{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01294286,0.0008837365,0.0008348615,0.001651224,0.0004603375,0.001545777,0.001105423,0.0006886707,0.00289091],"category_scores_gemma":[0.04845593,0.0003099346,0.001028567,0.001778054,0.0007564686,0.0009380495,0.001306911,0.001462737,0.0007693798],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005930612,"about_ca_system_score_gemma":0.001876964,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003992182,"about_ca_topic_score_gemma":0.006076592,"domain_scores_codex":[0.9958996,0.002594645,0.0002296548,0.0005911943,0.0005471394,0.0001377804],"domain_scores_gemma":[0.9553549,0.03784435,0.001394716,0.003292948,0.001644101,0.0004691259],"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":[0.001410039,0.0003254729,0.3301838,0.0007068049,0.001658716,0.0002091233,0.000262086,0.5408087,0.002018785,0.008161432,0.01332631,0.1009286],"study_design_scores_gemma":[0.0001499326,0.0003116418,0.02125584,0.0001375363,0.00026483,0.0001527259,0.00009003143,0.9601912,0.002129342,0.01220545,0.003066141,0.00004521352],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7028105,0.002124212,0.2669273,0.001901073,0.0002698889,0.0002954601,0.01099686,0.007240279,0.007434552],"genre_scores_gemma":[0.8936554,0.0004202519,0.09375015,0.000342893,0.00008276815,0.0002738476,0.01048588,0.0004027499,0.0005860077],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01294286,"threshold_uncertainty_score":0.06844926,"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."}}