{"id":"W2097508746","doi":"10.1136/amiajnl-2012-001525","title":"An information-gain approach to detecting three-way epistatic interactions in genetic association studies","year":2013,"lang":"en","type":"article","venue":"Journal of the American Medical Informatics Association","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":105,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"U.S. National Library of Medicine; National Institute of Allergy and Infectious Diseases; National Institute of General Medical Sciences; National Institute of Arthritis and Musculoskeletal and Skin Diseases; National Eye Institute; National Institutes of Health","keywords":"Epistasis; Association (psychology); Genetic association; Computer science; Genome-wide association study; Information gain; Computational biology; Genetics; Artificial intelligence; Biology; Psychology; Gene; Genotype; Single-nucleotide polymorphism","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002766851,0.0001427635,0.0003953721,0.0001814553,0.0001335284,0.00006244439,0.0003899162,0.0001113603,0.00001011669],"category_scores_gemma":[0.01503053,0.0001056518,0.0001400427,0.0004506835,0.00004385168,0.00008598909,0.0001080663,0.0004079326,0.00002581484],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000767712,"about_ca_system_score_gemma":0.0001927172,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001970336,"about_ca_topic_score_gemma":0.0002530252,"domain_scores_codex":[0.99712,0.0003852657,0.001383294,0.00007648543,0.0007018886,0.0003330183],"domain_scores_gemma":[0.995369,0.0004368043,0.003035247,0.0002170044,0.0007664909,0.0001754838],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003320124,0.0002309857,0.8876298,0.00004558526,0.0005985089,3.476686e-7,0.005163033,0.02556385,0.001007714,0.00003369177,0.02876467,0.0509286],"study_design_scores_gemma":[0.0008288509,0.0004656956,0.933972,0.00007411759,0.00008109072,0.00002863116,0.01118828,0.04889872,0.0002196699,0.0006598208,0.003293749,0.0002893839],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9649475,0.00003525014,0.03127811,0.002775698,0.0003725369,0.0002665712,0.000005086101,0.00000580955,0.0003134055],"genre_scores_gemma":[0.9728678,0.0001163516,0.02239421,0.004255607,0.0002376855,0.00003807206,0.00001205163,0.000009774678,0.00006837677],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05063921,"threshold_uncertainty_score":0.9932663,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01370544303170031,"score_gpt":0.3037846948312116,"score_spread":0.2900792517995113,"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."}}