{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":1034,"total_is_capped":false,"direct_labels_cover":1,"predictions_cover":1034,"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":"b05057a49128","filters":{"topic":"Machine Learning in Bioinformatics"}},"results":[{"id":"W2144499799","doi":"10.1007/978-3-642-24797-2","title":"Supervised Sequence Labelling with Recurrent Neural Networks","year":2012,"lang":"en","type":"book","venue":"Studies in computational intelligence","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3084,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Labelling; Computer science; Sequence (biology); Artificial intelligence; Artificial neural network; Recurrent neural network; Machine learning; Pattern recognition (psychology); Biology; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.06960736389883783,"gpt":0.3540499779592106,"spread":0.2844426140603727,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003069526,0.0003761573,0.0003431644,0.00008976984,0.0001087716,0.0000243889,0.0003561478,0.0002123199,0.00001986931],"category_scores_gemma":[0.0001195223,0.0003290859,0.00007436542,0.0001124304,0.0004036985,0.000008202152,0.0002969146,0.0005659725,0.00001895387],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001235942,"about_ca_system_score_gemma":0.0001530847,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003078985,"about_ca_topic_score_gemma":0.00002797664,"domain_scores_codex":[0.9983692,0.00006761252,0.0005096454,0.0003779386,0.0003144258,0.0003612099],"domain_scores_gemma":[0.9988939,0.0001963307,0.000255356,0.0002622518,0.0003264796,0.00006569348],"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":[0.00005994062,0.00002890887,0.0008871942,0.0002177987,0.0001824724,0.000009625002,0.0004837701,0.9813522,0.000003086486,0.001728317,0.002576813,0.01246988],"study_design_scores_gemma":[0.0002923704,0.0007317593,0.0001518304,0.001031972,0.00009017677,0.0001347751,0.0003596421,0.9630393,0.00005676995,0.00349673,0.0293014,0.001313293],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008856617,0.09265336,0.7923367,0.0006433577,0.005795483,0.002816194,0.0002050225,0.0002074102,0.09648586],"genre_scores_gemma":[0.7675835,0.01216038,0.111359,0.002308425,0.004429363,0.0002705564,0.005830442,0.0003551918,0.0957031],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.758727,"threshold_uncertainty_score":0.9999161,"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":"W2117486996","doi":"10.1038/nmeth.2340","title":"A large-scale evaluation of computational protein function prediction","year":2013,"lang":"en","type":"article","venue":"Nature Methods","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1095,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"U.S. National Library of Medicine; National Institute of General Medical Sciences; National Human Genome Research Institute; Office of Science; Biotechnology and Biological Sciences Research Council; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; Directorate for Biological Sciences; Ministero dell’Istruzione, dell’Università e della Ricerca; Biological and Environmental Research; National Natural Science Foundation of China; University of Miami; Alexander von Humboldt-Stiftung; U.S. Department of Energy; National Science Foundation","keywords":"Annotation; Computer science; Protein function prediction; Function (biology); Protein function; Set (abstract data type); Scale (ratio); Computational biology; Machine learning; Artificial intelligence; Data mining; Biology; Genetics; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.01041951972596435,"gpt":0.3501743383184968,"spread":0.3397548185925325,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001824708,0.00008216713,0.00008538494,0.00004896144,0.00004505897,0.00001166118,0.00007437269,0.0003045453,0.0001533519],"category_scores_gemma":[0.0005366442,0.00007323622,0.00005095325,0.0001027796,0.00002260698,0.000008039958,0.00004051509,0.0002348536,0.000007965159],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001836792,"about_ca_system_score_gemma":0.00005782675,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003517431,"about_ca_topic_score_gemma":0.000002127903,"domain_scores_codex":[0.9988378,0.000406484,0.0002064397,0.0001382851,0.0003094892,0.0001015139],"domain_scores_gemma":[0.9991103,0.00001902607,0.0001408183,0.0001793866,0.0005211197,0.00002939598],"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":[0.0001277861,0.0002154941,0.00553749,0.0001761402,0.0001805234,5.120175e-8,0.0005389171,0.02677101,0.7789689,0.001610679,0.007993629,0.1778793],"study_design_scores_gemma":[0.001903218,0.0006136087,0.1061362,0.0000421806,0.0001396988,0.00001060863,0.0002398681,0.7386695,0.1023189,0.01558889,0.03406348,0.0002738339],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3827606,0.0002669493,0.6120525,0.00008234633,0.0002230801,0.0005389331,0.00001291349,0.00001723259,0.004045377],"genre_scores_gemma":[0.6471722,0.000001123431,0.3520708,0.0001103212,0.000112573,0.0000629096,0.0002895785,0.000008509102,0.0001719725],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7118985,"threshold_uncertainty_score":0.2986487,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3019119825","doi":"10.1371/journal.pone.0232391","title":"Machine learning using intrinsic genomic signatures for rapid classification of novel pathogens: COVID-19 case study","year":2020,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1034,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo; Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Genome; Computational biology; Genomics; Biology; Novel virus; Virus classification; Decision tree; Virus; Artificial intelligence; Computer science; Genetics; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.1024710124406709,"gpt":0.3021214621668543,"spread":0.1996504497261834,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002859693,0.0001474307,0.0002312885,0.00005011852,0.0001315009,0.00001792196,0.000150153,0.0001129239,0.00001745716],"category_scores_gemma":[0.001331092,0.0001489817,0.00006521791,0.0001036883,0.00004064423,0.000004598138,0.0001188465,0.0001910865,0.000001358945],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002695897,"about_ca_system_score_gemma":0.0001029887,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004330067,"about_ca_topic_score_gemma":0.00001423504,"domain_scores_codex":[0.9990098,0.00008072358,0.0003457865,0.0002525281,0.0001536251,0.0001575462],"domain_scores_gemma":[0.9991982,0.00005419012,0.0002853336,0.0002229712,0.0001141682,0.0001251379],"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":[0.0001731275,0.0008776844,0.009383263,0.000359052,0.0002419524,0.00001086585,0.001110002,0.004992246,0.9822176,0.00001785919,0.00002092843,0.0005953898],"study_design_scores_gemma":[0.006157304,0.005101823,0.00154444,0.0000447969,0.0007294671,0.0001326621,0.004115591,0.8879853,0.09081358,0.000008093859,0.002653737,0.0007131335],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9753528,0.0003748089,0.02315808,0.000191541,0.00001682152,0.000766188,0.00007456903,0.00002793665,0.00003726985],"genre_scores_gemma":[0.9755908,0.00003051386,0.02348925,0.0004653906,0.0001508555,0.00002457219,0.0001993678,0.00003090173,0.00001836813],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.891404,"threshold_uncertainty_score":0.6075297,"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":"W2160072419","doi":"10.1093/nar/gkg602","title":"PSORT-B: improving protein subcellular localization prediction for Gram-negative bacteria","year":2003,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":426,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Biology; Computational biology; Subcellular localization; Source code; Probabilistic logic; Protein subcellular localization prediction; Bacterial genome size; Protein sequencing; Genetics; Peptide sequence; Genome; Artificial intelligence; Computer science; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.02278033779832832,"gpt":0.3099796708341906,"spread":0.2871993330358623,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001472576,0.0001472329,0.0001221886,0.0001092558,0.0003462298,0.00009400136,0.0002214357,0.0002454267,0.0000925897],"category_scores_gemma":[0.002065869,0.0001421985,0.00006832276,0.0002277695,0.0001518574,0.00001489815,0.00009761733,0.0002758843,0.00002992304],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006256799,"about_ca_system_score_gemma":0.0001443403,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000201082,"about_ca_topic_score_gemma":0.000008189912,"domain_scores_codex":[0.9982698,0.0002822946,0.0002838525,0.0003304869,0.0003685417,0.0004650241],"domain_scores_gemma":[0.998937,0.00003379686,0.00008432401,0.0004047366,0.0004325105,0.0001077022],"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":[0.0001906009,0.00008704946,0.003325487,0.0002672776,0.00004598439,0.000001129528,0.0002967731,0.0002527726,0.9850197,0.002030287,0.002988906,0.005493986],"study_design_scores_gemma":[0.001857838,0.001948227,0.001487495,0.00006170444,0.00001729418,0.00001594901,0.0006095298,0.04772964,0.7550562,0.001324057,0.1894867,0.0004053324],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7930859,0.00008512637,0.199856,0.0001022754,0.0001590088,0.001844465,0.00004608084,0.0000548214,0.004766318],"genre_scores_gemma":[0.9806186,0.00001830021,0.01672147,0.00004430328,0.0001778448,0.0002204066,0.0002773621,0.00005000945,0.001871736],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2299635,"threshold_uncertainty_score":0.5798686,"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":"W2788724289","doi":"10.1073/pnas.1800256115","title":"Classification and interaction in random forests","year":2018,"lang":"en","type":"letter","venue":"Proceedings of the National Academy of Sciences","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":276,"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","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Random forest; Ask price; Computer science; Artificial intelligence; Machine learning; Classifier (UML); Medical diagnosis; Decision tree; Complaint; Data science; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.03080431165518348,"gpt":0.3208278370013131,"spread":0.2900235253461296,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007785753,0.00008523718,0.0001105961,0.0001314951,0.00005609344,0.00001901988,0.0003972042,0.000287132,0.000003252622],"category_scores_gemma":[0.0006592115,0.00005914123,0.00003963851,0.0001689329,0.0005275456,0.00001907713,0.000121162,0.0003349015,5.645157e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001331555,"about_ca_system_score_gemma":0.00002521946,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000302688,"about_ca_topic_score_gemma":2.584267e-7,"domain_scores_codex":[0.9990057,0.0000084529,0.000280232,0.0001714954,0.0004446185,0.00008944882],"domain_scores_gemma":[0.9992513,0.00003974029,0.0005415443,0.000008056916,0.0001509192,0.000008447529],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.000118826,0.00003451595,0.07552771,0.0007593349,0.00005030503,1.067985e-8,0.0002925442,0.00007744595,0.2204501,0.001618874,0.7002667,0.000803722],"study_design_scores_gemma":[0.00170854,0.0004365236,0.4254773,0.0009341645,0.00005532298,0.00008125129,0.0002291197,0.01612406,0.1617141,0.01763684,0.3749893,0.0006134461],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8037363,0.000132151,0.000005907797,0.1820803,0.00007017628,0.0003870643,0.00001889494,0.00000565753,0.01356358],"genre_scores_gemma":[0.9789104,0.00005602084,0.000837404,0.01933642,0.0005476212,0.00001030926,0.000004163699,0.000005359727,0.0002922796],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3499496,"threshold_uncertainty_score":0.2411709,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2045510682","doi":"10.1101/gr.147901","title":"Evaluation of Gene-Finding Programs on Mammalian Sequences","year":2001,"lang":"en","type":"article","venue":"Genome Research","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":272,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Pacific Centre for Reproductive Medicine; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Biology; Exon; Sequence (biology); Gene prediction; Computational biology; Gene; Sequence analysis; Genetics; Strengths and weaknesses; Function (biology); Genome","retraction":null,"screen_n_in":null,"score":{"opus":0.1565077522533462,"gpt":0.4316221012825429,"spread":0.2751143490291966,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005328821,0.00008245864,0.0000849937,0.0001363228,0.0001135115,0.00003165482,0.0002808163,0.0001007268,0.00009611266],"category_scores_gemma":[0.0004049683,0.00007371401,0.00004366875,0.000268142,0.0001223208,0.000003340426,0.00008414347,0.000183654,0.00006292223],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000056573,"about_ca_system_score_gemma":0.0001922649,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003413591,"about_ca_topic_score_gemma":0.00001952273,"domain_scores_codex":[0.9977363,0.000377131,0.000196618,0.0001948376,0.001160233,0.0003348617],"domain_scores_gemma":[0.9989237,0.00001767727,0.00006500537,0.0003570461,0.0005693318,0.00006723317],"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":[0.0001304936,0.0001767254,0.02427672,0.00009516697,0.000107664,0.000006192744,0.0006289343,0.004482752,0.7806674,0.0003939153,0.0002596639,0.1887743],"study_design_scores_gemma":[0.004263208,0.01045772,0.09763709,0.0002094395,0.0001440269,0.0002168248,0.003040274,0.02881101,0.5914286,0.002607363,0.2597926,0.001391881],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9685731,0.0003420147,0.0002086265,0.0001310183,0.00003862043,0.0003900354,0.000003629087,0.000007312134,0.03030564],"genre_scores_gemma":[0.9972047,0.0001095272,0.001550645,0.00001667167,0.0001497411,0.00004330899,0.0001188542,0.00001293209,0.000793632],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2595329,"threshold_uncertainty_score":0.300597,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2160115185","doi":"10.1371/journal.pgen.1002741","title":"Stratifying