{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":19,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":19,"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":"d9fbe9c57fec","filters":{"venue":"Computer applications in the biosciences"}},"results":[{"id":"W2144014661","doi":"10.1093/bioinformatics/bti273","title":"Online Predicted Human Interaction Database","year":2005,"lang":"en","type":"article","venue":"Computer applications in the biosciences","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":620,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Ontario Institute for Cancer Research","funders":"","keywords":"Drosophila melanogaster; Gene ontology; Computer science; Ontology; Visualization; Computational biology; Artificial intelligence; Biology; Gene; Gene expression; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.0176614791024342,"gpt":0.2957764760332367,"spread":0.2781149969308025,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001828377,0.00006228572,0.00004228824,0.00003534122,0.0001344515,0.00004342803,0.0004706753,0.00003498314,0.000004066729],"category_scores_gemma":[0.000002248755,0.00004242141,0.00002180661,0.0001615345,0.00009806691,0.000008312377,0.0001023024,0.00006566379,0.000004812052],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007354082,"about_ca_system_score_gemma":0.00001512383,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006714523,"about_ca_topic_score_gemma":0.00007765475,"domain_scores_codex":[0.9994933,0.00002045292,0.0001527781,0.0001553628,0.00007241977,0.0001056941],"domain_scores_gemma":[0.9995862,0.00001088095,0.00005244188,0.0003099926,0.00001929446,0.00002117346],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004238245,0.003917722,0.01261485,0.00007671369,0.00008179749,0.000001380361,0.004040605,0.01263816,0.2006259,0.0334601,0.1160977,0.6164027],"study_design_scores_gemma":[0.0005094259,0.0002552667,0.02180664,0.00002622302,0.00001552716,0.00003039583,0.0007798728,0.1050383,0.00585267,0.0009407856,0.8643628,0.0003820738],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.739269,0.0002333225,0.2573932,0.001073729,0.0001597613,0.0005090412,0.00007031081,0.00002205506,0.001269641],"genre_scores_gemma":[0.9873303,0.00003847303,0.01088859,0.0006917875,0.0005826043,0.00003776597,0.0003892972,0.000002766169,0.00003846405],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7482651,"threshold_uncertainty_score":0.1729895,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2127325419","doi":"10.1093/bioinformatics/bti439","title":"pFind: a novel database-searching software system for automated peptide and protein identification via tandem mass spectrometry","year":2005,"lang":"en","type":"article","venue":"Computer applications in the biosciences","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":181,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Computer science; Usability; Software; XML; Database; Tandem mass spectrometry; Proteomics; Identification (biology); Database search engine; Tandem mass tag; Data mining; Mass spectrometry; Information retrieval; Quantitative proteomics; Programming language; Operating system; Chemistry; Search engine; Chromatography; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.01994045347924747,"gpt":0.2977135505692231,"spread":0.2777730970899757,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000527897,0.0001349466,0.0001216761,0.0001127568,0.0004871066,0.0001681796,0.0007846344,0.00005738823,0.000002526955],"category_scores_gemma":[0.00001786125,0.0001062023,0.00003549291,0.000490633,0.0001666221,0.0001970092,0.0001030324,0.0001420847,0.000004207719],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001023626,"about_ca_system_score_gemma":0.0000332912,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001317615,"about_ca_topic_score_gemma":0.000006901533,"domain_scores_codex":[0.9987743,0.00001436443,0.0003175333,0.0004709804,0.0001909675,0.0002318756],"domain_scores_gemma":[0.9990196,0.0001626291,0.0001731494,0.0005454546,0.00005406468,0.00004508772],"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":[0.000005005296,0.0001941612,0.0007010991,0.0002113908,0.000008925666,1.976033e-7,0.0003296084,0.0003305555,0.9520794,0.0322278,0.0002059554,0.0137059],"study_design_scores_gemma":[0.0006520482,0.00004653412,0.00161375,0.0002407361,0.00003336035,0.00005065761,0.0008353201,0.6595482,0.3070373,0.009716451,0.01956136,0.0006642634],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04091702,0.00007143852,0.9567735,0.0003884483,0.00001059525,0.001175319,0.00009885269,0.0004362642,0.0001285992],"genre_scores_gemma":[0.4444058,0.000006339982,0.5533766,0.00002745415,0.0001107874,0.001968115,0.00005559514,0.000008906731,0.00004040328],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6592177,"threshold_uncertainty_score":0.4330804,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2725970836","doi":"10.1093/bioinformatics/btx460","title":"Analysis and prediction of protein folding energy changes upon mutation by element specific persistent homology","year":2017,"lang":"en","type":"article","venue":"Computer applications in the biosciences","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":108,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Mutation; Homology modeling; Pearson product-moment correlation coefficient; Stability (learning theory); Mutation rate; Computational biology; Correlation coefficient; Computer science; Correlation; Persistent homology; Mutagenesis; Protein folding; Folding (DSP implementation); Mathematics; Protein design; Protein