058,0.000008017572,0.00003435342,0.00000676097,0.9922506,0.003170802,0.003016386,0.0004378221,0.000007290064],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1105956,0.0003767777,0.8846951,0.0001779763,0.00001533091,0.000134719,0.0006316472,0.001694845,0.001677956],"genre_scores_gemma":[0.5405874,0.0002450459,0.4550457,0.00005427165,0.00002379844,0.0001650517,0.002231009,0.0002029246,0.00144486],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009970807,"threshold_uncertainty_score":0.01982558,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2166542841","doi":"10.1093/bioinformatics/btq562","title":"GeneMANIA Cytoscape plugin: fast gene function predictions on the desktop","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":661,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Ontario Genomics; Ontario Genomics Institute; Genome Canada","keywords":"Plug-in; Computer science; Function (biology); Complement (music); Java; Set (abstract data type); Gene; Programming language; Biology; Genetics","authors":[{"name":"Jason Montojo","is_ca":true},{"name":"Khalid Zuberi","is_ca":true},{"name":"Harold Rodriguez","is_ca":true},{"name":"Farzana Kazi","is_ca":true},{"name":"George Wright","is_ca":true},{"name":"Sylva L. Donaldson","is_ca":true},{"name":"Quaid Morris","is_ca":true},{"name":"Gary D. Bader","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.007931295299022024,"gpt":0.200528499500222,"spread":0.1925972042011999,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001057865,0.002008568,0.001290755,0.003010206,0.0009469574,0.001387461,0.003786979,0.001623349,0.08352312],"category_scores_gemma":[0.00600103,0.001125276,0.001161151,0.002061949,0.0004044086,0.001652693,0.001535822,0.00242784,0.05946521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006586026,"about_ca_system_score_gemma":0.001676284,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005217165,"about_ca_topic_score_gemma":0.007091139,"domain_scores_codex":[0.9992903,0.00009848188,0.00003470285,0.0001846758,0.0003176934,0.00007415478],"domain_scores_gemma":[0.9981109,0.0007864132,0.0001141788,0.0003293494,0.0004085807,0.0002505768],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006519351,0.0001103824,0.001697928,0.001218457,0.0001944108,0.0003954358,0.0001296496,0.002941951,0.01623827,0.00492838,0.8219919,0.1495013],"study_design_scores_gemma":[0.0005200275,0.0001148503,0.005797999,0.0003693097,0.0001955655,0.0009801065,0.00007515257,0.09967504,0.09751061,0.03635606,0.7579823,0.0004228016],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"software","genre_gemma":"software","genre_scores_codex":[0.006848556,0.001205661,0.2302029,0.001043206,0.0008122255,0.0003105038,0.09388879,0.6519182,0.01376996],"genre_scores_gemma":[0.1026044,0.002119033,0.4339016,0.00173202,0.0005917316,0.002916627,0.3114508,0.09961162,0.04507217],"genre_candidate":"software","genre_consensus":"software","teacher_disagreement_score":0.08352312,"threshold_uncertainty_score":0.2794127,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2766641567","doi":"10.1093/bioinformatics/btx701","title":"Efficient comparative phylogenetics on large trees","year":2017,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":609,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; University of British Columbia","keywords":"Phylogenetics; Computer science; Tree (set theory); Computational biology; Biology; Mathematics; Genetics; Combinatorics; Gene","authors":[{"name":"Stilianos Louca","is_ca":true},{"name":"Michael Doebeli","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02820503632907191,"gpt":0.282642592489065,"spread":0.2544375561599931,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007882093,0.002289837,0.003319197,0.004889891,0.002511045,0.004414309,0.00374966,0.001762732,0.01759299],"category_scores_gemma":[0.04530516,0.001733007,0.002871654,0.008991838,0.001915707,0.006234578,0.004627567,0.004617319,0.01610108],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001527837,"about_ca_system_score_gemma":0.002440028,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001327625,"about_ca_topic_score_gemma":0.002835949,"domain_scores_codex":[0.993057,0.003210796,0.0006080299,0.001507841,0.001316836,0.000299402],"domain_scores_gemma":[0.9734771,0.01753556,0.001326748,0.004423298,0.002327365,0.0009099809],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001768245,0.0003257568,0.007198997,0.00619144,0.001256886,0.001034821,0.002050804,0.06303164,0.03440362,0.08461438,0.1741902,0.6239332],"study_design_scores_gemma":[0.0006543246,0.0003167105,0.005343098,0.000884993,0.0005049124,0.001637532,0.0006604679,0.364863,0.0161761,0.4237281,0.1849866,0.0002441144],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01318312,0.002054554,0.9425362,0.001122421,0.0003462735,0.0002442995,0.01073666,0.02417617,0.005600352],"genre_scores_gemma":[0.0494123,0.001055426,0.9194651,0.0003484875,0.0002879715,0.0005767195,0.02196768,0.005266751,0.0016196],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01759299,"threshold_uncertainty_score":0.05885446,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2125598538","doi":"10.1093/bioinformatics/17.2.149","title":"An information-based sequence distance and its application to whole mitochondrial genome phylogeny","year":2001,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":542,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; City University of Hong Kong","keywords":"Phylogenetics; Sequence (biology); Biology; Genome; Distance matrices in phylogeny; Evolutionary biology; Mitochondrial DNA; Edit distance; Computational biology; Computer science; Genetics; Algorithm; Bioinformatics; Gene","authors":[{"name":"Ming Li","is_ca":true},{"name":"Jonathan H. Badger","is_ca":true},{"name":"Xin Chen","is_ca":false},{"name":"Sam Kwong","is_ca":false},{"name":"Paul Kearney","is_ca":true},{"name":"Haoyong Zhang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.009646601906384321,"gpt":0.2431462677942042,"spread":0.2334996658878199,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002348432,0.0006479538,0.00061299,0.003895644,0.0008934652,0.001860047,0.0015234,0.001212225,0.002734197],"category_scores_gemma":[0.02084346,0.0003499538,0.0007375583,0.004545152,0.00159407,0.003575162,0.002826079,0.001921539,0.0008351328],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001471614,"about_ca_system_score_gemma":0.001480407,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001218242,"about_ca_topic_score_gemma":0.001192133,"domain_scores_codex":[0.9985313,0.0004682345,0.0001147781,0.0003374636,0.000474567,0.00007358803],"domain_scores_gemma":[0.9892484,0.007612381,0.0009012698,0.0007398419,0.001154596,0.0003433778],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002506724,0.0001213497,0.007961324,0.0006089273,0.0001217823,0.0003974965,0.000506155,0.3486495,0.009097769,0.3029218,0.005748019,0.3236152],"study_design_scores_gemma":[0.00002988538,0.000101003,0.002474571,0.00007038544,0.00002655755,0.0005368614,0.00008712811,0.6953413,0.00508429,0.2873219,0.008865397,0.00006069282],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01681398,0.0005238733,0.9795128,0.0003802373,0.00004093696,0.00003729853,0.0003381378,0.0005370465,0.001815704],"genre_scores_gemma":[0.2317331,0.0007497746,0.7638285,0.0001552754,0.00016505,0.0001599009,0.001247023,0.0002835426,0.001677846],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003895644,"threshold_uncertainty_score":0.01241988,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2146891463","doi":"10.1093/bioinformatics/btm604","title":"Mutual information without the influence of phylogeny or entropy dramatically improves residue contact prediction","year":2007,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":537,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"Canada Research Chairs","keywords":"Mutual information; Entropy (arrow of time); Computer science; Phylogenetic tree; Metric (unit); Information theory; Multiple sequence alignment; Computational biology; Protein family; Identification (biology); Artificial intelligence; Statistical physics; Theoretical computer science; Sequence alignment; Biology; Mathematics; Genetics; Physics; Statistics; Gene; Peptide sequence","authors":[{"name":"Stanley D. Dunn","is_ca":true},{"name":"Lindi M. Wahl","is_ca":true},{"name":"Gregory