{"id":"W4400262165","doi":"10.1186/s13059-024-03314-7","title":"Benchmarking computational variant effect predictors by their ability to infer human traits","year":2024,"lang":"en","type":"article","venue":"Genome biology","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University; Lunenfeld-Tanenbaum Research Institute; University of Toronto","funders":"National Human Genome Research Institute; Canadian Institutes of Health Research; National Institutes of Health; Verily Life Sciences; National Heart, Lung, and Blood Institute; Canada Excellence Research Chairs, Government of Canada; Canada Foundation for Innovation; National Institute of General Medical Sciences; American Heart Association","keywords":"Biobank; Benchmarking; Human genetics; Trait; Biology; Correlation; Population; Computational biology; Genetics; Computer science; Demography; Gene; Mathematics","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":[0.0006948188,0.0001946821,0.000244336,0.00006551762,0.0001256677,0.00002106874,0.0001850467,0.0002894512,0.0001169158],"category_scores_gemma":[0.00011033,0.0001586553,0.0001154957,0.0001176983,0.00009011081,0.000002017339,0.0001342924,0.0001170691,0.00003195383],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004456142,"about_ca_system_score_gemma":0.00006626713,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000281857,"about_ca_topic_score_gemma":0.00001713079,"domain_scores_codex":[0.9984109,0.0003013192,0.0003071429,0.0005698957,0.00004807724,0.0003626414],"domain_scores_gemma":[0.9994848,0.0001220765,0.00004625527,0.0001847416,0.00004920593,0.0001129383],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00003140782,0.00006081766,0.04939435,0.00004566718,0.0002901291,0.000002955089,0.000268572,0.001946987,0.9281334,0.0007520104,0.009195297,0.00987842],"study_design_scores_gemma":[0.0006998074,0.003638613,0.6541077,0.00001957528,0.00007157237,0.0000511757,0.00004106321,0.001015557,0.00261934,0.00408208,0.3328911,0.0007623857],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9776002,0.0009931563,0.01928418,0.0004657354,0.0003588294,0.0002884974,0.0003827131,0.00003789079,0.0005887559],"genre_scores_gemma":[0.9961008,0.00002117804,0.0009578562,0.0004749823,0.0004710692,0.00006820288,0.001765162,0.00001935926,0.0001214199],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.925514,"threshold_uncertainty_score":0.6469775,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007968062456199848,"score_gpt":0.2681240136893525,"score_spread":0.2601559512331526,"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."}}