{"id":"W2951553270","doi":"10.1038/s41467-019-09718-5","title":"Polygenic prediction via Bayesian regression and continuous shrinkage priors","year":2019,"lang":"en","type":"article","venue":"Nature Communications","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1990,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute on Aging; Horizon 2020 Framework Programme; European Commission; National Cancer Institute; National Institutes of Health; Cancer Research UK; Government of Canada; Canadian Institutes of Health Research; Genome Canada; National Human Genome Research Institute; Genomic Health","keywords":"Biobank; Linkage disequilibrium; Computer science; Bayesian probability; Regression; Prior probability; Single-nucleotide polymorphism; Multivariate statistics; Genome-wide association study; Sample size determination; Genetic association; Statistics; Artificial intelligence; Machine learning; Bioinformatics; Biology; Mathematics; Genetics; Genotype","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007634204,0.001018271,0.001195375,0.001251648,0.0004408543,0.0009673887,0.001350708,0.001096618,0.001971386],"category_scores_gemma":[0.02233872,0.0005830342,0.001212148,0.001471751,0.001258593,0.001406283,0.001443398,0.002685991,0.0008715284],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004799577,"about_ca_system_score_gemma":0.001287746,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006635063,"about_ca_topic_score_gemma":0.006800611,"domain_scores_codex":[0.997358,0.001642293,0.0001025153,0.000513748,0.0002762091,0.0001072008],"domain_scores_gemma":[0.9878793,0.009705974,0.0006318378,0.0009448816,0.0006666947,0.0001713852],"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":[0.0004008299,0.0001513783,0.02418593,0.0001504713,0.0004413567,0.0002493957,0.0002400019,0.6929747,0.003914244,0.04003339,0.005295462,0.2319628],"study_design_scores_gemma":[0.00004527145,0.00003258499,0.001815328,0.00001738978,0.00002765148,0.00003590887,0.0000106103,0.9731051,0.0005974721,0.02361614,0.0006760836,0.00002040575],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04325775,0.0003141885,0.9540046,0.0004503491,0.00002844736,0.00004856322,0.0002772608,0.0007056402,0.0009132551],"genre_scores_gemma":[0.6597821,0.0006241739,0.3332169,0.0005104703,0.0001971788,0.0002618877,0.001821227,0.0002379997,0.003348041],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007634204,"threshold_uncertainty_score":0.04037404,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006026226217509595,"score_gpt":0.267390661110364,"score_spread":0.2613644348928544,"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."}}