Type 2 Diabetes Cases by BMI Identifies Genetic Risk Variants in LAMA1 and Enrichment for Risk Variants in Lean Compared to Obese Cases","year":2012,"lang":"en","type":"article","venue":"PLoS Genetics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":267,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"National Cancer Institute; National Institute on Alcohol Abuse and Alcoholism; Medical Research Council; National Center for Research Resources; National Institute of Dental and Craniofacial Research; Novartis Pharma; National Institutes of Health; Fondation de France; National Heart, Lung, and Blood Institute; Vetenskapsrådet; Sanofi; European Commission; National Human Genome Research Institute; Wellcome Trust; Agence Nationale de la Recherche; Les Laboratories Pierre Fabre; Institut National de la Santé et de la Recherche Médicale; School of Medicine, Boston University; National Institute of Diabetes and Digestive and Kidney Diseases; Lunds Universitet; National Institute on Drug Abuse; Eli Lilly and Company","keywords":"Type 2 diabetes; Overweight; Obesity; Body mass index; Diabetes mellitus; Single-nucleotide polymorphism; Internal medicine; Genome-wide association study; Biology; Risk factor; Case-control study; Genetic association; Endocrinology; Medicine; Bioinformatics; Genetics; Genotype; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.02014445139635725,"gpt":0.2782651669371498,"spread":0.2581207155407926,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004048006,0.0002846383,0.0003053804,0.0001240435,0.0001112587,0.00007727317,0.0002183847,0.0001722574,0.00001567337],"category_scores_gemma":[0.001074861,0.0002915084,0.00004152349,0.0001796799,0.00005831961,0.00001312574,0.0002109496,0.0001846666,0.00001052076],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003369807,"about_ca_system_score_gemma":0.00004701514,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000109077,"about_ca_topic_score_gemma":0.00064254,"domain_scores_codex":[0.9981859,0.0001461207,0.0005378319,0.0003477529,0.0001858951,0.0005964944],"domain_scores_gemma":[0.9989418,0.0001646418,0.0002146752,0.0004046397,0.00008685358,0.000187435],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00008437182,0.0002905157,0.9036389,0.0001743898,0.00009259993,0.000006188204,0.0009550719,0.002166391,0.09052083,0.000005025633,0.0009413037,0.001124414],"study_design_scores_gemma":[0.003417428,0.001956878,0.6933162,0.0002456767,0.0003543296,0.00004765309,0.001758031,0.06497868,0.2289813,0.000184412,0.003146697,0.001612697],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9941131,0.004376328,0.0002880821,0.00002615568,0.0001891492,0.0006824356,0.0002557747,0.00001466057,0.00005430587],"genre_scores_gemma":[0.9897766,0.001150089,0.008500854,0.0001080532,0.0001427239,0.0000676441,0.0001583448,0.00004205236,0.00005361335],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2103227,"threshold_uncertainty_score":0.9999537,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3088578860","doi":"10.1016/j.cels.2020.08.016","title":"Fast and Flexible Protein Design Using Deep Graph Neural Networks","year":2020,"lang":"en","type":"article","venue":"Cell Systems","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":230,"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; Fonds de recherche du Québec – Nature et technologies; Canadian Institutes of Health Research; Nvidia","keywords":"Computer science; In silico; Benchmark (surveying); Protein design; Graph; Artificial neural network; Constraint (computer-aided design); Algorithm; Protein structure prediction; Protein sequencing; Sequence (biology); Protein structure; Theoretical computer science; Artificial intelligence; Peptide sequence; Mathematics; Biology; Gene; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.01847110912025982,"gpt":0.2246390681826954,"spread":0.2061679590624356,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001393167,0.0001372504,0.0001356582,0.00001762458,0.00008501803,0.00007160568,0.0001243679,0.0001224948,0.000003619474],"category_scores_gemma":[0.00002628723,0.0001267744,0.00003620279,0.00008432988,0.000038783,0.000004286318,0.00008940027,0.0001193563,0.000004062078],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005182838,"about_ca_system_score_gemma":0.00001451098,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001938419,"about_ca_topic_score_gemma":5.872547e-7,"domain_scores_codex":[0.9992149,0.0001005424,0.0002054925,0.0001912091,0.00008404225,0.0002038248],"domain_scores_gemma":[0.9995679,0.000007116946,0.0001116893,0.000163871,0.00003079202,0.0001185943],"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":[0.00006612406,0.00001474123,0.001858565,0.0003675339,0.00003112638,0.000005032948,0.0002606055,0.7602425,0.2353498,0.00003585192,0.0006797744,0.001088384],"study_design_scores_gemma":[0.0002761912,0.0001965653,0.00003159909,0.0000163312,0.00001155661,0.00001955638,0.0001275998,0.9848621,0.01236392,0.000001917814,0.001921222,0.000171409],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2263312,0.002113657,0.7697571,0.00004328535,0.0001560942,0.0005738259,0.000002103484,0.0000411426,0.0009815906],"genre_scores_gemma":[0.9951259,0.00001383221,0.004164513,0.0001521223,0.000304163,0.00001387466,0.00002141784,0.00002372279,0.0001804832],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7687947,"threshold_uncertainty_score":0.516971,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2790921906","doi":"10.1093/bioinformatics/bty095","title":"Improved genomic island predictions with IslandPath-DIMOB","year":2018,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":223,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Computer science; Computational biology; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.004793943520078781,"gpt":0.2206221854113326,"spread":0.2158282418912538,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001763985,0.0002166256,0.0001508972,0.00007284743,0.0002174502,0.00007373568,0.0002678096,0.0001584632,0.0000762873],"category_scores_gemma":[0.00007006736,0.0001671334,0.00005769524,0.0001265573,0.0002101498,0.00001721077,0.0001427708,0.0001439444,0.0001494319],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002033428,"about_ca_system_score_gemma":0.0001202061,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001167871,"about_ca_topic_score_gemma":0.0001363971,"domain_scores_codex":[0.9989624,0.00001777462,0.0003784798,0.0001456663,0.0001595085,0.0003361863],"domain_scores_gemma":[0.9989816,0.00001018918,0.0002027695,0.0005429663,0.0001511211,0.0001113451],"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":[0.004113267,0.001238107,0.1590388,0.002442027,0.0033521,0.00002045112,0.03099754,0.004607775,0.2318991,0.003474673,0.4825626,0.0762535],"study_design_scores_gemma":[0.004032671,0.00593861,0.009427648,0.00009126384,0.0001552652,0.0004371267,0.001109647,0.437321,0.02078998,0.00005526469,0.5192991,0.001342416],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5703038,0.0001015058,0.3327569,0.0001978167,0.0006401781,0.0008310604,0.0002102743,0.0001917162,0.09476673],"genre_scores_gemma":[0.9174026,0.00006797705,0.07737092,0.000889104,0.0009207302,0.00003285818,0.0004690163,0.00005371528,0.002793127],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4327132,"threshold_uncertainty_score":0.6815501,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2112905569","doi":"10.1093/nar/gkh380","title":"ConPred II: a consensus prediction method for obtaining transmembrane topology models with high reliability","year":2004,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":202,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institute of Aging","funders":"Ministry of Education, Culture, Sports, Science and Technology","keywords":"Topology (electrical circuits); Network topology; Biology; Computer science; Reliability (semiconductor); Process (computing); Algorithm; Data mining; Mathematics; Physics; Computer network; Combinatorics; Power (physics); Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.03156165825524426,"gpt":0.349017576479136,"spread":0.3174559182238917,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002064243,0.0001826263,0.0002425304,0.0001082271,0.0004544988,0.00002544886,0.0003101729,0.000335302,0.00002911014],"category_scores_gemma":[0.0005676163,0.0001554949,0.00007928536,0.0002034274,0.000429908,0.000009150912,0.0001374564,0.000479684,0.000004678217],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007805155,"about_ca_system_score_gemma":0.0003169172,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002366235,"about_ca_topic_score_gemma":0.00005277143,"domain_scores_codex":[0.9979186,0.0002801615,0.0003410568,0.0004733179,0.0003933409,0.0005935032],"domain_scores_gemma":[0.9985613,0.0001454178,0.00006174194,0.0005844526,0.0005076387,0.000139433],"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":[0.007710901,0.0006384059,0.001697804,0.0008144985,0.0004648911,0.00001777033,0.004774892,0.498124,0.4415337,0.02815425,0.003028321,0.01304061],"study_design_scores_gemma":[0.0261198,0.02690491,0.002594897,0.0002479812,0.0001766042,0.0005306987,0.002766345,0.5006266,0.3286997,0.04297597,0.06680374,0.001552699],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7536829,0.00007286957,0.2403818,0.002150845,0.0000776158,0.0009132727,0.00009385879,0.00006065433,0.002566229],"genre_scores_gemma":[0.7986664,0.00003523341,0.2003247,0.0001250122,0.0001355018,0.0001154359,0.0001484931,0.00003644684,0.0004127981],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.112834,"threshold_uncertainty_score":0.6340898,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2366093519","doi":"10.1093/nar/gkw409","title":"MoRFchibi SYSTEM: software tools for the identification of MoRFs in protein sequences","year":2016,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":182,"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; Canada's Michael Smith Genome Sciences Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Genome British Columbia; Michael Smith Health Research BC; Genome Canada","keywords":"Biology; Software; Web server; Identification (biology); Computational biology; Computer science; Bioinformatics; The Internet; World Wide Web; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.04208792933643683,"gpt":0.3482737489374061,"spread":0.3061858196009692,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001818061,0.00007092988,0.00009047284,0.00007956908,0.00008650929,0.00003949026,0.00043305,0.0001001395,0.00002592329],"category_scores_gemma":[0.002460168,0.00004047522,0.00004261224,0.0001483553,0.0002080278,0.00001038056,0.0001293188,0.00009728594,0.00003182985],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003284232,"about_ca_system_score_gemma":0.00007791515,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000307473,"about_ca_topic_score_gemma":0.0000194557,"domain_scores_codex":[0.9988655,0.0001285217,0.0003107247,0.0001710493,0.0002878217,0.000236368],"domain_scores_gemma":[0.9990664,0.0001651606,0.0001044507,0.0004481901,0.0001858889,0.00002988526],"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":[0.00007764922,0.00002254977,0.003891815,0.000251892,0.00002058592,4.602397e-7,0.00009990466,0.00004261039,0.9596665,0.002040985,0.0008707258,0.03301432],"study_design_scores_gemma":[0.001437958,0.0006703346,0.0176867,0.0004389028,0.00001091497,0.00001209686,0.001375962,0.004656591,0.933244,0.0004937478,0.03968209,0.0002906494],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9624165,0.0001836272,0.03264618,0.0007893026,0.00005363071,0.001610204,0.000045038,0.00002438249,0.002231108],"genre_scores_gemma":[0.9928085,0.00002348685,0.002496889,0.000007615843,0.00006399901,0.0002154908,0.00001000265,0.00002156063,0.004352447],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03881136,"threshold_uncertainty_score":0.2945229,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2163449716","doi":"10.1002/jcc.20918","title":"Prediction of protein structural class using novel evolutionary collocation‐based sequence representation","year":2008,"lang":"en","type":"article","venue":"Journal of Computational Chemistry","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":172,"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":"Computer science; Benchmark (surveying); Classifier (UML); Artificial intelligence; Pattern recognition (psychology); Representation (politics); Support vector machine; Sequence (biology); Protein methods; Class (philosophy); Pseudo amino acid composition; Data mining; Machine learning; Sequence analysis; Amino acid; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.03889561558284672,"gpt":0.2932569067144774,"spread":0.2543612911316307,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001304066,0.00009524165,0.0001294718,0.0000455291,0.0000890758,0.000006602374,0.0001382106,0.00009564211,0.0000225482],"category_scores_gemma":[0.0002282509,0.0000961184,0.00009179258,0.000132421,0.0001216885,0.00002013929,0.00002733318,0.0001406708,3.239716e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000643354,"about_ca_system_score_gemma":0.0005556899,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003638451,"about_ca_topic_score_gemma":9.263479e-8,"domain_scores_codex":[0.998858,0.00002615667,0.0005354511,0.00009598213,0.0003994562,0.00008491505],"domain_scores_gemma":[0.9983259,0.00002567,0.0007394713,0.0001112057,0.0007465539,0.00005122888],"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":[0.00006934657,0.0000256234,0.004334923,0.00004759799,0.00002685028,0.000001021069,0.00002469447,0.5113055,0.4840326,0.000007397284,0.00008821076,0.00003617195],"study_design_scores_gemma":[0.001966701,0.0002246651,0.03373256,0.0001336334,0.00003951598,0.001583673,0.00007727627,0.5301853,0.4306143,0.0007209118,0.0005217151,0.0001997453],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9425746,0.00006695339,0.0569228,0.00007067402,0.0000598125,0.00008015293,0.00004336253,0.000004640713,0.0001770175],"genre_scores_gemma":[0.9177994,0.000002402329,0.08170687,0.000028397,0.0001947949,0.000001534123,0.0002012321,0.000008521509,0.00005685396],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0534183,"threshold_uncertainty_score":0.3919595,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2036790151","doi":"10.1038/nrmicro1494","title":"Methods for predicting bacterial protein subcellular localization","year":2006,"lang":"en","type":"review","venue":"Nature Reviews Microbiology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":170,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"","keywords":"Subcellular localization; Protein subcellular localization prediction; Biology; Computational biology; Identification (biology); Bacterial protein; Drug target; Annotation; Genome; Bioinformatics; Genetics; Gene; Biochemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.01785802078933187,"gpt":0.3771686864157439,"spread":0.359310665626412,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.001905651,0.0007319105,0.002166876,0.0001342237,0.0001385463,0.00004153265,0.0006203184,0.003343147,0.00002931686],"category_scores_gemma":[0.00108499,0.0005566538,0.0009923067,0.0002090876,0.0001007018,0.000004298198,0.0002381985,0.00103035,0.0000312337],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006962821,"about_ca_system_score_gemma":0.0002118327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000282937,"about_ca_topic_score_gemma":0.000006451351,"domain_scores_codex":[0.9957995,0.001433698,0.001481137,0.0007398013,0.00004040858,0.0005054678],"domain_scores_gemma":[0.9975367,0.00009159352,0.001407387,0.0007613675,0.0001376727,0.00006524034],"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":[0.000016846,0.00003262312,0.000001931098,0.03164778,0.0001476505,5.278204e-7,0.000005247496,0.000002615274,0.01729823,0.00006496002,0.01442009,0.9363615],"study_design_scores_gemma":[0.0002318342,0.0001820469,3.29505e-8,0.003318516,0.0004551128,0.0001238908,4.89116e-7,0.0000335248,0.001041461,0.00001049105,0.9940786,0.0005239659],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000001808198,0.9009341,0.09345689,0.000009233619,0.0008303589,0.00431787,0.000197597,0.00003333329,0.0002188251],"genre_scores_gemma":[2.782514e-7,0.8758674,0.09759121,0.0001150546,0.00137701,0.0005835399,0.0234882,0.0001056516,0.0008717006],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9796585,"threshold_uncertainty_score":0.9996885,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1986913015","doi":"10.1016/j.bbrc.2006.07.141","title":"Classifier ensembles for protein structural class prediction with varying homology","year":2006,"lang":"en","type":"article","venue":"Biochemical and Biophysical Research Communications","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":164,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pattern recognition (psychology); Classifier (UML); Artificial intelligence; Computer science; Support vector machine; Homology (biology); Protein structure prediction; Computational biology; Mathematics; Algorithm; Protein structure; Biology; Genetics; Amino acid","retraction":null,"screen_n_in":null,"score":{"opus":0.03527510867903335,"gpt":0.3373514513869992,"spread":0.3020763427079659,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000248959,0.00012895,0.000125352,0.00005414265,0.0004147261,0.00006006336,0.0004219607,0.0001687432,0.000003047092],"category_scores_gemma":[0.0002138699,0.00009829617,0.00004961268,0.0001649456,0.0007979778,0.000009172209,0.0003231576,0.0003348048,0.000003260603],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002127912,"about_ca_system_score_gemma":0.00007050423,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004956383,"about_ca_topic_score_gemma":0.00001434069,"domain_scores_codex":[0.9988781,0.0001255068,0.0002008714,0.000255519,0.0002107322,0.0003292657],"domain_scores_gemma":[0.9987803,0.0001140412,0.00005438899,0.0006901413,0.0002717949,0.00008937984],"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":[0.0001449519,0.00007766288,0.0003533615,0.00004800163,0.00002132563,1.753011e-7,0.00001347584,0.000004789148,0.9877272,0.008753992,0.001963578,0.0008914765],"study_design_scores_gemma":[0.001789874,0.001778134,0.004623985,0.00009609344,0.00003976024,0.00003822529,0.00008830089,0.02660493,0.8788835,0.006611099,0.07894578,0.0005002759],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9914896,0.0003271837,0.001732126,0.002616538,0.00001423259,0.0006727686,0.00008907644,0.00003263591,0.003025794],"genre_scores_gemma":[0.983951,0.00004207446,0.0143243,0.00004103422,0.0002036533,0.0002315678,0.0007199577,0.00001677314,0.000469578],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1088437,"threshold_uncertainty_score":0.4008401,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2151031196","doi":"10.1093/bioinformatics/btr525","title":"Computational prediction of eukaryotic phosphorylation sites","year":2011,"lang":"en","type":"review","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":157,"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":"","keywords":"Phosphorylation; Kinase; Computational biology; Protein phosphorylation; Mechanism (biology); Resource (disambiguation); Sequence (biology); Posttranslational modification; Biology; Computer science; Bioinformatics; Protein kinase A; Biochemistry; Enzyme","retraction":null,"screen_n_in":null,"score":{"opus":0.02921289647721682,"gpt":0.2834585629456036,"spread":0.2542456664683868,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002826841,0.0003492781,0.0006695687,0.0001754697,0.00006393092,0.00002304487,0.0003237613,0.000465471,0.000054587],"category_scores_gemma":[0.000163801,0.0003029286,0.0003313799,0.0001871573,0.0001017167,0.00001405483,0.0001654419,0.0002214911,0.0001068293],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002963697,"about_ca_system_score_gemma":0.0002495121,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002452294,"about_ca_topic_score_gemma":6.433352e-7,"domain_scores_codex":[0.9981318,0.00005369841,0.001233237,0.0001501083,0.000225805,0.0002053973],"domain_scores_gemma":[0.9981927,0.00003936236,0.001101839,0.0004409234,0.0001529005,0.00007222326],"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":[0.00001941142,0.0001112806,0.0003456848,0.0375016,0.000514118,4.909408e-7,0.0005159305,0.0007836873,0.000002634521,0.0008821856,0.008827915,0.9504951],"study_design_scores_gemma":[0.0002134458,0.0002709664,0.0000811077,0.001584904,0.0003643629,0.00005368492,0.0000297997,0.01220068,0.00001680199,0.00005042861,0.9848034,0.0003304081],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0000411386,0.9768348,0.01508143,0.000001428009,0.0002645167,0.0006459972,0.0003972919,0.00004298706,0.006690418],"genre_scores_gemma":[0.00005231362,0.9557939,0.03701333,0.00002509493,0.0001229136,0.00002154411,0.006670414,0.00004264278,0.0002578614],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9759755,"threshold_uncertainty_score":0.9999423,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1996768014","doi":"10.1186/1472-6807-7-25","title":"Prediction of flexible/rigid regions from protein sequences using k-spaced amino acid pairs","year":2007,"lang":"en","type":"article","venue":"BMC Structural Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":145,"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":"Natural Sciences and Engineering Research Council of Canada; Mitacs; National Natural Science Foundation of China","keywords":"Curse of dimensionality; Pattern recognition (psychology); Feature (linguistics); Protein methods; Computer science; Representation (politics); Threading (protein sequence); Feature selection; Protein structure prediction; Artificial intelligence; Support vector machine; Protein structure; Pseudo amino acid composition; Sequence (biology); Protein tertiary structure; Algorithm; Peptide sequence; Amino acid; Biology; Biochemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.03267685854606961,"gpt":0.2933025375500183,"spread":0.2606256790039487,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002029802,0.000187058,0.0002045393,0.00007516475,0.00009486558,0.000009622811,0.0002254451,0.0003231271,0.00005540418],"category_scores_gemma":[0.0001892682,0.0001532798,0.00009399407,0.000117581,0.0002762561,0.00000775661,0.0001095366,0.0001448012,0.000003193356],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002517925,"about_ca_system_score_gemma":0.00007442412,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003519617,"about_ca_topic_score_gemma":0.0001122647,"domain_scores_codex":[0.9988201,0.00009590764,0.0004059945,0.0002785082,0.00009217415,0.0003072902],"domain_scores_gemma":[0.9991642,0.00002919531,0.0003040197,0.0003442493,0.00008742892,0.00007093045],"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":[0.000115817,0.000004526274,0.09419873,0.00002117154,0.00004602544,6.184446e-7,0.0001146007,0.0001002852,0.90359,0.0008327683,0.00004285633,0.0009326678],"study_design_scores_gemma":[0.000730915,0.0006704578,0.1340322,0.00003946878,0.00004227495,0.00005850845,0.0003719762,0.001964105,0.8579974,0.001424826,0.002337386,0.0003304419],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9714014,0.0002535821,0.02712071,0.00002643504,0.0003341783,0.0002616131,0.0001504375,0.00003680991,0.000414816],"genre_scores_gemma":[0.9603918,0.000006668544,0.03852324,0.00004452367,0.0002741202,0.000005411609,0.0006162848,0.00001303794,0.0001248814],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04559255,"threshold_uncertainty_score":0.6250569,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1997967533","doi":"10.1021/pr900665y","title":"SherLoc2: A High-Accuracy Hybrid Method for Predicting Subcellular Localization of Proteins","year":2009,"lang":"en","type":"article","venue":"Journal of Proteome Research","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":143,"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":"Computer science; Gene ontology; Subcellular localization; Data mining; Protein sequencing; Sequence (biology); Protein subcellular localization prediction; Feature (linguistics); Computational biology; Artificial intelligence; Gene; Biology; Peptide sequence; Genetics; Gene expression","retraction":null,"screen_n_in":null,"score":{"opus":0.02805623053856246,"gpt":0.3845717248430646,"spread":0.3565154943045022,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004703764,0.0001108259,0.0002405165,0.0002253786,0.0001205381,0.00004095391,0.0003677843,0.000113342,0.00001513093],"category_scores_gemma":[0.00407987,0.00009192916,0.0001301234,0.0002215762,0.00006198382,0.00001878038,0.00007217599,0.0004067624,0.000001221283],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004043064,"about_ca_system_score_gemma":0.0002762497,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001629571,"about_ca_topic_score_gemma":0.000001130354,"domain_scores_codex":[0.9979449,0.000320607,0.0006634813,0.0001370702,0.0006203809,0.0003135821],"domain_scores_gemma":[0.9977729,0.0001033441,0.0005265236,0.0002590124,0.00123204,0.0001061243],"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":[0.0006430915,0.0001556692,0.0007160667,0.0003826229,0.000077524,0.000006824972,0.0001853774,0.004000987,0.9743302,0.0002006415,0.001150597,0.01815041],"study_design_scores_gemma":[0.00130928,0.005316718,0.0003854337,0.0001916581,0.00002056098,0.0001148666,0.00009668053,0.04395754,0.9347381,0.001714261,0.01201554,0.0001393487],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.214931,0.0002901596,0.7829453,0.0005553341,0.00005017483,0.001043419,0.000009418767,0.000004751059,0.0001703977],"genre_scores_gemma":[0.7734576,0.00007183758,0.2257353,0.00003764495,0.0004306118,0.00002512981,0.00002347561,0.00001988669,0.0001985268],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5585266,"threshold_uncertainty_score":0.4884281,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2145023212","doi":"10.1093/bioinformatics/btr657","title":"Prediction and analysis of nucleotide-binding residues using sequence and sequence-derived structural descriptors","year":2011,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":137,"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":"Killam Trusts","keywords":"Sequence (biology); Computational biology; Sequence alignment; Peptide sequence; Sequence analysis; Nucleotide; Multiple sequence alignment; Protein sequencing; Binding site; Sequence logo; Sequence motif; Consensus sequence; Conserved