{"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"},"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001450443,0.00006037218,0.00008004256,0.00001418039,0.0001862571,0.0000247897,0.0000670633,0.0000611879,0.00008828917],"category_scores_gemma":[0.0003223503,0.00004852168,0.0000181111,0.0000341597,0.000217274,0.0002086378,0.0000816304,0.00008407011,0.00005098351],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001036644,"about_ca_system_score_gemma":0.000004990425,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003573327,"about_ca_topic_score_gemma":0.001055826,"domain_scores_codex":[0.9996265,0.000004331408,0.0001489002,0.00005731672,0.0000348792,0.0001281423],"domain_scores_gemma":[0.9995968,0.0002378947,0.00006352297,0.00006647449,0.000008215133,0.00002702903],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003331531,0.00008631394,0.7652224,0.0001265071,0.00007328652,0.000001178395,0.01069838,0.0001332121,0.007579598,0.05850369,0.006000383,0.1515417],"study_design_scores_gemma":[0.0008940421,0.0003430113,0.7501236,0.000006883387,0.00004085961,0.00003746814,0.003831417,0.2084675,0.0006846554,0.009909185,0.02525777,0.000403654],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9822965,0.000004856252,0.004109433,0.0003366525,0.000244036,0.0002080066,0.000011083,0.00002489557,0.01276458],"genre_scores_gemma":[0.9156446,0.00001189987,0.08365691,0.000408272,0.00001779166,0.00003306851,0.000006452009,0.000003186737,0.0002178047],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2083343,"threshold_uncertainty_score":0.1978657,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002018413,0.0001383771,0.0006891791,0.0001904138,0.00004639043,0.00002780736,0.00009878015,0.0001086801,0.0004580326],"category_scores_gemma":[0.03161228,0.0001105422,0.0001024292,0.0002973614,0.0002611346,0.00007263636,0.00008472461,0.0001197705,0.00001882624],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001975771,"about_ca_system_score_gemma":0.00003331175,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004145021,"about_ca_topic_score_gemma":0.000002809059,"domain_scores_codex":[0.9980693,0.0001910105,0.001118887,0.0001334977,0.0003010637,0.0001861676],"domain_scores_gemma":[0.9744291,0.024639,0.0003937161,0.0003102655,0.000103705,0.0001241875],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00005949864,0.00008061097,0.003427716,0.0003239025,0.0006071583,2.681079e-7,0.0001038614,0.00001867224,0.00002730743,0.9708732,0.003554716,0.02092304],"study_design_scores_gemma":[0.0008860613,0.0002451232,0.03172955,0.00003832728,0.00205995,0.000002225704,0.0001778576,0.2415557,0.0002733005,0.7214663,0.001275975,0.0002896124],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02043402,0.000005060273,0.9747825,0.00004313407,0.0001487401,0.0002132064,0.0003956085,0.0000402408,0.003937474],"genre_scores_gemma":[0.0913465,0.000008155534,0.9084182,0.00007589474,0.00005677631,0.00001258265,0.00001701913,0.00000982947,0.00005507294],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.249407,"threshold_uncertainty_score":0.9765449,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005671085,0.0001590023,0.000138786,0.00002918737,0.0001573104,0.00005789174,0.0002056064,0.0000939029,0.00008316615],"category_scores_gemma":[0.000006697142,0.0001285405,0.00004058863,0.0001191925,0.00005266445,0.0002144014,0.00003402944,0.0002188698,0.00005027228],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001329939,"about_ca_system_score_gemma":0.00007424059,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001173502,"about_ca_topic_score_gemma":0.000006587261,"domain_scores_codex":[0.9991833,0.000001192164,0.0002802607,0.0001103555,0.0001796687,0.0002452315],"domain_scores_gemma":[0.9993504,0.00001005,0.0001646088,0.0003570185,0.00003710881,0.00008084349],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001297486,0.0006981508,0.003965604,0.001831311,0.0003213255,0.00006755292,0.007887445,0.01298891,0.441067,0.5061486,0.0008282757,0.0240661],"study_design_scores_gemma":[0.001704992,0.0001152872,0.00005613579,0.000391848,0.00004413615,0.0001237774,0.001219596,0.001798087,0.8383054,0.1385807,0.01682394,0.0008360979],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04117195,0.00001851368,0.9030672,0.0002642554,0.00000871055,0.0003181967,0.00001761064,0.0004136863,0.05471988],"genre_scores_gemma":[0.2012698,0.00003572869,0.7980249,0.0001049349,0.00006054801,0.0001255724,0.0000273916,0.00002424056,0.0003269241],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3972384,"threshold_uncertainty_score":0.524173,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003536128,0.0002715155,0.0001939625,0.0000853086,0.0002181748,0.0001197015,0.0001428749,0.000296555,0.000005827842],"category_scores_gemma":[0.0003992946,0.0002218342,0.00004501318,0.0001165965,0.0002620541,0.00006983665,0.00007385167,0.000177672,0.000001932523],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001989487,"about_ca_system_score_gemma":0.0001145296,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001718558,"about_ca_topic_score_gemma":0.00007383664,"domain_scores_codex":[0.9987406,0.00002589408,0.0005179932,0.0002174352,0.0002006583,0.0002974083],"domain_scores_gemma":[0.9988263,0.00002327812,0.0003113988,0.0003805647,0.0003539422,0.0001045405],"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":[0.0108821,0.001448742,0.1859325,0.02424354,0.0024434,0.000004787657,0.0403502,0.04402855,0.5986182,0.03729136,0.02059428,0.03416235],"study_design_scores_gemma":[0.00146458,0.002060263,0.0006911913,0.00004748353,0.00008991313,0.00003147924,0.0008106132,0.8975166,0.06320073,0.0003732396,0.03329308,0.0004208156],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2038988,0.00005149547,0.793013,0.0001379432,0.00016743,0.002012748,0.0001692798,0.0001039732,0.0004453416],"genre_scores_gemma":[0.9402207,0.0000390522,0.05441234,0.000253472,0.0002350016,0.0003863009,0.003939302,0.00005968596,0.0004542051],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8534881,"threshold_uncertainty_score":0.9046136,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003137391,0.00007661487,0.00008377733,0.00008538982,0.0003253439,0.00001558488,0.00009195752,0.00005744861,0.0003368295],"category_scores_gemma":[0.0001329084,0.00006525646,0.00003296402,0.0001977256,0.0001349765,0.0002331484,0.000006553413,0.00009126979,0.0007469075],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005687869,"about_ca_system_score_gemma":0.00004014662,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001285275,"about_ca_topic_score_gemma":0.004645968,"domain_scores_codex":[0.9992557,0.00001266276,0.0002829503,0.00005772292,0.0001481571,0.0002427706],"domain_scores_gemma":[0.9994856,0.0001834025,0.00008940721,0.00009664484,0.00003863142,0.0001062833],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000002272447,0.000003447789,0.9756114,0.00001207027,0.00001184973,0.000001239096,0.0009366213,0.0002250031,8.779741e-7,0.0008938207,0.007617218,0.01468415],"study_design_scores_gemma":[0.0001064521,0.00002315767,0.9473146,0.000006042778,0.000006305088,0.00001674102,0.001100717,0.02987843,0.000004366615,0.000470418,0.02097796,0.00009480044],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.2386557,0.002520294,0.01279501,0.000995968,0.001212297,0.0002725936,0.00009487422,0.0002962823,0.743157],"genre_scores_gemma":[0.9318864,0.00006273331,0.06620695,0.001166557,0.0001497897,4.463853e-7,0.0001136878,0.000001551355,0.000411852],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7427451,"threshold_uncertainty_score":0.9600235,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003493265,0.0001221557,0.0001647051,0.00005995994,0.00003364539,0.00002761964,0.0002123796,0.0001356685,0.00000487853],"category_scores_gemma":[0.0001161769,0.0000927379,0.00002213798,0.00008698054,0.00009342511,0.00004859491,0.00008453898,0.00002473555,0.000001589055],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001212893,"about_ca_system_score_gemma":0.0000554431,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003999228,"about_ca_topic_score_gemma":0.00007713669,"domain_scores_codex":[0.9989736,0.00004281901,0.0005305987,0.0001609767,0.0001366791,0.000155339],"domain_scores_gemma":[0.9992299,0.0000158373,0.0002485157,0.0003647204,0.00009430668,0.00004668634],"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":[0.0001885676,0.0001896717,0.05528924,0.00045866,0.00001452262,2.253435e-7,0.0004037969,0.00002709888,0.9170269,0.0001171777,0.0001680694,0.02611608],"study_design_scores_gemma":[0.01057785,0.0009492646,0.03412147,0.0004650918,0.00009341623,0.00001163389,0.0003131348,0.04189195,0.9014316,0.0001691284,0.008987435,0.0009879947],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7410951,0.0003159135,0.257375,0.00004492954,0.00008713955,0.0001833772,0.0001166048,0.00001376343,0.0007682128],"genre_scores_gemma":[0.9972035,0.0002317421,0.002008096,0.0001171608,0.00004010443,0.000002770757,0.000291761,0.00001323564,0.00009162854],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2561084,"threshold_uncertainty_score":0.3781742,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001308582,0.0001450084,0.0001311275,0.00003620671,0.00009526879,0.00003657953,0.0001547767,0.0000823556,0.00001028631],"category_scores_gemma":[0.00003867704,0.0001330655,0.00007551243,0.00004966328,0.00007718147,0.000001394464,0.00006263013,0.00004106376,0.0000450549],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