{"id":"W3095435122","doi":"10.1093/nar/gkaa931","title":"DescribePROT: database of amino acid-level protein structure and function predictions","year":2020,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":85,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"National Institute of General Medical Sciences; National Institutes of Health; National Science Foundation","keywords":"UniProt; Proteome; Biology; Computational biology; Function (biology); Protein sequencing; Sequence database; Amino acid; Peptide sequence; Sequence (biology); Web server; Computer science; Database; Bioinformatics; Data mining; Genetics; World Wide Web","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0002155451,0.0001294942,0.0001343857,0.000064753,0.0001577198,0.0000294938,0.0002301991,0.000199423,0.00008487216],"category_scores_gemma":[0.000324868,0.0001169093,0.00003922453,0.0002564586,0.0002792332,0.00001298764,0.0003727699,0.0003501657,0.000004453304],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001276654,"about_ca_system_score_gemma":0.0001186377,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003116001,"about_ca_topic_score_gemma":0.00002135505,"domain_scores_codex":[0.9986297,0.000118097,0.0001836481,0.0004236262,0.0003598045,0.0002851566],"domain_scores_gemma":[0.9991515,0.000008436521,0.00004587821,0.0003800746,0.0002363275,0.0001778227],"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":[0.0003077196,0.00001703138,0.001386507,0.0001132333,0.0000387234,0.000002391589,0.00008243103,0.000007663321,0.9900513,0.0005920295,0.001227693,0.006173238],"study_design_scores_gemma":[0.001029136,0.001559577,0.01212903,0.00004484305,0.00002436371,0.00001877615,0.0002550073,0.001332321,0.9674788,0.001122404,0.0147663,0.0002394893],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9811434,0.0005058493,0.01587064,0.0004816065,0.0000394962,0.0007253318,0.0005532025,0.00001921775,0.0006612152],"genre_scores_gemma":[0.9948054,0.00005602548,0.004278414,0.0001127006,0.0002519266,0.00004112153,0.0002500125,0.00002450056,0.0001799124],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02257258,"threshold_uncertainty_score":0.4767423,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04592291001100515,"score_gpt":0.3025316401942852,"score_spread":0.2566087301832801,"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."}}