{"id":"W3216417141","doi":"10.1101/2021.11.18.21266545","title":"Global biobank analyses provide lessons for developing polygenic risk scores across diverse cohorts","year":2021,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research","funders":"Moonshot Research and Development Program; National Human Genome Research Institute; St. Olavs Hospital Universitetssykehuset i Trondheim; Japan Society for the Promotion of Science; National Institute on Aging; Fakultet for medisin og helsevitenskap, Norges Teknisk-Naturvitenskapelige Universitet; Japan Agency for Medical Research and Development; European Commission; National Institutes of Health; Eesti Teadusagentuur; Stiftelsen Kristian Gerhard Jebsen; Faculty of Medicine and Health, University of Sydney; Departamento Administrativo de Ciencia, Tecnología e Innovación (COLCIENCIAS)","keywords":"Biobank; Heritability; Genome-wide association study; Genetic architecture; Concordance; Genetic association; Missing heritability problem; Disease; Precision medicine; Medicine; Quantitative trait locus; Biology; Genetic variants; Bioinformatics; Genetics; Single-nucleotide polymorphism; Internal medicine; Environmental health; Population; Genotype","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006951625,0.0003751973,0.0005986877,0.00003542728,0.0003095623,0.00008547674,0.0004149649,0.000699484,0.000009555672],"category_scores_gemma":[0.00155504,0.0003637184,0.0004886513,0.0001477143,0.0001316866,0.000002684103,0.001234181,0.0001956268,0.000004195602],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001045286,"about_ca_system_score_gemma":0.0006055639,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007288383,"about_ca_topic_score_gemma":0.003539727,"domain_scores_codex":[0.9974156,0.000278384,0.0005253102,0.001019263,0.00014753,0.0006139405],"domain_scores_gemma":[0.9982363,0.0000629553,0.0005268747,0.0007373163,0.0003252162,0.0001113555],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003713134,0.00004541521,0.9865928,0.00009342165,0.0007986031,0.000006252389,0.00008067385,0.001811278,0.005582139,0.00003485605,0.001904634,0.003012754],"study_design_scores_gemma":[0.0004535502,0.00007348068,0.9862639,0.00006458187,0.0003040732,0.000009665695,0.0003604717,0.0003108937,0.006503632,0.0006846014,0.004407259,0.0005638796],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9490176,0.003454191,0.04432983,0.000678012,0.0008535256,0.0004776262,0.001110877,0.00002641451,0.00005195164],"genre_scores_gemma":[0.9791279,0.001944992,0.01622822,0.0002637299,0.0004150569,0.0002015485,0.00159905,0.00003126647,0.0001882512],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03011031,"threshold_uncertainty_score":0.9998815,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07198958106707898,"score_gpt":0.3958613972595285,"score_spread":0.3238718161924495,"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."}}