{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001495149,0.0003146428,0.0004829711,0.00009561658,0.00120238,0.0000110236,0.0004906416,0.0003143568,0.00008803071],"category_scores_gemma":[0.002182003,0.0002549787,0.0002609194,0.0001944663,0.000242186,0.000005392385,0.0003377061,0.0002549129,0.000004277612],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000106856,"about_ca_system_score_gemma":0.0003059182,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001123827,"about_ca_topic_score_gemma":0.0001340047,"domain_scores_codex":[0.9960334,0.001289102,0.001028613,0.0006793079,0.0001449781,0.0008246296],"domain_scores_gemma":[0.9976012,0.0008260063,0.000623164,0.0006724937,0.0001336955,0.0001434408],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004572937,0.0002525594,0.3911414,0.00005899201,0.0004339989,0.000003729329,0.0004743644,0.1973062,0.09940435,0.0002089279,0.2557388,0.05451928],"study_design_scores_gemma":[0.00372374,0.003505903,0.4553018,0.00002428605,0.0004632752,0.000498192,0.001602577,0.1404241,0.00273857,0.007179949,0.3833392,0.001198422],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7299137,0.003546882,0.261574,0.002522715,0.0007304411,0.001026648,0.0004650893,0.00003305407,0.0001874651],"genre_scores_gemma":[0.9007312,0.0007584582,0.09097721,0.003677416,0.0006266197,0.0009830671,0.001280457,0.00006364966,0.0009019028],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1708175,"threshold_uncertainty_score":0.9999902,"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."}}