001129877,"about_ca_system_score_gemma":0.00003416601,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000244288,"about_ca_topic_score_gemma":0.00002063833,"domain_scores_codex":[0.9992834,0.00001589813,0.0002563052,0.0001196371,0.0001134348,0.0002113617],"domain_scores_gemma":[0.9994653,0.00001044792,0.0001031151,0.0002971968,0.0000566042,0.00006728966],"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":[0.0001924389,0.0003425665,0.02447205,0.0005708141,0.0002524539,0.000001144642,0.001201669,0.03592805,0.8337291,0.001340188,0.01358887,0.08838063],"study_design_scores_gemma":[0.002563479,0.001153551,0.1748042,0.00004205828,0.000100759,0.00001422281,0.0005855403,0.2060574,0.1676944,0.0002290985,0.4456542,0.00110117],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8057655,0.0002056719,0.1757655,0.0002339317,0.0002796013,0.0002872648,0.0000502385,0.00001990286,0.01739242],"genre_scores_gemma":[0.9497785,0.0000501481,0.04905953,0.0003804777,0.0001559984,0.000009419794,0.0001728802,0.00001463166,0.0003784259],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6660348,"threshold_uncertainty_score":0.5426255,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001071647,0.0001705445,0.0001528228,0.00003885889,0.0001384132,0.00004581942,0.0001060711,0.0001046048,0.00000247343],"category_scores_gemma":[0.0001071054,0.0001647696,0.00006925699,0.00005098557,0.00005688396,0.000002314343,0.00005344352,0.00003908982,0.00000143763],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000757844,"about_ca_system_score_gemma":0.00003051811,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001248977,"about_ca_topic_score_gemma":0.000002458007,"domain_scores_codex":[0.9992264,0.00001179482,0.0002699596,0.0001812627,0.00007057888,0.000239998],"domain_scores_gemma":[0.9994782,0.00001358247,0.0001180495,0.000244928,0.00007288223,0.00007234071],"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":[0.00005486202,0.00003669975,0.003244672,0.0001272154,0.000110702,9.334685e-7,0.0002986289,0.00006501803,0.6279398,0.0004178495,0.001137005,0.3665666],"study_design_scores_gemma":[0.006247352,0.005601231,0.04042868,0.0002273219,0.0003983513,0.0004755504,0.002910038,0.01647065,0.8599095,0.01559751,0.04867041,0.003063436],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8278849,0.001451446,0.1688455,0.0001409481,0.0001681085,0.0004883913,0.00009432004,0.00001378623,0.0009126104],"genre_scores_gemma":[0.8406689,0.0002395453,0.1583599,0.0004973846,0.0001079002,0.00001823562,0.00005870399,0.0000133551,0.00003606186],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3635032,"threshold_uncertainty_score":0.6719108,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001736145,0.0001491912,0.0002503297,0.0001092182,0.00007754713,0.00001656648,0.0002760015,0.0001672041,0.0000150582],"category_scores_gemma":[0.0001931493,0.0001340124,0.0002053551,0.0001703682,0.0001574539,0.000002389954,0.0001595794,0.00005858048,0.00000487023],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003823919,"about_ca_system_score_gemma":0.0000688798,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001613655,"about_ca_topic_score_gemma":0.00005386451,"domain_scores_codex":[0.9991049,0.00001203207,0.0004081836,0.0001697556,0.00006761334,0.000237494],"domain_scores_gemma":[0.9989965,0.0000545838,0.0001969565,0.000518214,0.0001722991,0.00006145543],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00005606534,0.00006539922,0.03063592,0.00006797315,0.000926772,9.3644e-8,0.0001247777,0.0001881585,0.9567704,0.00103616,0.002370294,0.007757947],"study_design_scores_gemma":[0.00292147,0.001841047,0.3861789,0.00001332303,0.00188027,0.00002315353,0.00067214,0.02011802,0.2616823,0.00195196,0.3212845,0.001432819],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9787778,0.000521558,0.01806042,0.00005761596,0.0003950534,0.000375871,0.001087631,0.000004519233,0.0007195123],"genre_scores_gemma":[0.9431639,0.0001526946,0.05551376,0.00009509825,0.0001429701,0.0000398496,0.0007543848,0.0000112851,0.0001260405],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6950881,"threshold_uncertainty_score":0.5464867,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007351557,0.0001192192,0.0002270205,0.0001007629,0.0001662761,0.00001260207,0.0001641915,0.00007061697,0.00004590899],"category_scores_gemma":[0.0001353982,0.00009709726,0.00006584794,0.0001240456,0.00007788761,0.0002457663,0.0000145158,0.0000450417,0.00002208884],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003302577,"about_ca_system_score_gemma":0.00002188634,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009194097,"about_ca_topic_score_gemma":0.001387152,"domain_scores_codex":[0.9990336,0.0000889884,0.0003879742,0.00009568798,0.00009639725,0.0002973475],"domain_scores_gemma":[0.9990864,0.0003913101,0.0001328467,0.0001782426,0.00007969433,0.0001314861],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001249217,0.00005510376,0.5246338,0.0002451442,0.00009978952,1.079954e-7,0.01082643,0.04142544,0.0001476359,0.002414455,0.002695173,0.417332],"study_design_scores_gemma":[0.0002582322,0.0002770089,0.233027,0.00001408685,0.00002128705,0.000004726368,0.0009139593,0.7588537,0.0000976849,0.001584421,0.004788543,0.0001593363],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2305537,0.001222192,0.7470203,0.000169485,0.0005261025,0.000595251,0.0001679382,0.00007912421,0.0196659],"genre_scores_gemma":[0.5161876,0.00002934287,0.4832279,0.000333099,0.00006346377,0.000004591378,0.00005237754,0.00000225443,0.00009930427],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7174283,"threshold_uncertainty_score":0.3959511,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007673155,0.00008825802,0.00007885734,0.00002728643,0.00009251318,0.00002817541,0.00004641083,0.0000573768,0.000001245475],"category_scores_gemma":[0.00001760686,0.00008524041,0.00002532899,0.0000518023,0.00003490842,0.000003362768,0.00006105581,0.00001783502,0.00000449265],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001283126,"about_ca_system_score_gemma":0.00003612517,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005772461,"about_ca_topic_score_gemma":0.000003065331,"domain_scores_codex":[0.9995604,0.000006965389,0.0001757055,0.00008573439,0.00006229462,0.0001089134],"domain_scores_gemma":[0.99972,0.000001467644,0.0000678764,0.0001253416,0.00004782674,0.0000375264],"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":[0.00002085144,0.0000656515,0.001300723,0.0003090952,0.0001489842,0.000001495366,0.003288994,0.009551961,0.9762536,0.004913023,0.00004672361,0.00409894],"study_design_scores_gemma":[0.01386399,0.003535265,0.04029803,0.0004111532,0.0007867994,0.0005768547,0.01530893,0.0742966,0.4994317,0.01830992,0.3274314,0.005749379],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9013913,0.001727499,0.09631797,0.00003136462,0.00006952013,0.0001543941,0.000008907173,0.000004325663,0.0002947154],"genre_scores_gemma":[0.9873778,0.001491539,0.01075055,0.0002069968,0.00008442295,0.000005078862,0.00006134842,0.00001085038,0.00001145337],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4768219,"threshold_uncertainty_score":0.3476003,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002830015,0.0002572433,0.0002450147,0.00005702283,0.0001170694,0.0001190953,0.0004065708,0.0002289902,0.00001179429],"category_scores_gemma":[0.00003967464,0.0002255442,0.0001631926,0.00008920644,0.00006687825,0.00004997123,0.0001526013,0.0001294764,0.00003800961],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003148348,"about_ca_system_score_gemma":0.00006034605,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000155417,"about_ca_topic_score_gemma":0.000008987007,"domain_scores_codex":[0.9987283,0.00002457989,0.0004796507,0.0002397258,0.0001515726,0.0003761935],"domain_scores_gemma":[0.9989345,0.000022473,0.0002255582,0.0005469025,0.0001183225,0.0001522407],"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":[0.0004421528,0.0005757445,0.01035267,0.0003653023,0.0008882314,0.000002104192,0.01205284,0.02589823,0.9063955,0.009622977,0.001935769,0.03146845],"study_design_scores_gemma":[0.002555754,0.0003815152,0.0004967008,0.00002300825,0.0000517729,0.000006636547,0.006362132,0.8888485,0.09633284,0.0005407092,0.003751747,0.0006487275],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3880215,0.00003952466,0.6097022,0.000008924712,0.0001416022,0.0005302186,0.00008784777,0.00002222224,0.001446001],"genre_scores_gemma":[0.5583916,0.00002374604,0.4392778,0.0004443627,0.00006453268,0.00003777031,0.001630119,0.00002449334,0.0001055627],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8629502,"threshold_uncertainty_score":0.9197427,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0003686139,0.0001238441,0.0002023826,0.00003142433,0.0004152124,0.00003733134,0.0006674341,0.0001594715,0.005596327],"category_scores_gemma":[0.00004036031,0.00009408893,0.00005442421,0.0000811921,0.0005343158,0.0001878243,0.0005846064,0.000533885,0.001593771],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001812601,"about_ca_system_score_gemma":0.000008127505,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002584883,"about_ca_topic_score_gemma":0.00160117,"domain_scores_codex":[0.9992306,0.0001034773,0.0002987494,0.00005805038,0.00006666225,0.0002424566],"domain_scores_gemma":[0.9991462,0.0002800701,0.0001309748,0.0003755194,0.000006335419,0.0000608905],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