{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002946774,0.000111659,0.0001506739,0.00002893342,0.0001413875,0.00002153936,0.0004424944,0.00005159308,0.00000618033],"category_scores_gemma":[0.00003640865,0.0000821224,0.00003012232,0.00009473172,0.0001462494,0.00002745775,0.0003515435,0.000163388,3.605458e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005223114,"about_ca_system_score_gemma":0.00009897304,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001122505,"about_ca_topic_score_gemma":0.00003480828,"domain_scores_codex":[0.999287,0.0001271883,0.0002252283,0.0001364003,0.00008164108,0.0001425386],"domain_scores_gemma":[0.9993184,0.00001767719,0.000209732,0.0003970931,0.0000454646,0.00001164108],"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":[0.0003184933,0.0001178055,0.001088022,0.000424161,0.00005991329,3.368701e-7,0.001373622,0.0002110675,0.9556966,0.03004223,0.000566741,0.01010093],"study_design_scores_gemma":[0.006933653,0.01350639,0.02476421,0.0001269934,0.0001385681,0.0001093473,0.01325207,0.01582539,0.5389338,0.04104047,0.3429895,0.002379646],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9972442,0.0001043443,0.0002440957,0.0001757173,0.00004852467,0.0008889425,0.001151743,0.000004033042,0.0001384053],"genre_scores_gemma":[0.9962243,0.000005234987,0.0006725699,0.0001999206,0.00007354309,0.000110669,0.00268945,0.000005685055,0.00001856883],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4167629,"threshold_uncertainty_score":0.3348854,"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."}}