{"id":"W4293758551","doi":"10.3390/jpm12091394","title":"A Systematic Review of Polygenic Models for Predicting Drug Outcomes","year":2022,"lang":"en","type":"review","venue":"Journal of Personalized Medicine","topic":"Pharmacogenetics and Drug Metabolism","field":"Pharmacology, Toxicology and Pharmaceutics","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"BC Children's Hospital; University of British Columbia","funders":"Health Canada; Genome British Columbia; Provincial Health Services Authority; BC Children’s Hospital Foundation; BC Children's Hospital; Children's Hospital Foundation; Canadian Institutes of Health Research; Genome Canada","keywords":"Pharmacogenomics; Context (archaeology); Pharmacogenetics; Precision medicine; Personalized medicine; Polygenic risk score; Predictive modelling; Medicine; Computational biology; Bioinformatics; Computer science; Machine learning; Biology; Genetics; Genotype","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009521403,0.0006396694,0.008195264,0.0005744527,0.0001692295,0.000005621057,0.001046133,0.0002681194,0.002794173],"category_scores_gemma":[0.002915487,0.0004050409,0.00247334,0.0004734292,0.0002307097,0.0000923846,0.0001299425,0.001702378,0.000003234098],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001945533,"about_ca_system_score_gemma":0.0009075369,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006522106,"about_ca_topic_score_gemma":4.662642e-7,"domain_scores_codex":[0.9918243,0.002089789,0.004330786,0.0003097385,0.0009786622,0.0004666913],"domain_scores_gemma":[0.9873258,0.004992955,0.006448776,0.0003328042,0.0004646898,0.0004349658],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008345187,0.0001823532,0.000002090584,0.9534043,0.00439968,0.00004544711,0.0007658156,0.000008559881,0.000008516053,0.0002535009,0.008478959,0.03236734],"study_design_scores_gemma":[0.00213471,0.0001417543,6.544055e-8,0.3091555,0.03770267,0.0003864627,0.0001365894,0.0001449239,0.000001744659,0.000133625,0.6498504,0.0002115411],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000006587895,0.9920467,0.0001616519,0.0006047218,0.003273446,0.003017089,0.0003333063,0.00001529056,0.0005412006],"genre_scores_gemma":[0.000006676859,0.9942478,0.0002421053,0.002654418,0.0009509783,0.0003251121,0.00005852821,0.0000924077,0.001421979],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.6442488,"threshold_uncertainty_score":0.9998401,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2547634608513588,"score_gpt":0.5184883146027138,"score_spread":0.2637248537513551,"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."}}