{"id":"W4399641977","doi":"10.1038/s41588-024-01793-9","title":"Synthetic surrogates improve power for genome-wide association studies of partially missing phenotypes in population biobanks","year":2024,"lang":"en","type":"article","venue":"Nature Genetics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"National Human Genome Research Institute; National Heart, Lung, and Blood Institute; Natural Sciences and Engineering Research Council of Canada; National Cancer Institute; U.S. Department of Health and Human Services; National Institutes of Health; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Biobank; Imputation (statistics); Genome-wide association study; Missing data; Genetic association; Spurious relationship; Statistical power; Population; Trait; Biology; Data mining; Computational biology; Computer science; Statistics; Genetics; Machine learning; Single-nucleotide polymorphism; Mathematics; Genotype; Gene; Medicine","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":[0.1075381,0.001214697,0.002897335,0.001892677,0.001290417,0.004017352,0.003055541,0.003284623,0.004824389],"category_scores_gemma":[0.2897015,0.001470428,0.002483154,0.002820108,0.003128387,0.003867605,0.00569726,0.003926248,0.001002786],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005312245,"about_ca_system_score_gemma":0.001588296,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007835425,"about_ca_topic_score_gemma":0.0008210255,"domain_scores_codex":[0.9236592,0.06705226,0.00198451,0.004628121,0.002079497,0.0005964726],"domain_scores_gemma":[0.600935,0.3576129,0.008518405,0.02781079,0.003396369,0.001726408],"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":[0.01747363,0.001119564,0.2399727,0.00193311,0.00772842,0.002373039,0.001579576,0.3115202,0.008319146,0.1541692,0.01638196,0.2374294],"study_design_scores_gemma":[0.001824581,0.001128364,0.01992699,0.0002631256,0.001218386,0.001273259,0.0002299052,0.6293952,0.002852668,0.334181,0.007564372,0.00014223],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1881957,0.001848489,0.7992921,0.002861602,0.00052088,0.000224177,0.003363831,0.001398753,0.002294548],"genre_scores_gemma":[0.8620468,0.0005028622,0.1286969,0.001316724,0.0003145617,0.000425204,0.005179378,0.0002839576,0.001233557],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1075381,"threshold_uncertainty_score":0.5687224,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01198257031502786,"score_gpt":0.2997523580541439,"score_spread":0.287769787739116,"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."}}