{"id":"W4210826824","doi":"10.2142/biophysico.bppb-v19.0002","title":"Information quantity for secondary structure propensities of protein subsequences in the Protein Data Bank","year":2022,"lang":"en","type":"article","venue":"Biophysics and Physicobiology","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Japan Society for the Promotion of Science; Institute of Genetics; University of Tokyo","keywords":"Subsequence; Protein Data Bank; Protein Data Bank (RCSB PDB); Protein secondary structure; Sequence (biology); Protein structure; Proteome; Computer science; Biology; Computational biology; Mathematics; Bioinformatics; Genetics; Biochemistry","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003173891,0.0006244887,0.0008380585,0.01089778,0.0006668707,0.001464566,0.0005690861,0.0006639856,0.002016925],"category_scores_gemma":[0.02076817,0.0002481258,0.0007865881,0.008700467,0.0007975123,0.002239428,0.0007194466,0.0007701405,0.0006158272],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009159174,"about_ca_system_score_gemma":0.0005727657,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008453936,"about_ca_topic_score_gemma":0.001042613,"domain_scores_codex":[0.997169,0.0004001847,0.0004744793,0.0007094149,0.001103048,0.0001439595],"domain_scores_gemma":[0.9873261,0.008182679,0.001790952,0.001231745,0.001232627,0.0002359092],"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":[0.002476601,0.0005868465,0.3827044,0.002977336,0.001414378,0.001339877,0.001303119,0.05420212,0.1258525,0.03102935,0.008436524,0.3876769],"study_design_scores_gemma":[0.00009138419,0.001020047,0.4122565,0.000449018,0.0005888956,0.002795039,0.0007459894,0.4237587,0.07446898,0.05870455,0.024773,0.0003478615],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8062099,0.005455887,0.141513,0.0005243024,0.0001224966,0.0002023092,0.03763892,0.002323244,0.006009861],"genre_scores_gemma":[0.9116522,0.0009860958,0.06576169,0.00007165328,0.00009171432,0.0002827536,0.02042925,0.0001273948,0.0005972278],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01089778,"threshold_uncertainty_score":0.01678532,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01579465949709066,"score_gpt":0.2522218951302743,"score_spread":0.2364272356331836,"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."}}