B. Gloor","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.00398317915680753,"gpt":0.2248982414525908,"spread":0.2209150622957833,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001832849,0.001026296,0.001112107,0.001859807,0.000592741,0.0009052335,0.0008925038,0.0007614742,0.001952377],"category_scores_gemma":[0.007454407,0.0004305672,0.0006542653,0.001097785,0.0005652555,0.002206326,0.001593683,0.001015703,0.0009140883],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005595154,"about_ca_system_score_gemma":0.0008713944,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001641642,"about_ca_topic_score_gemma":0.003401781,"domain_scores_codex":[0.9988754,0.0003322375,0.0000634911,0.0002559377,0.0003694822,0.0001034636],"domain_scores_gemma":[0.9971137,0.001708184,0.0003242643,0.0003780242,0.0002762147,0.0001995341],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001566705,0.0005351824,0.05036226,0.0006590985,0.0005537424,0.0004709003,0.0003204693,0.2872007,0.136481,0.009148666,0.009087847,0.5036133],"study_design_scores_gemma":[0.00003151596,0.000151608,0.008667748,0.00002265528,0.00006652721,0.0001870996,0.00002374618,0.9495293,0.03483609,0.005053828,0.001390835,0.00003916083],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4630944,0.0008953065,0.5219526,0.0004615702,0.00004941149,0.00006728773,0.001127002,0.007648244,0.004704049],"genre_scores_gemma":[0.8470877,0.0002129111,0.1496783,0.00007789148,0.0000440403,0.00004277489,0.001514359,0.0004007203,0.0009412807],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001952377,"threshold_uncertainty_score":0.009693086,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2101347991","doi":"10.1093/bioinformatics/btm585","title":"Choosing BLAST options for better detection of orthologs as reciprocal best hits","year":2007,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":535,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Wilfrid Laurier University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reciprocal; Genome; Matching (statistics); Computational biology; Computer science; Gene; Biology; Genetics; Mathematics; Statistics","authors":[{"name":"Gabriel Moreno‐Hagelsieb","is_ca":true},{"name":"Kristen Latimer","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01455614558782914,"gpt":0.2589700547250416,"spread":0.2444139091372124,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01540145,0.002624437,0.003067904,0.005493366,0.001639209,0.002498676,0.002241461,0.003002172,0.00783434],"category_scores_gemma":[0.04746468,0.001056648,0.001522264,0.004567757,0.0007438138,0.003936914,0.002075787,0.00221811,0.003971528],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004344598,"about_ca_system_score_gemma":0.0006930121,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003276186,"about_ca_topic_score_gemma":0.0005697493,"domain_scores_codex":[0.9887902,0.005271143,0.002373447,0.001580758,0.001407695,0.000576851],"domain_scores_gemma":[0.9761342,0.017237,0.001648119,0.001805024,0.002402084,0.0007735798],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.01265645,0.001041672,0.04439763,0.007303128,0.0007083691,0.003217027,0.001613004,0.006637349,0.774065,0.004615853,0.01380727,0.1299372],"study_design_scores_gemma":[0.001279686,0.003419456,0.06599035,0.0016391,0.001214136,0.008095636,0.002434434,0.1257163,0.7232352,0.01609052,0.04997454,0.0009107382],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6028555,0.004100505,0.3475278,0.001508781,0.0004203428,0.00103962,0.009453053,0.02808009,0.005014205],"genre_scores_gemma":[0.3463446,0.0006443936,0.6373175,0.0005892671,0.00006128717,0.0009814526,0.009995043,0.003437569,0.0006289431],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01540145,"threshold_uncertainty_score":0.08145154,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2171475724","doi":"10.1093/bioinformatics/btl629","title":"Assembling millions of short DNA sequences using SSAKE","year":2006,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":506,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"BC Cancer Agency","funders":"BC Cancer Agency; Michael Smith Health Research BC","keywords":"DNA sequencing; Sanger sequencing; Computational biology; Hybrid genome assembly; Biology; Sequence assembly; Genome; Software; Sequence (biology); k-mer; Leverage (statistics); Deep sequencing; Genetics; DNA; Computer science; Reference genome; Gene; Transcriptome; Artificial intelligence","authors":[{"name":"Robin M. Warren","is_ca":true},{"name":"Granger G. Sutton","is_ca":false},{"name":"Steven J.M. Jones","is_ca":true},{"name":"Robert A. Holt","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02626783783145639,"gpt":0.2625682878332075,"spread":0.2363004500017511,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008082796,0.0009473807,0.001092639,0.001102027,0.0007559796,0.001048348,0.0008335289,0.0007295684,0.006112167],"category_scores_gemma":[0.004032689,0.0006746189,0.001116904,0.001187954,0.0004490108,0.001412291,0.001268152,0.001330711,0.0092563],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002461582,"about_ca_system_score_gemma":0.0004125249,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002471157,"about_ca_topic_score_gemma":0.0008173551,"domain_scores_codex":[0.9993561,0.00009544373,0.00009421589,0.0002348501,0.0001732849,0.00004605504],"domain_scores_gemma":[0.9982609,0.0007779068,0.0002367761,0.0003558275,0.0002525958,0.000115903],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001406598,0.000159654,0.005075798,0.001721721,0.0002431811,0.0006176047,0.0008010876,0.006907922,0.7017155,0.004853942,0.008126274,0.2683707],"study_design_scores_gemma":[0.0001366108,0.0004972334,0.0044807,0.0001790488,0.0001970111,0.00143079,0.0002715543,0.07781446,0.7972476,0.009730401,0.1078824,0.000132196],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1026282,0.001433431,0.8670198,0.0002876048,0.0002446828,0.0002675462,0.003226757,0.02059858,0.004293358],"genre_scores_gemma":[0.1282411,0.0006488964,0.8556283,0.0001809485,0.00005429872,0.0004693728,0.009549356,0.001410577,0.003817175],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006112167,"threshold_uncertainty_score":0.02044719,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2109363750","doi":"10.1093/bioinformatics/btq315","title":"Count: evolutionary analysis of phylogenetic profiles with parsimony and likelihood","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":491,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Phylogenetic tree; Java; Phylogenetics; Computer science; Source code; Lineage (genetic); Maximum parsimony; Software; Biology; Gene; Programming language; Genetics; Clade","authors":[{"name":"Miklós Csűös","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.005104281382279222,"gpt":0.203892047635604,"spread":0.1987877662533248,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004291379,0.002253696,0.003014641,0.007259753,0.002110565,0.003759101,0.003562113,0.001146361,0.04902266],"category_scores_gemma":[0.02041302,0.00164739,0.002952776,0.006574394,0.001005181,0.004896378,0.003100848,0.003661533,0.01422509],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009560562,"about_ca_system_score_gemma":0.001906264,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001806646,"about_ca_topic_score_gemma":0.002294129,"domain_scores_codex":[0.9977634,0.0008522971,0.0002518818,0.0004705211,0.0005283203,0.0001335311],"domain_scores_gemma":[0.9933009,0.004564815,0.0005903922,0.0006455933,0.0006509102,0.0002473614],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001807882,0.0003394526,0.01719544,0.006283438,0.002279739,0.001409923,0.002336941,0.06049934,0.01404984,0.08490808,0.3259012,0.4829887],"study_design_scores_gemma":[0.0005973096,0.0003139613,0.01155834,0.0006310372,0.0008346972,0.00200472,0.0004924831,0.6019543,0.01141767,0.1673874,0.2023945,0.0004135287],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01554796,0.0007162609,0.8950194,0.0004561423,0.0002187499,0.0003686341,0.03265414,0.04993447,0.005084446],"genre_scores_gemma":[0.064205,0.0005164222,0.8689741,0.0001510783,0.000134391,0.001471386,0.03668071,0.02464291,0.003223941],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.04902266,"threshold_uncertainty_score":0.1639971,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2144015117","doi":"10.1093/bioinformatics/btu277","title":"Deep learning of the tissue-regulated splicing code","year":2014,"lang":"en","type":"article","venue":"Bioinformatics","topic":"RNA Research and Splicing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":487,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; Canadian Institute for Advanced Research","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Computer science; Context (archaeology); Artificial intelligence; RNA splicing; Deep learning; Source code; Machine learning; Alternative splicing; Hyperparameter; Computational biology; Graphics processing unit; Biology; Gene; RNA; Genetics; Exon","authors":[{"name":"Michael K. K. Leung","is_ca":true},{"name":"Hui Xiong","is_ca":true},{"name":"Leo J. Lee","is_ca":true},{"name":"Brendan