{"id":"W1600589292","doi":"10.1002/gepi.21830","title":"Applications of Machine Learning and Data Mining Methods to Detect Associations of Rare and Common Variants with Complex Traits","year":2014,"lang":"en","type":"article","venue":"Genetic Epidemiology","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"David Geffen School of Medicine, University of California, Los Angeles; National Institute of General Medical Sciences; National Heart, Lung, and Blood Institute; National Institutes of Health","keywords":"Pedigree chart; Covariate; Imputation (statistics); Data mining; Computer science; Support vector machine; Artificial intelligence; Machine learning; Statistics; Missing data; Biology; Mathematics; Genetics; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026017,0.0001564643,0.0006391048,0.00007695304,0.000111624,0.000002689249,0.0002525265,0.00020188,0.000008697425],"category_scores_gemma":[0.003214146,0.0001407627,0.00003179009,0.0001331696,0.0001844729,0.000002404567,0.000346162,0.00010286,5.493893e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006172532,"about_ca_system_score_gemma":0.00003509628,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001866692,"about_ca_topic_score_gemma":0.0004413345,"domain_scores_codex":[0.9969947,0.001549282,0.0006205927,0.0005085195,0.00004938358,0.0002775185],"domain_scores_gemma":[0.9974935,0.001380486,0.0004773236,0.0004302047,0.0001031608,0.0001153215],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003010463,0.00002450168,0.6892781,0.00003800007,0.0001643848,1.16738e-7,0.00009535134,0.0006511358,0.04237676,0.0001964176,0.0002674056,0.2668777],"study_design_scores_gemma":[0.0004884619,0.0007051073,0.9732795,0.00001194415,0.0001042708,0.00002486921,0.00007830883,0.009043839,0.0004992189,0.001138296,0.01444381,0.0001824139],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3588218,0.00169181,0.6382776,0.0004987509,0.00001815934,0.0002865707,0.0001638987,0.000007851869,0.0002335196],"genre_scores_gemma":[0.5298075,0.0001926201,0.4694414,0.0002281078,0.00003692349,0.00002523925,0.0002305646,0.00001187739,0.00002575344],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.2840013,"threshold_uncertainty_score":0.5740136,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06426845486811747,"score_gpt":0.3841630564182604,"score_spread":0.3198946015501429,"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."}}