{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00004874367,0.0001089633,0.0001329689,0.00002448445,0.00005057804,0.000005767293,0.00004187731,0.0001855723,0.000004969969],"category_scores_gemma":[0.0001244705,0.0001114088,0.00002633982,0.00005791989,0.00001247374,0.000002467574,0.00003717424,0.00005915051,4.321103e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002062232,"about_ca_system_score_gemma":0.00002332351,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001234461,"about_ca_topic_score_gemma":0.00009646862,"domain_scores_codex":[0.9992037,0.00004708786,0.00021493,0.0002945987,0.00007748667,0.0001621318],"domain_scores_gemma":[0.9996874,0.00002830491,0.00007288547,0.00007313817,0.00007329376,0.00006499863],"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":[0.0001143048,0.00005200157,0.05444616,0.00003291169,0.00005874722,2.999737e-7,0.0000791123,0.7442101,0.1966944,0.00007244849,0.0003650858,0.003874419],"study_design_scores_gemma":[0.0007035775,0.0005319203,0.0423651,0.000005072371,0.00004216312,0.000003315678,0.00001555578,0.9429007,0.0115747,0.001504546,0.0002169253,0.0001364013],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9936268,0.0006665794,0.004871421,0.0002590201,0.00007127621,0.0003560935,0.0001328124,0.0000104794,0.00000550823],"genre_scores_gemma":[0.9910479,0.0001612696,0.007399714,0.0003903349,0.0003073772,0.00002525511,0.0006352497,0.00001650428,0.00001642621],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1986906,"threshold_uncertainty_score":0.4543121,"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."}}