J. Frey","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.008313087259342699,"gpt":0.2503122765791818,"spread":0.241999189319839,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004916419,0.0003675195,0.000344206,0.0003103624,0.0001682395,0.0004166865,0.0007582234,0.0005652695,0.001343121],"category_scores_gemma":[0.001598369,0.0002601683,0.0003515074,0.0004325356,0.0005058513,0.0007244131,0.0004358663,0.001154873,0.0003945103],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007366023,"about_ca_system_score_gemma":0.0006814935,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004104778,"about_ca_topic_score_gemma":0.006095548,"domain_scores_codex":[0.9999011,0.00002134384,0.000004296181,0.00003260711,0.00002238837,0.00001829725],"domain_scores_gemma":[0.9995207,0.0002292199,0.00005554183,0.00005260737,0.0001095068,0.00003245939],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001006532,0.00005184995,0.00446269,0.00006597708,0.00004239759,0.0001006494,0.00005003619,0.8945782,0.01485015,0.01714457,0.001949048,0.06660387],"study_design_scores_gemma":[0.000003471087,0.000006881207,0.0003800974,0.00000351262,0.000003109929,0.00001344268,0.000003213331,0.9885462,0.001490914,0.009365415,0.0001806613,0.000003051852],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2395192,0.0004258672,0.7546957,0.0008370077,0.00004856717,0.00002197343,0.0008227018,0.0009909426,0.002638099],"genre_scores_gemma":[0.921198,0.0002870115,0.07360359,0.0001958406,0.00002922864,0.00004981618,0.001046205,0.00007034257,0.003520112],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004104778,"threshold_uncertainty_score":0.008161783,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2346950316","doi":"10.1093/bioinformatics/btw228","title":"Drug repositioning based on comprehensive similarity measures and Bi-Random walk algorithm","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":470,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Saskatchewan","funders":"Program for New Century Excellent Talents in University; U.S. Food and Drug Administration; National Natural Science Foundation of China; Stowers Institute for Medical Research","keywords":"Similarity (geometry); Drug repositioning; Drug; Computer science; Disease; Random walk; Machine learning; Drug development; Data mining; Artificial intelligence; Mathematics; Medicine; Statistics; Pharmacology","authors":[{"name":"Huimin Luo","is_ca":false},{"name":"Jianxin Wang","is_ca":false},{"name":"Min Li","is_ca":false},{"name":"Junwei Luo","is_ca":false},{"name":"Xiaoqing Peng","is_ca":false},{"name":"Fang‐Xiang Wu","is_ca":true},{"name":"Yi Pan","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02364108547326174,"gpt":0.2691134950196628,"spread":0.2454724095464011,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009382617,0.001060177,0.001972119,0.002943567,0.0005333252,0.0009480782,0.001732554,0.001370799,0.001643791],"category_scores_gemma":[0.002888524,0.000478305,0.001233205,0.001888738,0.0005628614,0.001558106,0.0009462071,0.0008045538,0.0003537487],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007669459,"about_ca_system_score_gemma":0.001526616,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006409603,"about_ca_topic_score_gemma":0.005367205,"domain_scores_codex":[0.9991711,0.0001876641,0.00009366151,0.0002197232,0.0002504481,0.00007739447],"domain_scores_gemma":[0.99886,0.0005776254,0.0001778875,0.0000915309,0.0001987851,0.00009417343],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001103524,0.0001680975,0.00320752,0.0001583078,0.0001457237,0.0001628368,0.00005396845,0.8350003,0.002484581,0.007546526,0.001779542,0.1491821],"study_design_scores_gemma":[0.000009408142,0.00002994204,0.0001443801,0.000003473412,0.00001239614,0.0000342973,0.000004214147,0.9976914,0.0002831649,0.001601521,0.0001807823,0.00000498867],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0411038,0.0006829105,0.9551173,0.0002235298,0.00004837935,0.00017158,0.000140434,0.0008871612,0.001624979],"genre_scores_gemma":[0.5372532,0.0005936229,0.4578458,0.0002109184,0.00007406106,0.0004504354,0.0008731072,0.0001139107,0.00258492],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006409603,"threshold_uncertainty_score":0.01274461,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2269649163","doi":"10.1093/bioinformatics/btw252","title":"Classifying and segmenting microscopy images with deep multiple instance learning","year":2016,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":449,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Nvidia","keywords":"Pooling; Artificial intelligence; Convolutional neural network; Computer science; Pattern recognition (psychology); Segmentation; Deep learning; Feature (linguistics); Microscopy; Pixel; Contextual image classification; Machine learning; Computer vision; Image (mathematics)","authors":[{"name":"Oren Kraus","is_ca":true},{"name":"Jimmy Ba","is_ca":true},{"name":"Brendan J. Frey","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.005466362266401763,"gpt":0.232331095263102,"spread":0.2268647329967002,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008694059,0.00117396,0.0005763955,0.0008989658,0.0003337716,0.001129354,0.002074155,0.001040791,0.002805634],"category_scores_gemma":[0.002250276,0.0005613337,0.0007966441,0.001041529,0.000665987,0.001878366,0.001118359,0.001604627,0.001607862],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001225008,"about_ca_system_score_gemma":0.0008391787,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00472064,"about_ca_topic_score_gemma":0.005642443,"domain_scores_codex":[0.9995301,0.00005632332,0.00003058498,0.00020203,0.0001210975,0.00005993437],"domain_scores_gemma":[0.9992092,0.0002000166,0.0001486113,0.000222064,0.0001641569,0.00005591803],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004650955,0.0003908076,0.007303204,0.0004686926,0.0001845631,0.0003233078,0.0001233135,0.2686735,0.1531197,0.008284786,0.01476449,0.5458985],"study_design_scores_gemma":[0.000009698023,0.00004508037,0.001490837,0.00001825669,0.000023121,0.00008726282,0.00002831269,0.9165812,0.07404254,0.005044286,0.002611697,0.00001763801],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06715748,0.0006550043,0.9133796,0.0006891648,0.00006013166,0.0001493363,0.001772044,0.01358616,0.002551069],"genre_scores_gemma":[0.3999055,0.0005197762,0.5898533,0.0002692629,0.00005397101,0.0001669591,0.005851295,0.0004068594,0.002973181],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00472064,"threshold_uncertainty_score":0.009386301,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2118446779","doi":"10.1093/bioinformatics/btg415","title":"Functional topology in a network of protein interactions","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":430,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computational biology; Computer science; Network analysis; Function (biology); Interaction network; Construct (python library); Mutation; Protein–protein interaction; Network model; Set (abstract data type); Biological network; Biology; Genetics; Artificial intelligence; Gene; Computer network","authors":[{"name":"Nataša Pržulj","is_ca":true},{"name":"Dennis A. Wigle","is_ca":true},{"name":"Igor Jurišica","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01075372265891568,"gpt":0.2299940728744953,"spread":0.2192403502155796,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006128907,0.0004441072,0.000349894,0.002250802,0.0004987887,0.0009202961,0.0005447247,0.0005775105,0.001698239],"category_scores_gemma":[0.004961294,0.0002276978,0.0003990685,0.001622444,0.0009784726,0.001564889,0.0004903215,0.0003864513,0.0002584185],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007528014,"about_ca_system_score_gemma":0.0004173325,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001622155,"about_ca_topic_score_gemma":0.001315127,"domain_scores_codex":[0.9994994,0.0001998096,0.00002982245,0.0001297702,0.0001149048,0.00002633213],"domain_scores_gemma":[0.9965444,0.002625245,0.0004052622,0.0001323482,0.0001837174,0.0001091311],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.0001474229,0.00006410307,0.02313856,0.0004715486,0.0001143489,0.0005538298,0.0001964448,0.8793411,0.007877604,0.05905986,0.001059074,0.02797616],"study_design_scores_gemma":[0.00001516301,0.00004870294,0.006570697,0.00003224002,0.00005019988,0.0004542802,0.00005634917,0.8732211,0.002173974,0.1150187,0.002341024,0.00001766725],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6054022,0.001363187,0.3832875,0.00112069,0.00002400826,0.00007942757,0.002356556,0.000740351,0.005626101],"genre_scores_gemma":[0.9561072,0.0005972569,0.04083288,0.00005572345,0.00001986754,0.00007041793,0.001731087,0.0000379019,0.0005477352],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002250802,"threshold_uncertainty_score":0.005681157,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2172358623","doi":"10.1093/bioinformatics/btv693","title":"Genefu: an R/Bioconductor package for computation of gene expression-based signatures in breast cancer","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":410,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"National Cancer Institute; Cancer Research Society; Canadian Institutes of Health Research; Instituto de Salud Carlos III; Banco Bilbao Vizcaya Argentaria; Fondation Brain Canada","keywords":"Bioconductor; Compendium; Subtyping; Computer science; R package; Breast cancer; Source code; Computational biology; Data mining; Bioinformatics; Cancer; Gene; Biology; Programming language; Genetics","authors":[{"name":"Deena M.A. Gendoo","is_ca":true},{"name":"Natchar