structure; Algorithm; Biology; Genetics; Machine learning; Statistics; Gene; Biochemistry; Engineering; Geometry","retraction":null,"screen_n_in":null,"score":{"opus":0.01058242335798177,"gpt":0.2405717421445445,"spread":0.2299893187865628,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001766416,0.0000572891,0.00007000916,0.00006397293,0.0002133728,0.00004496326,0.0003345663,0.00004147955,8.423242e-7],"category_scores_gemma":[0.00000366425,0.00004150221,0.0000329278,0.0001197076,0.0001688877,0.000005141805,0.00008625213,0.00002133707,7.428086e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006337679,"about_ca_system_score_gemma":0.000008488828,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004893535,"about_ca_topic_score_gemma":0.00008719668,"domain_scores_codex":[0.9994927,0.00003148776,0.00009958162,0.0002155354,0.00008068302,0.0000800194],"domain_scores_gemma":[0.9995151,0.000006570579,0.0001228065,0.000314392,0.00002696619,0.0000142235],"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":[0.0000272436,0.000205316,0.03186113,0.00003724729,0.0002229749,8.063146e-7,0.0007286545,0.0005779475,0.8083845,0.01025078,0.0004461031,0.1472573],"study_design_scores_gemma":[0.001454585,0.002879024,0.3142847,0.0000534947,0.0004756314,0.00004760309,0.00175205,0.09357813,0.4908511,0.007781791,0.08595224,0.0008896677],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6875604,0.0009186229,0.3108481,0.0002878142,0.00003407756,0.0002478817,0.00002998872,0.000003255611,0.00006978699],"genre_scores_gemma":[0.9968076,0.0001893408,0.002729579,0.00002949541,0.00005632419,0.0001041271,0.00006859339,0.000001732428,0.00001316509],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3175333,"threshold_uncertainty_score":0.1692411,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2156336405","doi":"10.1093/bioinformatics/bti1041","title":"Multi-way clustering of microarray data using probabilistic sparse matrix factorization","year":2005,"lang":"en","type":"article","venue":"Computer applications in the biosciences","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":97,"is_retracted":false,"has_abstract":true,"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; Canadian Institutes of Health Research; University of Toronto; Microsoft","keywords":"Cluster analysis; Probabilistic logic; Computer science; Data mining; Sparse matrix; Non-negative matrix factorization; Noise (video); Hierarchical clustering; Matrix decomposition; Generative model; Matrix (chemical analysis); Algorithm; Artificial intelligence; Generative grammar; Eigenvalues and eigenvectors","retraction":null,"screen_n_in":null,"score":{"opus":0.07690284190076663,"gpt":0.3453961809586526,"spread":0.268493339057886,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002522365,0.00006843449,0.00005918415,0.00005130272,0.00008895208,0.00003137938,0.0008499566,0.00004101374,0.000002187848],"category_scores_gemma":[0.00001227056,0.00004907874,0.00001686318,0.0002752618,0.0001159275,0.00001174761,0.0001801862,0.00003296154,0.000001392271],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001221569,"about_ca_system_score_gemma":0.00004504516,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001013093,"about_ca_topic_score_gemma":0.00003157344,"domain_scores_codex":[0.999268,0.00004715421,0.0001858236,0.000304022,0.0001006994,0.00009430664],"domain_scores_gemma":[0.9991813,0.00001226664,0.0001040729,0.0006446529,0.00003923272,0.00001849134],"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":[0.00000364016,0.0001352572,0.002168767,0.00001528035,0.000002943463,2.379797e-8,0.0002557527,0.009301743,0.978449,0.0001281258,0.0002462121,0.009293277],"study_design_scores_gemma":[0.0005165109,0.00007971248,0.02688073,0.00004326279,0.00002265981,0.00001073108,0.0006092904,0.7785661,0.1092032,0.0001080963,0.08361028,0.0003493984],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1461277,0.0002391447,0.8530672,0.0001281476,0.00007860534,0.0003090916,0.00001811158,0.000005916729,0.00002607639],"genre_scores_gemma":[0.9178421,0.00003761112,0.08179219,0.00005099208,0.000148336,0.0000255926,0.00007865622,0.000003811742,0.00002065303],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8692458,"threshold_uncertainty_score":0.2001373,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2121105117","doi":"10.1093/bioinformatics/bti406","title":"Modularized learning of genetic interaction networks from biological annotations and mRNA expression data","year":2005,"lang":"en","type":"article","venue":"Computer applications in the biosciences","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":59,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"Expression (computer science); Computer science; Messenger RNA; Computational biology; Annotation; Artificial