{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009994655,0.0001639206,0.0003282161,0.0001950622,0.0001070725,0.00002496487,0.0001665165,0.0001113043,0.000001088492],"category_scores_gemma":[0.0004037543,0.0001354024,0.00006503631,0.0006529597,0.00004722352,0.0000180185,0.00004329364,0.000110571,1.233086e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006788506,"about_ca_system_score_gemma":0.00003339377,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001201695,"about_ca_topic_score_gemma":0.003333724,"domain_scores_codex":[0.9983807,0.0001525796,0.0006408222,0.0004431904,0.0001414618,0.0002412731],"domain_scores_gemma":[0.9991898,0.00007914009,0.0003030091,0.0002294075,0.0001677635,0.00003090557],"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":[0.0001273091,0.0006534354,0.773056,0.00003914652,0.00035918,0.0001606655,0.005613109,0.2134109,0.005692212,0.00001644752,0.0001131864,0.0007583342],"study_design_scores_gemma":[0.001935396,0.0009719523,0.1928532,0.0000714575,0.001280083,0.001614634,0.09509441,0.7047271,0.000115989,0.0008652787,0.000004367112,0.0004661377],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9926241,0.0006323606,0.005734406,0.00008671746,0.00001930673,0.0008173331,0.00006799026,0.000005177063,0.00001263137],"genre_scores_gemma":[0.9956217,0.00002091711,0.004056897,0.00005589552,0.00007461508,0.00006105432,0.00009690329,0.000007869807,0.00000413502],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5802029,"threshold_uncertainty_score":0.5521548,"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."}}