Ratanasirigulchai","is_ca":true},{"name":"Markus Schröder","is_ca":false},{"name":"Laia Paré","is_ca":false},{"name":"Joel S. Parker","is_ca":false},{"name":"Aleix Prat","is_ca":false},{"name":"Benjamin Haibe‐Kains","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03109304409576368,"gpt":0.3002827501170188,"spread":0.2691897060212551,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004921597,0.003409109,0.003888082,0.004686331,0.001197075,0.003068876,0.006291312,0.001723204,0.07262591],"category_scores_gemma":[0.01833904,0.001621294,0.002861573,0.006439942,0.0009837315,0.002171446,0.003517039,0.003388315,0.08145295],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001361496,"about_ca_system_score_gemma":0.005068794,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007072493,"about_ca_topic_score_gemma":0.007580501,"domain_scores_codex":[0.9968036,0.0009417438,0.0002890245,0.0008847995,0.0008084525,0.000272284],"domain_scores_gemma":[0.9933709,0.003148016,0.0005630314,0.001084406,0.001488089,0.0003455235],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007485022,0.00005990236,0.003964307,0.004000402,0.001056487,0.0002747306,0.0003192693,0.006423289,0.003486944,0.009514165,0.8967363,0.07341562],"study_design_scores_gemma":[0.000613947,0.0001920396,0.01163744,0.001083643,0.0009098543,0.0008947784,0.0001627456,0.09261557,0.01148938,0.05323693,0.8268584,0.0003052361],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"software","genre_gemma":"software","genre_scores_codex":[0.004503896,0.004724947,0.3292332,0.002177115,0.001099189,0.0005680693,0.2724838,0.3721277,0.01308201],"genre_scores_gemma":[0.04705314,0.003301325,0.501153,0.002353496,0.000393478,0.006189192,0.3027973,0.1187409,0.01801822],"genre_candidate":"software","genre_consensus":"software","teacher_disagreement_score":0.07262591,"threshold_uncertainty_score":0.2429578,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2112491476","doi":"10.1093/bioinformatics/btp367","title":"<i>De novo</i> transcriptome assembly with ABySS","year":2009,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":410,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"BC Cancer Agency","funders":"Genome British Columbia; Michael Smith Health Research BC; National Cancer Institute; Genome Canada","keywords":"Contig; Sequence assembly; Transcriptome; Genome; Computational biology; Java; Biology; De novo transcriptome assembly; Software; Computer science; Hybrid genome assembly; Source code; Shotgun sequencing; Reference genome; Perl; Genetics; Gene; Programming language; Gene expression","authors":[{"name":"İnanç Birol","is_ca":true},{"name":"Shaun D. Jackman","is_ca":true},{"name":"Cydney Nielsen","is_ca":true},{"name":"Jenny Q. Qian","is_ca":true},{"name":"Richard Varhol","is_ca":true},{"name":"Greg Stazyk","is_ca":true},{"name":"Ryan D. Morin","is_ca":true},{"name":"Yongjun Zhao","is_ca":true},{"name":"Martin Hirst","is_ca":true},{"name":"Jacqueline E. Schein","is_ca":true},{"name":"Doug Horsman","is_ca":true},{"name":"Joseph M. Connors","is_ca":true},{"name":"Randy D. Gascoyne","is_ca":true},{"name":"Marco A. Marra","is_ca":true},{"name":"Steven J.M. Jones","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.009809137250629119,"gpt":0.2413464444821044,"spread":0.2315373072314753,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001255243,0.00135697,0.001077289,0.001365208,0.001240932,0.001417599,0.001341532,0.000473187,0.01085775],"category_scores_gemma":[0.002508519,0.0007159594,0.0009406978,0.001998946,0.0003408731,0.0009607808,0.001017283,0.001632274,0.01074004],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006508848,"about_ca_system_score_gemma":0.001148939,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002905208,"about_ca_topic_score_gemma":0.002795181,"domain_scores_codex":[0.9993291,0.00009023656,0.00007970218,0.0002475982,0.00018667,0.00006675911],"domain_scores_gemma":[0.9990481,0.0002372529,0.0001380167,0.0002157884,0.0002767429,0.00008413003],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001874581,0.0003061548,0.009438693,0.00243257,0.0002616401,0.0007770505,0.001042124,0.01291445,0.6658593,0.007731067,0.1010009,0.1963614],"study_design_scores_gemma":[0.0002451697,0.0003221306,0.01809814,0.0002120205,0.0001896128,0.001120157,0.000238528,0.118048,0.6131237,0.0142615,0.2339628,0.0001782109],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.07456221,0.000832986,0.7816455,0.0007854522,0.0004173405,0.0006638335,0.05449798,0.07887584,0.007718813],"genre_scores_gemma":[0.05934261,0.0006425941,0.8372577,0.0002591162,0.0001018689,0.001048399,0.08777719,0.008014159,0.00555637],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.01085775,"threshold_uncertainty_score":0.03632283,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2955502047","doi":"10.1093/bioinformatics/btz318","title":"MOLI: multi-omics late integration with deep neural networks for drug response prediction","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":407,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"Canadian Institutes of Health Research; Terry Fox Foundation; Canada Foundation for Innovation","keywords":"Drug response; Computer science; Representation (politics); Machine learning; Artificial intelligence; Omics; Precision oncology; Artificial neural network; Computational biology; Data mining; Drug; Precision medicine; Bioinformatics; Biology","authors":[{"name":"Hossein Sharifi-Noghabi","is_ca":true},{"name":"Olga Zolotareva","is_ca":false},{"name":"Colin C. Collins","is_ca":true},{"name":"Martin Ester","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.007039244457505459,"gpt":0.2143085593870241,"spread":0.2072693149295187,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001739378,0.002151058,0.001500639,0.001420994,0.0003407212,0.001088042,0.001988208,0.001601907,0.002113415],"category_scores_gemma":[0.003012094,0.0005651776,0.001466643,0.001239714,0.0003870634,0.001129382,0.00156821,0.00254249,0.0007691149],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001722425,"about_ca_system_score_gemma":0.001431206,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006165219,"about_ca_topic_score_gemma":0.007571811,"domain_scores_codex":[0.999433,0.000142246,0.00003323162,0.0001440732,0.0001537544,0.00009368087],"domain_scores_gemma":[0.9993058,0.0003177108,0.0001189667,0.0000732386,0.0001291748,0.00005503238],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007902061,0.0006774492,0.01439816,0.0006097226,0.0008572573,0.0003581514,0.0001129249,0.5752792,0.01511381,0.004018153,0.0210484,0.3667366],"study_design_scores_gemma":[0.00001442192,0.00006682864,0.0005470891,0.00001697918,0.00003852174,0.00002724667,0.00000668726,0.9940704,0.00217333,0.002161146,0.0008648022,0.00001257087],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1085525,0.008728731,0.8443263,0.003481431,0.0003549055,0.0004281357,0.006199761,0.02209473,0.005833456],"genre_scores_gemma":[0.6858149,0.001661355,0.2897608,0.002354423,0.0003307235,0.0007332042,0.01255741,0.0004341541,0.006353132],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006165219,"threshold_uncertainty_score":0.01249713,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2107861779","doi":"10.1093/bioinformatics/btp253","title":"Fluctuation AnaLysis CalculatOR: a web tool for the determination of mutation rate using Luria–Delbrück fluctuation analysis","year":2009,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Evolution and Genetic Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":405,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Brock University","funders":"U.S. Public Health Service; National Institutes of Health","keywords":"Calculator; Java applet; Computer science; Java; Estimator; Mutation testing; Mutation; Programming language; Operating system; Statistics; Biology; Genetics; Mathematics; Gene","authors":[{"name":"Brandon M. Hall","is_ca":true},{"name":"Chang‐Xing Ma","is_ca":true},{"name":"Ping Liang","is_ca":true},{"name":"Keshav K. Singh","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01108313750975241,"gpt":0.2770608778069041,"spread":0.2659777402971517,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002116491,0.001909998,0.002091875,0.003910659,0.0007743476,0.00138152,0.002831221,0.0008577561,0.04108955],"category_scores_gemma":[0.006309549,0.0009631705,0.001014609,0.002233298,0.0003558017,0.001304477,0.001421908,0.001896192,0.023132],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005609775,"about_ca_system_score_gemma":0.0009137205,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001146915,"about_ca_topic_score_gemma":0.001074541,"domain_scores_codex":[0.9987601,0.0002194994,0.0001433344,0.0002753047,0.0005195957,0.00008217471],"domain_scores_gemma":[0.997229,0.001340285,0.0002984709,0.0003389583,0.0006514051,0.0001417954],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001131369,0.0004597708,0.008780741,0.002032836,0.0004168366,0.0007355249,0.0004465247,0.006154893,0.08343007,0.008711472,0.4561118,0.4315882],"study_design_scores_gemma":[0.0004716736,0.0004839627,0.02095181,0.0004018901,0.0002867991,0.001974032,0.0001323694,0.3445713,0.2938215,0.01561482,0.3205573,0.0007325007],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.007161888,0.0003669891,0.614564,0.000205547,0.0001673892,0.0003552667,0.01582485,0.3580134,0.00334074],"genre_scores_gemma":[0.05560883,0.000603969,0.8291672,0.0004239366,0.0001377433,0.003791517,0.033908,0.06436624,0.01199247],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.04108955,"threshold_uncertainty_score":0.1374582,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2153369847","doi":"10.1093/bioinformatics/btq588","title":"Interactive