intelligence; Biology; Genetics; Gene; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.02539486015560128,"gpt":0.2782883853891387,"spread":0.2528935252335375,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002124462,0.0000641241,0.00006797441,0.00002637225,0.0001138694,0.00003732873,0.0005041048,0.00006051367,0.000002000181],"category_scores_gemma":[0.000008361762,0.0000424018,0.00001504638,0.0001177975,0.000141568,0.00001100086,0.0002640799,0.00007995635,7.922698e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000002998564,"about_ca_system_score_gemma":0.0000106097,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001137951,"about_ca_topic_score_gemma":0.00001026499,"domain_scores_codex":[0.9993918,0.00005339117,0.0001931011,0.0002164383,0.0000566468,0.00008865037],"domain_scores_gemma":[0.9994681,0.00005339026,0.00009772218,0.0003424054,0.00001882464,0.0000195176],"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":[0.00005522471,0.0004147773,0.05025238,0.00001545979,0.00004358987,3.697526e-7,0.001880195,0.1436995,0.1492333,0.001500814,0.002647593,0.6502568],"study_design_scores_gemma":[0.0002048989,0.00008159496,0.0367886,0.00001389618,0.000007342903,0.000004262779,0.0003262043,0.9394178,0.001122905,0.000484476,0.02142632,0.0001217014],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4469866,0.000569954,0.5520864,0.0001175984,0.00003798979,0.0001433061,0.000009510952,0.000004082688,0.00004460293],"genre_scores_gemma":[0.95592,0.0003326448,0.04320483,0.0001124783,0.0002117848,0.00001934314,0.0001933748,0.000002153055,0.000003403279],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7957183,"threshold_uncertainty_score":0.1729095,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2120815702","doi":"10.1093/bioinformatics/bti1040","title":"ExonHunter: a comprehensive approach to gene finding","year":2005,"lang":"en","type":"article","venue":"Computer applications in the biosciences","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":52,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Annotation; Hidden Markov model; Gene prediction; Probabilistic logic; Set (abstract data type); Sequence (biology); Markov chain; Extension (predicate logic); Data mining; Artificial intelligence; Machine learning; Gene; Genome; Genetics; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.02161260978141782,"gpt":0.2653430076089932,"spread":0.2437303978275753,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001767067,0.00008540764,0.00006747269,0.00004968384,0.0001433991,0.00006762808,0.0006748206,0.00004339789,9.29954e-7],"category_scores_gemma":[0.000001603519,0.00005905487,0.00003327843,0.0002633682,0.00008650836,0.000004566964,0.0001589756,0.00005293541,0.00001640658],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009268369,"about_ca_system_score_gemma":0.0000189145,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002618248,"about_ca_topic_score_gemma":0.000004134205,"domain_scores_codex":[0.9993395,0.00002179816,0.0001551943,0.0002220389,0.00009074963,0.0001707652],"domain_scores_gemma":[0.9995515,0.0000146002,0.0000403488,0.0003309931,0.00002406553,0.00003853587],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005101534,0.001589435,0.004588107,0.00008097455,0.00009210959,9.265168e-7,0.0142136,0.09209768,0.1599213,0.04017558,0.07363579,0.6135535],"study_design_scores_gemma":[0.0004122018,0.0002067157,0.01373572,0.00001291044,0.00001097605,0.00005119868,0.001098338,0.06666889,0.008390477,0.0006943238,0.9081886,0.0005296121],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2367634,0.0003139538,0.7584493,0.0006082423,0.00008227594,0.0006138367,0.000008882598,0.00001141056,0.003148692],"genre_scores_gemma":[0.9101133,0.00002681231,0.08720454,0.002057926,0.0003982151,0.000122292,0.00003036399,0.000003832053,0.00004269663],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8345528,"threshold_uncertainty_score":0.2408188,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2103184043","doi":"10.1093/bioinformatics/bti321","title":"MtbRegList, a database dedicated to the analysis of transcriptional regulation in Mycobacterium tuberculosis","year":2005,"lang":"en","type":"article","venue":"Computer applications in the biosciences","topic":"Tuberculosis Research and Epidemiology","field":"Medicine","cited_by":49,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke","funders":"Fonds Québécois de la Recherche sur la Nature et les Technologies; U.S. National Library of Medicine; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Mycobacterium tuberculosis; Tuberculosis; Database; Computational biology; Biology; Computer science; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.03446879600612759,"gpt":0.3397371658698042,"spread":0.3052683698636766,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001390833,0.00008377802,0.0002189022,0.000576534,0.00009422103,0.00001902105,0.0005187095,0.00004124226,0.0000386167],"category_scores_gemma":[0.00006694492,0.00004555237,0.00008623504,0.003895821,0.0002427826,0.00009009358,0.00005539764,0.0001302856,0.00001236573],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000560976,"about_ca_system_score_gemma":0.00005664833,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002731399,"about_ca_topic_score_gemma":0.000885358,"domain_scores_codex":[0.9986045,0.000193858,0.0003725214,0.0002962922,0.0003175094,0.0002153353],"domain_scores_gemma":[0.9989756,0.0003260349,0.00005776464,0.0005016293,0.00007095685,0.00006797612],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003108788,0.003371852,0.6499946,0.0001350417,0.0006716423,0.000004163307,0.01196401,0.03450738,0.09005664,0.03992225,0.02077295,0.1482886],"study_design_scores_gemma":[0.0001407407,0.00004092786,0.9032727,0.00001395856,0.00008619097,0.000004029448,0.0001194076,0.07849117,0.0002432379,0.00007961858,0.01745771,0.00005027588],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8733548,0.0002860328,0.05974582,0.06520201,0.00004208635,0.0009997207,0.00007507416,0.0000198475,0.0002746183],"genre_scores_gemma":[0.9916072,0.00007738944,0.005837079,0.001963968,0.000125781,0.0002279092,0.0001443768,0.000002715988,0.00001361283],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2532782,"threshold_uncertainty_score":0.1871813,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2159605359","doi":"10.1093/bioinformatics/bti483","title":"Ensemble dependence