{"id":"W3189151603","doi":"10.1093/bib/bbab294","title":"Drug sensitivity prediction from cell line-based pharmacogenomics data: guidelines for developing machine learning models","year":2021,"lang":"en","type":"review","venue":"Briefings in Bioinformatics","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":63,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Institute for Cancer Research; University of Toronto; Princess Margaret Cancer Centre; Simon Fraser University","funders":"Canadian Institutes of Health Research","keywords":"Pharmacogenomics; Machine learning; Sensitivity (control systems); Computer science; Drug response; Generalization; Artificial intelligence; Precision medicine; Set (abstract data type); Drug; Training set; Task (project management); Data mining; Medicine; Pharmacology; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008426174,0.0005338655,0.001073958,0.0001313702,0.0001383335,0.0001486098,0.0004452647,0.0004262612,0.000002328428],"category_scores_gemma":[0.0007780729,0.0005580261,0.0002941901,0.0001800085,0.00004511981,0.00002489704,0.000665502,0.0003715755,0.000003538113],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001466444,"about_ca_system_score_gemma":0.001437818,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003332844,"about_ca_topic_score_gemma":0.000246439,"domain_scores_codex":[0.9973024,0.00008527927,0.00143424,0.0005946801,0.0001833494,0.0004000345],"domain_scores_gemma":[0.9976951,0.0003201466,0.0007699548,0.0007485633,0.0003769893,0.00008922444],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006617941,0.0001424917,0.00001759791,0.01567438,0.0004044516,0.00002025435,0.0001830952,0.04379559,0.0001840371,0.00006899758,0.03465298,0.9047899],"study_design_scores_gemma":[0.0005494982,0.00002252764,1.09657e-7,0.001782405,0.000276561,0.000008977541,0.00001978661,0.2990856,0.00049612,0.00002060619,0.6973162,0.0004215716],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0000521252,0.782591,0.2090403,0.0001227856,0.0003902645,0.0007078568,0.007019878,0.0000245317,0.00005127278],"genre_scores_gemma":[0.000009544373,0.8178,0.1333295,0.001163903,0.0005770548,0.00005717553,0.04692561,0.00008356819,0.00005365175],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9043684,"threshold_uncertainty_score":0.9996871,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1381740203395102,"score_gpt":0.3515715457664991,"score_spread":0.2133975254269888,"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."}}