microbial genome visualization with GView","year":2010,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":400,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba; Public Health Agency of Canada; University of Alberta","funders":"","keywords":"Bitmap; Computer science; Zoom; Application programming interface; Interface (matter); Java; Documentation; File format; Visualization; Context (archaeology); Source code; Scalable Vector Graphics; Programming language; Graphical user interface; MIT License; Scalability; User interface; Operating system; World Wide Web; Computer graphics (images); License; Data mining; Biology","authors":[{"name":"Aaron Petkau","is_ca":true},{"name":"Matthew Stuart-Edwards","is_ca":true},{"name":"Paul Stothard","is_ca":true},{"name":"Gary Van Domselaar","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.006221952275581206,"gpt":0.2327077491382062,"spread":0.226485796862625,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009544757,0.001148939,0.0007731896,0.002333168,0.0004062486,0.001576171,0.00195157,0.0008963703,0.08995217],"category_scores_gemma":[0.00337201,0.00059023,0.001098224,0.0014766,0.0002321809,0.001669857,0.003183065,0.001501014,0.0167938],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003288137,"about_ca_system_score_gemma":0.0006892374,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001901838,"about_ca_topic_score_gemma":0.001705559,"domain_scores_codex":[0.9995605,0.00006894615,0.00003448588,0.00009783517,0.0001739308,0.00006426518],"domain_scores_gemma":[0.9990183,0.0004559599,0.00005440271,0.0001427407,0.0002078643,0.000120763],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001082654,0.0001425658,0.002023908,0.002075815,0.0002575171,0.0007605843,0.0009508542,0.007087052,0.05715191,0.01180854,0.6027104,0.3139482],"study_design_scores_gemma":[0.0005855103,0.0001396367,0.00565584,0.0005239446,0.0001397647,0.001173472,0.0002644437,0.1019655,0.06962352,0.02633769,0.7932963,0.0002943894],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"software","genre_gemma":"software","genre_scores_codex":[0.0090901,0.0006342679,0.4556977,0.0007491737,0.000419073,0.0002055849,0.03239768,0.4785296,0.02227695],"genre_scores_gemma":[0.1310526,0.001316108,0.6520041,0.0009339183,0.0003492918,0.0009889537,0.1002553,0.0882274,0.02487235],"genre_candidate":"software","genre_consensus":"software","teacher_disagreement_score":0.08995217,"threshold_uncertainty_score":0.30092,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2158376448","doi":"10.1093/bioinformatics/btp045","title":"QMSim: a large-scale genome simulator for livestock","year":2009,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic and phenotypic traits in livestock","field":"Biochemistry, Genetics and Molecular Biology","cited_by":399,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Executable; Computer science; Population; Scale (ratio); Pedigree chart; Programming language; Biology; Genetics; Cartography; Geography","authors":[{"name":"Mehdi Sargolzaei","is_ca":true},{"name":"Flávio S. Schenkel","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01019544802522883,"gpt":0.2439689393708104,"spread":0.2337734913455816,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001057875,0.0007405737,0.0006735374,0.000447305,0.0005473911,0.0007405279,0.002415678,0.001005373,0.01768017],"category_scores_gemma":[0.002807671,0.0005641026,0.0007690665,0.0007894905,0.0003548282,0.0009383301,0.0008894645,0.001326102,0.002447979],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007502232,"about_ca_system_score_gemma":0.001297231,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007645097,"about_ca_topic_score_gemma":0.00439309,"domain_scores_codex":[0.9997515,0.00008885522,0.000016789,0.00003162896,0.00007691523,0.00003427232],"domain_scores_gemma":[0.9989061,0.0006268608,0.00005560767,0.00009284828,0.0002005714,0.0001180072],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003208559,0.0001131822,0.003934341,0.0002910506,0.0001403764,0.0002254175,0.0002046946,0.9275572,0.004483797,0.01276943,0.02908901,0.02087056],"study_design_scores_gemma":[0.00007776424,0.00002121468,0.0002333787,0.00001017984,0.0000121603,0.00002090915,0.0000137778,0.9877837,0.001310844,0.002190436,0.008314315,0.0000112221],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09020126,0.0005436103,0.7987743,0.0008882784,0.0003382442,0.0004364775,0.01809549,0.06377664,0.0269457],"genre_scores_gemma":[0.5454764,0.0007506418,0.4106079,0.0004990269,0.00008802974,0.001899693,0.0199645,0.009189866,0.01152398],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01768017,"threshold_uncertainty_score":0.05914605,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2121621283","doi":"10.1093/bioinformatics/btg004","title":"IslandPath: aiding detection of genomic islands in prokaryotes","year":2003,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Salmonella and Campylobacter epidemiology","field":"Agricultural and Biological Sciences","cited_by":395,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"BC Cancer Agency; Simon Fraser University","funders":"","keywords":"Computational biology; Computer science; Biology","authors":[{"name":"William Hsiao","is_ca":true},{"name":"Ivan Wan","is_ca":true},{"name":"Steven J.M. Jones","is_ca":true},{"name":"Fiona S. L. Brinkman","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02301700446856152,"gpt":0.2163937504433632,"spread":0.1933767459748017,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012954,0.001704747,0.001041787,0.002008042,0.0006668088,0.001242543,0.001742657,0.0009301726,0.01035489],"category_scores_gemma":[0.005051598,0.0006470698,0.000786912,0.00191658,0.0003090026,0.001487573,0.00138516,0.00109684,0.007231247],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002841019,"about_ca_system_score_gemma":0.0006446707,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0015695,"about_ca_topic_score_gemma":0.002720685,"domain_scores_codex":[0.9995178,0.0001240594,0.00003178289,0.0001464981,0.0001401852,0.00003959532],"domain_scores_gemma":[0.9982534,0.001073994,0.0001618737,0.0001821926,0.0001775094,0.0001510165],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002707924,0.000364794,0.02665199,0.003605108,0.0004725782,0.0008387154,0.0009848278,0.008002048,0.1098136,0.004548796,0.1962157,0.6457939],"study_design_scores_gemma":[0.0009641919,0.0005951552,0.04131516,0.0004740287,0.0005491953,0.002514456,0.0005115681,0.4960079,0.1698033,0.02489361,0.2619899,0.0003815439],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.05524239,0.001405873,0.5658828,0.001057815,0.0003342737,0.0004944411,0.03073762,0.3389094,0.005935413],"genre_scores_gemma":[0.1250545,0.0007762692,0.8204612,0.0002694001,0.0001226851,0.0006622626,0.03987972,0.008291608,0.004482321],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.01035489,"threshold_uncertainty_score":0.03464061,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2157460239","doi":"10.1093/bioinformatics/btt178","title":"Assembling the 20 Gb white spruce (<i>Picea glauca</i>) genome from whole-genome shotgun sequencing data","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":393,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Ministry of Forests; Government of British Columbia; Simon Fraser University; University of British Columbia","funders":"BC Cancer Agency; Canada's Michael Smith Genome Sciences Centre","keywords":"Shotgun sequencing; Sequence assembly; Genome; Shotgun; Hybrid genome assembly; Biology; Computational biology; Whole genome sequencing; Illumina dye sequencing; Genomics; DNA sequencing; Reference genome; Genome project; Genetics; Gene; Transcriptome","authors":[{"name":"İnanç Birol","is_ca":true},{"name":"Anthony Raymond","is_ca":true},{"name":"Shaun D. Jackman","is_ca":true},{"name":"Stephen Pleasance","is_ca":true},{"name":"Robin Coope","is_ca":true},{"name":"Greg Taylor","is_ca":true},{"name":"Macaire M. S. Yuen","is_ca":true},{"name":"Christopher I. Keeling","is_ca":true},{"name":"Dana Brand","is_ca":true},{"name":"Benjamin P. Vandervalk","is_ca":true},{"name":"Heather Kirk","is_ca":true},{"name":"Pawan Pandoh","is_ca":true},{"name":"Richard A. Moore","is_ca":true},{"name":"Yongjun Zhao","is_ca":true},{"name":"Andrew J. Mungall","is_ca":true},{"name":"Barry Jaquish","is_ca":true},{"name":"Alvin D. Yanchuk","is_ca":true},{"name":"Carol Ritland","is_ca":true},{"name":"Brian