{"id":"W4362696954","doi":"10.1016/j.ajhg.2023.03.009","title":"Fast and accurate Bayesian polygenic risk modeling with variational inference","year":2023,"lang":"en","type":"article","venue":"The American Journal of Human Genetics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":32,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill Genome Centre; McGill University","funders":"Fonds de recherche du Québec – Nature et technologies; Canadian Institutes of Health Research; Canada First Research Excellence Fund; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Inference; Polygenic risk score; Bayesian inference; Bayesian probability; Computer science; Artificial intelligence; Machine learning; Econometrics; Mathematics; Biology; Genetics","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":[0.005485889,0.001248603,0.002286234,0.001249916,0.0008956327,0.002161066,0.004302927,0.002770247,0.005264379],"category_scores_gemma":[0.02603351,0.002614732,0.00189686,0.001571318,0.001469546,0.003105993,0.004180336,0.004808564,0.001748385],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001274052,"about_ca_system_score_gemma":0.002917549,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01184733,"about_ca_topic_score_gemma":0.0130059,"domain_scores_codex":[0.9975528,0.001382512,0.0001073722,0.0003405312,0.0004762896,0.0001405401],"domain_scores_gemma":[0.9883377,0.009723117,0.00035175,0.0008833242,0.0004522892,0.0002518153],"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":[0.0002251152,0.000066467,0.001600113,0.0001648188,0.0002403473,0.0002094179,0.0001617379,0.6945472,0.001344637,0.2120097,0.005414573,0.08401581],"study_design_scores_gemma":[0.00002328205,0.000006490934,0.0001092123,0.00001134496,0.00001299627,0.00004440722,0.000005605876,0.9038217,0.0001842117,0.09495398,0.0008128012,0.00001392696],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002137942,0.000194719,0.9966475,0.0002330768,0.00002718365,0.00001479436,0.00008825302,0.0002815878,0.0003748956],"genre_scores_gemma":[0.1829813,0.0006799293,0.8070778,0.0004732064,0.0002555855,0.0003080363,0.0009083486,0.000632696,0.006683109],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01184733,"threshold_uncertainty_score":0.0290125,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07272685854056225,"score_gpt":0.3766116209136786,"score_spread":0.3038847623731163,"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."}}