{"id":"W2891083911","doi":"10.1186/s12863-018-0646-3","title":"Data mining and machine learning approaches for the integration of genome-wide association and methylation data: methodology and main conclusions from GAW20","year":2018,"lang":"en","type":"article","venue":"BMC Genetics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"U.S. National Library of Medicine; National Institute of General Medical Sciences; National Heart, Lung, and Blood Institute; National Institute on Aging","keywords":"Population stratification; Random forest; Artificial intelligence; Computer science; Machine learning; Linkage disequilibrium; Population; Data mining; Computational biology; Correlation; Biology; Genotype; Genetics; Mathematics; Gene; Medicine","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":[0.002140515,0.0001092245,0.0001986657,0.00002751063,0.0002224043,0.00001996172,0.0002095376,0.0001911238,0.00000292148],"category_scores_gemma":[0.004659649,0.00008830154,0.00001558172,0.00004539112,0.0001383141,0.000006737442,0.0007020455,0.00006368551,1.530824e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009664797,"about_ca_system_score_gemma":0.00004380607,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009463866,"about_ca_topic_score_gemma":0.002203768,"domain_scores_codex":[0.99865,0.0004533424,0.0002763867,0.0004086009,0.00006348807,0.0001482144],"domain_scores_gemma":[0.9974101,0.001724492,0.0002907951,0.0004556866,0.00008289642,0.00003599466],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00008662412,0.00002420268,0.8924575,0.00002584269,0.0002729656,6.014501e-8,0.0008974714,0.0003918489,0.06552833,0.0000602409,0.001115676,0.03913924],"study_design_scores_gemma":[0.0008390862,0.0003927887,0.657526,0.000008118332,0.0003576951,0.0000032771,0.0017574,0.3181323,0.002790218,0.001007713,0.01697176,0.000213639],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5823379,0.00481164,0.4116065,0.0003785126,0.00006147532,0.0002023928,0.0005807159,0.000003032213,0.00001786822],"genre_scores_gemma":[0.7503347,0.001876896,0.2445231,0.0001138677,0.0002202149,0.00001048699,0.002793763,0.00001297116,0.0001140232],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3177405,"threshold_uncertainty_score":0.5578372,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2717211955671607,"score_gpt":0.3598412288360815,"score_spread":0.08812003326892076,"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."}}