000367734,0.0001826271,0.8224443,0.00008377925,0.0001462918,0.000002741519,0.01828391,0.0000394423,0.1222732,0.003646711,0.008154508,0.02470572],"study_design_scores_gemma":[0.0002940871,0.000199804,0.9617447,0.00001003396,0.00004401335,0.00001500794,0.002069994,0.0009978617,0.001266673,0.008633963,0.02429758,0.0004262842],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9883207,0.000005127452,0.0004665358,0.00008660745,0.0002079673,0.0001063874,0.00002002378,0.00005363547,0.01073301],"genre_scores_gemma":[0.9885812,0.00003008981,0.01084093,0.0002980613,0.00003011294,0.000004597114,0.00007103985,0.000004676822,0.0001392769],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1393004,"threshold_uncertainty_score":0.9991836,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007689703,0.0001159392,0.0001004287,0.00004761077,0.00004861367,0.00002853289,0.00008244366,0.00009835843,0.00004906911],"category_scores_gemma":[0.0000105713,0.0001045519,0.00003386239,0.00004153347,0.00009690647,0.000006085493,0.0001504816,0.00006578237,0.0001170934],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007576432,"about_ca_system_score_gemma":0.000005767653,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004509628,"about_ca_topic_score_gemma":0.000002570175,"domain_scores_codex":[0.999371,0.00001869275,0.0001619285,0.0001206022,0.0001012539,0.0002265377],"domain_scores_gemma":[0.9996264,0.000005954258,0.00003696228,0.0002100824,0.00004951935,0.0000710594],"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":[0.0001718472,0.0005956846,0.06667341,0.001162692,0.001251715,0.0001643188,0.03549735,0.0002005916,0.2175867,0.0002517019,0.06521757,0.6112264],"study_design_scores_gemma":[0.01253966,0.005318941,0.1300381,0.0002089332,0.000310449,0.003072743,0.02373178,0.2770445,0.2954906,0.00008192672,0.2475483,0.004614041],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9884837,0.0002644184,0.005183738,0.0004446278,0.00009455485,0.0002110694,0.00003686682,0.00001605368,0.005265012],"genre_scores_gemma":[0.9904829,0.0003417295,0.006180048,0.0009150857,0.0001250664,0.000006978489,0.00007551162,0.00001731116,0.001855416],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6066124,"threshold_uncertainty_score":0.4263504,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000874893,0.0001568013,0.0004555573,0.0002465266,0.0001096065,0.00003485283,0.0004093598,0.00008740869,0.00001328916],"category_scores_gemma":[0.0003485796,0.0001325679,0.0001061115,0.0005271782,0.0001785963,0.00002603138,0.000381745,0.00003470782,0.000001356004],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003598878,"about_ca_system_score_gemma":0.00004517109,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001872968,"about_ca_topic_score_gemma":0.00009206388,"domain_scores_codex":[0.9987965,0.00002149598,0.0004617912,0.000377327,0.0001203129,0.000222545],"domain_scores_gemma":[0.9976974,0.00001885872,0.0002677755,0.001706662,0.0002318211,0.000077529],"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":[0.0008238535,0.0005735047,0.02071026,0.0005517453,0.02941096,6.143491e-7,0.001597647,0.00009311463,0.8575886,0.01952509,0.02434792,0.04477668],"study_design_scores_gemma":[0.001549081,0.001831259,0.01027128,0.000008790511,0.009663052,0.000006737772,0.001724941,0.06210416,0.6754194,0.000555169,0.236047,0.0008191103],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8609006,0.002916414,0.1313115,0.0001196181,0.0002594272,0.0004978272,0.002040375,0.00003297552,0.001921252],"genre_scores_gemma":[0.765791,0.002263421,0.2277533,0.0002492605,0.0003489878,0.00001759843,0.002981659,0.00002675991,0.0005679681],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2116991,"threshold_uncertainty_score":0.5405962,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003426364,0.0001537266,0.0002493471,0.000180199,0.0001196583,0.00005595655,0.000104925,0.0001348112,0.00001122258],"category_scores_gemma":[0.0002647296,0.0001319279,0.0001501094,0.0002894448,0.00006202977,0.000007934496,0.00006426852,0.00005727168,0.00000193579],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003943763,"about_ca_system_score_gemma":0.00006484742,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002558332,"about_ca_topic_score_gemma":0.0000816983,"domain_scores_codex":[0.9992281,0.00001196729,0.0003022697,0.0001623223,0.00009668825,0.0001987009],"domain_scores_gemma":[0.9993544,0.00002811581,0.000151875,0.0002773548,0.0001315379,0.00005672735],"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":[0.0001684054,0.000157606,0.02506521,0.0002263986,0.002056692,4.264988e-7,0.0001702785,0.0001031177,0.9312223,0.02226972,0.002479382,0.01608053],"study_design_scores_gemma":[0.00280151,0.0004142781,0.01015395,0.000004359781,0.00140062,0.000004732698,0.0001617418,0.1212691,0.3810505,0.00027151,0.481689,0.0007786328],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7793525,0.0002425547,0.2191196,0.00008866658,0.0002239947,0.0003491479,0.000198397,0.00002387431,0.0004012296],"genre_scores_gemma":[0.8798808,0.0002307607,0.1185162,0.0004427165,0.0001366848,0.00006413615,0.0005085133,0.00001915816,0.0002010136],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5501717,"threshold_uncertainty_score":0.5379864,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003629441,0.0002853581,0.0002145223,0.00006042564,0.0001727416,0.0001287267,0.0004429382,0.0003717247,0.0001262621],"category_scores_gemma":[0.00004464739,0.0002572039,0.0001367136,0.0001385918,0.0001229104,0.00003364824,0.0001529398,0.000384053,0.000144393],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000128922,"about_ca_system_score_gemma":0.0002543734,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000038755,"about_ca_topic_score_gemma":0.0001704633,"domain_scores_codex":[0.9985684,0.00002590949,0.0005284565,0.0001922621,0.0001815276,0.0005035169],"domain_scores_gemma":[0.9985961,0.00002340388,0.000257682,0.0007519709,0.0001297776,0.0002410377],"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":[0.001280937,0.0008699831,0.009627581,0.0004659648,0.0006489448,0.00001496911,0.001535246,0.01433536,0.3527481,0.005701444,0.4858561,0.1269154],"study_design_scores_gemma":[0.001850193,0.0005408791,0.0007257535,0.00003174908,0.00004424899,0.00004253062,0.0002394368,0.4543544,0.008225552,0.000268676,0.5329311,0.0007455387],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9201182,0.0001420682,0.02537923,0.0003923422,0.003366328,0.0008676971,0.0001629606,0.0002033298,0.04936789],"genre_scores_gemma":[0.951735,0.00003630085,0.04342945,0.002485919,0.001203167,0.00002761552,0.0006026601,0.00004586436,0.000433995],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.440019,"threshold_uncertainty_score":0.999988,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001318976,0.0001952533,0.0003072996,0.0001537749,0.00008893712,0.00004286896,0.0001316191,0.0001929874,0.00002051104],"category_scores_gemma":[0.00007239404,0.0001726256,0.00008702922,0.0002981585,0.0001201818,0.00003165229,0.00009198807,0.00009045011,0.000005622523],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002532925,"about_ca_system_score_gemma":0.00007348062,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004881129,"about_ca_topic_score_gemma":0.00003499744,"domain_scores_codex":[0.9987788,0.00004328842,0.0006427977,0.0001490246,0.0002288948,0.0001572],"domain_scores_gemma":[0.999035,0.000008216559,0.0004121903,0.000326562,0.000136688,0.00008131246],"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":[0.0009958898,0.0004800538,0.01294438,0.000900951,0.002956508,0.000003002774,0.03426037,0.05582236,0.8888124,0.001178999,0.0004682461,0.001176898],"study_design_scores_gemma":[0.004519755,0.001288405,0.008666976,0.0001425658,0.0006003722,0.000007425035,0.001898801,0.2525485,0.7246639,0.0006717031,0.004361083,0.0006305194],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8251913,0.00005990437,0.1736371,0.00001603046,0.00004891512,0.0005405703,0.0001013396,0.00002448163,0.0003802911],"genre_scores_gemma":[0.9697294,0.00002605553,0.027267,0.00003309084,0.0000804228,0.00002834466,0.002790982,0.00001064079,0.00003404932],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1967262,"threshold_uncertainty_score":0.7039467,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003869637,0.0001413648,0.0001695176,0.0001193002,0.00007060402,0.000089789,0.0001307788,0.0001529361,0.000006421943],"category_scores_gemma":[0.0000505795,0.0001224333,0.0001187891,0.0002037063,0.00006706235,0.00002884654,0.0001053444,0.00004391486,0.000006037057],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005722662,"about_ca_system_score_gemma":0.00006493564,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":9.677408e-7,"about_ca_topic_score_gemma":0.000002727526,"domain_scores_codex":[0.9992323,0.00002162379,0.0003400983,0.0001109016,0.00009602912,0.0001990545],"domain_scores_gemma":[0.9993608,0.00002515883,0.0001514231,0.0002554914,0.0000563373,0.00015076],"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":[0.003055116,0.0005244962,0.02738804,0.00121526,0.009371289,0.000003681989,0.01940308,0.004485482,0.004858342,0.1414197,0.4149057,0.3733698],"study_design_scores_gemma":[0.007263586,0.002478407,0.003574005,0.00006291592,0.002315517,0.00006095758,0.009468464,0.4683122,0.01747865,0.05442793,0.4322098,0.002347584],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1071042,0.001183973,0.8820716,0.0001946971,0.0002491843,0.0006