{"id":"W4382795050","doi":"10.1007/s12561-023-09375-9","title":"Statistical Learning of Large-Scale Genetic Data: How to Run a Genome-Wide Association Study of Gene-Expression Data Using the 1000 Genomes Project Data","year":2023,"lang":"en","type":"article","venue":"Statistics in Biosciences","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"SickKids Foundation; Hospital for Sick Children; Public Health Ontario; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; University of Toronto","keywords":"Biostatistics; Genetic data; Genome-wide association study; Computational biology; Genome; Scale (ratio); Data mining; Genetic association; Computer science; Data science; Biology; Gene; Genetics; Single-nucleotide polymorphism; Geography; Cartography; Medicine; Population; Public health; Genotype","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":[0.01163665,0.002263208,0.001485829,0.002217769,0.001096615,0.004724076,0.004837217,0.001969781,0.08585914],"category_scores_gemma":[0.06945091,0.001644114,0.002540463,0.001625159,0.001488945,0.00478762,0.003134981,0.00534129,0.05107072],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009687112,"about_ca_system_score_gemma":0.001775295,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002825626,"about_ca_topic_score_gemma":0.003334829,"domain_scores_codex":[0.9958836,0.002026518,0.0003322468,0.0007312411,0.0008733626,0.0001528332],"domain_scores_gemma":[0.9546226,0.03445516,0.0009852096,0.003923332,0.004089761,0.001924014],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007161907,0.0005189195,0.004725944,0.001127043,0.0002765388,0.001195145,0.001673548,0.01615455,0.008923995,0.01646351,0.4997366,0.448488],"study_design_scores_gemma":[0.001465292,0.0004396434,0.01155759,0.001114946,0.000222839,0.001547548,0.001955717,0.2548532,0.0263831,0.2655161,0.4342102,0.0007338044],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003826078,0.0001549498,0.9099637,0.004705874,0.0007550975,0.0006405688,0.003437917,0.06905465,0.007461071],"genre_scores_gemma":[0.02035434,0.000233382,0.9573951,0.001768649,0.0002921924,0.001252329,0.002783475,0.009769355,0.006151019],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.08585914,"threshold_uncertainty_score":0.2872275,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07540431863356317,"score_gpt":0.37668960225481,"score_spread":0.3012852836212468,"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."}}