{"id":"W1979595209","doi":"10.1186/1471-2105-14-61","title":"ETHNOPRED: a novel machine learning method for accurate continental and sub-continental ancestry identification and population stratification correction","year":2013,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Alberta Health Services; Alberta Innovates; University of Alberta","funders":"Alberta Innovates; University of Alberta; Alberta Cancer Foundation","keywords":"International HapMap Project; Population stratification; Ancestry-informative marker; Single-nucleotide polymorphism; Population; Biology; Allele frequency; Classifier (UML); Evolutionary biology; Artificial intelligence; Genetics; Computational biology; Computer science; Genotype; Demography; Gene","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0004367044,0.0001298279,0.0001473755,0.00004763938,0.000181312,0.00007920227,0.00005206304,0.0001788318,0.000003101474],"category_scores_gemma":[0.0003891012,0.000125741,0.00003952593,0.00005593316,0.00003644977,0.00003616748,0.00003900809,0.00008170304,0.000002660577],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001439822,"about_ca_system_score_gemma":0.0000178422,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002217106,"about_ca_topic_score_gemma":0.0002030026,"domain_scores_codex":[0.99909,0.00004793958,0.0004449163,0.0001900622,0.00006414869,0.000162964],"domain_scores_gemma":[0.9992563,0.0000708551,0.0003831649,0.0001219187,0.0001139289,0.00005390016],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001098225,0.0001059234,0.3883442,0.0002300884,0.0001007207,3.306977e-8,0.0005723407,0.003255555,0.5100434,0.0002676876,0.002096572,0.09487361],"study_design_scores_gemma":[0.0004928825,0.00008688544,0.3948435,0.000007317975,0.00002419083,0.00001574123,0.0004836353,0.6009179,0.002645404,0.00008582869,0.0002700312,0.0001267025],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.555728,0.0001030554,0.4434726,0.00009247909,0.0001414784,0.0003928468,0.00002254784,0.00001390192,0.00003315526],"genre_scores_gemma":[0.8694583,0.0001024318,0.1281401,0.00006457997,0.00007682003,0.00009904298,0.001730222,0.00001160937,0.0003169164],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5976623,"threshold_uncertainty_score":0.512757,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02711538026442467,"score_gpt":0.3013754095818035,"score_spread":0.2742600293173789,"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."}}