{"id":"W1531430623","doi":"10.1186/1471-2105-3-1","title":"Identification and characterization of subfamily-specific signatures in a large protein superfamily by a hidden Markov model approach","year":2002,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":134,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research","funders":"National Cancer Institute; Canadian Institutes of Health Research; Howard Hughes Medical Institute","keywords":"Hidden Markov model; Subfamily; Biology; Structural Classification of Proteins database; Computational biology; Threading (protein sequence); Sequence alignment; Sequence motif; GenBank; Multiple sequence alignment; Sequence database; Protein family; Structural motif; Genetics; Protein structure; Artificial intelligence; Computer science; Peptide sequence; 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":[],"consensus_categories":[],"category_scores_codex":[0.0005844674,0.0002978457,0.0003490026,0.001048451,0.0003823779,0.0003795683,0.0004425898,0.0004593085,0.001106736],"category_scores_gemma":[0.0014894,0.0002340662,0.0006233755,0.0005365259,0.0002757301,0.0004756214,0.0003755088,0.0004406212,0.0004854517],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005637382,"about_ca_system_score_gemma":0.0007541185,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003130666,"about_ca_topic_score_gemma":0.003902465,"domain_scores_codex":[0.9998191,0.00004993584,0.00001393168,0.00005576236,0.00003754491,0.00002378538],"domain_scores_gemma":[0.9992498,0.000429534,0.00009521339,0.00008373986,0.00008572831,0.00005601637],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001270772,0.0005184981,0.1290104,0.0006082606,0.0004279807,0.0008389283,0.001220269,0.1999228,0.2005631,0.01829575,0.003557709,0.4437656],"study_design_scores_gemma":[0.00002437867,0.00007209707,0.01450926,0.00001903255,0.00006160981,0.0002211928,0.00007578635,0.9685444,0.00736321,0.008206159,0.0008804438,0.00002257761],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3562245,0.0004279305,0.6396078,0.000179608,0.00001447781,0.00008744701,0.0007464704,0.001552521,0.001159227],"genre_scores_gemma":[0.756962,0.0002227782,0.2398739,0.00004730328,0.00001438511,0.0001307327,0.001897001,0.0001131757,0.0007388118],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003130666,"threshold_uncertainty_score":0.00622493,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008643251258559427,"score_gpt":0.1988899288491742,"score_spread":0.1902466775906148,"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."}}