model for classification and prediction of cancer and normal gene expression data","year":2005,"lang":"en","type":"article","venue":"Computer applications in the biosciences","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":39,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Ensemble forecasting; Ensemble learning; Computational biology; Cancer; Expression (computer science); Gene; Gene expression; Artificial intelligence; Genetics; Biology; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.06174760510571803,"gpt":0.3243864251374056,"spread":0.2626388200316875,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000246378,0.0000563536,0.0000484656,0.0000370801,0.0001122105,0.00002330246,0.0003653445,0.00004525386,3.467107e-7],"category_scores_gemma":[0.000006554603,0.00004037567,0.000008876611,0.00009827456,0.0001147964,0.00001964776,0.0001168444,0.00002604521,8.798455e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004928307,"about_ca_system_score_gemma":0.0000399128,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004779697,"about_ca_topic_score_gemma":0.00002628341,"domain_scores_codex":[0.999366,0.00001807563,0.000138236,0.0003147257,0.00008807405,0.0000748913],"domain_scores_gemma":[0.9994646,0.0000166666,0.00008038471,0.0003763022,0.00004047433,0.00002157568],"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":[0.000009414029,0.00004209391,0.003144165,0.00001112131,0.000001758494,2.796216e-9,0.0001772897,0.0008115225,0.9407602,0.0003343771,0.0007206755,0.05398737],"study_design_scores_gemma":[0.0002720783,0.00005012043,0.03364914,0.00001442517,0.00001167622,0.000002403617,0.0001815339,0.7682949,0.1880156,0.0003745242,0.009041795,0.00009182892],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3056756,0.001119695,0.6922686,0.0004405227,0.0000286561,0.0003635535,0.00007275536,0.000004488417,0.0000261298],"genre_scores_gemma":[0.9667563,0.0008220775,0.03186209,0.00008778532,0.0001116267,0.0002465839,0.00008546645,0.000002854276,0.00002523174],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7674834,"threshold_uncertainty_score":0.1646472,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3108440423","doi":"10.1093/bioinformatics/btaa976","title":"Deep feature extraction of single-cell transcriptomes by generative adversarial network","year":2020,"lang":"en","type":"article","venue":"Computer applications in the biosciences","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":39,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"Douglas Mental Health University Institute; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Computer science; Generative model; Generative grammar; Feature (linguistics); Source code; Embedding; Generative adversarial network; Raw data; Code (set theory); Artificial intelligence; Data mining; Machine learning; Deep learning","retraction":null,"screen_n_in":null,"score":{"opus":0.01653542818112854,"gpt":0.2360269951309656,"spread":0.219491566949837,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001176639,0.0001052994,0.0001020893,0.00001706525,0.0001153368,0.00003473751,0.0004682392,0.00008334827,0.00000259533],"category_scores_gemma":[0.000004108499,0.00007741167,0.00006112002,0.0003274009,0.0001697292,0.000008168206,0.00002489714,0.00008197199,0.000001131314],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005986997,"about_ca_system_score_gemma":0.00002629614,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007948742,"about_ca_topic_score_gemma":0.00001296081,"domain_scores_codex":[0.9992223,0.00006683136,0.0001560205,0.0002875139,0.0001257648,0.0001415968],"domain_scores_gemma":[0.9996604,0.00002708376,0.00007369287,0.0001662871,0.00003470438,0.0000378616],"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":[0.00002500132,0.0001647775,0.001111779,0.00001085621,0.000007090963,1.616171e-7,0.0007132134,0.001937559,0.9877474,0.0001446154,0.005696903,0.002440648],"study_design_scores_gemma":[0.001208466,0.001203162,0.002070974,0.00001536157,0.00005411274,0.000007136056,0.0008875421,0.02712739,0.7567224,0.0003704657,0.2097836,0.0005493808],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.168782,0.001509135,0.8271095,0.001388925,0.0002691059,0.0004426335,0.00002124342,0.00001419139,0.0004632852],"genre_scores_gemma":[0.9864381,0.00008588042,0.01199874,0.0008222531,0.0005283279,0.00003028936,0.00007097887,0.000006074227,0.00001936978],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8176562,"threshold_uncertainty_score":0.3156756,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2107500667","doi":"10.1093/bioinformatics/bti397","title":"A robust neural networks approach for spatial and intensity-dependent normalization of cDNA microarray data","year":2005,"lang":"en","type":"article","venue":"Computer applications in the biosciences","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":39,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université Laval","funders":"","keywords":"Normalization (sociology); Sampling bias; Computer science; Microarray; Computational biology; Pattern recognition (psychology); Biology; Biological system; Statistics; Sample size determination; Artificial intelligence; Mathematics; Gene