{"id":"W4280596677","doi":"10.21203/rs.3.rs-1643278/v1","title":"Fast and Accurate Bayesian Polygenic Risk Modeling with Variational Inference","year":2022,"lang":"en","type":"preprint","venue":"Research Square","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"Fonds de recherche du Québec – Nature et technologies; Medical Research Council; Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund","keywords":"Markov chain Monte Carlo; Inference; Computer science; Genome-wide association study; Bayesian probability; Bayesian inference; Posterior probability; Artificial intelligence; Machine learning; Statistics; Single-nucleotide polymorphism; 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":[0.00516106,0.001451303,0.002618546,0.001217336,0.0008686238,0.002185717,0.004184584,0.00304787,0.007024589],"category_scores_gemma":[0.02780041,0.002950618,0.001664723,0.001681829,0.001500901,0.003249424,0.003952541,0.004654911,0.002190082],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001425768,"about_ca_system_score_gemma":0.002980185,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01763496,"about_ca_topic_score_gemma":0.02016558,"domain_scores_codex":[0.9978828,0.00116836,0.0001007548,0.0003239436,0.000384772,0.0001393471],"domain_scores_gemma":[0.9864764,0.01137826,0.0003300299,0.0009428777,0.0005711772,0.0003013075],"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":[0.0002575346,0.000076706,0.001678079,0.0001804692,0.0002368245,0.0001683806,0.0001454253,0.7840367,0.001032657,0.1224775,0.007949534,0.08176018],"study_design_scores_gemma":[0.00002191446,0.000004839083,0.00008559061,0.00000923826,0.000009904336,0.0000215108,0.000005101744,0.9407475,0.0001379933,0.05826393,0.0006838207,0.000008608993],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002780031,0.0003023287,0.9952188,0.0003640525,0.00004393655,0.0000209577,0.0001688255,0.0005354594,0.0005655228],"genre_scores_gemma":[0.2050087,0.0006940546,0.7814492,0.0005668604,0.0003694099,0.0003180684,0.001549817,0.0009523549,0.009091512],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01763496,"threshold_uncertainty_score":0.03506464,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04840386599570677,"score_gpt":0.3817140802249877,"score_spread":0.3333102142292809,"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."}}