{"id":"W1993731989","doi":"10.1016/j.jmb.2007.01.063","title":"Towards Fully Automated Structure-based Function Prediction in Structural Genomics: A Case Study","year":2007,"lang":"en","type":"article","venue":"Journal of Molecular Biology","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":80,"is_retracted":false,"has_abstract":false,"ca_institutions":"University Health Network; University of Toronto","funders":"National Institute of General Medical Sciences; European Commission","keywords":"Structural genomics; Computer science; Pipeline (software); Data mining; Schema (genetic algorithms); Protein structure database; Sequence (biology); Genomics; Function (biology); Gene ontology; Pace; Protein Data Bank; Artificial intelligence; Machine learning; Protein structure; Biology; Sequence database; Gene; Genome; Genetics","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":[0.0007679933,0.0001920841,0.000266504,0.000231027,0.00005524095,0.00002129453,0.0001736087,0.0003056207,0.00001580945],"category_scores_gemma":[0.00004657469,0.0001626724,0.0001254449,0.0001492681,0.00006199033,0.000006711643,0.00005901877,0.0002737682,8.992835e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007418193,"about_ca_system_score_gemma":0.000189237,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005075607,"about_ca_topic_score_gemma":0.0002507041,"domain_scores_codex":[0.9984968,0.0001235081,0.0007734769,0.0001938188,0.0001101083,0.0003023031],"domain_scores_gemma":[0.9990512,0.00001186562,0.0004233945,0.0002272718,0.0001797319,0.0001065213],"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":[0.001245473,0.0001479557,0.0151928,0.00002020781,0.0003212192,0.00160211,0.0002683823,0.008585366,0.9549177,0.000094442,0.0001694996,0.0174349],"study_design_scores_gemma":[0.05956909,0.06710544,0.196655,0.0001976084,0.001474338,0.07866066,0.01435437,0.1027491,0.4493195,0.01456677,0.01119024,0.004157997],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9480424,0.0004299289,0.05055143,0.00002772074,0.0006133403,0.0002445762,0.00001712432,0.00001219219,0.00006127091],"genre_scores_gemma":[0.9969142,0.000004689442,0.002467632,0.0002606676,0.0002764706,0.000001615972,0.00005161385,0.00001844641,0.000004646393],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5055982,"threshold_uncertainty_score":0.6633589,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005502434985270158,"score_gpt":0.2606332399751476,"score_spread":0.2551308049898775,"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."}}