{"id":"W2227395312","doi":"10.1186/s13059-016-1037-6","title":"An expanded evaluation of protein function prediction methods shows an improvement in accuracy","year":2016,"lang":"en","type":"article","venue":"Genome biology","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":452,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"Lawrence Berkeley National Laboratory; National Center for Advancing Translational Sciences; National Institute of General Medical Sciences; KU Leuven; National Institute of Mental Health; Natural Sciences and Engineering Research Council of Canada; Instituto de Salud Carlos III; Biotechnology and Biological Sciences Research Council; Office of Science; Ministarstvo Prosvete, Nauke i Tehnološkog Razvoja; China Scholarship Council; Parkinson's UK; National Key Research and Development Program of China; U.S. National Library of Medicine; British Heart Foundation; Alexander von Humboldt-Stiftung; Fundação de Amparo à Pesquisa do Estado de São Paulo; Università degli Studi di Padova; U.S. Department of Energy; National Natural Science Foundation of China; Microsoft Research; Directorate for Biological Sciences; National Institutes of Health; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; FP7 Research Potential of Convergence Regions; Gordon and Betty Moore Foundation; National Science Foundation","keywords":"Gene ontology; Bottleneck; Function (biology); Context (archaeology); Annotation; Computer science; Set (abstract data type); Computational biology; Protein function prediction; Ontology; Field (mathematics); Biology; Machine learning; Data mining; Artificial intelligence; Protein function; Gene; Genetics; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.03559808,0.002816801,0.002174204,0.006335072,0.001252624,0.004478027,0.001456383,0.002144395,0.003401285],"category_scores_gemma":[0.06603228,0.0003863867,0.003923332,0.0049905,0.0009002892,0.003962524,0.002604717,0.002713176,0.002658209],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001605519,"about_ca_system_score_gemma":0.001504954,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003898598,"about_ca_topic_score_gemma":0.004003617,"domain_scores_codex":[0.9732167,0.008625888,0.002640102,0.005987136,0.008781042,0.0007492065],"domain_scores_gemma":[0.9094629,0.0615509,0.004010785,0.008943012,0.01498692,0.001045444],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.003699607,0.000756724,0.1975141,0.006680165,0.006564402,0.0003635826,0.0007943964,0.03940325,0.02829105,0.002990636,0.03629648,0.6766456],"study_design_scores_gemma":[0.0005802648,0.003670466,0.3407376,0.002909593,0.004543096,0.003146878,0.001234615,0.3939477,0.1003419,0.01734905,0.1308104,0.0007284797],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5973794,0.08943601,0.240562,0.004575689,0.001672643,0.0005533525,0.02576163,0.01936584,0.02069336],"genre_scores_gemma":[0.8151042,0.005599207,0.1491052,0.0009501061,0.0004264389,0.0003104685,0.02392659,0.002081432,0.002496357],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03559808,"threshold_uncertainty_score":0.1882629,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02814504185848216,"score_gpt":0.3355122508901335,"score_spread":0.3073672090316513,"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."}}