{"id":"W2104873783","doi":"10.1093/bioinformatics/btm475","title":"PFRES: protein fold classification by using evolutionary information and predicted secondary structure","year":2007,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":122,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Protein tertiary structure; Protein secondary structure; Computer science; Pseudo amino acid composition; Similarity (geometry); Classifier (UML); Pattern recognition (psychology); Protein Data Bank (RCSB PDB); Fold (higher-order function); Protein superfamily; Protein structure prediction; Representation (politics); Feature vector; Structural Classification of Proteins database; Protein structure; Sequence (biology); Structural alignment; Data mining; Algorithm; Artificial intelligence; Sequence alignment; Biology; Peptide sequence; Amino acid; Genetics","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":[0.0002944054,0.0002152097,0.0001377569,0.0001289061,0.00019547,0.00008329767,0.0001786211,0.0003191696,0.00002529937],"category_scores_gemma":[0.0001980836,0.0002049834,0.00004076739,0.0001594257,0.0001167605,0.0001156277,0.0001310161,0.0002345238,0.000008141166],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005165589,"about_ca_system_score_gemma":0.000131484,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001287465,"about_ca_topic_score_gemma":0.000006678512,"domain_scores_codex":[0.9985908,0.00002300433,0.0006936755,0.0001106434,0.0002751153,0.0003067388],"domain_scores_gemma":[0.9990007,0.00001420307,0.0003830947,0.0003206131,0.0001525176,0.0001288937],"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":[0.0008285359,0.0002021013,0.03233182,0.00331084,0.0004787053,0.000002579436,0.005494997,0.0008239126,0.5722207,0.00276272,0.1080604,0.2734827],"study_design_scores_gemma":[0.003043147,0.0007773762,0.02749417,0.0001712224,0.00008754944,0.0002722591,0.003011813,0.4953915,0.0480703,0.0002346727,0.4200628,0.001383185],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9147561,0.0002366762,0.07972391,0.00007191006,0.0001615121,0.0007279984,0.0004501704,0.00008083306,0.003790896],"genre_scores_gemma":[0.9090248,0.00004172964,0.0867198,0.0005179283,0.0001363391,0.00000827685,0.003372542,0.00002309145,0.0001554495],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5241504,"threshold_uncertainty_score":0.835898,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006359821080226958,"score_gpt":0.233839707426869,"score_spread":0.2274798863466421,"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."}}