{"id":"W3021517978","doi":"10.1371/journal.pgen.1008766","title":"Simultaneous SNP selection and adjustment for population structure in high dimensional prediction models","year":2020,"lang":"en","type":"article","venue":"PLoS Genetics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal; École de Technologie Supérieure; Jewish General Hospital; Memorial University of Newfoundland; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Ludmer Centre for Neuroinformatics and Mental Health; Compute Canada","keywords":"Lasso (programming language); Population; Mendelian randomization; Coordinate descent; Statistics; Multivariate statistics; Selection (genetic algorithm); Principal component analysis; Computer science; False positive paradox; Biology; Mathematics; Artificial intelligence; Algorithm; Genetics; Genetic variants","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":[0.006773782,0.001485191,0.001860499,0.0006788416,0.001105372,0.001158682,0.002849922,0.001422562,0.004618117],"category_scores_gemma":[0.01939382,0.00117667,0.001717858,0.001288492,0.001110662,0.001214489,0.002678601,0.002916076,0.002358456],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008091771,"about_ca_system_score_gemma":0.002685514,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006853845,"about_ca_topic_score_gemma":0.009165768,"domain_scores_codex":[0.996758,0.00208617,0.000101201,0.0006203863,0.0002917445,0.0001424561],"domain_scores_gemma":[0.9938539,0.004339441,0.0003959388,0.0007837054,0.00044326,0.0001837471],"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":[0.0003788409,0.0001604091,0.0129525,0.0002611799,0.0004977607,0.0005260791,0.000619899,0.6792824,0.006966519,0.05541609,0.011135,0.2318033],"study_design_scores_gemma":[0.00004784347,0.00004141479,0.001015225,0.00001424569,0.00003030942,0.00005794578,0.00001769125,0.9784412,0.0007666145,0.01764493,0.001901576,0.00002092735],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005475261,0.00006074886,0.9933124,0.0001063068,0.00001674083,0.00004992911,0.00008151617,0.0007121588,0.0001848592],"genre_scores_gemma":[0.1032172,0.0001376572,0.8921633,0.00023832,0.00008088543,0.0007605048,0.0008094914,0.0006454268,0.001947353],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006853845,"threshold_uncertainty_score":0.03582364,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0186174140985134,"score_gpt":0.2422887210013374,"score_spread":0.223671306902824,"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."}}