sequence; Biology; Biochemistry; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.05324823264434206,"gpt":0.2742169801333416,"spread":0.2209687474889996,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002130249,0.0001631788,0.0002268757,0.0002038872,0.0001203814,0.00003420444,0.0001214308,0.0001313712,0.00001411185],"category_scores_gemma":[0.0001237278,0.0001471214,0.00005782142,0.0002402214,0.0002369248,0.00004445947,0.0001422742,0.00009225012,6.71984e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001784245,"about_ca_system_score_gemma":0.0000381757,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000731999,"about_ca_topic_score_gemma":0.00001735336,"domain_scores_codex":[0.9990314,0.00002965666,0.0004758612,0.0001272427,0.0001455957,0.0001902934],"domain_scores_gemma":[0.9992514,0.00001194169,0.0003266417,0.0002430917,0.00008375175,0.0000831293],"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":[0.0001038004,0.0000166267,0.5978204,0.000471091,0.001078687,0.000001993036,0.01144042,0.0007431892,0.3825969,0.0004510431,0.000060939,0.005214886],"study_design_scores_gemma":[0.0006273041,0.0004707671,0.1492639,0.00009826153,0.001031856,0.00008415028,0.002973565,0.756606,0.08804028,0.0000994066,0.000163915,0.0005406129],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9951564,0.00006537051,0.003899582,0.000004037565,0.00006800095,0.0001246756,0.0001065522,0.00002037624,0.0005549855],"genre_scores_gemma":[0.9081873,0.0001092488,0.09148451,0.00003546915,0.00001733885,0.000001435993,0.0001374803,0.00001026143,0.00001697941],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7558628,"threshold_uncertainty_score":0.5999437,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2118769225","doi":"10.1093/nar/gki027","title":"PSORTdb: a protein subcellular localization database for bacteria","year":2004,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":135,"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":"Natural Sciences and Engineering Research Council of Canada; Genome British Columbia; Genome Canada; Genome Prairie; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Michael Smith Health Research BC; National Science Foundation","keywords":"Biology; Identification (biology); Annotation; Database; Bacterial genome size; Computational biology; Function (biology); Protein function; Genome; Database search engine; Computer science; Information retrieval; Bioinformatics; Search engine; Data mining; Genetics; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.03065818731062588,"gpt":0.3387933180577546,"spread":0.3081351307471287,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001014213,0.0001306436,0.0001114093,0.00009897183,0.000246226,0.00007730525,0.0003618372,0.0001736683,0.00008241799],"category_scores_gemma":[0.0007278395,0.0001244787,0.00006005556,0.000202957,0.0001508458,0.00001120012,0.0002442501,0.0002322653,0.00009572183],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005198004,"about_ca_system_score_gemma":0.0001810237,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003992926,"about_ca_topic_score_gemma":0.00001948956,"domain_scores_codex":[0.99854,0.00009724504,0.000233365,0.0003020849,0.0003686196,0.0004587102],"domain_scores_gemma":[0.9989548,0.00001418838,0.00005164311,0.0005722539,0.0002852464,0.0001219221],"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":[0.0002303968,0.000108313,0.0006571601,0.0002422447,0.00002987163,0.000003867241,0.0001639416,0.0005144023,0.9899961,0.002609137,0.003482399,0.001962201],"study_design_scores_gemma":[0.002198796,0.001151503,0.0003760922,0.00009554085,0.000009475945,0.00001765431,0.000164731,0.007055813,0.5873732,0.0009778986,0.4002203,0.0003589753],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8117856,0.000123232,0.1843332,0.000499592,0.0000741746,0.001270987,0.00006292157,0.00003972176,0.001810526],"genre_scores_gemma":[0.9659567,0.00004180751,0.03062714,0.0001419997,0.0002999238,0.0001780666,0.001231245,0.00005670223,0.001466448],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4026228,"threshold_uncertainty_score":0.5076094,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2164620224","doi":"10.1093/bioinformatics/btm115","title":"SherLoc: high-accuracy prediction of protein subcellular localization by integrating text and protein sequence data","year":2007,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":127,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Sequence (biology); Protein sequencing; Artificial intelligence; Computational biology; Protein subcellular localization prediction; Data mining; Pattern recognition (psychology); Peptide sequence; Biology; Genetics; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.01554791924248027,"gpt":0.2587434904356499,"spread":0.2431955711931696,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001070518,0.0001998337,0.0001749212,0.00006875397,0.0001254872,0.00005264568,0.0003783803,0.0002136502,0.00001049287],"category_scores_gemma":[0.0009825751,0.0001804632,0.00002548696,0.00016855,0.0001504589,0.00006826115,0.0003090237,0.0001992147,0.000004310628],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002310734,"about_ca_system_score_gemma":0.00007184323,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006749696,"about_ca_topic_score_gemma":0.00001510447,"domain_scores_codex":[0.9984665,0.00004297691,0.0007794937,0.0001846281,0.0002705635,0.0002558643],"domain_scores_gemma":[0.9985701,0.00002576373,0.0004933398,0.0006863225,0.0001349817,0.00008941843],"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":[0.0001509318,0.0001200351,0.005353782,0.001747429,0.0001081649,0.00000183296,0.001376343,0.0002810404,0.9125117,0.001145522,0.004378585,0.07282461],"study_design_scores_gemma":[0.001125617,0.0008396425,0.0004412004,0.0003712785,0.00004562359,0.00003975186,0.001217991,0.4934039,0.4311437,0.00007527509,0.07076634,0.0005296674],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3825758,0.0002390887,0.6151128,0.00004481961,0.00006038992,0.0007799867,0.0002698641,0.0000407454,0.0008764815],"genre_scores_gemma":[0.8742926,0.00006316589,0.1214126,0.00009452315,0.00008244013,0.00001338955,0.003749633,0.00002696057,0.000264728],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4937002,"threshold_uncertainty_score":0.7359077,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2021901733","doi":"10.1016/s1672-0229(07)60022-9","title":"FragAnchor: A Large-Scale Predictor of Glycosylphosphatidylinositol Anchors in Eukaryote Protein Sequences by Qualitative Scoring","year":2007,"lang":"en","type":"article","venue":"Genomics Proteomics & Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":125,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University; Université du Québec à Montréal","funders":"National Center for Research Resources; National Institutes of Health","keywords":"Eukaryote; UniProt; Proteome; Computational biology; Hidden Markov model; Protein sequencing; Human proteome project; Computer science; Noise (video); Scale (ratio); Biology; Artificial intelligence; Proteomics; Bioinformatics; Machine learning; Pattern recognition (psychology); Genetics; Peptide sequence; Gene; Genome","retraction":null,"screen_n_in":null,"score":{"opus":0.00645521733399634,"gpt":0.2699390928318512,"spread":0.2634838754978549,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002643641,0.0004554936,0.000520987,0.000309382,0.0001431494,0.00006501823,0.0006951342,0.0004635383,0.00001342864],"category_scores_gemma":[0.0003522986,0.0004666939,0.000161749,0.0004648083,0.0002291156,0.0000618427,0.0003528618,0.000521903,0.00001815137],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001713998,"about_ca_system_score_gemma":0.0003010232,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005418401,"about_ca_topic_score_gemma":0.0001538361,"domain_scores_codex":[0.9964401,0.00009051995,0.001807125,0.00035214,0.0004376876,0.0008724454],"domain_scores_gemma":[0.9978416,0.00005653072,0.001026636,0.0006537841,0.0002071098,0.0002143525],"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":[0.001301895,0.0005563817,0.02000463,0.001864291,0.0002874444,0.000008683857,0.06429885,0.002399663,0.9005675,0.001895712,0.001402692,0.005412253],"study_design_scores_gemma":[0.002901311,0.001002325,0.000842332,0.000302417,0.00003676283,0.00002565549,0.01205171,0.03370461,0.9393394,0.0006386949,0.008085943,0.00106881],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8401929,0.0003459692,0.155951,0.00004884595,0.0001552633,0.00164409,0.0003497473,0.00003502191,0.00127715],"genre_scores_gemma":[0.7004365,0.000161504,0.2981883,0.0002191739,0.0001407092,0.00007888321,0.0004610317,0.00006534826,0.0002485537],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1422373,"threshold_uncertainty_score":0.9997784,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2040630248","doi":"10.1371/journal.pcbi.0010066","title":"Refining Protein Subcellular Localization","year":2005,"lang":"en","type":"article","venue":"PLoS Computational Biology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":123,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Canadian Institutes of Health Research; Genome Canada","keywords":"Proteome; Computational biology; Subcellular localization; Protein subcellular localization prediction; Protein–protein interaction; Biology; Protein targeting; Function (biology); Organelle; Proteomics; Computer science; Bioinformatics; Membrane protein; Cell biology; Biochemistry; Gene; Cytoplasm","retraction":null,"screen_n_in":null,"score":{"opus":0.009820439929410696,"gpt":0.2489673547677503,"spread":0.2391469148383396,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001242831,0.0001135578,0.00009939144,0.00005121989,0.00009080691,0.00001414486,0.0001341817,0.0001342474,0.00006384312],"category_scores_gemma":[0.0001469631,0.0001101523,0.00003929477,0.00007137127,0.00006724418,0.000004384018,0.00007813574,0.00009287261,0.0001283948],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001678171,"about_ca_system_score_gemma":0.00004884321,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003731347,"about_ca_topic_score_gemma":0.000005700257,"domain_scores_codex":[0.9992263,0.00007525981,0.0002407908,0.0001979981,0.00008993675,0.0001697355],"domain_scores_gemma":[0.9995936,0.00001911829,0.0001027946,0.0001370371,0.000102678,0.00004474115],"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":[0.0001185902,0.0002343737,0.02710129,0.0000761304,0.000171476,0.000001721067,0.0001789757,0.5606968,0.3668637,0.02389838,0.002274871,0.01838364],"study_design_scores_gemma":[0.0009507938,0.0005340412,0.001215355,0.00002903102,0.00001839194,0.00003079709,0.00001781939,0.67119,0.03924868,0.001659943,0.2846359,0.000469286],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5605589,0.0002657296,0.4328955,0.0009310202,0.00007526208,0.0002006433,0.00002304922,0.00007616141,0.004973693],"genre_scores_gemma":[0.9513955,0.00000334927,0.04539203,0.0008156717,0.0002799416,0.00001984797,0.00166315,0.00001579392,0.0004146897],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3908366,"threshold_uncertainty_score":0.4491881,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3157437194","doi":"10.1002/cpz1.113","title":"Learned Embeddings from Deep Learning to Visualize and Predict Protein Sets","year":2021,"lang":"en","type":"article","venue":"Current Protocols","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":123,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Vector Institute; University of Toronto","funders":"Deutsche Forschungsgemeinschaft","keywords":"Computer science; Workflow; Artificial intelligence; Pipeline (software); ENCODE; Classifier (UML); Protocol (science); Machine learning; Inference; Natural language processing; Programming language; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.02184703544408889,"gpt":0.3633679176334731,"spread":0.3415208821893843,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002322891,0.0002091428,0.0001964519,0.00003643999,0.0001277662,0.0001371744,0.0001816957,0.0001292588,0.0001097422],"category_scores_gemma":[0.0008306727,0.000207637,0.00006085936,0.000118993,0.00004236887,0.000009800011,0.0004192276,0.0003126245,0.00004917585],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001549274,"about_ca_system_score_gemma":0.00007578169,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004732027,"about_ca_topic_score_gemma":0.000005329493,"domain_scores_codex":[0.99861,0.0001519948,0.0003034358,0.000426393,0.0002144573,0.0002937848],"domain_scores_gemma":[0.9992104,0.00001708995,0.0001320796,0.0003365644,0.0001222208,0.0001816986],"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":[0.0004570693,0.0003655942,0.04560076,0.0009958436,0.0001577162,0.0000168524,0.002129208,0.0008737925,0.6254632,0.0003657942,0.00402983,0.3195443],"study_design_scores_gemma":[0.001423141,0.0006246667,0.004115373,0.0004840041,0.00001761387,0.00001520742,0.000169927,0.004880822,0.1408153,0.0001702017,0.8467857,0.0004980848],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.938684,0.0004983468,0.01486524,0.0003544708,0.0001422734,0.04360462,0.00003605671,0.0001326999,0.001682285],"genre_scores_gemma":[0.7334429,0.0001315328,0.05110348,0.001037089,0.00158062,0.2049755,0.00231997,0.0002837708,0.005125082],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8427559,"threshold_uncertainty_score":0.8467189,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2104873783","doi":"10.1093/bioinformatics/btm475","title":"PFRES: protein fold classification by using evolutionary information and predicted secondary structure","year":2007,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":122,"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":"Natural Sciences and Engineering Research Council of Canada","keywords":"Protein tertiary structure; Protein secondary structure; Computer science; Pseudo amino acid