765217,0.0002823124,0.00007123374,0.008166251],"genre_scores_gemma":[0.8586696,0.0004930671,0.1315146,0.00276832,0.0004922834,0.00009016221,0.004360649,0.00005846245,0.001552762],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7515655,"threshold_uncertainty_score":0.4992687,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002192943,0.0002226453,0.000191196,0.0001417587,0.0001175621,0.00009528366,0.0005271406,0.0002163449,0.00003057366],"category_scores_gemma":[0.0001100634,0.0001751797,0.0001166271,0.000278715,0.00005261499,0.00002347905,0.0003769675,0.0001564135,0.0001134566],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004432363,"about_ca_system_score_gemma":0.0001467436,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001761484,"about_ca_topic_score_gemma":0.00006018454,"domain_scores_codex":[0.9986805,0.000006883942,0.0005683533,0.000145333,0.0002034941,0.0003954124],"domain_scores_gemma":[0.9989104,0.000008281428,0.000122238,0.0007057073,0.00009743673,0.000155969],"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":[0.00217103,0.001126077,0.0009684461,0.001644866,0.001189189,0.00004214167,0.00792734,0.6107327,0.01266674,0.00464877,0.1237614,0.2331213],"study_design_scores_gemma":[0.0134272,0.00259461,0.0002457208,0.0004075073,0.0001806453,0.0006755096,0.00432603,0.8244441,0.02658308,0.005074819,0.118866,0.003174784],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3136464,0.0003771064,0.6755754,0.0002939013,0.0006379348,0.0004112712,0.00007425321,0.00007158805,0.008912086],"genre_scores_gemma":[0.9018155,0.0003856422,0.09519894,0.001331669,0.0003836962,0.00001715073,0.0002262547,0.00003725902,0.0006039007],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.588169,"threshold_uncertainty_score":0.7143619,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001739111,0.0001810113,0.0001337806,0.00005127281,0.0001329389,0.00005600803,0.000193525,0.0001795287,0.00001775285],"category_scores_gemma":[0.00001574268,0.0001704765,0.00008561479,0.00008918672,0.00006971605,0.00001248078,0.00009735288,0.0001048043,0.00007018661],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004761605,"about_ca_system_score_gemma":0.0001015658,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008920393,"about_ca_topic_score_gemma":0.00002452058,"domain_scores_codex":[0.9989736,0.000009415706,0.0004402753,0.0001171207,0.000155955,0.0003036415],"domain_scores_gemma":[0.9992957,0.000003114062,0.0001598446,0.0003616019,0.00006591915,0.0001138517],"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":[0.0007603734,0.0006673419,0.0008176204,0.001630566,0.0004466685,0.00001142647,0.001694281,0.3634143,0.3719793,0.002482502,0.01887151,0.2372241],"study_design_scores_gemma":[0.005308786,0.001048965,0.001139827,0.0001683593,0.00004643011,0.0000754146,0.0002920673,0.8001881,0.05437536,0.0007267407,0.1357055,0.0009244187],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03687418,0.00004687402,0.9569559,0.0001934985,0.0002058201,0.0008047072,0.00007127411,0.00006050132,0.004787212],"genre_scores_gemma":[0.9034337,0.00001277748,0.09423505,0.001060207,0.000246778,0.00006489016,0.0007903316,0.00002622183,0.0001300387],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8665595,"threshold_uncertainty_score":0.6951829,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002997757,0.0002058761,0.0001168939,0.00004753696,0.0003307995,0.00009308058,0.000309788,0.0002503232,0.00011746],"category_scores_gemma":[0.00004560072,0.0001436547,0.0001126536,0.0001132604,0.0001121944,0.0000117827,0.0001207547,0.0003094226,0.0002262943],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001103821,"about_ca_system_score_gemma":0.00007561409,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003530469,"about_ca_topic_score_gemma":0.00003847812,"domain_scores_codex":[0.9989569,0.00001530693,0.0003933179,0.0001381561,0.0001876846,0.0003086353],"domain_scores_gemma":[0.9989277,0.00002198055,0.000169111,0.0006888948,0.00008313894,0.0001091687],"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":[0.0005943195,0.0005268953,0.001835854,0.0002264556,0.0009387692,0.00000387602,0.002136505,0.00543018,0.4789933,0.04733384,0.3281898,0.1337902],"study_design_scores_gemma":[0.001853961,0.001533643,0.008589058,0.00004320667,0.0001878823,0.0001867341,0.001279901,0.1374743,0.0751906,0.001345063,0.7710359,0.001279785],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7784215,0.0001570589,0.1287857,0.001226673,0.003715359,0.00116347,0.0002197129,0.000139991,0.08617061],"genre_scores_gemma":[0.989897,0.00009582756,0.005546142,0.002264481,0.000933772,0.00004878765,0.000303084,0.00002849512,0.0008824035],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4428461,"threshold_uncertainty_score":0.585807,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001231321,0.0001776586,0.0001711259,0.00002807684,0.0005125086,0.0000808388,0.0003693977,0.0000880049,0.000006509893],"category_scores_gemma":[0.00005156936,0.0001506805,0.00008724076,0.00001755273,0.000122293,4.828756e-7,0.0002552969,0.00005794931,0.00007638692],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009079636,"about_ca_system_score_gemma":0.00003232429,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003299899,"about_ca_topic_score_gemma":0.00002902172,"domain_scores_codex":[0.9991991,0.00001265172,0.0002232767,0.0001545939,0.0001337293,0.000276676],"domain_scores_gemma":[0.9989123,0.00001006446,0.0001956494,0.0007363105,0.00007157342,0.00007413792],"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":[0.001372993,0.003222857,0.104715,0.0004360593,0.00271542,0.00002594537,0.01638365,0.05447274,0.6503267,0.02607474,0.09183825,0.04841561],"study_design_scores_gemma":[0.004512767,0.002398054,0.3546484,0.000073844,0.0001111765,0.00001975401,0.002298065,0.05279286,0.1988433,0.0002466232,0.3824724,0.001582714],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9725388,0.0002656988,0.0006887853,0.00008564749,0.0002973097,0.0001948605,0.0001111342,0.000004636353,0.0258131],"genre_scores_gemma":[0.9963142,0.00009961865,0.002733097,0.0002471467,0.0001701043,0.00001156506,0.00002394267,0.00001110374,0.0003892262],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4514834,"threshold_uncertainty_score":0.6144573,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000937994,0.0001432954,0.00009994057,0.00006889979,0.0000943647,0.00007113843,0.0002186329,0.00009365513,0.000007206448],"category_scores_gemma":[0.00003224322,0.0001437709,0.00002811747,0.0001528274,0.00002798674,0.00004383499,0.00004806724,0.0000450409,0.0001401819],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002567115,"about_ca_system_score_gemma":0.00005501286,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004050935,"about_ca_topic_score_gemma":0.0000103562,"domain_scores_codex":[0.9991843,0.00001210944,0.0002849975,0.0001324242,0.0001635715,0.0002226687],"domain_scores_gemma":[0.9992558,0.000004370517,0.0001069515,0.0003517806,0.0001221144,0.0001589556],"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":[0.0001317996,0.00007527239,0.001242461,0.0001426217,0.0000339808,0.00000103869,0.0008031449,0.006197969,0.9622129,0.0001931949,0.0004424838,0.02852309],"study_design_scores_gemma":[0.001802876,0.0008425246,0.006725016,0.00002142094,0.00003434105,0.00002499258,0.0004956163,0.188703,0.03610294,0.00005873707,0.7643053,0.0008832723],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4926944,0.0001439707,0.5046146,0.0002354014,0.0001295964,0.00101049,0.00021931,0.00004685433,0.0009053349],"genre_scores_gemma":[0.9703941,0.00005893382,0.02702279,0.0009484094,0.000195755,0.0001065305,0.001156506,0.00001439176,0.0001025398],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.92611,"threshold_uncertainty_score":0.5862808,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003847354,0.0001402597,0.0001352109,0.00005001023,0.00008754973,0.00003688376,0.0002398418,0.0001732177,0.000004035571],"category_scores_gemma":[0.0003456493,0.00008543733,0.00005730012,0.0001100488,0.0001150513,0.0000467852,0.00009053966,0.0001046816,0.000009401018],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001714126,"about_ca_system_score_gemma":0.0001214846,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001337989,"about_ca_topic_score_gemma":0.00002879991,"domain_scores_codex":[0.9988525,0.00001647049,0.0006116377,0.00006894654,0.0002296519,0.0002208115],"domain_scores_gemma":[0.9990457,0.00003139069,0.000320687,0.0003562338,0.0001852902,0.00006071954],"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":[0.002565943,0.0000867661,0.0144445,0.0007225488,0.000315356,0.000002122902,0.004158066,0.001369392,0.9259248,0.00812686,0.001523098,0.04076056],"study_design_scores_gemma":[0.004244458,0.00386687,0.4121157,0.0001878992,0.0002091991,0.0002161703,0.00357644,0.03132218,0.5060959,0.00109694,0.03609903,0.0009691786],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9472955,0.00002582545,0.05097091,0.00003014795,0.00009493776,0.00043149,0.00006203777,0.00001862015,0.001070469],"genre_scores_gemma":[0.9893273,0.00004392151,0.009918805,0.000417752,0.00008683902,0.000008523823,0.0001332906,0.000007004313,0.00005663953],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4198289,"threshold_uncertainty_score":0.3484033,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002044649,0.00009772973,0.0001057504,0.00004581468,0.0000928249,0.00000968786,0.00007862526,0.0001127798,0.000001772424],"category_scores_gemma":[0.00006589921,0.00009186391,0.0000770047,0.00005577089,0.00006214493,0.000001555598,0.00005633297,0.00003783976,0.000007222366],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009004282,"about_ca_system_score_gemma":0.0000241102,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004246789,"about_ca_topic_score_gemma":0.00003177073,"domain_scores_codex":[0.9993845,0.000004874307,0.0002712277,0.00009079371,0.00006392631,0.0001847418],"domain_scores_gemma":[0.9995567,0.00001825528,0.0001231227,0.0001569754,0.0001031013,0.00004187991],"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":[0.0001011093,0.00005502255,0.001983778,0.00008442614,0.00008364423,2.990201e-7,0.0002856873,0.00007076142,0.9264577,0.0001237688,0.0002603643,0.07049344],"study_design_scores_gemma":[0.0007108047,0.0009670394,0.008045319,0.00002229602,0.00005757223,0.00002927515,0.0007362784,0.0005157939,0.9321695,0.0001614669,0.05632963,0.0002550012],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9382151,0.0002439337,0.05941732,0.00004071429,0.0001946307,0.0002220129,0.0000306455,0.000003368922,0.001632219],"genre_scores_gemma":[0.971857,0.0001119771,0.02752107,0.0001625851,0.0001595189,0.00001211207,0.00003181957,0.00001103935,0.0001329067],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07023844,"threshold_uncertainty_score":0.3746102,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001005301,0.0001006262,0.0001217744,0.0000402725,0.00007333628,0.00001323162,0.0001133102,0.00007242782,0.000002355182],"category_scores_gemma":[0.00001593426,0.00009059,0.00006902486,0.00007644943,0.00006885668,0.000001283711,0.00007509184,0.00002713724,0.000001730198],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006999951,"about_ca_system_score_gemma":0.0000508835,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004135825,"about_ca_topic_score_gemma":0.00002954219,"domain_scores_codex":[0.9993551,0.000007792549,0.0003064719,0.0000808422,0.00009277602,0.000156985],"domain_scores_gemma":[0.9996264,0.000007511152,0.000084646,0.0001788985,0.00007691856,0.00002562914],"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":[0.000005686232,0.00002600503,0.01272015,0.00004412118,0.0000466449,4.152976e-7,0.00007475852,0.00203306,0.9836224,0.0002590793,0.0004212978,0.0007464046],"study_design_scores_gemma":[0.0004580031,0.0002824099,0.02372783,0.0000530063,0.0001036277,0.00004095449,0.001013701,0.01566724,0.9341495,0.0005226017,0.02338027,0.0006008669],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9923909,0.0006176092,0.0030399,0.00001352993,0.000109821,0.00008617996,0.00003461989,0.000002819885,0.003704592],"genre_scores_gemma":[0.9762148,0.0001228263,0.02342182,0.00003479234,0.0001098428,0.000002310184,0.00003214134,0.000007798129,0.00005366907],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0494729,"threshold_uncertainty_score":0.3694153,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000840651,0.0001192855,0.0001791702,0.00008312841,0.00006056953,0.00001086225,0.000100791,0.00008390852,0.00000702999],"category_scores_gemma":[0.00001828003,0.00009358575,0.00005407237,0.0001724027,0.0001638852,0.000001135823,0.00008311307,0.00005128089,0.000001296589],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000002418441,"about_ca_system_score_gemma":0.00005364932,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001072834,"about_ca_topic_score_gemma":0.00009608135,"domain_scores_codex":[0.9993967,0.000007074947,0.0002182253,0.000118344,0.0001050747,0.0001545333],"domain_scores_gemma":[0.999438,0.00001116682,0.0001223503,0.0002617107,0.0001102312,0.00005653589],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001063534,0.0001207138,0.4985297,0.0001376376,0.002464504,8.970355e-7,0.0007298901,0.0003802625,0.4893207,0.000480485,0.0007314017,0.006997471],"study_design_scores_gemma":[0.0008464389,0.0007881873,0.9205887,0.00001346852,0.001228065,0.00002094292,0.0007108142,0.01025021,0.04963052,0.0001428759,0.01527398,0.0005058013],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9977893,0.0006121142,0.0003610679,0.00002770886,0.0000455986,0.0001281595,0.0001055204,0.000002442232,0.0009281134],"genre_scores_gemma":[0.9834595,0.0002795048,0.0160482,0.00005868242,0.00003840224,0.00001067671,0.00006755625,0.00000771397,0.00002979397],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4396901,"threshold_uncertainty_score":0.3816316,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002545879,0.00007746069,0.00009368925,0.00002392718,0.0001014362,0.00001652749,0.0002206993,0.00007481412,0.000008387356],"category_scores_gemma":[0.0002491106,0.00005318152,0.00005007731,0.00009124511,0.00006609647,0.000004063669,0.0001375574,0.00009284836,0.00001292148],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006410922,"about_ca_system_score_gemma":0.00002246946,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001436397,"about_ca_topic_score_gemma":0.00001638047,"domain_scores_codex":[0.9993294,0.0000388907,0.0002160753,0.00006761872,0.0001571427,0.0001908882],"domain_scores_gemma":[0.9994767,0.00001510903,0.000110209,0.0002828615,0.00006528315,0.00004985315],"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":[0.00002305726,0.00001549637,0.004054567,0.0001010433,0.00003276238,1.452657e-7,0.0002250664,0.003299613,0.94124,0.0004794007,0.0005907729,0.04993813],"study_design_scores_gemma":[0.0004717381,0.0002684475,0.00509589,0.0000474468,0.00001226013,0.00001174966,0.0002420307,0.2390103,0.7099431,0.00003275156,0.04470453,0.0001597149],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9640225,0.00007323049,0.0314331,0.00007266258,0.00005926919,0.0001198699,0.00000159763,0.00001062341,0.004207153],"genre_scores_gemma":[0.9955649,0.00002888106,0.00230406,0.00009367936,0.00005432748,0.000002270073,0.00001663024,0.000009729833,0.001925517],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2357107,"threshold_uncertainty_score":0.216868,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005054561,0.0001622003,0.0001915188,0.0001499713,0.0001980237,0.0002130904,0.0003238339,0.00004509043,0.000004216943],"category_scores_gemma":[0.0001734837,0.0001126104,0.00006417168,0.0002088895,0.000080366,0.0007263161,0.0001674608,0.00008940382,0.00002620953],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006381188,"about_ca_system_score_gemma":0.0001019224,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000779712,"about_ca_topic_score_gemma":0.00000123,"domain_scores_codex":[0.9985952,0.0001448108,0.0003634389,0.0001955812,0.0004883358,0.0002126511],"domain_scores_gemma":[0.997887,0.001259014,0.0001612273,0.0004022686,0.0001809313,0.0001095946],"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":[0.00004480107,0.00008355886,0.0002402257,0.00007579318,0.00004051007,0.00001662855,0.001326389,0.009048631,0.0001354261,0.01115449,0.002175495,0.9756581],"study_design_scores_gemma":[0.001146242,0.0000559922,0.002661139,0.0001145092,0.000007127051,0.00001966971,0.00003214039,0.9879351,0.001237794,0.004278034,0.002313572,0.000198643],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005537219,0.00003897664,0.9908693,0.001605967,0.0002572448,0.0001864233,0.00001952836,0.0001400158,0.001345273],"genre_scores_gemma":[0.1084383,0.000014843,0.8899248,0.001493781,0.00005178587,0.00001113863,0.000006207491,0.000008824815,0.00005037913],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9788865,"threshold_uncertainty_score":0.4592119,"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)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001328838,0.0001214603,0.0001088113,0.00004269223,0.0001037762,0.00005503358,0.00008999562,0.00006410146,0.000005471034],"category_scores_gemma":[0.0001004637,0.00008007123,0.0000302966,0.00005995881,0.00009892211,0.00002218395,0.0001094426,0.00005486533,0.000005964717],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001186603,"about_ca_system_score_gemma":0.00001841204,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002932687,"about_ca_topic_score_gemma":0.0000189929,"domain_scores_codex":[0.9993795,0.00001512031,0.0001922526,0.0001363466,0.0000854042,0.0001913702],"domain_scores_gemma":[0.9995422,0.00001931299,0.0001350156,0.0001961038,0.00006141303,0.00004591305],"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":[0.00002316507,0.00001020384,0.03802434,0.00004281202,0.00003704259,0.000001398025,0.00009950177,0.000004866135,0.9302178,0.000003654847,0.0006743136,0.03086091],"study_design_scores_gemma":[0.0005446231,0.0001411794,0.001065364,0.00007593694,0.00002382797,0.00001817398,0.0003272377,0.001520451,0.9733163,0.00000513125,0.022741,0.0002208386],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6323153,0.0004303746,0.3627881,0.00005139917,0.00001034478,0.0001452363,0.000002717309,0.000068395,0.004188184],"genre_scores_gemma":[0.8870393,0.0005013921,0.1115132,0.0001355698,0.00003491537,0.000009361403,0.00001838576,0.00001786079,0.0007299411],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2547241,"threshold_uncertainty_score":0.326521,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001510532,0.0001004056,0.0001283544,0.00004088399,0.00003706217,0.000009035948,0.0001072557,0.0001098096,0.00002785158],"category_scores_gemma":[0.00002651782,0.0000946753,0.00006208968,0.0001235041,0.00007157816,0.000009281924,0.0000817787,0.0001016985,0.00002287419],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002662345,"about_ca_system_score_gemma":0.0001164899