{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001596772,0.0001406222,0.0001477731,0.000074622,0.00003848614,0.00003122758,0.0001378461,0.0002156809,0.000004174205],"category_scores_gemma":[0.00002916203,0.0001331625,0.00003565725,0.0001213809,0.00005200884,0.000024612,0.00006760472,0.00009012986,0.000001357207],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001137953,"about_ca_system_score_gemma":0.00002105458,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001595379,"about_ca_topic_score_gemma":0.000003406411,"domain_scores_codex":[0.9990959,0.0000260357,0.0003982164,0.0001625864,0.0001382323,0.0001790611],"domain_scores_gemma":[0.9994686,0.000003493381,0.0001609909,0.0002649118,0.00005262349,0.00004943848],"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":[0.00004644312,0.00009445987,0.000798903,0.0002667374,0.0000106391,1.351506e-7,0.0004494953,0.0001077326,0.9936398,0.0003562147,0.0005770813,0.003652345],"study_design_scores_gemma":[0.0007729838,0.00006356282,0.00235969,0.00002446296,0.000007723436,0.000003064505,0.0001594439,0.9573731,0.03850805,0.0001138952,0.0003766785,0.000237294],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7460905,0.0005725634,0.252047,0.00001466849,0.00001929029,0.0005327687,0.0001812028,0.000009999515,0.0005319935],"genre_scores_gemma":[0.9564377,0.0003561589,0.04193489,0.00008099013,0.00002431623,0.00005019784,0.0006424452,0.00001635885,0.0004569418],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9572654,"threshold_uncertainty_score":0.5430207,"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."}}