{"id":"W4318391569","doi":"10.1093/bioinformatics/btad063","title":"Efficient penalized generalized linear mixed models for variable selection and genetic risk prediction in high-dimensional data","year":2023,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Medical Research Council; Compute Canada","keywords":"Generalized linear mixed model; Lasso (programming language); Feature selection; Genome-wide association study; Curse of dimensionality; Linear model; Generalized linear model; Computer science; Mixed model; Binary number; Model selection; Covariance; Mathematics; Statistics; Artificial intelligence; Biology; Single-nucleotide polymorphism","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":[0.0007368076,0.000127645,0.0001869524,0.0001001505,0.0001343381,0.00001485121,0.0001342723,0.0001944707,0.000005821822],"category_scores_gemma":[0.0003491574,0.0001201169,0.00003097821,0.0002055995,0.00002705961,0.000006367176,0.000187404,0.00006718906,0.0000089429],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002103943,"about_ca_system_score_gemma":0.00008947246,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009425078,"about_ca_topic_score_gemma":0.00005395517,"domain_scores_codex":[0.9988164,0.00007934401,0.0004738013,0.0002471003,0.0001048799,0.0002785259],"domain_scores_gemma":[0.9993118,0.0000591531,0.0001803477,0.0002991047,0.00009019005,0.00005941354],"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":[0.00009079873,0.00004314849,0.006132552,0.00004921412,0.00006973992,2.413555e-7,0.00006755425,0.9758844,0.004016983,0.0002017705,0.0119662,0.001477328],"study_design_scores_gemma":[0.001403768,0.00012024,0.01630202,0.000007782591,0.00003818384,0.000006735571,0.00003478477,0.9794391,0.0001782517,0.0008256307,0.001521181,0.0001223216],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8115708,0.0001004361,0.1870868,0.00006637003,0.0001910854,0.0003757696,0.0005506019,0.00002715319,0.00003094976],"genre_scores_gemma":[0.5097656,0.0003408972,0.4842314,0.0001446565,0.0002148965,0.00008590043,0.004893073,0.00002662501,0.0002969478],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3018053,"threshold_uncertainty_score":0.4898224,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02586253173424735,"score_gpt":0.2652881851989897,"score_spread":0.2394256534647424,"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."}}