{"id":"W2246311611","doi":"10.1371/journal.pone.0141603","title":"Computational Identification of MoRFs in Protein Sequences Using Hierarchical Application of Bayes Rule","year":2015,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":50,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Canadian Institutes of Health Research; Genome British Columbia; Michael Smith Health Research BC","keywords":"Bayes' theorem; Computer science; Identification (biology); Protein sequencing; Computational biology; Sequence (biology); Sequence alignment; Naive Bayes classifier; Artificial intelligence; Data mining; Bioinformatics; Peptide sequence; Biology; Bayesian probability; Genetics","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":[0.0002462697,0.00004532489,0.00009168659,0.00004664421,0.00001028771,0.000004636682,0.0000921618,0.00005302364,0.000001662295],"category_scores_gemma":[0.000174068,0.00004669187,0.00001473054,0.00008317883,0.00006513282,0.000005246749,0.00003527659,0.00005538988,0.000001757177],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001114372,"about_ca_system_score_gemma":0.00006030499,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004168326,"about_ca_topic_score_gemma":0.000004519423,"domain_scores_codex":[0.9993407,0.00004035797,0.0002877584,0.00008627925,0.0001872202,0.00005764137],"domain_scores_gemma":[0.9995294,0.00000785211,0.0001868724,0.0001205978,0.0001322046,0.00002305744],"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":[0.00002690237,0.0002468653,0.02025414,0.0001239621,0.00002163977,5.918616e-8,0.0001306156,0.01278252,0.9656643,0.0004014578,0.000002938443,0.0003446506],"study_design_scores_gemma":[0.0002878837,0.00009637478,0.008007556,0.0000522503,0.00001250687,0.000001042666,0.00004648612,0.32806,0.661122,0.002230236,0.000009646866,0.00007410026],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9764127,0.00003772587,0.02313439,0.00006082427,0.000004321696,0.000200729,0.00001055818,0.000003755267,0.0001350252],"genre_scores_gemma":[0.9471138,0.000001676085,0.05269631,0.000008244178,0.00002068729,0.00001345243,0.0001199422,0.000004571345,0.00002131442],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3152775,"threshold_uncertainty_score":0.1904039,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0328941551623359,"score_gpt":0.2779105196041278,"score_spread":0.2450163644417919,"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."}}