{"id":"W3155041571","doi":"10.1101/2021.04.09.439076","title":"Drug Sensitivity Prediction From Cell Line-Based Pharmacogenomics Data: Guidelines for Developing Machine Learning Models","year":2021,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Institute for Cancer Research; University of Toronto; Princess Margaret Cancer Centre; Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Pharmacogenomics; Machine learning; Sensitivity (control systems); Computer science; Artificial intelligence; Generalization; Drug response; Precision medicine; Set (abstract data type); Training set; Drug; Data set; Data mining; Bioinformatics; Medicine; Pharmacology; Biology; Engineering; Pathology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.02242511,0.002083216,0.002031929,0.005036003,0.0006977059,0.003805159,0.004752222,0.003454917,0.001841187],"category_scores_gemma":[0.08481928,0.00152176,0.00167147,0.003312122,0.001542646,0.002582726,0.002144869,0.0074582,0.004368096],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001049151,"about_ca_system_score_gemma":0.002577709,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004285236,"about_ca_topic_score_gemma":0.004886813,"domain_scores_codex":[0.9835451,0.01022514,0.002483719,0.0007994189,0.00278503,0.0001615727],"domain_scores_gemma":[0.9437534,0.03994421,0.002092017,0.004755865,0.008945525,0.0005089722],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002937742,0.000787905,0.009085664,0.002854301,0.0005835688,0.001056292,0.0003767941,0.3199514,0.01477417,0.087874,0.1292106,0.4331516],"study_design_scores_gemma":[0.00009504402,0.0001414782,0.002026281,0.001178636,0.0001372085,0.0003157972,0.00009838234,0.7592502,0.01536718,0.159525,0.06170793,0.0001568105],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001253726,0.001582181,0.9907022,0.00168035,0.00006862483,0.0003499745,0.001494911,0.001809535,0.00105859],"genre_scores_gemma":[0.01442023,0.001546412,0.9794511,0.0005179917,0.0001045142,0.0008692848,0.002257858,0.0003135391,0.0005190059],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02242511,"threshold_uncertainty_score":0.1185967,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1113435668353388,"score_gpt":0.3115824551846816,"score_spread":0.2002388883493428,"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."}}