composition; Similarity (geometry); Classifier (UML); Pattern recognition (psychology); Protein Data Bank (RCSB PDB); Fold (higher-order function); Protein superfamily; Protein structure prediction; Representation (politics); Feature vector; Structural Classification of Proteins database; Protein structure; Sequence (biology); Structural alignment; Data mining; Algorithm; Artificial intelligence; Sequence alignment; Biology; Peptide sequence; Amino acid; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.006359821080226958,"gpt":0.233839707426869,"spread":0.2274798863466421,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002944054,0.0002152097,0.0001377569,0.0001289061,0.00019547,0.00008329767,0.0001786211,0.0003191696,0.00002529937],"category_scores_gemma":[0.0001980836,0.0002049834,0.00004076739,0.0001594257,0.0001167605,0.0001156277,0.0001310161,0.0002345238,0.000008141166],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005165589,"about_ca_system_score_gemma":0.000131484,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001287465,"about_ca_topic_score_gemma":0.000006678512,"domain_scores_codex":[0.9985908,0.00002300433,0.0006936755,0.0001106434,0.0002751153,0.0003067388],"domain_scores_gemma":[0.9990007,0.00001420307,0.0003830947,0.0003206131,0.0001525176,0.0001288937],"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":[0.0008285359,0.0002021013,0.03233182,0.00331084,0.0004787053,0.000002579436,0.005494997,0.0008239126,0.5722207,0.00276272,0.1080604,0.2734827],"study_design_scores_gemma":[0.003043147,0.0007773762,0.02749417,0.0001712224,0.00008754944,0.0002722591,0.003011813,0.4953915,0.0480703,0.0002346727,0.4200628,0.001383185],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9147561,0.0002366762,0.07972391,0.00007191006,0.0001615121,0.0007279984,0.0004501704,0.00008083306,0.003790896],"genre_scores_gemma":[0.9090248,0.00004172964,0.0867198,0.0005179283,0.0001363391,0.00000827685,0.003372542,0.00002309145,0.0001554495],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5241504,"threshold_uncertainty_score":0.835898,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2059926522","doi":"10.1016/j.bbrc.2007.02.040","title":"Prediction of protein crystallization using collocation of amino acid pairs","year":2007,"lang":"en","type":"article","venue":"Biochemical and Biophysical Research Communications","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":118,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"In silico; Protein crystallization; Naive Bayes classifier; Computer science; Crystallization; Classifier (UML); Sequence (biology); Protein Data Bank (RCSB PDB); Artificial intelligence; Threading (protein sequence); Protein sequencing; Peptide sequence; Computational biology; Pattern recognition (psychology); Protein structure; Algorithm; Chemistry; Biology; Biochemistry; Support vector machine","retraction":null,"screen_n_in":null,"score":{"opus":0.07206198932686944,"gpt":0.3613267705409309,"spread":0.2892647812140614,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007792594,0.00007626984,0.0001099447,0.00008516377,0.0001167727,0.000009660816,0.0003260703,0.000133137,0.000002911447],"category_scores_gemma":[0.0006515912,0.00007033968,0.00004305224,0.0003527348,0.0006850079,0.000007915434,0.0003179792,0.0001809006,7.472916e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002094609,"about_ca_system_score_gemma":0.00007054573,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004066433,"about_ca_topic_score_gemma":0.000004672077,"domain_scores_codex":[0.9989595,0.0001139372,0.0003313788,0.0001344495,0.0002913109,0.0001693581],"domain_scores_gemma":[0.9986571,0.00007232353,0.0001217684,0.0006026113,0.0004697735,0.00007643588],"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":[0.00005637936,0.0001774583,0.0006632044,0.00009572658,0.00001572679,3.206513e-8,0.00005871607,0.000003353205,0.9957882,0.001671213,0.00006216107,0.001407899],"study_design_scores_gemma":[0.0001955163,0.0002510461,0.003100189,0.00006110971,0.000008763617,0.00000141814,0.0001248136,0.005190875,0.9896389,0.0001930015,0.001172769,0.00006164497],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9861175,0.0002890688,0.01246228,0.000134521,0.000008086823,0.0003082096,0.00003487421,0.000008192904,0.000637243],"genre_scores_gemma":[0.9856464,0.0001356985,0.01387256,0.000007096449,0.00004333585,0.00001117645,0.0002328611,0.000008203447,0.000042641],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006149277,"threshold_uncertainty_score":0.2868369,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1972434016","doi":"10.1093/nar/gkn255","title":"PROTEUS2: a web server for comprehensive protein structure prediction and structure-based annotation","year":2008,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":116,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta; National Institute for Nanotechnology","funders":"Alberta Prion Research Institute; Natural Sciences and Engineering Research Council of Canada; Genome Alberta","keywords":"Protein secondary structure; Web server; Threading (protein sequence); Biology; Computational biology; Annotation; Protein structure prediction; Protein structure database; Homology modeling; Computer science; Hidden Markov model; Pipeline (software); Sequence alignment; Protein tertiary structure; Protein structure; Artificial intelligence; Bioinformatics; Peptide sequence; Sequence database; Genetics; The Internet","retraction":null,"screen_n_in":null,"score":{"opus":0.03240950971587583,"gpt":0.3212105942469039,"spread":0.288801084531028,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002159561,0.0001554132,0.0001340836,0.0001188123,0.000394203,0.00004555165,0.000183714,0.0002590498,0.00003440699],"category_scores_gemma":[0.0003184121,0.0001392097,0.00004272178,0.0001727934,0.0002570538,0.00001268653,0.0001094262,0.000360342,0.000003137556],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003157424,"about_ca_system_score_gemma":0.0001961963,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001399057,"about_ca_topic_score_gemma":0.00001931104,"domain_scores_codex":[0.9985577,0.0001540914,0.0002135704,0.0003150594,0.0004153042,0.0003442396],"domain_scores_gemma":[0.9989747,0.0000300671,0.00007318363,0.0003338909,0.0004898955,0.00009828062],"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":[0.0004398959,0.00002734863,0.007150369,0.0003359324,0.00003805129,0.00000209537,0.0002464067,0.0004712643,0.984063,0.0001113267,0.004900603,0.00221366],"study_design_scores_gemma":[0.00702113,0.004707423,0.08448517,0.0001447364,0.00002669988,0.0001514839,0.0003658361,0.1707775,0.5770261,0.001026915,0.1534831,0.0007838445],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9963092,0.00007542801,0.001125922,0.0003079922,0.00004194802,0.001708745,0.0002436059,0.00003737229,0.0001498538],"genre_scores_gemma":[0.9884899,0.00001238903,0.01025422,0.0001240479,0.0001938971,0.00009976657,0.0005008233,0.00003289989,0.0002920958],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4070369,"threshold_uncertainty_score":0.5676808,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2012352014","doi":"10.1101/gr.2650004","title":"Predicting Subcellular Localization via Protein Motif Co-Occurrence","year":2004,"lang":"en","type":"article","venue":"Genome Research","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":114,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Canadian Institutes of Health Research; Genome Canada","keywords":"Subcellular localization; Biology; Protein subcellular localization prediction; Computational biology; Protein Sorting Signals; Membrane protein; Organelle; Green fluorescent protein; Bioinformatics; Cell biology; Cytoplasm; Biochemistry; Gene; Peptide sequence; Signal peptide; Membrane","retraction":null,"screen_n_in":null,"score":{"opus":0.02705706486612943,"gpt":0.337070739419401,"spread":0.3100136745532716,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001168235,0.0001191818,0.00009620529,0.0001133571,0.000275747,0.00006128826,0.0003448311,0.0001486977,0.00004899503],"category_scores_gemma":[0.0003602326,0.0001180506,0.00004199158,0.0002664397,0.0001558367,0.000006755328,0.0002006467,0.0003562742,0.000178014],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006659705,"about_ca_system_score_gemma":0.0001753138,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005819823,"about_ca_topic_score_gemma":0.00001074508,"domain_scores_codex":[0.9983727,0.0001406688,0.0002372032,0.0002793694,0.0004934769,0.0004765954],"domain_scores_gemma":[0.9991591,0.00001108056,0.00005952839,0.0004250182,0.0002203593,0.0001248962],"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":[0.00006943875,0.0001228889,0.01364599,0.000322653,0.00004303486,0.00001269989,0.0006099165,0.02303077,0.9587982,0.0002930976,0.0002509138,0.002800406],"study_design_scores_gemma":[0.002661247,0.002391763,0.005145958,0.0001759451,0.00001637067,0.00009947511,0.0004868635,0.02841743,0.7854591,0.001601702,0.1725303,0.001013785],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8382422,0.0004188408,0.1567396,0.0001831562,0.00005143682,0.0007498476,0.00004391629,0.00004322366,0.003527777],"genre_scores_gemma":[0.9967285,0.00005114415,0.001754246,0.00003426232,0.0001827573,0.00004536254,0.0007965934,0.00001940301,0.0003876801],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1733391,"threshold_uncertainty_score":0.4813965,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2069116068","doi":"10.1145/507515.507523","title":"KDD Cup 2001 report","year":2002,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":110,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Canadian Imperial Bank of Commerce (Canada)","funders":"National Science Foundation","keywords":"Computer science; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.03648866402031892,"gpt":0.2723488489952492,"spread":0.2358601849749303,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001616701,0.0001813945,0.0001263133,0.00006850316,0.0001618763,0.00006956306,0.0003778904,0.0001424874,0.0008425448],"category_scores_gemma":[0.0007396833,0.0001742422,0.00009063919,0.0001494745,0.00006699174,0.00002338724,0.0002032578,0.0001780216,0.0009980784],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001452035,"about_ca_system_score_gemma":0.00001779696,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009239325,"about_ca_topic_score_gemma":0.00001354434,"domain_scores_codex":[0.9988,0.00005226003,0.0003749913,0.0002807268,0.000185376,0.0003065941],"domain_scores_gemma":[0.9983925,0.00002402311,0.0001412375,0.001262724,0.00008701246,0.00009253453],"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":[0.000005581297,0.00005974116,0.004385849,0.00000917409,0.00003892383,0.0000332745,0.0002333277,0.0003191782,0.03570089,0.00006012698,0.9573221,0.001831859],"study_design_scores_gemma":[0.000342795,0.00009709546,0.0007456791,0.000007566597,0.00002035222,0.000221526,0.00006188864,0.001610284,0.01148792,0.0001074671,0.984975,0.0003224004],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7355424,0.0005940037,0.07506728,0.08697352,0.001600189,0.001088335,0.00004132806,0.0003766677,0.09871628],"genre_scores_gemma":[0.8407871,0.0002831094,0.07345465,0.03020592,0.002573693,0.0002461803,0.001464755,0.0001303525,0.05085421],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1052447,"threshold_uncertainty_score":0.9997798,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2887711510","doi":"10.1038/s41598-019-40561-2","title":"Interpretable genotype-to-phenotype classifiers with performance guarantees","year":2019,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":108,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo; Canada Research Chairs; Government of Canada; Compute Canada; Université Laval","keywords":"Interpretability; Machine learning; Computer science; Artificial intelligence; Scalability; Curse of dimensionality; Generalization; Turnkey; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.003900188324957552,"gpt":0.2139763805367878,"spread":0.2100761922118303,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005487816,0.0001473799,0.0001343646,0.00008374186,0.0001348653,0.0001430291,0.0002045752,0.00007564116,0.0001324596],"category_scores_gemma":[0.00006755553,0.0001145278,0.00004371725,0.000234727,0.0001059654,0.00001346141,0.0001336893,0.0001118556,0.00023121],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001748088,"about_ca_system_score_gemma":0.0001385637,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006799797,"about_ca_topic_score_gemma":0.00001013005,"domain_scores_codex":[0.9986022,0.00001700141,0.0002772193,0.0004943582,0.0003011867,0.0003080017],"domain_scores_gemma":[0.9986231,0.000004447346,0.0001618245,0.0009774837,0.000136217,0.00009692604],"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":[0.0003141006,0.0001092753,0.2799732,0.0002212721,0.0001252105,0.00002846954,0.001155613,0.01535422,0.6484696,0.0001324987,0.04728903,0.006827521],"study_design_scores_gemma":[0.0003856497,0.0008264869,0.0163319,0.0001329842,0.00002910395,0.0003701155,0.0002052842,0.006406235,0.1235116,0.0001025429,0.850999,0.0006990708],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9546636,0.00004777213,0.001250222,0.00004131725,0.00212185,0.0002917131,0.000001071635,0.00002899586,0.04155343],"genre_scores_gemma":[0.9728314,0.000002729393,0.003614056,0.0001630575,0.00004848031,0.00001019115,0.00007450837,0.00001980135,0.02323573],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.80371,"threshold_uncertainty_score":0.4670309,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2910654431","doi":"10.1016/j.gpb.2018.08.004","title":"Integration