{"id":"W3098791801","doi":"10.1101/107409","title":"A machine-learning heuristic to improve gene score prediction of polygenic traits","year":2017,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hamilton Health Sciences; University of Toronto; McMaster University; Population Health Research Institute","funders":"","keywords":"Linkage disequilibrium; Receiver operating characteristic; Biobank; Statistics; Machine learning; Artificial intelligence; Computer science; Heuristics; Polygene; Regression; Genome-wide association study; Quantitative trait locus; Single-nucleotide polymorphism; Mathematics; Biology; Bioinformatics; Genetics; Genotype; Gene","routes":{"ca_aff":true,"ca_fund":false,"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":[0.003887066,0.0008075678,0.001419148,0.001776838,0.0004937457,0.0007740507,0.001341071,0.001071316,0.001683386],"category_scores_gemma":[0.01263521,0.0004347529,0.0007133214,0.001102711,0.000797632,0.0008870584,0.0009254391,0.001076852,0.0003376121],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009044032,"about_ca_system_score_gemma":0.001566189,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003960754,"about_ca_topic_score_gemma":0.003245854,"domain_scores_codex":[0.9986734,0.0007521933,0.00007962383,0.00021062,0.0001540627,0.0001300356],"domain_scores_gemma":[0.9919336,0.006204414,0.0004978148,0.0004092573,0.000758977,0.0001958236],"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":[0.000225351,0.0002385462,0.01281814,0.00008173722,0.0001175845,0.0001702413,0.00009452945,0.8825336,0.001795458,0.006623087,0.002678237,0.09262348],"study_design_scores_gemma":[0.00002780658,0.0000375151,0.0005067048,0.000008476759,0.00001097954,0.00001675828,0.000006495676,0.9959534,0.0002818937,0.002991299,0.0001534881,0.000005223545],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2330737,0.000534433,0.7609468,0.000881574,0.0001189097,0.0002078429,0.0002321559,0.0011799,0.002824803],"genre_scores_gemma":[0.7953693,0.00008113194,0.2025385,0.0004398744,0.00009640861,0.000170656,0.0003636034,0.00007527388,0.0008651878],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003960754,"threshold_uncertainty_score":0.02055705,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01387832506519504,"score_gpt":0.2308679894144885,"score_spread":0.2169896643492935,"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."}}