{"id":"W2044679407","doi":"10.1114/1.1289470","title":"Automatic Classification of Protein Sequences into Structure/Function Groups via Parallel Cascade Identification: A Feasibility Study","year":2000,"lang":"en","type":"article","venue":"Annals of Biomedical Engineering","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":24,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"","keywords":"Cascade; Artificial intelligence; Weighting; Binary classification; Computer science; Hidden Markov model; Pattern recognition (psychology); Identification (biology); Set (abstract data type); Protein sequencing; Test set; Binary number; Algorithm; Nonlinear system; Machine learning; Peptide sequence; Mathematics; Support vector machine; Biology; Engineering; Genetics","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0004611733,0.0001296122,0.0001851663,0.00007700335,0.00003459498,0.00001105383,0.0002052967,0.0001371711,0.0001002544],"category_scores_gemma":[0.0002162001,0.0001172035,0.00006415612,0.0002157548,0.0001022988,0.00001353461,0.00003275751,0.0001159423,0.000003519801],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009408172,"about_ca_system_score_gemma":0.00003495533,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003580289,"about_ca_topic_score_gemma":0.000005432178,"domain_scores_codex":[0.9987121,0.00005742803,0.0005819111,0.000199672,0.0003028195,0.0001460417],"domain_scores_gemma":[0.9992833,0.00001307924,0.0001876773,0.0003516533,0.00008887792,0.00007545073],"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":[0.00006361301,0.0002867383,0.001603673,0.000453955,0.000121919,6.72117e-7,0.0004559811,0.002514943,0.9556223,0.00007472164,0.0000500376,0.03875147],"study_design_scores_gemma":[0.001316877,0.002350648,0.4026548,0.0001908471,0.00008654358,0.00001654732,0.0004122613,0.4167199,0.1729331,0.0007538022,0.00193817,0.0006265316],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9745021,0.0001140276,0.02471075,0.0001635553,0.00005732297,0.0003980574,0.000008411425,0.00002719466,0.00001860005],"genre_scores_gemma":[0.9962798,0.00001221696,0.003458457,0.00001641396,0.00006411935,0.00002429419,0.0001070414,0.00001095162,0.00002666696],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7826892,"threshold_uncertainty_score":0.4779422,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01709792020223794,"score_gpt":0.2927448131064455,"score_spread":0.2756468929042075,"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."}}