{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002390675,0.0007911774,0.0007123808,0.0006778696,0.0008830694,0.001537714,0.001526532,0.001925209,0.001628735],"category_scores_gemma":[0.008554515,0.0004567139,0.0007248973,0.001415899,0.0008880964,0.001659452,0.001105944,0.001213063,0.000776818],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006463043,"about_ca_system_score_gemma":0.001124448,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005690222,"about_ca_topic_score_gemma":0.007270483,"domain_scores_codex":[0.99882,0.0004584373,0.00005723795,0.0001499847,0.0004355708,0.00007867186],"domain_scores_gemma":[0.9931895,0.004824818,0.00017929,0.001029505,0.0006776234,0.00009945864],"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":[0.001306894,0.001061635,0.01937392,0.001074442,0.0001805254,0.006128337,0.001774967,0.300663,0.05541823,0.02634128,0.01721959,0.5694572],"study_design_scores_gemma":[0.0001268287,0.0001723514,0.002810277,0.00003255452,0.00006146914,0.001361106,0.000411852,0.9327735,0.02684111,0.02752906,0.007847372,0.00003254623],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5116183,0.0009745713,0.4655395,0.003463103,0.00004998494,0.0003229371,0.001926774,0.008865618,0.007239137],"genre_scores_gemma":[0.5746841,0.0003476625,0.4211642,0.0001648817,0.00001688456,0.00006030632,0.001621789,0.0003583062,0.001581875],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005690222,"threshold_uncertainty_score":0.01264328,"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."}}