Boyle","is_ca":true},{"name":"Jean Bousquet","is_ca":true},{"name":"Kermit Ritland","is_ca":true},{"name":"John Mackay","is_ca":true},{"name":"Jörg Bohlmann","is_ca":true},{"name":"Steven J.M. Jones","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03217634457678138,"gpt":0.2396316445186623,"spread":0.2074552999418809,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008666149,0.0008359649,0.0006161659,0.001517992,0.0006513023,0.001039739,0.0007928949,0.0005862614,0.003696506],"category_scores_gemma":[0.001974236,0.0003807701,0.0009790224,0.00203354,0.000292903,0.0007119552,0.0006541586,0.0008298098,0.0032847],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005527181,"about_ca_system_score_gemma":0.001071087,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005677532,"about_ca_topic_score_gemma":0.007789088,"domain_scores_codex":[0.9996812,0.00003770834,0.00003674999,0.0001165264,0.00008330715,0.00004459633],"domain_scores_gemma":[0.9991251,0.0002025463,0.000158117,0.000130366,0.0002488006,0.0001350872],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0009240587,0.0001953109,0.01590683,0.001442071,0.0001924875,0.000866849,0.0006140429,0.003116308,0.8851888,0.001364769,0.01100132,0.07918723],"study_design_scores_gemma":[0.0002916028,0.001237107,0.2325193,0.0007231894,0.001107949,0.002666635,0.001138089,0.03239522,0.5325257,0.005450283,0.1896995,0.0002454037],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5811459,0.003464007,0.2507219,0.001127612,0.000595815,0.0008032093,0.1405219,0.01154391,0.01007576],"genre_scores_gemma":[0.2555579,0.002540465,0.3559116,0.0003065867,0.000148806,0.0003877671,0.3781309,0.001398547,0.005617426],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005677532,"threshold_uncertainty_score":0.01236606,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2139627484","doi":"10.1093/bioinformatics/btp030","title":"IslandViewer: an integrated interface for computational identification and visualization of genomic islands","year":2009,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Salmonella and Campylobacter epidemiology","field":"Agricultural and Biological Sciences","cited_by":392,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"SFU Community Trust Endowment Fund; Canadian Institutes of Health Research; Michael Smith Health Research BC; Genome Canada","keywords":"Upload; Computer science; Graphical user interface; Interface (matter); Visualization; MIT License; License; Source code; Identification (biology); Web service; User interface; Genomics; Data mining; Comparative genomics; Chromosome; Hidden Markov model; Computational biology; Genome; World Wide Web; Biology; Artificial intelligence; Gene; Operating system; Genetics","authors":[{"name":"Morgan G. I. Langille","is_ca":true},{"name":"Fiona S. L. Brinkman","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02674891515514453,"gpt":0.2853578140212567,"spread":0.2586088988661122,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001943266,0.00252773,0.00215611,0.002475863,0.0005405461,0.001966515,0.004688155,0.001698654,0.1039722],"category_scores_gemma":[0.004748511,0.001603075,0.001476369,0.001652853,0.000433373,0.002882213,0.003220201,0.002776684,0.03038888],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005281208,"about_ca_system_score_gemma":0.001011914,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00260145,"about_ca_topic_score_gemma":0.003085962,"domain_scores_codex":[0.999431,0.0001187115,0.0000635803,0.0001184062,0.0002065604,0.00006172011],"domain_scores_gemma":[0.9981969,0.00107452,0.00008847228,0.0001811985,0.0002418519,0.000217194],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002218198,0.000331328,0.003196452,0.002750595,0.0005629035,0.0008366458,0.000851716,0.01536505,0.03016124,0.008643794,0.6683619,0.2667202],"study_design_scores_gemma":[0.001931315,0.0003369105,0.008712871,0.0007383265,0.0002792596,0.001259037,0.0002437272,0.4013804,0.04882584,0.02991175,0.5057373,0.0006431837],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"software","genre_gemma":"software","genre_scores_codex":[0.003856155,0.000559831,0.4207924,0.0002873071,0.0001659869,0.0003513022,0.04737673,0.5216063,0.005003936],"genre_scores_gemma":[0.04414479,0.001425052,0.6938098,0.0005800774,0.0001681879,0.002951225,0.1519078,0.089513,0.01550013],"genre_candidate":"software","genre_consensus":"software","teacher_disagreement_score":0.1039722,"threshold_uncertainty_score":0.3478218,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2168220711","doi":"10.1093/bioinformatics/bts209","title":"MoRFpred, a computational tool for sequence-based prediction and characterization of short disorder-to-order transitioning binding regions in proteins","year":2012,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":369,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"U.S. National Library of Medicine; Natural Sciences and Engineering Research Council of Canada; Killam Trusts; Russian Academy of Sciences; National Institutes of Health; National Science Foundation","keywords":"Sequence (biology); Support vector machine; Computer science; Computational biology; Intrinsically disordered proteins; Artificial intelligence; Chemistry; Biology; Biochemistry","authors":[{"name":"Fatemeh Miri Disfani","is_ca":true},{"name":"Wei-Lun Hsu","is_ca":true},{"name":"Marcin J. Mizianty","is_ca":true},{"name":"Christopher J. Oldfield","is_ca":true},{"name":"Bin Xue","is_ca":true},{"name":"A. Keith Dunker","is_ca":true},{"name":"Vladimir N. Uversky","is_ca":true},{"name":"Lukasz Kurgan","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01248384632375651,"gpt":0.2417982339169962,"spread":0.2293143875932397,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001167401,0.001407384,0.001313724,0.001668484,0.0006991343,0.0007788304,0.001530588,0.001003316,0.002189916],"category_scores_gemma":[0.002845216,0.0005999394,0.001125751,0.0008350879,0.0004118915,0.001046298,0.0008345124,0.001215583,0.001000144],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007827974,"about_ca_system_score_gemma":0.001402283,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003041266,"about_ca_topic_score_gemma":0.006072129,"domain_scores_codex":[0.9995543,0.00008190772,0.00002825681,0.0001696265,0.0001320973,0.00003371117],"domain_scores_gemma":[0.9989905,0.0005345522,0.0001824407,0.00009481351,0.0001165438,0.00008113759],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002700759,0.0009115653,0.03943468,0.002966034,0.001195227,0.001423501,0.0003805482,0.465318,0.1151531,0.011403,0.08887684,0.2702368],"study_design_scores_gemma":[0.00009653487,0.000150809,0.002470498,0.00004577897,0.00005758618,0.0002997588,0.00003963722,0.9718992,0.01526031,0.003182569,0.006459316,0.00003803885],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.302891,0.003085799,0.5657097,0.0007559659,0.0001755714,0.0003951465,0.0203743,0.1025927,0.004019872],"genre_scores_gemma":[0.3697949,0.0009901483,0.5915069,0.0004812914,0.00007706819,0.0006662846,0.03197681,0.002748187,0.001758425],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003041266,"threshold_uncertainty_score":0.007325947,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2140154634","doi":"10.1093/bioinformatics/btr046","title":"SHRiMP2: Sensitive yet Practical Short Read Mapping","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":365,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Executable; Computer science; Shrimp; Space (punctuation); Sensitivity (control systems); Source code; Code (set theory); Data mining; Programming language; Biology; Operating system; Engineering; Set (abstract data type)","authors":[{"name":"Matei David","is_ca":true},{"name":"Misko Dzamba","is_ca":true},{"name":"D. A. LISTER","is_ca":true},{"name":"Lucian Ilie","is_ca":true},{"name":"Michael Brudno","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0499284744864106,"gpt":0.2654698643525903,"spread":0.2155413898661797,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003281861,0.002035207,0.001003576,0.0008575113,0.0009245406,0.001868995,0.002867581,0.000774864,0.02306305],"category_scores_gemma":[0.006511597,0.001474684,0.001340981,0.001019792,0.0004734839,0.001572559,0.003574281,0.003048306,0.01651144],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004534078,"about_ca_system_score_gemma":0.001232424,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001389093,"about_ca_topic_score_gemma":0.001953835,"domain_scores_codex":[0.9981798,0.0002855566,0.0001541432,0.00053369,0.0007267412,0.0001202535],"domain_scores_gemma":[0.9975883,0.0007535549,0.0001450046,0.0006741054,0.0006241862,0.0002148341],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002725861,0.0002013592,0.006769337,0.001923806,0.0004461163,0.0007369116,0.0006977162,0.01033531,0.2854612,0.007964789,0.3340289,0.3487087],"study_design_scores_gemma":[0.0006062617,0.000471779,0.006096875,0.0002517429,0.0001392808,0.001237927,0.0001614866,0.09837721,0.3542326,0.01344786,0.5245686,0.0004084595],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.02522522,0.0006005464,0.7541982,0.0007038187,0.001052698,0.0006012954,0.03554086,0.1722401,0.009837268],"genre_scores_gemma":[0.0849712,0.0005171804,0.7402457,0.001087837,0.0002682364,0.001682209,0.1020674,0.04038066,0.02877953],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.02306305,"threshold_uncertainty_score":0.07715362,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2151790371","doi":"10.1093/bioinformatics/btg447","title":"Predicting