expression; Gene; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.04246975923685588,"gpt":0.2754001957445745,"spread":0.2329304365077187,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002837823,0.00006032387,0.00006077706,0.00003573823,0.00009229792,0.00003177772,0.000567134,0.00004230877,4.552955e-7],"category_scores_gemma":[0.000006381622,0.0000425589,0.00001458587,0.0001336419,0.0001239236,0.000009244536,0.0001537684,0.00003134271,7.667787e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004010404,"about_ca_system_score_gemma":0.00001676077,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001052978,"about_ca_topic_score_gemma":0.00002300916,"domain_scores_codex":[0.9993703,0.00002903125,0.0001425875,0.0003000561,0.00007212954,0.00008584443],"domain_scores_gemma":[0.9994227,0.00001188508,0.00007890789,0.0004204837,0.00004802121,0.00001794486],"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":[0.0001691058,0.001051383,0.0352787,0.0001095176,0.00003956158,9.446277e-8,0.001450482,0.1675111,0.3135206,0.002468931,0.01370925,0.4646913],"study_design_scores_gemma":[0.0002261259,0.00006250352,0.008867825,0.000003522159,0.000009087417,0.000005456559,0.0002253476,0.9706756,0.009448414,0.00002406273,0.01035377,0.00009821821],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03681192,0.0003239201,0.9621029,0.0002880754,0.00004768325,0.0003686033,0.00001336425,0.000003789227,0.0000397501],"genre_scores_gemma":[0.975278,0.00006736567,0.02384873,0.0002118577,0.0002373527,0.0000779433,0.0002638343,0.000003083179,0.00001184578],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9384661,"threshold_uncertainty_score":0.1735501,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2108149347","doi":"10.1093/bioinformatics/bti330","title":"Recoverable one-dimensional encoding of three-dimensional protein structures","year":2005,"lang":"en","type":"article","venue":"Computer applications in the biosciences","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":34,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Institute of Genetics; Ministry of Education, Culture, Sports, Science and Technology","keywords":"Protein structure; Protein secondary structure; Sequence (biology); Protein structure prediction; Computer science; Protein tertiary structure; Set (abstract data type); Structural bioinformatics; Structural motif; Biological system; Algorithm; Crystallography; Biology; Chemistry; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.01384964738495638,"gpt":0.251645521404076,"spread":0.2377958740191197,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002418996,0.0000919797,0.00008791536,0.00005002693,0.0001344475,0.00002239379,0.0005050365,0.00006408588,0.000007156977],"category_scores_gemma":[0.000009709639,0.00006317918,0.00004160405,0.000213114,0.000188775,0.000008471884,0.0001241457,0.00007103891,0.000001836204],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009418554,"about_ca_system_score_gemma":0.00006570566,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000203844,"about_ca_topic_score_gemma":0.00007479432,"domain_scores_codex":[0.9991791,0.00003371668,0.0001859507,0.0002655334,0.0001941503,0.0001415734],"domain_scores_gemma":[0.9995075,0.00002360968,0.00008589,0.0003112926,0.00004844811,0.00002319824],"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":[0.00004202958,0.0002663061,0.005072117,0.00003068064,0.00003116881,4.920113e-7,0.000167133,0.02079635,0.900361,0.03654314,0.0009167159,0.03577286],"study_design_scores_gemma":[0.001275395,0.0008073999,0.06447357,0.0001105511,0.00004079296,0.00009410836,0.00009766373,0.06566592,0.7237163,0.1001861,0.04241393,0.001118173],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9588709,0.0004360043,0.03939516,0.0003920936,0.00005747702,0.0005152543,0.00001507754,0.000008253595,0.0003097186],"genre_scores_gemma":[0.9368061,0.000004411077,0.06263053,0.0002475121,0.0002008685,0.00005965908,0.00002504767,0.00000380643,0.00002209976],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1766447,"threshold_uncertainty_score":0.2576373,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2096149709","doi":"10.1093/bioinformatics/bti1037","title":"Reversal distance for partially ordered genomes","year":2005,"lang":"en","type":"article","venue":"Computer applications in the biosciences","topic":"Genome Rearrangement Algorithms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":27,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Genome; Position (finance); Chromosome; Computer science; Representation (politics); Order (exchange); Gene; Mutation; Genetics; Computational biology; Biology; Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.01449698518350952,"gpt":0.2713342964950228,"spread":0.2568373113115133,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002448477,0.00007053955,0.00005444142,0.00002630138,0.0001291578,0.00004429817,0.0005740098,0.00002963359,0.000002387958],"category_scores_gemma":[0.000005021171,0.00005023264,0.00003487708,0.000178242,0.0001180423,0.000004517814,0.00005771356,0.00002437365,0.000005978916],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009264976,"about_ca_system_score_gemma":0.00002991711,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001754161,"about_ca_topic_score_gemma":0.00004612869,"domain_scores_codex":[0.9993659,0.00002069285,0.0001185632,0.0002524739,0.0000871583,0.000155165],"domain_scores_gemma":[0.999602,0.00002022169,0.00004054664,0.0002852755,0.00003149695,0.00002049355],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006912697,0.001292318,0.02891959,0.00009310161,0.00009080805,8.198558e-7,0.003387346,0.006575761,0.1838259,0.03223098,0.03402265,0.7094916],"study_design_scores_gemma":[0.0002328114,0.00009383247,0.004444204,0.000002487467,0.000006039696,0.000002055252,0.0001189339,0.00414939,0.004370305,0.0005012362,0.985938,0.0001407045],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07748479,0.001390144,0.9173352,0.002203227,0.0001031698,0.001041841,0.00002469462,0.00001572517,0.0004012216],"genre_scores_gemma":[0.9251399,0.0001251808,0.07307196,0.0004597388,0.0005482941,0.0004283975,0.00004911393,0.000005997521,0.0001714198],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9519153,"threshold_uncertainty_score":0.2048427,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2121194346","doi":"10.1093/bioinformatics/bti427","title":"NodMutDB: