{"id":"W4308603651","doi":"10.1002/gepi.22505","title":"Sparse prediction informed by genetic annotations using the logit normal prior for Bayesian regression tree ensembles","year":2022,"lang":"en","type":"article","venue":"Genetic Epidemiology","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institute on Aging; Canadian Institutes of Health Research; National Institutes of Health; Alzheimer's Disease Neuroimaging Initiative; BioClinica; National Heart, Lung, and Blood Institute; U.S. Department of Defense; University of Minnesota; Alzheimer's Association","keywords":"Computer science; Overfitting; Bayesian probability; Inference; Bayesian inference; Machine learning; Artificial intelligence; Tree (set theory); Generalized linear model; Regression; Linkage disequilibrium; Prior probability; Data mining; Single-nucleotide polymorphism; Statistics; Biology; Mathematics; Genetics; Artificial neural network","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006427926,0.001246931,0.002541717,0.001350813,0.0008306143,0.001493296,0.002497507,0.001981713,0.003272356],"category_scores_gemma":[0.01797084,0.001188537,0.001534881,0.001560284,0.001150957,0.002041772,0.002071382,0.003608258,0.001108011],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001310101,"about_ca_system_score_gemma":0.001628125,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01363967,"about_ca_topic_score_gemma":0.017239,"domain_scores_codex":[0.9979658,0.001304377,0.0000691622,0.0002243715,0.0002807769,0.0001556123],"domain_scores_gemma":[0.9892294,0.008833859,0.000413043,0.0004640974,0.0007605856,0.0002989311],"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":[0.00007342314,0.00003412452,0.0009006202,0.00003721042,0.00005763658,0.00004747413,0.00007178867,0.9460296,0.0003198628,0.0207901,0.001465778,0.03017237],"study_design_scores_gemma":[0.000005997215,0.000005125543,0.00005062918,0.000005521069,0.000004341433,0.000005240935,0.000002951419,0.9901208,0.00004494241,0.009563195,0.0001864059,0.000004881963],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01035568,0.0002982163,0.9877038,0.0002979647,0.00003550342,0.00003331887,0.0001358055,0.0004480182,0.0006918142],"genre_scores_gemma":[0.5352971,0.001298717,0.4526088,0.0006672892,0.0004087884,0.0005615809,0.00194328,0.0004636475,0.006750919],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01363967,"threshold_uncertainty_score":0.03399456,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04028623542101332,"score_gpt":0.3143453019881302,"score_spread":0.2740590665671168,"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."}}