{"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":"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"},"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."}}