a database for genes and mutants involved in symbiosis","year":2005,"lang":"en","type":"article","venue":"Computer applications in the biosciences","topic":"Legume Nitrogen Fixing Symbiosis","field":"Agricultural and Biological Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Functional genomics; Mutant; Gene; Computational biology; Function (biology); Biology; Schema (genetic algorithms); Symbiosis; Genomics; Database; Computer science; Genetics; Genome; Information retrieval","retraction":null,"screen_n_in":null,"score":{"opus":0.02845852507165696,"gpt":0.2535519766941076,"spread":0.2250934516224506,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000508713,0.0001032518,0.0001068139,0.00003593889,0.0002169547,0.000105127,0.0006849131,0.00004253387,0.000005929754],"category_scores_gemma":[0.00001388683,0.00003768216,0.0000313866,0.000768777,0.0001679022,0.0001727644,0.0001092519,0.0000580526,0.00000572702],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002076424,"about_ca_system_score_gemma":0.000008784456,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001250101,"about_ca_topic_score_gemma":0.00113575,"domain_scores_codex":[0.9990262,0.00005144119,0.0001947626,0.0003640922,0.0001363224,0.0002272038],"domain_scores_gemma":[0.9993812,0.0003939807,0.00005355455,0.000108696,0.000025062,0.00003753015],"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":[0.00001406657,0.0006415632,0.2101929,0.00002376569,0.000008003003,9.296839e-7,0.001157374,0.000005006886,0.341685,0.005734884,0.0007901278,0.4397464],"study_design_scores_gemma":[0.0009578142,0.0004156559,0.846499,0.0001102568,0.0000364859,0.00002394737,0.002690534,0.01840216,0.07659052,0.00623338,0.04695125,0.001088967],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9954876,0.0005144281,0.0002350279,0.002971509,0.00003499489,0.000639781,0.00005421723,0.00002766966,0.00003473622],"genre_scores_gemma":[0.9917539,0.00004758591,0.00704738,0.0006300703,0.0001826175,0.0003066775,0.00002525237,6.506557e-7,0.000005883453],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6363062,"threshold_uncertainty_score":0.1668662,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2114368649","doi":"10.1093/bioinformatics/bti1045","title":"GenXHC: a probabilistic generative model for cross-hybridization compensation in high-density genome-wide microarray data","year":2005,"lang":"en","type":"article","venue":"Computer applications in the biosciences","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Generative model; Computer science; Probabilistic logic; Generative grammar; Genome; Compensation (psychology); Computational biology; Statistical model; Microarray; Data mining; Artificial intelligence; Biology; Genetics; Gene; Gene expression","retraction":null,"screen_n_in":null,"score":{"opus":0.04346260838480358,"gpt":0.3150488217447869,"spread":0.2715862133599833,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005293801,0.000106061,0.00008843435,0.00007843462,0.000189422,0.00009868706,0.0008888767,0.00006002082,0.000001290092],"category_scores_gemma":[0.00003171908,0.0000823168,0.00002231056,0.0003140318,0.0001577093,0.00002370279,0.0001424514,0.00005149076,0.00000248876],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003892796,"about_ca_system_score_gemma":0.0001085443,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001191145,"about_ca_topic_score_gemma":0.0002294039,"domain_scores_codex":[0.9988448,0.00006793327,0.0002537562,0.0005540453,0.0001236919,0.0001557917],"domain_scores_gemma":[0.9990366,0.0000373174,0.0001087162,0.0006978556,0.00009294049,0.00002657089],"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":[0.00007834867,0.0008021338,0.02207671,0.0000549312,0.00001616581,1.889759e-7,0.002249743,0.410062,0.5272419,0.006708571,0.005572909,0.02513641],"study_design_scores_gemma":[0.0005077994,0.00005207564,0.07807157,0.000007800623,0.000008081193,0.000002151013,0.0001008713,0.8813123,0.02074239,0.002029917,0.01692748,0.0002375878],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3822097,0.0001005025,0.6162708,0.0006303068,0.00003952845,0.000682828,0.00003939678,0.00000674528,0.0000201681],"genre_scores_gemma":[0.9565369,0.00004759501,0.04135664,0.0005919743,0.0002167588,0.0003602795,0.0008274369,0.000006296738,0.0000560663],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5749142,"threshold_uncertainty_score":0.3356782,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2108926360","doi":"10.1093/bioinformatics/bti1050","title":"Search for folding nuclei in native protein structures","year":2005,"lang":"en","type":"article","venue":"Computer applications in the biosciences","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":true,"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","keywords":"Executable; Computer science; Protein folding; Folding (DSP implementation); Simple (philosophy); Algorithm; Graph; Theoretical computer science; Topology (electrical