subcellular localization of proteins using machine-learned classifiers","year":2004,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":334,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Subcellular localization; Computer science; Artificial intelligence; Protein subcellular localization prediction; Machine learning; Computational biology; Pattern recognition (psychology); Chemistry; Biology; Biochemistry; Cytoplasm; Gene","authors":[{"name":"Zhonghua Lu","is_ca":true},{"name":"Duane Szafron","is_ca":false},{"name":"Russell Greiner","is_ca":false},{"name":"P. Lu","is_ca":false},{"name":"David S. Wishart","is_ca":false},{"name":"Brett Poulin","is_ca":false},{"name":"John Anvik","is_ca":false},{"name":"Cam Macdonell","is_ca":false},{"name":"Roman Eisner","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01636032850905748,"gpt":0.2565539395148381,"spread":0.2401936110057807,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001605731,0.0009999998,0.0007692644,0.001827884,0.0005086212,0.001224818,0.0008635198,0.001301174,0.001374691],"category_scores_gemma":[0.005892015,0.0002012723,0.0005536355,0.001272891,0.0003884324,0.001383709,0.0003916012,0.001137074,0.001704004],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000727628,"about_ca_system_score_gemma":0.0009743246,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003008402,"about_ca_topic_score_gemma":0.002507197,"domain_scores_codex":[0.9992713,0.0001848781,0.00007172086,0.0001886365,0.000188052,0.00009529493],"domain_scores_gemma":[0.9945561,0.003391995,0.0004762525,0.0002372805,0.001192959,0.0001454284],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006753776,0.0007225715,0.1302864,0.0007647161,0.0002735602,0.0006887997,0.0001330424,0.3642166,0.02794119,0.002958906,0.0189751,0.4523638],"study_design_scores_gemma":[0.00003002292,0.00008338333,0.006273776,0.00005533452,0.00007263832,0.0001989223,0.00004289263,0.9678016,0.01913107,0.004038227,0.002253691,0.00001845828],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5351475,0.003599474,0.44152,0.001714312,0.0002897501,0.0001707505,0.005740761,0.006227084,0.005590328],"genre_scores_gemma":[0.8100172,0.0009264064,0.1773298,0.0003020031,0.0001677151,0.0001253299,0.00926194,0.000101916,0.00176776],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003008402,"threshold_uncertainty_score":0.008492053,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2022441134","doi":"10.1093/bioinformatics/btg182","title":"Class prediction and discovery using gene microarray andproteomics mass spectroscopy data: curses, caveats, cautions","year":2003,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":332,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada; National Research Council Institute for Biodiagnostics","funders":"","keywords":"Computer science; Curse of dimensionality; Artificial intelligence; Pattern recognition (psychology); Feature (linguistics); Relevance (law); Data mining; Microarray analysis techniques; Identification (biology); Outlier; Machine learning; Biology; Gene","authors":[{"name":"Ray Somorjai","is_ca":true},{"name":"B. Dolenko","is_ca":true},{"name":"Richard Baumgartner","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02672686303689213,"gpt":0.270721456698394,"spread":0.2439945936615018,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1796042,0.001531537,0.002446074,0.00530771,0.004426388,0.006545733,0.007214189,0.003686488,0.002363728],"category_scores_gemma":[0.4895865,0.0009583092,0.001863114,0.005488106,0.009792486,0.00741513,0.004712669,0.010185,0.002040396],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002325916,"about_ca_system_score_gemma":0.004105507,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01178083,"about_ca_topic_score_gemma":0.02010186,"domain_scores_codex":[0.8853942,0.0689757,0.01307398,0.005416232,0.02624118,0.0008988306],"domain_scores_gemma":[0.4902711,0.3845799,0.02004348,0.06128975,0.0419264,0.00188933],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0008763171,0.0002476487,0.03888613,0.003307163,0.001225909,0.001900594,0.008468962,0.01004438,0.004863781,0.1162334,0.3819064,0.4320394],"study_design_scores_gemma":[0.0003369114,0.0003437484,0.02906239,0.004865755,0.0005395048,0.004405912,0.004230811,0.07430884,0.01426827,0.675099,0.1919379,0.000601083],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04042498,0.009708071,0.59969,0.3181714,0.01056303,0.001319844,0.003461407,0.005013795,0.01164755],"genre_scores_gemma":[0.2642408,0.004080911,0.6048182,0.1046801,0.009547694,0.003185086,0.001212038,0.001223517,0.007011552],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8203958,"threshold_uncertainty_score":0.9498491,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2261944919","doi":"10.1093/bioinformatics/btv723","title":"PharmacoGx: an R package for analysis of large pharmacogenomic datasets","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":299,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Hospital for Sick Children; Montreal Clinical Research Institute; Institute of Cancer Research; Ontario Institute for Cancer Research; University Health Network; University of Toronto; Princess Margaret Cancer Centre","funders":"Ontario Institute for Cancer Research; Fondation Brain Canada; Canadian Institutes of Health Research; Cancer Research Society","keywords":"Pharmacogenomics; Computer science; R package; Drug response; Source code; Cancer cell lines; Data science; Data mining; Open source; Realization (probability); Precision medicine; Software; Drug; Bioinformatics; Cancer; Medicine; Biology; Pharmacology; Programming language","authors":[{"name":"Petr Smirnov","is_ca":true},{"name":"Zhaleh Safikhani","is_ca":true},{"name":"Nehmé El-Hachem","is_ca":true},{"name":"Dong Wang","is_ca":true},{"name":"Adrian She","is_ca":true},{"name":"Catharina Olsen","is_ca":true},{"name":"Mark Freeman","is_ca":true},{"name":"Heather M. Selby","is_ca":false},{"name":"Deena M.A. Gendoo","is_ca":true},{"name":"Patrick Großmann","is_ca":false},{"name":"Andrew H. Beck","is_ca":false},{"name":"Hugo J.W.L. Aerts","is_ca":false},{"name":"Mathieu Lupien","is_ca":true},{"name":"Anna Goldenberg","is_ca":true},{"name":"Benjamin Haibe‐Kains","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04707972317749436,"gpt":0.3602983026076302,"spread":0.3132185794301359,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009313316,0.003403332,0.002838389,0.004190625,0.000745329,0.002480224,0.004366785,0.001318512,0.0701431],"category_scores_gemma":[0.04207283,0.002158405,0.003750573,0.003828852,0.001539836,0.002610058,0.004656725,0.004541751,0.03217839],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009964121,"about_ca_system_score_gemma":0.005176151,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003594293,"about_ca_topic_score_gemma":0.004488953,"domain_scores_codex":[0.9954066,0.002155835,0.0004233401,0.0008426249,0.0008956262,0.0002759507],"domain_scores_gemma":[0.9744229,0.01933285,0.001926651,0.002358252,0.001222221,0.0007370897],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001269814,0.0001102801,0.01048159,0.004288276,0.003167714,0.0006740405,0.0004912397,0.01784685,0.003279683,0.0147117,0.8437666,0.09991225],"study_design_scores_gemma":[0.002381721,0.000392903,0.01668476,0.001007207,0.001599506,0.001581758,0.0001900791,0.162783,0.009509526,0.1063263,0.6969984,0.0005447789],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.004132795,0.001083183,0.488666,0.002097548,0.0005407597,0.0008644959,0.1475522,0.3499709,0.005092045],"genre_scores_gemma":[0.05816478,0.00144027,0.6575598,0.002083457,0.0004427856,0.007700899,0.127881,0.1380951,0.006632041],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.0701431,"threshold_uncertainty_score":0.234652,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2971405760","doi":"10.1093/bioinformatics/btz699","title":"Protein–protein interaction site prediction through combining local and global features with deep neural networks","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":296,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Saskatchewan","funders":"Higher Education Discipline Innovation Project; National Natural Science Foundation of China; Fundamental Research Funds for the Central Universities; Central South University; Virginia Commonwealth University","keywords":"Computer science; Convolutional neural network; Sequence (biology); Artificial intelligence; Deep learning; Artificial neural network; Source code; Code (set theory); Protein sequencing; Sliding window protocol; Machine learning; Peptide