,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001756509,"about_ca_topic_score_gemma":0.000110399,"domain_scores_codex":[0.9991954,0.000009415361,0.0004386938,0.00007237679,0.00007542289,0.0002086901],"domain_scores_gemma":[0.9995437,0.00000603755,0.0001522865,0.0002042993,0.0000514547,0.00004219421],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001716601,0.001535763,0.01403775,0.00119386,0.0007824909,0.00001383526,0.004917903,0.4570121,0.100128,0.2530143,0.03974316,0.1259043],"study_design_scores_gemma":[0.02962434,0.005891891,0.06539228,0.001733005,0.0001993402,0.0008414533,0.005807293,0.05057667,0.1668124,0.1810956,0.4870909,0.00493473],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7743024,0.0004282345,0.2025331,0.0005918019,0.0007656839,0.000732676,0.00003117848,0.00002366503,0.02059132],"genre_scores_gemma":[0.9796134,0.00002855062,0.01955693,0.0002461252,0.0001779139,0.00002107026,0.0001025449,0.000008212296,0.0002452565],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4473478,"threshold_uncertainty_score":0.3860747,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001558309,0.000107761,0.000117595,0.00007902699,0.00002442485,0.00001468943,0.0001423493,0.000182608,0.000006923643],"category_scores_gemma":[0.00002945862,0.00009307463,0.00004327817,0.00009124016,0.00003488061,0.00001414686,0.00001936066,0.00005109623,8.628346e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002571054,"about_ca_system_score_gemma":0.0002365486,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008336536,"about_ca_topic_score_gemma":0.000007978995,"domain_scores_codex":[0.999271,0.00002701296,0.0002952873,0.0001344076,0.0001389772,0.0001333186],"domain_scores_gemma":[0.9992787,0.000006888278,0.0001873101,0.0002278529,0.0002022887,0.00009695611],"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":[0.0002169404,0.00009806028,0.002080118,0.0001039384,0.000007863956,1.172976e-7,0.0002086782,0.007475091,0.980761,0.00002771325,0.006252501,0.002768],"study_design_scores_gemma":[0.001386013,0.0001438013,0.003385637,0.00004335222,0.000008304053,8.906378e-7,0.0003641665,0.0260418,0.9663185,0.00004919209,0.002093667,0.0001646605],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9067128,0.0005773257,0.09103753,0.0002065128,0.0003470029,0.0005597638,0.0003396486,0.0000184462,0.0002009747],"genre_scores_gemma":[0.9769823,0.00002497287,0.02213881,0.000280815,0.0001101448,0.00007907332,0.0003429871,0.00001399068,0.0000268902],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07026952,"threshold_uncertainty_score":0.3795473,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008221749,0.0001009066,0.00007508678,0.00003286066,0.00005228736,0.00004040577,0.000137057,0.00008603499,0.000009808737],"category_scores_gemma":[0.000008327382,0.00007901855,0.00003876605,0.00009264829,0.0000224046,0.000007514822,0.000007712173,0.00005189536,0.00001496428],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001231678,"about_ca_system_score_gemma":0.00006871361,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":5.826631e-7,"about_ca_topic_score_gemma":0.000001048587,"domain_scores_codex":[0.9994358,0.000009957727,0.0001592548,0.00009631336,0.0001195682,0.0001790934],"domain_scores_gemma":[0.9995604,0.000001801207,0.00006314139,0.0002550034,0.00004053687,0.00007910762],"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":[0.0001323271,0.00007364222,0.0003245116,0.00002620607,0.00001900716,0.000001388251,0.0003624748,0.0001012088,0.955516,0.0006376433,0.01457695,0.02822868],"study_design_scores_gemma":[0.001642544,0.001037232,0.007781,0.00004461695,0.00003056975,0.00009293351,0.0004431247,0.001440564,0.4272533,0.0001087238,0.5596684,0.0004569664],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7296356,0.0004617217,0.1758008,0.001721551,0.0002105132,0.0004196342,0.00002332595,0.00009854194,0.09162831],"genre_scores_gemma":[0.9883066,0.00008871114,0.008279017,0.002241423,0.00008810328,0.000008521934,0.00005852093,0.000008194496,0.0009208595],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5450915,"threshold_uncertainty_score":0.3222283,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004239053,0.0002296258,0.0001855258,0.00005905475,0.00010894,0.000083616,0.0001946819,0.000215278,0.000006223783],"category_scores_gemma":[0.00003240709,0.0001841976,0.00009772956,0.00009727219,0.00005132613,0.00003084774,0.00007199503,0.0001453325,0.00001658748],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003298366,"about_ca_system_score_gemma":0.00004892464,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003085306,"about_ca_topic_score_gemma":0.00002500099,"domain_scores_codex":[0.9988811,0.00002865478,0.0004646225,0.000164358,0.0001195929,0.0003416747],"domain_scores_gemma":[0.9990695,0.00003484503,0.000245416,0.0004106174,0.0001424213,0.00009717936],"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":[0.01671185,0.0003683862,0.007036805,0.0006482315,0.0006918294,0.000002775903,0.005703407,0.767199,0.02502389,0.0009686112,0.0151301,0.1605152],"study_design_scores_gemma":[0.001643322,0.0005111439,0.0008021471,0.00002031669,0.00002900249,0.00001531426,0.0003915458,0.9891064,0.001637598,0.0000181123,0.005573541,0.0002516243],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3964393,0.0001188036,0.6015738,0.00008652623,0.0004526041,0.0009474637,0.00007340361,0.00003742781,0.000270769],"genre_scores_gemma":[0.9383566,0.00007482649,0.0582154,0.0007188065,0.0002183907,0.00006399735,0.00115367,0.00004426564,0.001154087],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5433583,"threshold_uncertainty_score":0.7511362,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005235405,0.0001330001,0.0002014276,0.0002794639,0.0001334536,0.00004109147,0.0001294984,0.0001323155,0.000009058293],"category_scores_gemma":[0.0002018668,0.0001096055,0.0003024778,0.0008590017,0.00004068618,0.00002044661,0.00001971397,0.00003541563,0.000001566667],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003843494,"about_ca_system_score_gemma":0.00008620449,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009562947,"about_ca_topic_score_gemma":0.00007914092,"domain_scores_codex":[0.9989177,0.00004373068,0.0005496259,0.0001389679,0.000199008,0.0001509707],"domain_scores_gemma":[0.9988232,0.00003993122,0.0004084111,0.0003377994,0.0003584409,0.0000321741],"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":[0.0002418628,0.0001908865,0.003372283,0.0001195404,0.003614614,3.467664e-7,0.001444318,0.6577722,0.257242,0.0009831503,0.0002501993,0.07476856],"study_design_scores_gemma":[0.0003760441,0.0001068868,0.01719761,0.000003380132,0.002684573,0.000001264858,0.0001370152,0.9709963,0.008134264,0.000112331,0.0001150022,0.0001353275],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3508092,0.00005045005,0.6486943,0.00005188786,0.00003619142,0.0002698448,0.00004410876,0.000007541415,0.00003642281],"genre_scores_gemma":[0.9521323,0.0000520616,0.04645224,0.0001505457,0.00005424802,0.0000107648,0.001067916,0.000006309922,0.00007358653],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6022421,"threshold_uncertainty_score":0.4469582,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006377915,0.0001115013,0.00009180962,0.00002636195,0.00007027725,0.00002968036,0.0001110857,0.00006930486,0.00001564241],"category_scores_gemma":[0.00002037036,0.00008809161,0.00003371186,0.00005095623,0.00005906462,0.000001686299,0.0000755599,0.00006259749,0.00002492808],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004394551,"about_ca_system_score_gemma":0.00004315477,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000372269,"about_ca_topic_score_gemma":0.00004971445,"domain_scores_codex":[0.9995375,0.00000659655,0.0001615744,0.00009665318,0.00005884944,0.00013886],"domain_scores_gemma":[0.9995773,0.000004748873,0.0000896399,0.0001950939,0.00008983825,0.00004341161],"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":[0.00005390959,0.00003864836,0.001423837,0.00003840877,0.00008911167,5.620868e-7,0.0005779411,0.0000315912,0.9942716,0.0002947177,0.0005857655,0.002593925],"study_design_scores_gemma":[0.001886625,0.001169452,0.0282863,0.00003276921,0.0001009662,0.0001567696,0.0009244541,0.001266443,0.268907,0.00008944243,0.6961918,0.000988026],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9911751,0.00009472,0.004546015,0.00003885352,0.0002133174,0.0001798848,0.00002923132,0.000005565289,0.003717282],"genre_scores_gemma":[0.9877061,0.0001197996,0.01137975,0.0003088117,0.0001725261,0.00000987751,0.0001039583,0.00001444788,0.0001847409],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7253646,"threshold_uncertainty_score":0.3592272,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001195817,0.0001776394,0.0001537651,0.00003437142,0.0001201953,0.00003052772,0.0002385243,0.0001683164,0.00001884868],"category_scores_gemma":[0.00004718969,0.0001648352,0.0001151768,0.00006227917,0.00003585318,0.000006398104,0.00004643592,0.0000602082,0.00003572727],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009222652,"about_ca_system_score_gemma":0.00006829609,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":3.634906e-7,"about_ca_topic_score_gemma":0.00000194729,"domain_scores_codex":[0.9990396,0.000009900225,0.0003078878,0.000168156,0.0001132412,0.0003611548],"domain_scores_gemma":[0.9993058,0.00001271878,0.00009832815,0.0003748001,0.00008087113,0.0001274556],"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