circuits); Physics; Mathematics; Combinatorics; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.01417628164947042,"gpt":0.296746002949353,"spread":0.2825697212998826,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002742091,0.00007376099,0.00005960177,0.00006266978,0.0001132293,0.0000429639,0.0005461828,0.00005157879,9.110313e-7],"category_scores_gemma":[0.000008210748,0.00005035289,0.00002752332,0.0002517068,0.0001292063,0.000006453842,0.00008165104,0.00005957697,6.063651e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000147925,"about_ca_system_score_gemma":0.00003832268,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001026207,"about_ca_topic_score_gemma":0.0000599751,"domain_scores_codex":[0.9993408,0.00003471377,0.0001194439,0.0002522615,0.00009380748,0.0001589543],"domain_scores_gemma":[0.9996895,0.00002394244,0.0000308203,0.0002101198,0.00002907516,0.00001652736],"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":[0.00007015953,0.0003096521,0.01445649,0.00007141736,0.000025182,8.350718e-7,0.003758771,0.009881844,0.4515449,0.2484774,0.0007471413,0.2706562],"study_design_scores_gemma":[0.001871816,0.000762179,0.06600282,0.00005825699,0.0000140843,0.00002549208,0.00181174,0.07761411,0.6443381,0.06446171,0.1419542,0.001085524],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8214436,0.0002106372,0.1764905,0.0005273179,0.00002795414,0.001065406,0.0000115785,0.000006377868,0.000216651],"genre_scores_gemma":[0.960841,0.000008567871,0.03839782,0.0002188225,0.0002048461,0.000294173,0.00001595865,0.000003909446,0.00001489698],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2695706,"threshold_uncertainty_score":0.2053331,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2099398646","doi":"10.1093/bioinformatics/bti170","title":"BIAS: Bioinformatics Integrated Application Software","year":2004,"lang":"en","type":"article","venue":"Computer applications in the biosciences","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Software; Object (grammar); Data mining; Relational database; Bioinformatics; Data science; Software engineering; Artificial intelligence; Programming language; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.01302460520350489,"gpt":0.2429522021158472,"spread":0.2299275969123423,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003521589,0.0001093845,0.00007509383,0.00005931253,0.0001750534,0.00008424817,0.0007512162,0.00007654867,9.563033e-7],"category_scores_gemma":[0.000009626289,0.00007116482,0.00004146829,0.0004692584,0.0001854974,0.00000999885,0.0001004967,0.00008292867,0.00002235224],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001813281,"about_ca_system_score_gemma":0.00007560769,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002190791,"about_ca_topic_score_gemma":0.0000466304,"domain_scores_codex":[0.9992515,0.00001772502,0.0002552872,0.0001791215,0.0001223433,0.0001740062],"domain_scores_gemma":[0.9993637,0.00002003517,0.0001001818,0.0004383992,0.00004461158,0.000033025],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000342407,0.001022117,0.01402106,0.0001390467,0.00006881813,9.276474e-7,0.007231658,0.0505727,0.009758146,0.07646255,0.009578618,0.8311101],"study_design_scores_gemma":[0.002587136,0.00104683,0.02382923,0.000125772,0.00005981817,0.0001495842,0.005368883,0.1154532,0.01880224,0.06630053,0.7642174,0.00205943],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04934921,0.0001411759,0.9493681,0.0002857798,0.00007288201,0.0004635899,0.00001146972,0.00002043187,0.000287311],"genre_scores_gemma":[0.87099,0.00008523864,0.1271278,0.001152112,0.0002000295,0.000215263,0.0002038733,0.000006967691,0.00001865095],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8290507,"threshold_uncertainty_score":0.2902018,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2117003089","doi":"10.1093/bioinformatics/bti280","title":"Computational identification of human mitochondrial proteins based on homology to yeast mitochondrially targeted proteins","year":2005,"lang":"en","type":"article","venue":"Computer applications in the biosciences","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Hospital for Sick Children","funders":"Canadian Institutes of Health Research; Hospital for Sick Children","keywords":"Biology; Human genome; Computational biology; Saccharomyces cerevisiae; Homology (biology); Genetics; Human proteins; Gene; Genome; Human mitochondrial genetics; Mitochondrion; UniGene; Expressed sequence tag","retraction":null,"screen_n_in":null,"score":{"opus":0.008637087028099883,"gpt":0.2773267700318632,"spread":0.2686896830037633,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000349312,0.0001228425,0.0001107205,0.0001623809,0.0001877507,0.00005199677,0.000842194,0.0000763003,0.000005833036],"category_scores_gemma":[0.00005142143,0.00009483609,0.00005195672,0.0004234471,0.0001997447,0.000008643574,0.00008169287,0.00009735442,0.00001831654],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001918702,"about_ca_system_score_gemma":0.00008715712,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001046467,"about_ca_topic_score_gemma":0.00002650523,"domain_scores_codex":[0.9987223,0.0001174067,0.0004125753,0.0003055676,0.0002793439,0.0001628229],"domain_scores_gemma":[0.9991548,0.00003513303,0.0001997863,0.0004700097,0.0001009184,0.00003937551],"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":[0.0000634388,0.0009601353,0.002019543,0.00004743509,0.00001609731,2.916779e-7,0.001192075,0.3120451,0.6627139,0.00950203,0.00276607,0.0086739],"study_design_scores_gemma":[0.00267358,0.003665024,0.09341098,0.00009881986,0.00003917755,0.00002108415,0.0003284836,0.5328889,0.2937756,0.00249205,0.06940371,0.00120253],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2648056,0.00001337776,0.7311255,0.00145854,0.000144087,0.002024307,0.00004002636,0.00002147973,0.0003670552],"genre_scores_gemma":[0.8750894,5.11473e-7,0.1234643,0.0004856781,0.0003639227,0.0004058769,0.0001464142,0.000006905703,0.00003698076],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6102837,"threshold_uncertainty_score":0.3867303,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2509574344","doi":"10.1093/bioinformatics/btw481","title":"ECCB 