{"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,"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","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01944185,0.002887662,0.001613613,0.003430276,0.001663516,0.001990213,0.003676044,0.00207979,0.002066692],"category_scores_gemma":[0.0354337,0.0005061392,0.001365416,0.003975017,0.001339996,0.003071866,0.00230904,0.002273912,0.001352797],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002134306,"about_ca_system_score_gemma":0.002427778,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008282436,"about_ca_topic_score_gemma":0.008398658,"domain_scores_codex":[0.9882948,0.005112411,0.0005684212,0.001801398,0.003766594,0.0004562286],"domain_scores_gemma":[0.9639375,0.02443147,0.0008233972,0.003861931,0.006175441,0.0007702428],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.002936429,0.003014029,0.04868483,0.003528696,0.002474797,0.0004160765,0.0004247687,0.3673985,0.03027672,0.006846879,0.0455024,0.4884959],"study_design_scores_gemma":[0.0003317057,0.00143736,0.02010041,0.0001636932,0.0002126156,0.0002745228,0.0003243066,0.9346015,0.02531586,0.00514597,0.0119803,0.0001118768],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7601141,0.01824133,0.1767736,0.002355613,0.0007763591,0.001136948,0.01100346,0.01527446,0.01432418],"genre_scores_gemma":[0.7077769,0.003286543,0.2592014,0.0004707933,0.0001400301,0.0005741199,0.02569946,0.00102121,0.001829464],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9805582,"threshold_uncertainty_score":0.1028196,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01041951972596435,"score_gpt":0.3501743383184968,"score_spread":0.3397548185925325,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}