":[0.003693771,0.005768979,0.005653778,0.002237606,0.001454839,0.000004315243,0.03380809,0.1125803,0.2710867,0.1561797,0.2145653,0.1929667],"study_design_scores_gemma":[0.005398133,0.006797223,0.07562892,0.00004693959,0.0001483942,0.00003969522,0.001538988,0.01664191,0.01348903,0.009627755,0.8690333,0.001609714],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3587419,0.0005807659,0.6314827,0.0002076596,0.00029946,0.0009780258,0.0002375535,0.00006085782,0.007411097],"genre_scores_gemma":[0.6381629,0.0000236518,0.3572983,0.001765696,0.0004907499,0.00002769484,0.0003257377,0.00002306085,0.001882171],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.654468,"threshold_uncertainty_score":0.6721787,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003316122,0.0000738466,0.0001515565,0.00001829326,0.00003791321,0.000008004106,0.0000801762,0.00008246986,0.00005243134],"category_scores_gemma":[0.0001100878,0.00002853398,0.00004416735,0.0001514812,0.00002199515,0.00008203793,0.00001585357,0.00006089543,0.00002447913],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001837625,"about_ca_system_score_gemma":0.000006014713,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002486861,"about_ca_topic_score_gemma":0.0001275743,"domain_scores_codex":[0.9993343,0.00004939752,0.0003257166,0.00006675197,0.00005740537,0.0001664418],"domain_scores_gemma":[0.9996525,0.000149389,0.0001158452,0.0000365194,0.00001844674,0.00002729183],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000347533,0.00007944016,0.5085257,0.0000552092,0.00001366125,0.000001555076,0.001330936,0.00002113134,0.4237526,0.0006484778,0.0001683335,0.06536819],"study_design_scores_gemma":[0.0004735074,0.0005106375,0.9245027,0.00004321577,0.0000131169,0.00004294936,0.002234231,0.004068433,0.05425024,0.002520402,0.01099145,0.0003491479],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9958662,0.00008006264,0.0001307358,0.00003056086,0.0000948501,0.00009904461,0.000006940491,0.00001679711,0.003674854],"genre_scores_gemma":[0.999447,0.00005077576,0.0003169454,0.0001164153,0.00002768474,0.000004320746,0.000009647223,3.910337e-7,0.00002685222],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.415977,"threshold_uncertainty_score":0.1163582,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003166987,0.0003006603,0.0002491368,0.00004094138,0.0002998043,0.0002202591,0.001212028,0.0001621374,0.00005159705],"category_scores_gemma":[0.00007446704,0.0002242513,0.00008923375,0.0001251826,0.0001115355,0.00001479099,0.001138912,0.0001631115,0.0002734105],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003397367,"about_ca_system_score_gemma":0.000133954,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001440856,"about_ca_topic_score_gemma":0.00008331267,"domain_scores_codex":[0.9983712,0.00003870216,0.0005529998,0.0003457967,0.0002236843,0.0004675828],"domain_scores_gemma":[0.9978464,0.00003626559,0.0002391921,0.00161185,0.0001408532,0.000125405],"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":[0.00001097438,0.0000205407,0.002686704,0.00003885621,0.0002551987,0.000001280843,0.001177434,0.0008493644,0.9897457,0.00001562106,0.003417312,0.001781058],"study_design_scores_gemma":[0.001870437,0.0004368978,0.07396197,0.00006871182,0.0003611828,0.00006265592,0.008522984,0.04222282,0.01428223,0.0007379969,0.8552854,0.002186726],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9866604,0.00266497,0.004456205,0.0007907371,0.0003788668,0.0005843657,0.001180985,0.0000182158,0.003265205],"genre_scores_gemma":[0.9621523,0.0008878522,0.02912996,0.002493905,0.001066114,0.000050861,0.003191295,0.00006192578,0.0009657863],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9754634,"threshold_uncertainty_score":0.9144701,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020912,0.00006522936,0.000122101,0.00001374039,0.00005125999,0.00002386293,0.00007733824,0.00005817413,0.00002526115],"category_scores_gemma":[0.00004065251,0.00002762853,0.00002588564,0.0000766655,0.00002563819,0.0001395038,0.000008590488,0.00002118168,0.0000045575],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008025504,"about_ca_system_score_gemma":0.000003184968,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004521998,"about_ca_topic_score_gemma":0.0000103196,"domain_scores_codex":[0.9994352,0.00002630672,0.0003303271,0.00007393622,0.00004976984,0.00008439207],"domain_scores_gemma":[0.9995893,0.0000911664,0.0001682599,0.00002864042,0.00009156443,0.00003105839],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001957242,0.0003341399,0.02866332,0.0001148191,0.00004725671,1.651634e-7,0.004905733,0.0008727909,0.1362846,0.004768081,0.00617901,0.8176343],"study_design_scores_gemma":[0.0004258436,0.001197128,0.5344011,0.00002683895,0.00002874073,0.0000119455,0.001186022,0.4477676,0.001618725,0.005051627,0.008046568,0.0002378433],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.97498,0.00008733203,0.02428667,0.0002067488,0.00005102158,0.0001805678,0.00006489913,0.00002681349,0.0001159566],"genre_scores_gemma":[0.9972908,0.00004687959,0.001839236,0.000226772,0.00003342082,0.00000295757,0.0005283552,3.85093e-7,0.00003115782],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8173965,"threshold_uncertainty_score":0.1126659,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001147755,0.00007834074,0.00008412961,0.00007684351,0.00005221009,0.00001174227,0.00003807508,0.00008414896,6.398659e-7],"category_scores_gemma":[0.00003348497,0.00007825989,0.0000240893,0.0001070968,0.00002737103,0.00002397309,0.00001401307,0.00003214348,2.339058e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001292091,"about_ca_system_score_gemma":0.00004890958,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001719359,"about_ca_topic_score_gemma":0.000003764314,"domain_scores_codex":[0.9994707,0.000009784936,0.0002433262,0.0000689135,0.00007548504,0.0001317752],"domain_scores_gemma":[0.9997504,0.000007597586,0.00006036448,0.00007870535,0.00006633567,0.00003659248],"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":[0.000258388,0.0001391046,0.05389807,0.0005417717,0.00005260684,1.476778e-7,0.001833571,0.0280237,0.8911421,0.001223988,0.00002221747,0.02286432],"study_design_scores_gemma":[0.002818728,0.0008595354,0.1231609,0.0003330855,0.0000667421,0.00002274567,0.0004572383,0.7798951,0.08960784,0.0002837604,0.001776503,0.0007178744],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5558724,0.0000075343,0.4434526,0.00003491233,0.0000235034,0.0004145982,0.0001747174,0.000004789862,0.0000149952],"genre_scores_gemma":[0.9065661,0.00000846668,0.09137856,0.00009008312,0.0000386523,0.00009005075,0.001814528,0.000007608282,0.000005974091],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8015343,"threshold_uncertainty_score":0.3191346,"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)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001565957,0.0001445522,0.0001329408,0.00003284373,0.00008388453,0.00001611235,0.00009326126,0.0001135351,0.00001532911],"category_scores_gemma":[0.00009087575,0.0001303471,0.00006876078,0.00005402002,0.00008217278,0.000002093192,0.0001670863,0.00007029137,0.00005115902],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008981299,"about_ca_system_score_gemma":0.00005946942,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000924592,"about_ca_topic_score_gemma":0.000007701881,"domain_scores_codex":[0.9992459,0.00001736437,0.0002623703,0.000134419,0.00009653297,0.0002434328],"domain_scores_gemma":[0.9994694,0.00001321922,0.00006625839,0.0002800105,0.00009109812,0.00008003413],"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":[0.0008081504,0.0009293281,0.04237609,0.000512736,0.002693739,0.0001332313,0.03653371,0.00004487654,0.6844125,0.01243056,0.09276902,0.1263561],"study_design_scores_gemma":[0.001665206,0.001791227,0.1170001,0.0000992282,0.0002369154,0.0006885375,0.01656009,0.00365515,0.4085402,0.001006901,0.4464517,0.002304693],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8718505,0.0001843853,0.01134682,0.0001088044,0.0004380447,0.0003117165,0.0000526998,0.00001635429,0.1156907],"genre_scores_gemma":[0.9292775,0.0002460259,0.0695459,0.0004718759,0.0001199283,0.00000925669,0.00003949834,0.00001592166,0.0002741126],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3536827,"threshold_uncertainty_score":0.53154,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003133821,0.0001994204,0.0001947118,0.0001035948,0.0001316998,0.00003310751,0.0002402075,0.0002159689,0.00001120961],"category_scores_gemma":[0.0002852633,0.0001886611,0.0001000356,0.0002058024,0.0001203016,0.00002319544,0.0001418608,0.0001553448,0.00001122326],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004844045,"about_ca_system_score_gemma":0.0001683179,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007791262,"about_ca_topic_score_gemma":0.00001987182,"domain_scores_codex":[0.9986153,0.0000298008,0.0006653707,0.0001263482,0.000288357,0.00027481],"domain_scores_gemma":[0.9989064,0.000007718168,0.0004562255,0.0004107606,0.000127815,0.00009113401],"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":[0.0003232186,0.000387831,0.1186998,0.002958801,0.0004150221,0.000006481164,0.006011193,0.6570231,0.2049209,0.003479333,0.000292383,0.005481977],"study_design_scores_gemma":[0.001456546,0.0004485492,0.0002555183,0.0001440167,0.00005335089,0.00005091455,0.0006580178,0.7999644,0.1916935,0.0001321311,0.004751978,0.0003911357],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