2016: The 15th European Conference on Computational Biology","year":2016,"lang":"en","type":"editorial","venue":"Computer applications in the biosciences","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Cancer Research UK Cambridge Institute, University of Cambridge; RIKEN; Swiss Institute of Bioinformatics; Università di Bologna; Rigshospitalet; University of Oxford; Vrije Universiteit Amsterdam; Wageningen University and Research; Aalto-Yliopisto; Universiteit Utrecht; Univerzita Karlova v Praze; Centre National de la Recherche Scientifique; Cancer Research UK; University College London; Institut National de la Recherche Agronomique; University of Toronto; Technische Universität Dresden; Eidgenössische Technische Hochschule Zürich; Universiteit Leiden; Okinawa Institute of Science and Technology Graduate University; Universität des Saarlandes; University of Notre Dame; European Bioinformatics Institute; University of California, Santa Cruz; Vrije Universiteit Brussel; Massachusetts General Hospital","keywords":"Computational biology; Computer science; Biology; Data science","retraction":null,"screen_n_in":null,"score":{"opus":0.01384154714427038,"gpt":0.2938038882816018,"spread":0.2799623411373314,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006254465,0.0001988775,0.0001333222,0.00005820749,0.0002714897,0.0001361765,0.001892771,0.0001630299,0.000005222436],"category_scores_gemma":[0.00007184935,0.0001013384,0.00007060666,0.0001543054,0.0006013467,0.000002503171,0.0003007843,0.0002011761,0.000055418],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002312773,"about_ca_system_score_gemma":0.0003196914,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001783917,"about_ca_topic_score_gemma":0.00002551466,"domain_scores_codex":[0.9985738,0.0001994894,0.0002427964,0.0005439552,0.000219452,0.0002204886],"domain_scores_gemma":[0.998412,0.0005988047,0.0001718854,0.0006493858,0.0001330562,0.00003489121],"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":[0.000006570763,0.00005928434,0.00003903384,0.000004440697,0.00001083,3.571391e-7,0.00007042964,0.0001792868,0.0002565887,0.008247491,0.9831763,0.007949388],"study_design_scores_gemma":[0.0001468559,0.0001628649,0.0002691227,0.00002178694,0.000007829338,0.000001162631,0.00002132711,0.000199452,0.0000580661,0.004038454,0.9949045,0.0001686077],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"editorial","genre_gemma":"editorial","genre_scores_codex":[0.002372707,0.002642673,0.3391173,0.007526687,0.6227795,0.002774102,0.00265787,0.00006317041,0.02006608],"genre_scores_gemma":[0.130778,0.002882963,0.002722238,0.002149099,0.8585654,0.0004392694,0.001907603,0.00005242501,0.000502957],"genre_candidate":"editorial","genre_consensus":"editorial","teacher_disagreement_score":0.336395,"threshold_uncertainty_score":0.4132461,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2403880286","doi":"10.1093/bioinformatics/bts490","title":"ECCB 2012: The 11th European Conference on Computational Biology","year":2012,"lang":"en","type":"article","venue":"Computer applications in the biosciences","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"University at Buffalo; Swiss Institute of Bioinformatics; Schweizerische Akademie der Medizinischen Wissenschaften; Université de Genève; Eidgenössische Technische Hochschule Zürich; Universität Zürich; Branco Weiss Fellowship – Society in Science; Universität Basel; European Bioinformatics Institute; Universitätsspital Zürich; Microsoft Research","keywords":"Computer science; Computational biology; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.04298584498611423,"gpt":0.3267162124132776,"spread":0.2837303674271634,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001061255,0.00009494361,0.00006332375,0.00004975098,0.0002427577,0.00006526432,0.001042024,0.00004555075,0.000009224178],"category_scores_gemma":[0.00002623378,0.0000482315,0.00003706363,0.0002222684,0.0006984681,0.000006955097,0.0002027422,0.0001077216,0.00008356563],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006987778,"about_ca_system_score_gemma":0.00004794898,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004714703,"about_ca_topic_score_gemma":0.000004964215,"domain_scores_codex":[0.9989661,0.0001851795,0.0001825939,0.0001800726,0.0002044847,0.0002815431],"domain_scores_gemma":[0.9993792,0.00009587029,0.00005815552,0.0003442611,0.00005619678,0.00006633477],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005771571,0.00233474,0.04440832,0.00008202827,0.0001000647,0.000001169554,0.007083193,0.001368277,0.02530053,0.2774445,0.08932539,0.552494],"study_design_scores_gemma":[0.0005666695,0.0008150817,0.1900456,0.00002353431,0.00001515622,0.00002952146,0.001414778,0.01411671,0.002989008,0.008868077,0.7805799,0.0005360389],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2873871,0.001401714,0.6636204,0.01152549,0.0009494307,0.001790889,0.00009193783,0.00004535747,0.03318772],"genre_scores_gemma":[0.9946063,0.0001237027,0.003378404,0.001266514,0.0004425384,0.00003853603,0.0000726189,0.000003813786,0.00006762553],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7072191,"threshold_uncertainty_score":0.2573535,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}