{"id":"W2161241698","doi":"10.1093/bioinformatics/bts060","title":"Predicting kinase substrates using conservation of local motif density","year":2012,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Kinase; Computer science; Motif (music); Computational biology; Training set; Artificial intelligence; Biology; Machine learning; Genetics; Physics","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":[0.0003207998,0.0001281013,0.000140747,0.00003553951,0.00007556781,0.00001622169,0.0001076746,0.0001615676,0.000007105199],"category_scores_gemma":[0.00002987771,0.0001201536,0.00006564093,0.00008132205,0.0001078318,0.00002482919,0.00009119278,0.00007367534,0.000006869238],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001698183,"about_ca_system_score_gemma":0.00005909282,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003216196,"about_ca_topic_score_gemma":0.0000126914,"domain_scores_codex":[0.9990718,0.00001477202,0.0004582923,0.00005930857,0.0001203453,0.0002755139],"domain_scores_gemma":[0.9992882,0.00001317305,0.0002666606,0.0002339815,0.00009948916,0.00009852411],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003317654,0.0005369151,0.6955696,0.00174332,0.0005695702,0.000001897022,0.005099587,0.009626519,0.2241188,0.004933796,0.006300804,0.05116741],"study_design_scores_gemma":[0.001101241,0.0002596862,0.02408954,0.0001116081,0.0001188526,0.00008990145,0.003784149,0.5748546,0.3915861,0.0001569309,0.003229006,0.0006184386],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8877548,0.000220993,0.1109338,0.00001179715,0.0001882462,0.0001219933,0.00001780632,0.00001011503,0.000740403],"genre_scores_gemma":[0.9813557,0.0000273873,0.01815849,0.0001632199,0.0001543606,0.000001599118,0.0001080849,0.00001013056,0.00002104984],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6714801,"threshold_uncertainty_score":0.489972,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01841955684306828,"score_gpt":0.23568615793772,"score_spread":0.2172666010946518,"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."}}