{"id":"W2171565287","doi":"10.1186/1753-6561-3-s7-s60","title":"Predictive modeling in case-control single-nucleotide polymorphism studies in the presence of population stratification: a case study using Genetic Analysis Workshop 16 Problem 1 dataset","year":2009,"lang":"en","type":"article","venue":"BMC Proceedings","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Public Health Ontario; University of Toronto; Toronto Public Health","funders":"National Institute of General Medical Sciences; National Institutes of Health","keywords":"Population stratification; Univariate; Confounding; Cluster analysis; Multivariate statistics; Population; Computer science; Context (archaeology); Genetic model; Predictive modelling; Econometrics; Machine learning; Statistics; Data mining; Medicine; Artificial intelligence; Single-nucleotide polymorphism; Mathematics; Biology; Genetics; Genotype","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":[0.01892483,0.0007092036,0.001338103,0.001304098,0.0009747178,0.001217946,0.002763243,0.002500056,0.002182903],"category_scores_gemma":[0.03058686,0.0005168146,0.001986314,0.00180342,0.0008294023,0.0005018789,0.001019372,0.001753275,0.0005717125],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008894352,"about_ca_system_score_gemma":0.001222878,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005586925,"about_ca_topic_score_gemma":0.006203782,"domain_scores_codex":[0.9915763,0.006135998,0.0004504453,0.001046943,0.0006030544,0.0001872199],"domain_scores_gemma":[0.9766682,0.01832371,0.0009678176,0.002931393,0.0008604623,0.0002483101],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00319403,0.002498945,0.367192,0.001620724,0.002582476,0.005970223,0.0004871077,0.2665706,0.003764156,0.01360467,0.07501023,0.2575048],"study_design_scores_gemma":[0.00144586,0.0006248545,0.1006443,0.0002425922,0.000721004,0.004060672,0.0003215782,0.8158645,0.003379402,0.0488635,0.02366807,0.0001635681],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6205738,0.004466982,0.3245833,0.009249986,0.0006009408,0.001251561,0.03537883,0.001351046,0.002543611],"genre_scores_gemma":[0.7218859,0.0006354294,0.236645,0.0006861378,0.0002415913,0.001408488,0.03662773,0.00009484684,0.001775005],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01892483,"threshold_uncertainty_score":0.1000853,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08856272106233316,"score_gpt":0.3377235853513174,"score_spread":0.2491608642889842,"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."}}