.437516,0.0001175454,0.5592595,0.00004396578,0.0001404,0.0004145683,0.00002508152,0.00004635561,0.002436504],"genre_scores_gemma":[0.8751088,0.0000510268,0.1242062,0.0001646685,0.00008801662,0.000006408234,0.0002699748,0.00003352679,0.00007132959],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4375928,"threshold_uncertainty_score":0.7693377,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016134,0.0001427239,0.0001080956,0.00005231334,0.0001624988,0.00009888608,0.0001493769,0.0001380961,0.000004695149],"category_scores_gemma":[0.00003851781,0.00013321,0.00002862935,0.00009610545,0.00007403421,0.00004750143,0.00007251379,0.00008040398,0.000003133748],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003383332,"about_ca_system_score_gemma":0.0001647615,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005349584,"about_ca_topic_score_gemma":0.000005396958,"domain_scores_codex":[0.9991549,0.00003253181,0.0002742917,0.00022886,0.0001142922,0.0001951745],"domain_scores_gemma":[0.9991248,0.000003783961,0.0001351605,0.0006108661,0.00004454256,0.00008090024],"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":[0.00001734975,0.00002247456,0.001806108,0.00002800284,0.0000245255,2.497175e-7,0.00004507237,0.0001073347,0.9937503,0.0003752942,0.003649843,0.0001734629],"study_design_scores_gemma":[0.0007975999,0.0001135847,0.001028959,0.00003228048,0.00006597338,0.0000646655,0.0004323355,0.01467741,0.8888269,0.000139671,0.09350351,0.0003170893],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4786457,0.001299118,0.5162196,0.0001173228,0.0006932209,0.0004699252,0.0005660174,0.00003167191,0.001957531],"genre_scores_gemma":[0.8009924,0.002766727,0.1923028,0.0003542175,0.0003685787,0.00002756982,0.002315417,0.00004316487,0.0008292151],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3239168,"threshold_uncertainty_score":0.5432148,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007136444,0.0001091445,0.0002439196,0.000103843,0.00004435153,0.000008585373,0.0002086534,0.00009881089,0.00001770974],"category_scores_gemma":[0.000163272,0.0001014069,0.0001309593,0.0001760232,0.0000317765,0.00000838564,0.0000780322,0.00003259439,0.000008143728],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001429957,"about_ca_system_score_gemma":0.00008459596,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007663451,"about_ca_topic_score_gemma":0.00001913801,"domain_scores_codex":[0.9990977,0.00004561774,0.000409027,0.0001257831,0.00008365092,0.0002381932],"domain_scores_gemma":[0.9991306,0.00002146604,0.0002471565,0.0003291592,0.000129324,0.0001423144],"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":[0.0007280416,0.00129662,0.124609,0.0002786641,0.01028892,0.000002006765,0.003278715,0.007189533,0.2668337,0.0008099534,0.5643791,0.02030573],"study_design_scores_gemma":[0.007038737,0.00136064,0.01749626,0.000007210535,0.00417472,0.00000814817,0.002686321,0.3780367,0.08469236,0.0001883931,0.5033684,0.0009420743],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8940732,0.0002057943,0.09776591,0.00006122491,0.0001783608,0.0002875479,0.006977583,0.00001162152,0.0004387122],"genre_scores_gemma":[0.9590099,0.00007711874,0.02461462,0.0006035496,0.0001048001,0.0000221899,0.01547804,0.00001175921,0.00007799462],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3708472,"threshold_uncertainty_score":0.4135252,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001200853,0.0002302396,0.0001794492,0.00002040106,0.0001093181,0.0001138098,0.0001177856,0.0002421281,0.000008992907],"category_scores_gemma":[0.000007127268,0.0001855477,0.00005080132,0.000102457,0.00009773959,0.00005628607,0.000137676,0.0002063876,0.00001421303],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003439415,"about_ca_system_score_gemma":0.00002523814,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002098002,"about_ca_topic_score_gemma":0.00004771885,"domain_scores_codex":[0.9989852,0.00002022842,0.0003554528,0.0001735399,0.0001554269,0.0003101936],"domain_scores_gemma":[0.9993302,0.000005647963,0.0002178438,0.0002944302,0.0000667429,0.00008511977],"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":[0.006840742,0.0005614285,0.03710401,0.00265593,0.001677803,0.00002412773,0.006886265,0.4074034,0.01981302,0.01408322,0.01094913,0.4920009],"study_design_scores_gemma":[0.001685431,0.001306704,0.001746837,0.0001283906,0.0000376001,0.0001903169,0.001231411,0.9866479,0.00120098,0.0001404531,0.005249027,0.0004349392],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.686982,0.0003579319,0.3073968,0.00007683143,0.0002557121,0.000829152,0.00002977981,0.00004368664,0.004028102],"genre_scores_gemma":[0.990287,0.00002611493,0.008723098,0.0003483817,0.0001219059,0.00002279657,0.0003189675,0.00001633479,0.0001354201],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5792445,"threshold_uncertainty_score":0.7566417,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000405995,0.0001020825,0.0001009121,0.00009625998,0.00008823929,0.0000410056,0.0001254562,0.00007400123,0.000003671781],"category_scores_gemma":[0.0000890286,0.00009668152,0.00003985396,0.00007213145,0.00002484426,0.000008099729,0.00008381678,0.00003873502,0.00001646557],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003228492,"about_ca_system_score_gemma":0.0000717466,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001031111,"about_ca_topic_score_gemma":0.00003197422,"domain_scores_codex":[0.9992913,0.00001550617,0.0002991304,0.00007278304,0.00008875036,0.0002325124],"domain_scores_gemma":[0.9996089,0.00001619739,0.00005626374,0.0001738843,0.00009439445,0.00005032528],"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":[0.0009539637,0.0002098931,0.02535073,0.0009301656,0.0002631759,6.873553e-7,0.02587542,0.04963628,0.6437137,0.00624713,0.01022104,0.2365979],"study_design_scores_gemma":[0.00254577,0.0009242512,0.01792073,0.0001170719,0.00003248212,0.00001561856,0.005612841,0.04892699,0.6529571,0.0004247903,0.2695218,0.001000574],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9202262,0.0001926227,0.075395,0.0001391598,0.00005468008,0.0009178389,0.00006729455,0.000005367217,0.003001817],"genre_scores_gemma":[0.8223749,0.00004328556,0.1766567,0.0005740299,0.0001530924,0.00005217045,0.00005448998,0.00001073431,0.00008055181],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2593007,"threshold_uncertainty_score":0.3942558,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002067124,0.000116864,0.0001261217,0.00004154367,0.00003223499,0.00003355927,0.0001540771,0.00007173029,0.00000377754],"category_scores_gemma":[0.0008424057,0.0001160694,0.00004032022,0.00008724468,0.00005741842,0.000006628168,0.0001499487,0.00005928304,0.00001345076],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004955589,"about_ca_system_score_gemma":0.0002874618,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002325968,"about_ca_topic_score_gemma":0.0003502466,"domain_scores_codex":[0.9992504,0.00001527386,0.0002968411,0.0001129213,0.0001115766,0.0002129803],"domain_scores_gemma":[0.9993956,0.00004233321,0.00009808326,0.0002629129,0.00008718728,0.0001138634],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004770631,0.0004908425,0.8190572,0.0003091586,0.0001087842,0.00002446019,0.00248884,0.03898191,0.1154825,0.002023485,0.006789144,0.01376665],"study_design_scores_gemma":[0.01087737,0.001291736,0.112273,0.0002036399,0.00009388896,0.0001125056,0.004730361,0.4072638,0.1809683,0.003469208,0.2758317,0.002884587],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9892208,0.0002627792,0.009418479,0.0000184533,0.0001813879,0.0001418245,0.00009682961,0.0000076212,0.0006518382],"genre_scores_gemma":[0.9755713,0.00005054113,0.02373355,0.0003932616,0.0001211198,0.00000623668,0.0001008797,0.000009833017,0.00001323439],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7067842,"threshold_uncertainty_score":0.4733175,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008704988,0.00008046292,0.00008125212,0.00001918484,0.000123729,0.00002943173,0.0001302309,0.00007232954,0.00006121434],"category_scores_gemma":[0.0001970337,0.00005849775,0.00005434204,0.00007805265,0.0002219286,0.000007246771,0.00005988923,0.00005312451,0.00001437887],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002144496,"about_ca_system_score_gemma":0.0002084928,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004178316,"about_ca_topic_score_gemma":0.0002227321,"domain_scores_codex":[0.9994169,0.000010276,0.0002571022,0.00006557707,0.0001088521,0.0001412278],"domain_scores_gemma":[0.9994208,0.00003249607,0.000171061,0.0001680268,0.0001680026,0.00003958349],"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":[0.00005439361,0.0002281564,0.3099374,0.0001687345,0.0006574104,7.649112e-7,0.001290228,0.004911284,0.5991126,0.006245536,0.06416274,0.01323078],"study_design_scores_gemma":[0.001737977,0.0005394507,0.2708405,0.0001318519,0.0002210754,0.000025066,0.003100872,0.01682393,0.6720494,0.0009783512,0.03285584,0.0006956272],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9952684,0.0007651962,0.0009155847,0.0003457523,0.0003212652,0.0002068272,0.0001626568,0.000009416993,0.002004881],"genre_scores_gemma":[0.998338,0.0004587514,0.0004901381,0.0003082656,0.0001057222,0.00004934677,0.0001155556,0.000005134238,0.0001290318],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07293682,"threshold_uncertainty_score":0.2385469,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}