sequence; Window (computing); Biology","authors":[{"name":"Min Zeng","is_ca":false},{"name":"Fuhao Zhang","is_ca":false},{"name":"Fang‐Xiang Wu","is_ca":true},{"name":"Yaohang Li","is_ca":false},{"name":"Jianxin Wang","is_ca":false},{"name":"Min Li","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.004727256528390456,"gpt":0.2081237899887306,"spread":0.2033965334603402,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005781298,0.001696653,0.001200142,0.001304341,0.0003948191,0.0008674353,0.001570502,0.001078154,0.004188485],"category_scores_gemma":[0.001447447,0.0005650438,0.001112911,0.001221803,0.0004712885,0.001627011,0.001468673,0.001969265,0.002309793],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008027167,"about_ca_system_score_gemma":0.0008903141,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005100264,"about_ca_topic_score_gemma":0.007416299,"domain_scores_codex":[0.9995492,0.00005437512,0.0000236083,0.000178896,0.0001315584,0.00006233413],"domain_scores_gemma":[0.9996186,0.0001019596,0.00007216679,0.000049499,0.00009640733,0.00006125528],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009281622,0.0006558078,0.01656187,0.001387276,0.0006550044,0.0007394903,0.0001057043,0.409487,0.06116423,0.0105471,0.06434027,0.4334281],"study_design_scores_gemma":[0.00002356513,0.00003804869,0.001167622,0.00002215644,0.00004642284,0.00005831731,0.000009761027,0.9843653,0.005607471,0.006543742,0.00209981,0.00001772815],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1899636,0.009304972,0.7492157,0.002102822,0.0003572399,0.0002212461,0.01341076,0.02396571,0.01145805],"genre_scores_gemma":[0.7400098,0.003464169,0.2105037,0.001146891,0.0002691321,0.0003615298,0.03378724,0.0008612549,0.009596449],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005100264,"threshold_uncertainty_score":0.01401186,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2131848438","doi":"10.1093/bioinformatics/bti671","title":"Using information theory to search for co-evolving residues in proteins","year":2005,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":287,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Multiple sequence alignment; Phylogenetic tree; Computational biology; Computer science; Normalization (sociology); In silico; Sequence alignment; Protein sequencing; Conserved sequence; Mutual information; Biology; Genetics; Peptide sequence; Artificial intelligence; Gene","authors":[{"name":"Louise C. Martin","is_ca":true},{"name":"Gregory B. Gloor","is_ca":true},{"name":"Stanley D. Dunn","is_ca":true},{"name":"Lindi M. Wahl","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02920641743422231,"gpt":0.2963293837242249,"spread":0.2671229662900026,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004770319,0.0008417631,0.001329943,0.005749028,0.0007243569,0.001648716,0.001192079,0.001475356,0.0009448359],"category_scores_gemma":[0.0201323,0.0006017356,0.0008842857,0.00259428,0.001700587,0.002729758,0.001643585,0.001032528,0.0002531351],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001543538,"about_ca_system_score_gemma":0.0009468352,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001244786,"about_ca_topic_score_gemma":0.0009953898,"domain_scores_codex":[0.9980661,0.0009962957,0.0001097594,0.0002566006,0.0004797241,0.00009142693],"domain_scores_gemma":[0.9831955,0.01474629,0.0009922134,0.0003849978,0.0004401065,0.0002408662],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000546952,0.0002887757,0.02114863,0.0006656888,0.0005939881,0.0006089468,0.000332766,0.7665965,0.01025378,0.05353377,0.001634823,0.1437953],"study_design_scores_gemma":[0.00001758273,0.00004179309,0.00115633,0.00001288826,0.00002293169,0.0000657045,0.00001924874,0.9622241,0.001623369,0.03456587,0.0002306871,0.00001962428],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1521314,0.001106166,0.843144,0.0006513158,0.00002998722,0.00009839926,0.0002687188,0.0008856619,0.001684386],"genre_scores_gemma":[0.7353771,0.0005275963,0.2624266,0.0001747861,0.0000858431,0.0002408257,0.000631579,0.00008645922,0.0004492156],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005749028,"threshold_uncertainty_score":0.0252282,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2002295829","doi":"10.1093/bioinformatics/btv003","title":"Clonality inference in multiple tumor samples using phylogeny","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":284,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University; BC Cancer Agency","funders":"BC Cancer Agency; Natural Sciences and Engineering Research Council of Canada; Genome Canada","keywords":"Phylogenetics; Biology; Phylogenetic tree; Inference; In silico; Computational biology; Evolutionary biology; Computer science; Genetics; Gene; Artificial intelligence","authors":[{"name":"Salem Malikić","is_ca":true},{"name":"Andrew McPherson","is_ca":true},{"name":"Nilgun Donmez","is_ca":true},{"name":"Cenk S. Sahinalp","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06875968615801234,"gpt":0.2941810204304562,"spread":0.2254213342724438,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002913309,0.0007642996,0.00124739,0.001706021,0.0007884863,0.001469694,0.001491611,0.001395968,0.001762333],"category_scores_gemma":[0.01542285,0.0007040271,0.001014635,0.001884396,0.0009145087,0.001404644,0.00155505,0.001775848,0.0004169235],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007963766,"about_ca_system_score_gemma":0.001039568,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002434882,"about_ca_topic_score_gemma":0.003371203,"domain_scores_codex":[0.9984394,0.0006675389,0.000089869,0.0004835149,0.0002322982,0.00008740499],"domain_scores_gemma":[0.9914785,0.006161212,0.0009382514,0.000675465,0.0004435906,0.0003030144],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000519363,0.00009550799,0.06872291,0.0003771381,0.0003245736,0.0007671125,0.0002764028,0.81392,0.02618374,0.01234199,0.002640311,0.07383101],"study_design_scores_gemma":[0.00003010065,0.00003949388,0.004173824,0.00002860148,0.00004517441,0.0003247084,0.00003391402,0.9674817,0.004653782,0.02184294,0.001327165,0.0000186986],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2067012,0.0006238822,0.7879759,0.0004264394,0.00002784603,0.00008160478,0.001972797,0.0009981206,0.00119222],"genre_scores_gemma":[0.7478815,0.0002533022,0.247286,0.0001998299,0.00005211174,0.0001191726,0.003523527,0.0001980582,0.0004864473],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002913309,"threshold_uncertainty_score":0.01540726,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2141014201","doi":"10.1093/bioinformatics/btt182","title":"Predicting the functional consequences of cancer-associated amino acid substitutions","year":2013,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":282,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Institute of Nutrition, Metabolism and Diabetes; Biotechnology and Biological Sciences Research Council; Directorate for Biological Sciences; Medical Research Council; University of Bristol","keywords":"Missense mutation; Computational biology; Computer science; Mutation; Exome; Neutral mutation; Genome; Cancer; Exome sequencing; Genetics; Biology; Gene","authors":[{"name":"Hashem A. Shihab","is_ca":false},{"name":"Julian Gough","is_ca":false},{"name":"D.N. Cooper","is_ca":false},{"name":"Ian N.M. Day","is_ca":false},{"name":"Tom R. Gaunt","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01464170372766504,"gpt":0.2333726178322742,"spread":0.2187309141046092,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009401655,0.0009457917,0.000652675,0.0009104875,0.0003407079,0.0006354598,0.0007841614,0.000900898,0.001648055],"category_scores_gemma":[0.002769031,0.0001695386,0.0004798977,0.0009145165,0.0002504963,0.0004332984,0.0003340505,0.0004396648,0.0007463871],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005409425,"about_ca_system_score_gemma":0.0007420594,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003313833,"about_ca_topic_score_gemma":0.004462557,"domain_scores_codex":[0.9997215,0.00006287095,0.00002675039,0.00009526515,0.00006722381,0.00002641641],"domain_scores_gemma":[0.9987621,0.0007995968,0.0001265727,0.00007764928,0.0001790942,0.00005501466],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001865634,0.0004334877,0.144473,0.001343907,0.0003715284,0.0009763408,0.0001136335,0.5426825,0.1089427,0.002121852,0.007049032,0.1896264],"study_design_scores_gemma":[0.00004896367,0.0001800418,0.02872026,0.00003185613,0.000129138,0.0007244389,0.00003182221,0.9032842,0.06189811,0.003306523,0.001616368,0.00002817776],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8857361,0.00144717,0.09778075,0.0003911676,0.00004947129,0.00008493039,0.005544161,0.006977688,0.001988541],"genre_scores_gemma":[0.9165873,0.0005592594,0.07382801,0.0001079948,0.0000245136,0.00004799265,0.007850441,0.000205172,0.0007893439],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003313833,"threshold_uncertainty_score":0.006589115,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}