of A Deep Learning Classifier with A Random Forest Approach for Predicting Malonylation Sites","year":2018,"lang":"en","type":"article","venue":"Genomics Proteomics & Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":107,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"National Natural Science Foundation of China; Natural Science Foundation of Shandong Province; Qingdao Postdoctoral Science Foundation","keywords":"Classifier (UML); Computer science; Random forest; Artificial intelligence; Deep learning; Machine learning; Training set; Pattern recognition (psychology); End-to-end principle","retraction":null,"screen_n_in":null,"score":{"opus":0.009638930436779197,"gpt":0.2327989324049696,"spread":0.2231600019681904,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007470973,0.0002891822,0.0003093744,0.0001814526,0.0002674029,0.00008765745,0.0002855927,0.0002725199,0.000003997207],"category_scores_gemma":[0.0006811352,0.000246543,0.0001202703,0.0002045749,0.0002264948,0.00004028978,0.0001302095,0.0002406882,0.000004759852],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005300203,"about_ca_system_score_gemma":0.0001148765,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006034313,"about_ca_topic_score_gemma":0.00004162797,"domain_scores_codex":[0.9983714,0.00004357592,0.0007961334,0.0002210742,0.0002014549,0.000366373],"domain_scores_gemma":[0.9979585,0.00004369651,0.0008367057,0.0003944236,0.000683243,0.00008337718],"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":[0.00952904,0.0003946581,0.06743961,0.002796902,0.0009803291,5.217637e-7,0.0189511,0.1544034,0.6900275,0.003588369,0.0007164055,0.05117214],"study_design_scores_gemma":[0.002317528,0.001524401,0.0005781217,0.00003469656,0.00006943367,0.00001862754,0.0009058933,0.9402418,0.05132271,0.0000921131,0.002566772,0.0003278881],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.366096,0.00002180896,0.6303003,0.00001046124,0.00005208304,0.001130839,0.00002089786,0.00002734232,0.002340201],"genre_scores_gemma":[0.462782,0.00002182833,0.5357367,0.00005679582,0.0002696459,0.00009902081,0.0008915429,0.00003790569,0.0001044967],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7858384,"threshold_uncertainty_score":0.9999987,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2150408357","doi":"10.1093/nar/gkh485","title":"Proteome Analyst: custom predictions with explanations in a web-based tool for high-throughput proteome annotations","year":2004,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":100,"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":"Natural Sciences and Engineering Research Council of Canada","keywords":"Proteome; Gene ontology; Classifier (UML); Naive Bayes classifier; Computer science; Biology; Human proteome project; Bayes' theorem; Function (biology); Machine learning; Protein function; Artificial intelligence; Protein function prediction; Computational biology; Bioinformatics; Gene; Proteomics; Bayesian probability; Genetics; Support vector machine; Gene expression","retraction":null,"screen_n_in":null,"score":{"opus":0.02065510645228343,"gpt":0.3270776948286184,"spread":0.306422588376335,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008465347,0.0001708331,0.0001693168,0.0004340416,0.0003914897,0.00009157749,0.0003412786,0.0001923404,0.00004073354],"category_scores_gemma":[0.0006293913,0.0001512092,0.00006170379,0.0008732136,0.0002333748,0.00002550714,0.00008721816,0.0004403951,0.00003225434],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001445369,"about_ca_system_score_gemma":0.000772243,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009942389,"about_ca_topic_score_gemma":0.0005369356,"domain_scores_codex":[0.9980994,0.0001251645,0.0003473522,0.0003781134,0.0005262815,0.0005236629],"domain_scores_gemma":[0.998722,0.00005772675,0.00008373173,0.0005417556,0.0004952644,0.00009951926],"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":[0.002728148,0.002746098,0.07065281,0.001203724,0.0006200858,0.00004284921,0.003179441,0.4010558,0.4864552,0.01599839,0.01182242,0.003495006],"study_design_scores_gemma":[0.06670774,0.02463745,0.2441403,0.001400056,0.0002787228,0.0002002112,0.004136654,0.1927365,0.2646157,0.008901021,0.1877462,0.004499414],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9082172,0.00002397863,0.0839904,0.002898463,0.00003922238,0.003003544,0.0002162669,0.00006641921,0.001544542],"genre_scores_gemma":[0.941668,0.00001011313,0.05512609,0.00009123999,0.0001262854,0.001917528,0.000555519,0.00004082147,0.0004644324],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2218395,"threshold_uncertainty_score":0.6166131,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2148271643","doi":"10.1093/bioinformatics/btv060","title":"Computational identification of MoRFs in protein sequences","year":2015,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":99,"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; Canadian Institutes of Health Research; Genome Canada","keywords":"Computer science; Support vector machine; Identification (biology); Sequence (biology); Artificial intelligence; Computational biology; Data mining; Set (abstract data type); Machine learning; Pattern recognition (psychology); Biology; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.01588503249904103,"gpt":0.2752276049529452,"spread":0.2593425724539041,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004737129,0.000086075,0.0001024604,0.00008365383,0.00001751453,0.00001888121,0.0001736436,0.00008186047,0.000003584063],"category_scores_gemma":[0.0002872231,0.00008087633,0.00002956849,0.0001362354,0.00007196372,0.00001601997,0.00006361571,0.00006566528,0.00002574515],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001874208,"about_ca_system_score_gemma":0.0001395814,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001288071,"about_ca_topic_score_gemma":0.000006545612,"domain_scores_codex":[0.999001,0.00002613475,0.0005689557,0.00006508335,0.000221576,0.0001172963],"domain_scores_gemma":[0.9993374,0.00000732813,0.0002807088,0.000187045,0.000136938,0.00005058802],"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":[0.0004679011,0.0006981196,0.1108896,0.002189263,0.0002140829,0.000005934539,0.01616872,0.696732,0.1019054,0.02120921,0.01320169,0.03631808],"study_design_scores_gemma":[0.002056672,0.0005929616,0.01131818,0.0001079043,0.00001498385,0.00003948985,0.002382481,0.8965242,0.07379486,0.002792018,0.009825882,0.0005503698],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9578253,0.00006279942,0.03634404,0.000106439,0.000088507,0.0003332973,0.00002278456,0.00001603884,0.005200814],"genre_scores_gemma":[0.950223,0.000004140103,0.04926631,0.00005918998,0.0000266297,0.00001176775,0.0001979176,0.000006428236,0.0002046421],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1997922,"threshold_uncertainty_score":0.3298041,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2076460489","doi":"10.1186/1471-2105-10-414","title":"Modular prediction of protein structural classes from sequences of twilight-zone identity with predicting sequences","year":2009,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":96,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Benchmark (surveying); Artificial intelligence; Support vector machine; Modular design; Similarity (geometry); Feature selection; Feature (linguistics); Pattern recognition (psychology); Class (philosophy); Sequence (biology); Contrast (vision); Data mining; Machine learning; Biology; Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.01020080503328411,"gpt":0.2450921923098636,"spread":0.2348913872765795,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002641913,0.0002240961,0.0002941823,0.00008533739,0.0000854942,0.0000457381,0.0003816294,0.0001873624,0.00001610088],"category_scores_gemma":[0.000168725,0.0001729553,0.00008682906,0.0001923584,0.0002107022,0.0001140844,0.00008043292,0.0001575729,0.000002152314],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001933075,"about_ca_system_score_gemma":0.0001682296,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009971873,"about_ca_topic_score_gemma":0.00007166038,"domain_scores_codex":[0.9982685,0.00004998824,0.0008198606,0.0001566883,0.0004753672,0.0002296321],"domain_scores_gemma":[0.998455,0.00002283095,0.0008062866,0.0004299079,0.0002161369,0.00006977116],"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":[0.00050312,0.000139297,0.2439422,0.001666712,0.0003140036,0.000002334117,0.003156425,0.04426293,0.6989824,0.00150646,0.0001326316,0.0053915],"study_design_scores_gemma":[0.001477094,0.002696015,0.08932839,0.0005441598,0.0001425327,0.00004517549,0.002105898,0.4293652,0.4725552,0.0008788293,0.0003387001,0.0005227565],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9133903,0.0001952222,0.08507766,0.00002325013,0.00006673965,0.0003580908,0.0001907268,0.0000353627,0.0006626502],"genre_scores_gemma":[0.8010221,0.00002360855,0.1985356,0.00002902733,0.00007373931,0.000005596295,0.0002692163,0.000008730897,0.00003247354],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3851023,"threshold_uncertainty_score":0.7052912,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2132581719","doi":"10.1002/jcc.21053","title":"Prediction of integral membrane protein type by collocated hydrophobic amino acid pairs","year":2008,"lang":"en","type":"article","venue":"Journal of Computational Chemistry","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":89,"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":"Feature selection; Computer science; Classifier (UML); Benchmark (surveying); Transmembrane protein; Feature (linguistics); Transmembrane domain; Integral membrane protein; Sequence (biology); Artificial intelligence; Pattern recognition (psychology); Membrane protein; Algorithm; Biological system; Chemistry; Amino acid; Membrane; Biology; Biochemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.008975504715840538,"gpt":0.2198560894298847,"spread":0.2108805847140442,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001576744,0.0001134609,0.0001710121,0.0000292418,0.00004725847,0.00000601422,0.0001676963,0.0001238001,0.0000491139],"category_scores_gemma":[0.000152529,0.0001038679,0.00009057983,0.0001167645,0.0001037717,0.000008612924,0.00003258,0.000207483,0.000002022763],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002655634,"about_ca_system_score_gemma":0.0002363601,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001743363,"about_ca_topic_score_gemma":7.318623e-8,"domain_scores_codex":[0.9989747,0.00002713935,0.0005012428,0.000084972,0.0003109435,0.0001010196],"domain_scores_gemma":[0.9988424,0.00001395673,0.0005065539,0.00009723552,0.0004713525,0.00006857127],"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":[0.0001800056,0.00008665826,0.001433523,0.00008930023,0.00008414259,0.000004535644,0.00005008371,0.01628686,0.9761193,0.000001301382,0.005577314,0.00008697021],"study_design_scores_gemma":[0.0008042724,0.0003520927,0.001156559,0.00005102321,0.00001736655,0.0005302533,0.00003496978,0.00309935,0.9905336,0.00007340225,0.003248856,0.00009828162],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9968599,0.0001940703,0.001986767,0.00007021263,0.00006487477,0.00006174788,0.00002686019,0.000006295403,0.0007292875],"genre_scores_gemma":[0.9951514,0.00002715449,0.003857606,0.00003714248,0.0001480019,0.000001357777,0.000248581,0.00001220868,0.0005165319],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01441427,"threshold_uncertainty_score":0.423561,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2098676247","doi":"10.1093/nar/gkq1093","title":"PSORTdb--an expanded, auto-updated, user-friendly protein subcellular localization database for Bacteria and Archaea","year":2010,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":89,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Biology; Archaea; Bacteria; Database; Bacterial protein; Computational biology; Genetics; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.01996824358640841,"gpt":0.3300858543855556,"spread":0.3101176107991472,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00177879,0.0001915433,0.0001593158,0.0001357242,0.0003409191,0.0001379827,0.0004281666,0.0002906738,0.0001428619],"category_scores_gemma":[0.0007522943,0.0001793298,0.00004418478,0.0001664231,0.000337737,0.00004123881,0.0004278876,0.0005317191,0.0000251342],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001578419,"about_ca_system_score_gemma":0.0001226186,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005554453,"about_ca_topic_score_gemma":0.00007740568,"domain_scores_codex":[0.998072,0.0001954319,0.0002907136,0.0004160854,0.0004025711,0.0006231734],"domain_scores_gemma":[0.9984859,0.00002797462,0.00007496774,0.0008195475,0.0002991155,0.0002924826],"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":[0.0002261396,0.00009896448,0.005889031,0.0001495248,0.00002436548,0.000002047308,0.0002301292,0.000007300635,0.9845562,0.001480752,0.004313336,0.003022189],"study_design_scores_gemma":[0.001509886,0.001283434,0.001644852,0.00003344375,0.00001397283,0.0000472521,0.0003345951,0.03282361,0.3313389,0.000175792,0.630338,0.0004563466],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9565959,0.00004804358,0.04159151,0.0001543048,0.0001108293,0.0009609224,0.00009526952,0.00003903544,0.0004041732],"genre_scores_gemma":[0.9553645,0.00003974291,0.04005128,0.00008523346,0.0003822283,0.0001569864,0.002473755,0.00006991807,0.00137636],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6532173,"threshold_uncertainty_score":0.7312858,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2512143001","doi":"10.1186/s12859-016-1115-5","title":"Predicting