{"id":"W3126160703","doi":"10.1038/s41586-021-03205-y","title":"Sequencing of 53,831 diverse genomes from the NHLBI TOPMed Program","year":2021,"lang":"en","type":"article","venue":"Nature","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2295,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill Genome Centre; McGill University; University of British Columbia","funders":"National Institute on Minority Health and Health Disparities; National Institute of Environmental Health Sciences; National Institute of Arthritis and Musculoskeletal and Skin Diseases; National Institute of Allergy and Infectious Diseases; National Institute of General Medical Sciences; National Human Genome Research Institute; National Institute on Drug Abuse; National Institute of Diabetes and Digestive and Kidney Diseases; National Heart, Lung, and Blood Institute; National Institute on Aging; National Cancer Institute; U.S. Department of Health and Human Services; National Institutes of Health; U.S. Department of Veterans Affairs","keywords":"Imputation (statistics); Biology; 1000 Genomes Project; Genetics; Genome; Haplotype; Genomics; Whole genome sequencing; DNA sequencing; Structural variation; Copy-number variation; Computational biology; Genetic variation; Precision medicine; Human genetics; Phenotype; Genome-wide association study; Single-nucleotide polymorphism; Genotype; Gene; Missing data; Computer science","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001545571,0.0004511085,0.0005525782,0.002360193,0.0009532102,0.00130556,0.0007703615,0.0007860235,0.005467797],"category_scores_gemma":[0.002375599,0.0003005527,0.000612667,0.004363888,0.0002267271,0.0002278859,0.001065274,0.0008461915,0.002313985],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008932542,"about_ca_system_score_gemma":0.001134258,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01747464,"about_ca_topic_score_gemma":0.03266999,"domain_scores_codex":[0.9986246,0.000285047,0.00008297351,0.0004563558,0.0003857471,0.0001653936],"domain_scores_gemma":[0.9987343,0.0003987791,0.0001493039,0.0001940707,0.0003115606,0.0002120067],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.003719049,0.000458684,0.223091,0.002845364,0.002196335,0.003151629,0.001826742,0.00597601,0.1894056,0.003237186,0.2714369,0.2926555],"study_design_scores_gemma":[0.0007049407,0.0002652471,0.7478591,0.0005284019,0.0006604576,0.001771967,0.0004880233,0.004327085,0.01437332,0.001838417,0.2270985,0.00008447401],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.3444717,0.00513693,0.01683798,0.001040339,0.0001625021,0.0005182014,0.621353,0.001098597,0.00938066],"genre_scores_gemma":[0.2094811,0.001506995,0.03139793,0.002078578,0.0001303732,0.0005741914,0.7509681,0.000426808,0.00343596],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01747464,"threshold_uncertainty_score":0.03474587,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0126128075483058,"score_gpt":0.2774735486380148,"score_spread":0.264860741089709,"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."}}