{"id":"W2209382794","doi":"10.1016/j.cels.2015.12.003","title":"Prediction of Synergism from Chemical-Genetic Interactions by Machine Learning","year":2015,"lang":"en","type":"article","venue":"Cell Systems","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":124,"is_retracted":false,"has_abstract":false,"ca_institutions":"Institute for Research in Immunology and Cancer; Université de Montréal; Lunenfeld-Tanenbaum Research Institute; Mount Sinai Hospital; McMaster University","funders":"National Institutes of Health; National Center for Research Resources; Wellcome Trust","keywords":"Computational biology; Machine learning; Biology; Random forest; Benchmark (surveying); Bayesian network; Predictive power; Artificial intelligence; Computer science; 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":[0.000253529,0.00009413686,0.0001575377,0.00005953551,0.00003095539,0.00006747353,0.0003509587,0.00003862348,0.000005434976],"category_scores_gemma":[0.00007223853,0.00009299217,0.00004385958,0.0002002883,0.00002034329,0.0002198828,0.0001373235,0.0001334816,0.00003509727],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007877748,"about_ca_system_score_gemma":0.00005640886,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007394394,"about_ca_topic_score_gemma":0.000001206623,"domain_scores_codex":[0.9987876,0.0002474841,0.0003050105,0.0002552188,0.0002908818,0.0001138393],"domain_scores_gemma":[0.9990912,0.0002640975,0.0001728201,0.0002638131,0.000105258,0.0001028296],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002554427,0.0003700408,0.006173283,0.0001273077,0.0001040295,0.00001056339,0.003581031,0.6373985,0.3194937,0.001747251,0.0195607,0.01140803],"study_design_scores_gemma":[0.0002705998,0.00003418286,0.0002992244,0.00003632799,0.000008735909,0.000008044674,0.00007101989,0.9698215,0.01638676,0.0004552104,0.01252047,0.00008795061],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2481059,0.00128643,0.7464805,0.00004610517,0.00139402,0.0001110217,0.00003558065,0.0001006096,0.00243989],"genre_scores_gemma":[0.987228,0.000005504869,0.01193317,0.000008971208,0.0001126135,0.00001445742,0.00005033142,0.000009351839,0.00063756],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7391222,"threshold_uncertainty_score":0.3792111,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03472847907015147,"score_gpt":0.253152565442247,"score_spread":0.2184240863720955,"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."}}