essential proteins based on subcellular localization, orthology and PPI networks","year":2016,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":88,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Saskatchewan","funders":"National Natural Science Foundation of China","keywords":"Subcellular localization; Computational biology; DNA microarray; Protein subcellular localization prediction; Biology; Computer science; Genetics; Gene; Gene expression","retraction":null,"screen_n_in":null,"score":{"opus":0.00529630127268006,"gpt":0.2175242514484297,"spread":0.2122279501757496,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003719677,0.0002285992,0.0001729003,0.00008542567,0.000167345,0.00004957788,0.0001886815,0.0002783148,0.00002993884],"category_scores_gemma":[0.0003607324,0.0001631014,0.00006417721,0.0001089644,0.0001743849,0.00001668051,0.0001355212,0.0001220096,0.00002393533],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001677702,"about_ca_system_score_gemma":0.00008462506,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003731314,"about_ca_topic_score_gemma":0.00001977321,"domain_scores_codex":[0.9986998,0.00006910775,0.0005035982,0.00018628,0.0002023304,0.0003388446],"domain_scores_gemma":[0.9990087,0.00005666697,0.0002640401,0.0004576122,0.0000963192,0.0001166868],"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":[0.0006194391,0.0002343919,0.7254546,0.001070081,0.0001324488,0.000007100472,0.0006096036,0.2392773,0.005008139,0.002031562,0.005160405,0.02039485],"study_design_scores_gemma":[0.00109874,0.0004274436,0.002359519,0.00008547123,0.00002140044,0.00002325041,0.00005289388,0.9863968,0.002826711,0.00001882699,0.006413172,0.0002757781],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05067428,0.0000464123,0.9469353,0.0001150543,0.0001586326,0.0003753233,0.00001600033,0.00006110574,0.001617911],"genre_scores_gemma":[0.9158099,0.00007903006,0.08202196,0.001023505,0.0003380537,0.00003996753,0.0002623712,0.0000486223,0.0003765556],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8651357,"threshold_uncertainty_score":0.6651084,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2104332903","doi":"10.1016/j.bbrc.2007.03.164","title":"Prediction of protein structural class for the twilight zone sequences","year":2007,"lang":"en","type":"article","venue":"Biochemical and Biophysical Research Communications","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":87,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Representation (politics); Computer science; In silico; Classifier (UML); Artificial intelligence; Protein structure prediction; Pattern recognition (psychology); Protein structure; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.06387065908451027,"gpt":0.3770602085118304,"spread":0.3131895494273201,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008430965,0.00007994794,0.00008807754,0.00003382219,0.0003047014,0.00002312516,0.0006099703,0.0001076473,0.000002664238],"category_scores_gemma":[0.0006488007,0.00005137961,0.00005921942,0.0001813299,0.001107002,0.000005202574,0.0003662885,0.0002637893,0.000001303731],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001226012,"about_ca_system_score_gemma":0.00004968516,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000301548,"about_ca_topic_score_gemma":0.00001221929,"domain_scores_codex":[0.9990923,0.00007339704,0.0002276259,0.0001414605,0.0002374555,0.0002277227],"domain_scores_gemma":[0.9985196,0.0003575341,0.00006191216,0.0006967676,0.0002887581,0.00007543548],"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":[0.00007748148,0.00004149459,0.0001794361,0.00004066757,0.0000248441,2.975441e-8,0.00004644725,8.098328e-7,0.9897826,0.00533133,0.0005377735,0.003937026],"study_design_scores_gemma":[0.000326072,0.0004471644,0.003742701,0.0000320322,0.00001456153,0.000003529282,0.0002191292,0.006997047,0.9416203,0.0009220773,0.04557471,0.0001006256],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9904706,0.001125647,0.003952036,0.002950018,0.00002306971,0.000709551,0.00009400547,0.00001276167,0.0006622793],"genre_scores_gemma":[0.9934765,0.0001717358,0.005769725,0.00003111407,0.0001290101,0.00006243523,0.0001466216,0.000006930236,0.0002059168],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04816232,"threshold_uncertainty_score":0.4078796,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2962655813","doi":"10.1093/bioinformatics/btz337","title":"Prediction of mRNA subcellular localization using deep recurrent neural networks","year":2019,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":86,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Montreal Clinical Research Institute; McGill University","funders":"Institut de Valorisation des Données","keywords":"Computational biology; Sequence (biology); Computer science; Identification (biology); RNA; Subcellular localization; Variety (cybernetics); Messenger RNA; Biology; Set (abstract data type); Deep learning; RNA-binding protein; Artificial neural network; Artificial intelligence; Gene; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.01212322715081878,"gpt":0.2315241812715117,"spread":0.2194009541206929,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002319338,0.0001632247,0.0001711886,0.00007228552,0.0000559363,0.0000257577,0.0001808594,0.0001895959,0.00003170953],"category_scores_gemma":[0.00006412285,0.0001541256,0.00008806523,0.0001540683,0.0000490366,0.00002181441,0.0001165017,0.0001273762,0.00001360244],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002418262,"about_ca_system_score_gemma":0.00003163056,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005642093,"about_ca_topic_score_gemma":0.000001775203,"domain_scores_codex":[0.9988273,0.00003370631,0.0005916753,0.0001068548,0.000217274,0.0002232111],"domain_scores_gemma":[0.9990464,0.00001016048,0.000372779,0.0003841603,0.000123985,0.00006249459],"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":[0.00007988734,0.00006635729,0.08589184,0.0005727056,0.00007807434,3.634134e-7,0.0005480394,0.895071,0.006911257,0.000182685,0.0006111136,0.009986633],"study_design_scores_gemma":[0.0003961125,0.0002598029,0.0008184561,0.00003465286,0.00002459827,0.00001551847,0.0001277927,0.9923142,0.002878559,0.000005055027,0.002983814,0.0001414743],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5164503,0.0002149016,0.4809129,0.000007328431,0.00063824,0.0003494949,0.00001808411,0.00002834695,0.001380397],"genre_scores_gemma":[0.9863076,0.00008420002,0.01268665,0.0001117879,0.0001271832,0.000002676683,0.0005983424,0.00002139937,0.00006021604],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4698572,"threshold_uncertainty_score":0.6285062,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2113944588","doi":"10.1093/bioinformatics/btn433","title":"Accurate sequence-based prediction of catalytic residues","year":2008,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":85,"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":"Nankai University","keywords":"Support vector machine; Curse of dimensionality; Sequence (biology); Computer science; Classifier (UML); Protein structure prediction; Feature selection; Artificial intelligence; Biological system; Data mining; Pattern recognition (psychology); Protein structure; Chemistry; Biology; Biochemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.02821141345171289,"gpt":0.2624030186154391,"spread":0.2341916051637262,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001965857,0.0001582458,0.0001639965,0.00008781871,0.0001061629,0.00001199356,0.0002401312,0.0001505152,0.0000142338],"category_scores_gemma":[0.0002597765,0.0001421885,0.00008579824,0.0001447371,0.0001881718,0.00001779626,0.00007282638,0.0001084505,0.00003681927],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001864774,"about_ca_system_score_gemma":0.0002096762,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001326527,"about_ca_topic_score_gemma":0.000004286005,"domain_scores_codex":[0.9988642,0.000023092,0.0005599108,0.00009711723,0.0002453457,0.0002103603],"domain_scores_gemma":[0.9989862,0.00002001109,0.0003193919,0.0004607067,0.000140494,0.00007320621],"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":[0.001577343,0.001232331,0.3538381,0.006312343,0.001176217,0.00005293434,0.01507288,0.1254538,0.2429012,0.002539364,0.2164298,0.03341367],"study_design_scores_gemma":[0.003024219,0.001848285,0.03851151,0.0002011507,0.00009503387,0.0003010558,0.0005523268,0.5443331,0.3453241,0.00005258086,0.06484751,0.0009090563],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9414378,0.000130545,0.03953401,0.0001187483,0.000280164,0.0004288964,0.0002838111,0.00009670048,0.01768932],"genre_scores_gemma":[0.9678375,0.0001038654,0.03064948,0.0002277495,0.00008060606,0.000008977158,0.0007035214,0.0000170239,0.0003713224],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4188793,"threshold_uncertainty_score":0.579828,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2152856869","doi":"10.1186/1477-5956-9-s1-s4","title":"ATPsite: sequence-based prediction of ATP-binding residues","year":2011,"lang":"en","type":"article","venue":"Proteome Science","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":81,"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":"Natural Sciences and Engineering Research Council of Canada; Killam Trusts","keywords":"Support vector machine; Dihedral angle; Classifier (UML); Annotation; Computer science; Machine learning; Artificial intelligence; Matthews correlation coefficient; Sequence (biology); Sequence alignment; Computational biology; Data mining; Bioinformatics; Peptide sequence; Biology; Chemistry; Biochemistry; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.03824075508694257,"gpt":0.2718583389464778,"spread":0.2336175838595352,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006435507,0.00008264177,0.00007377737,0.0000982745,0.000126105,0.00001656167,0.0003816201,0.00005809019,0.00003177553],"category_scores_gemma":[0.000324552,0.0000728015,0.00003107904,0.0003050159,0.0004883211,0.00001585938,0.0001066258,0.00007682901,0.00001285411],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001760811,"about_ca_system_score_gemma":0.0001875859,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002520271,"about_ca_topic_score_gemma":0.000002087836,"domain_scores_codex":[0.9991034,0.00002113895,0.0001960461,0.0002067704,0.000265621,0.0002070563],"domain_scores_gemma":[0.9993392,0.000004355601,0.0001465449,0.0003183339,0.0001301408,0.00006137739],"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":[0.0000224483,0.00001695126,0.02517197,0.00003022865,0.000002810596,3.853473e-7,0.0003015946,0.00006214066,0.9735093,0.0001116478,0.00003130257,0.0007392925],"study_design_scores_gemma":[0.0001457206,0.0003139935,0.01793923,0.00002906367,0.000003886024,0.000005043104,0.00003511729,0.002516109,0.9780971,0.00004651946,0.0007844148,0.00008378549],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9871611,0.00001966778,0.005588845,0.00003295453,0.00009477264,0.0002383652,0.00001652244,0.00002485861,0.006822933],"genre_scores_gemma":[0.9625444,0.000004776683,0.03713305,0.00004572608,0.00003162445,0.00001695943,0.00001290445,0.000006451422,0.0002040633],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0315442,"threshold_uncertainty_score":0.2968759,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2085102470","doi":"10.1186/1471-2164-15-50","title":"Prediction of bacterial type IV secreted effectors by C-terminal features","year":2014,"lang":"en","type":"article","venue":"BMC Genomics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":80,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"National Institutes of Health; National Natural Science Foundation of China","keywords":"Effector; Biology; Computational biology; Secretion; DNA microarray; Gene; Genetics; Gene expression; Cell biology; Biochemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.006200473368906618,"gpt":0.2176059170049314,"spread":0.2114054436360248,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001610003,0.0001062624,0.0001131962,0.00002237986,0.00003379239,0.00001427399,0.0001349395,0.0001515764,0.00002386623],"category_scores_gemma":[0.0001661263,0.0001012785,0.00004879507,0.0000347675,0.00004080701,0.000002266182,0.00006546956,0.00007539165,0.000008195343],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000114069,"about_ca_system_score_gemma":0.00004009336,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009294056,"about_ca_topic_score_gemma":0.00001072493,"domain_scores_codex":[0.9994344,0.00006281871,0.0001796703,0.0001272913,0.00007044895,0.0001253792],"domain_scores_gemma":[0.9995329,0.00001699638,0.0001233843,0.0002385076,0.00004431717,0.00004391927],"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":[0.0001869897,0.00001529171,0.009257592,0.00007441395,0.00002216007,6.926103e-8,0.00007051454,0.0002031853,0.9810008,0.00002110929,0.008251247,0.0008965834],"study_design_scores_gemma":[0.001905306,0.002027294,0.03909225,0.00002668862,0.00008258614,0.00004632178,0.000049739,0.01057387,0.6554942,0.00003435848,0.2902422,0.0004252383],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9953283,0.00005781853,0.003159521,0.000005758247,0.0004101199,0.0001124772,0.00005369203,0.00001296655,0.0008593633],"genre_scores_gemma":[0.994257,0.00002025315,0.003882621,0.00004259086,0.0003526976,0.000003039165,0.001042437,0.00001895641,0.0003804476],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3255067,"threshold_uncertainty_score":0.4130018,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1496257230","doi":"10.1186/s12859-015-0586-0","title":"ProtDCal: