{"id":"W2922257230","doi":"10.1101/563866","title":"Sequencing of 53,831 diverse genomes from the NHLBI TOPMed Program","year":2019,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":423,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; University of British Columbia","funders":"National Heart, Lung, and Blood Institute","keywords":"Imputation (statistics); Biology; Genetics; 1000 Genomes Project; Genome; Genomics; Whole genome sequencing; Haplotype; Structural variation; Genome-wide association study; Computational biology; Precision medicine; DNA sequencing; Single-nucleotide polymorphism; Genotype; Gene; Computer science; Missing data","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":[0.001357063,0.0005493289,0.0005874651,0.001869964,0.0009416196,0.001440591,0.0006829157,0.0006578361,0.01338406],"category_scores_gemma":[0.002666792,0.000372385,0.0006644536,0.003744545,0.0002041202,0.0002399212,0.0008644224,0.0007972984,0.005826784],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008184762,"about_ca_system_score_gemma":0.001608078,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01837639,"about_ca_topic_score_gemma":0.0277792,"domain_scores_codex":[0.9989148,0.0002056506,0.00006863875,0.0003881523,0.0002676237,0.0001552426],"domain_scores_gemma":[0.999139,0.0002292869,0.00006521404,0.0002096484,0.0002282569,0.0001286649],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.002664778,0.0002650242,0.09788553,0.001449633,0.001229085,0.001304923,0.0008338699,0.004944553,0.06765069,0.003748378,0.5934093,0.2246143],"study_design_scores_gemma":[0.001245013,0.0003006895,0.3907798,0.0005274237,0.0007372464,0.001187804,0.0005876198,0.006792392,0.0226715,0.005236105,0.5698181,0.0001162],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.131432,0.001735644,0.01254445,0.001201348,0.0001374516,0.0003340052,0.8407829,0.001706229,0.01012598],"genre_scores_gemma":[0.07008123,0.000560915,0.01627593,0.000797726,0.00007822096,0.0003682614,0.9071733,0.0004885492,0.004175866],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01837639,"threshold_uncertainty_score":0.04477412,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01898156326133077,"score_gpt":0.2397284785358168,"score_spread":0.220746915274486,"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."}}