A program to compute general-purpose-numerical descriptors for sequences and 3D-structures of proteins","year":2015,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":80,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; Universidad de San Buenaventura","keywords":"Computer science; Data mining; Sequence (biology); Java; Feature (linguistics); Sequence alignment; Software; Key (lock); Protein function prediction; Artificial intelligence; Theoretical computer science; Machine learning; Programming language; Protein function; Peptide sequence","retraction":null,"screen_n_in":null,"score":{"opus":0.03172182749760137,"gpt":0.3074146386683912,"spread":0.2756928111707899,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003449909,0.0002323421,0.0002770669,0.00008531394,0.00006992371,0.00007063879,0.0002792291,0.000173934,0.000001838739],"category_scores_gemma":[0.0004456703,0.0001876369,0.00007704661,0.0001525246,0.0001370003,0.00001889954,0.0002175604,0.00009953089,0.000003777455],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001888569,"about_ca_system_score_gemma":0.0002062964,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001940417,"about_ca_topic_score_gemma":0.000009259032,"domain_scores_codex":[0.9986406,0.00003576148,0.0005885141,0.0001657095,0.0002487717,0.0003206695],"domain_scores_gemma":[0.9988888,0.00001777544,0.0002735941,0.0003256272,0.000239656,0.0002545796],"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":[0.003608525,0.001333566,0.08849426,0.0152456,0.00100378,0.000004983217,0.0225468,0.08221702,0.03315035,0.01483366,0.09274741,0.6448141],"study_design_scores_gemma":[0.002004338,0.00556362,0.001350482,0.00008645164,0.00006371437,0.00009327011,0.000580967,0.7749156,0.02197147,0.0004769226,0.1921245,0.0007686365],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1694367,0.0001430437,0.8243211,0.00016136,0.0002413293,0.004615882,0.00008232175,0.00009896783,0.000899306],"genre_scores_gemma":[0.0294172,0.000006242099,0.9695728,0.000285419,0.0001232041,0.0002726596,0.0001400592,0.00002406393,0.0001582973],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6926986,"threshold_uncertainty_score":0.765161,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2143507938","doi":"10.1145/956750.956800","title":"Frequent-subsequence-based prediction of outer membrane proteins","year":2003,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":78,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Bacterial outer membrane; Subsequence; Support vector machine; Computational biology; Classifier (UML); Bacteria; Membrane protein; Computer science; Artificial intelligence; Biology; Bioinformatics; Machine learning; Biochemistry; Membrane; Mathematics; Gene; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.01055053056386303,"gpt":0.2280865789526886,"spread":0.2175360483888255,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001888597,0.00009668761,0.0000896571,0.00003363705,0.00002953948,0.000008461321,0.000100034,0.0001090945,0.0001832715],"category_scores_gemma":[0.0001556589,0.0000818679,0.00005897955,0.00006010253,0.00005759388,0.00000311568,0.00001493851,0.00006963839,0.00001188627],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008280776,"about_ca_system_score_gemma":0.00007449434,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001324168,"about_ca_topic_score_gemma":0.000007089957,"domain_scores_codex":[0.9993322,0.00005057118,0.0002271978,0.0001276126,0.0001272891,0.000135079],"domain_scores_gemma":[0.999497,0.000005310143,0.00009317716,0.0002909745,0.00007032444,0.00004323408],"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":[0.00002751244,0.00007618079,0.0142228,0.0000862284,0.00003662496,0.000001015143,0.00003646425,0.001317469,0.9808853,0.002150726,0.0006379659,0.0005217395],"study_design_scores_gemma":[0.0005116304,0.0002748061,0.0009596338,0.00001256124,0.000009519371,0.000008973685,0.0000181224,0.001361597,0.9752344,0.00004271703,0.02146751,0.00009848314],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8171511,0.00007872345,0.1029101,0.000160347,0.0002027009,0.0005328823,0.00004070929,0.00005030357,0.07887315],"genre_scores_gemma":[0.969466,0.000008325266,0.02904548,0.0002446443,0.00003346242,0.00001846222,0.00009551673,0.00001157009,0.001076536],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1523149,"threshold_uncertainty_score":0.3338476,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2065795346","doi":"10.1093/nar/gkn619","title":"Protein networks markedly improve prediction of subcellular localization in multiple eukaryotic species","year":2008,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":77,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Korea Advanced Institute of Science and Technology; National Chiao Tung University; National Institute of General Medical Sciences; McGill University","keywords":"Biology; Subcellular localization; Protein subcellular localization prediction; Computational biology; Genetics; Evolutionary biology; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.02705196244913349,"gpt":0.2706103783399174,"spread":0.2435584158907839,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009167715,0.0001184888,0.0001469557,0.0001645473,0.0001404289,0.00001525116,0.0002627668,0.0002304019,0.0000566925],"category_scores_gemma":[0.0006910334,0.0001156063,0.00005095622,0.0003725885,0.0003204636,0.00001118598,0.0002054278,0.0003830856,0.00001291157],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005100613,"about_ca_system_score_gemma":0.00008931385,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007297443,"about_ca_topic_score_gemma":0.00002696377,"domain_scores_codex":[0.9983441,0.0002433994,0.0003646498,0.0002405295,0.0004418303,0.0003654644],"domain_scores_gemma":[0.9991854,0.0000338401,0.00008074248,0.0004008534,0.0002313221,0.00006781825],"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":[0.0004103599,0.0002084008,0.5360231,0.0002292832,0.0000351451,0.0000138544,0.000450935,0.01467652,0.4430246,0.0001846757,0.003062514,0.001680595],"study_design_scores_gemma":[0.001636107,0.001134009,0.1579175,0.00009873036,0.000005246826,0.00001930408,0.0002608409,0.7104663,0.1134144,0.00005260619,0.01475214,0.0002428668],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9756109,0.0001843978,0.02059654,0.000050985,0.00006559394,0.0006043176,0.00001303323,0.00001660517,0.002857692],"genre_scores_gemma":[0.9962271,0.0001856083,0.001220954,0.00001827548,0.0001479921,0.00003287695,0.0001695675,0.00002620348,0.001971436],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6957898,"threshold_uncertainty_score":0.4714289,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4385373960","doi":"10.1093/bib/bbad289","title":"Artificial intelligence-aided protein engineering: from topological data analysis to deep protein language models","year":2023,"lang":"en","type":"review","venue":"Briefings in Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":77,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Institute of General Medical Sciences; Bristol-Myers Squibb Canada; Michigan State University Foundation; Nuclear Safety and Security Commission; Bristol-Myers Squibb; National Aeronautics and Space Administration; National Institutes of Health; National Science Foundation; Michigan Economic Development Corporation; National Institute of Allergy and Infectious Diseases; Pfizer","keywords":"Computer science; Artificial intelligence; Topological data analysis; Protein engineering; Natural language processing; Computational biology; Biology; Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.08793799256485617,"gpt":0.3524052727944185,"spread":0.2644672802295623,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009526258,0.000746408,0.001639092,0.0007406719,0.00008151499,0.0002254931,0.002148617,0.0009091995,0.00004377614],"category_scores_gemma":[0.001615425,0.0006641797,0.0004223166,0.001753305,0.00008070757,0.00004021627,0.002077955,0.0007920215,0.0002487048],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009004574,"about_ca_system_score_gemma":0.0002142516,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003676045,"about_ca_topic_score_gemma":0.0002973193,"domain_scores_codex":[0.9957688,0.00010477,0.002229529,0.000690665,0.0004946404,0.0007115305],"domain_scores_gemma":[0.9967106,0.00009972414,0.0006926263,0.002203423,0.00006822196,0.0002253884],"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":[0.00005133208,0.0001736085,0.000003363954,0.01080147,0.002423106,0.00004831041,0.001787795,0.02152747,0.0000740876,0.002504821,0.0007155444,0.9598891],"study_design_scores_gemma":[0.0001324859,0.0002351787,0.000002907473,0.004113905,0.001344774,0.00001723632,0.0003927659,0.6442308,0.000241463,0.0006495393,0.3466512,0.001987748],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.001115596,0.4356805,0.5528654,0.0002650018,0.0002716141,0.006450762,0.002124841,0.0004419897,0.0007843237],"genre_scores_gemma":[0.0002772762,0.498168,0.47043,0.0006328632,0.0007419036,0.0009189324,0.02792231,0.0003110139,0.0005976589],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9579014,"threshold_uncertainty_score":0.9995809,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3083386021","doi":"10.1101/2020.09.04.283929","title":"Self-Supervised Contrastive Learning of Protein Representations By Mutual Information Maximization","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":77,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Vector Institute; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research; Vector Institute; Microsoft Research","keywords":"Maximization; Computer science; Mutual information; Embedding; Artificial intelligence; Hyperparameter; Machine learning; Autoregressive model; Supervised learning; Contrast (vision); Mathematics; Artificial neural network","retraction":null,"screen_n_in":null,"score":{"opus":0.006008598428195527,"gpt":0.2124216015829576,"spread":0.2064130031547621,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003288266,0.0003857314,0.0003796164,0.0001288985,0.0001269699,0.0001223487,0.0004032066,0.0005280182,0.00002111493],"category_scores_gemma":[0.001099314,0.0004440311,0.0001295581,0.0002704829,0.00008666023,0.00004191892,0.0004689441,0.0006614967,0.00003136448],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006211838,"about_ca_system_score_gemma":0.0004028775,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002329782,"about_ca_topic_score_gemma":3.861695e-7,"domain_scores_codex":[0.997973,0.0002013676,0.0007548267,0.000422995,0.0003550734,0.000292764],"domain_scores_gemma":[0.9977142,0.00002334778,0.0008635235,0.0005964241,0.0006431088,0.000159408],"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":[0.0001131575,0.00009416912,0.005397572,0.001064921,0.0002878229,0.000001652327,0.0001294105,0.002642994,0.9888855,0.0003888594,0.0009813192,0.00001259633],"study_design_scores_gemma":[0.001619048,0.0004223996,0.007047886,0.0002505897,0.0001801703,3.875742e-8,0.00004813848,0.09015203,0.8701236,0.000002275559,0.02910033,0.001053513],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.733438,0.0004317411,0.261691,0.0003797138,0.0003832433,0.002422902,0.000645529,0.0004064252,0.0002014752],"genre_scores_gemma":[0.9661594,0.0001226342,0.0331315,0.0001358504,0.0001591897,0.0001660457,0.00005521385,0.00006222323,0.000007964288],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2327214,"threshold_uncertainty_score":0.9998012,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2074156599","doi":"10.1142/9789812776136_0058","title":"EPILOC: A (WORKING) TEXT-BASED SYSTEM FOR PREDICTING PROTEIN SUBCELLULAR LOCATION","year":2007,"lang":"en","type":"article","venue":"","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":74,"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":"Computer science; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.00840131759235885,"gpt":0.2408423958874599,"spread":0.2324410782951011,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008711293,0.0001344718,0.0001033154,0.00004969891,0.0001157768,0.00002959806,0.0001492139,0.0001620587,0.000005277613],"category_scores_gemma":[0.0002271959,0.0001220347,0.00006443464,0.0001030826,0.00002890936,0.000002325762,0.00003544135,0.00008453355,0.00001013951],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003290542,"about_ca_system_score_gemma":0.00006166938,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001900388,"about_ca_topic_score_gemma":0.00002562918,"domain_scores_codex":[0.99905,0.00002435666,0.0003203788,0.0001983895,0.0001323697,0.0002745003],"domain_scores_gemma":[0.9993305,0.00002773263,0.0001563867,0.0002898993,0.000129148,0.00006638563],"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":[0.0006727964,0.0001457244,0.02667527,0.001917794,0.0001490124,0.000004438816,0.0001596713,0.006866318,0.9403035,0.005382702,0.0015024,0.01622039],"study_design_scores_gemma":[0.001148131,0.0005018094,0.0006366537,0.0001502917,0.00003098894,0.00001237526,0.0002644744,0.1000778,0.8513375,0.00001329209,0.04550423,0.0003224461],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2394114,0.00008565042,0.753072,0.00009200226,0.0001114469,0.000758282,0.000002801886,0.00008515579,0.006381292],"genre_scores_gemma":[0.9616334,3.747686e-7,0.03684385,0.0001243702,0.0002683265,0.00005376545,0.0001783363,0.00002499726,0.0008726168],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.722222,"threshold_uncertainty_score":0.4976431,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}