{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003631227,0.001066815,0.001200626,0.001941485,0.0008262065,0.0008740878,0.001943351,0.001103889,0.001533733],"category_scores_gemma":[0.006862585,0.0003880661,0.001108655,0.001238305,0.0005057129,0.000759042,0.001883791,0.002282901,0.0007445258],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000669747,"about_ca_system_score_gemma":0.001198437,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004694877,"about_ca_topic_score_gemma":0.006798868,"domain_scores_codex":[0.9983381,0.000581977,0.0001377928,0.000491975,0.0003299717,0.0001201074],"domain_scores_gemma":[0.9978938,0.00103474,0.0001585602,0.0003298566,0.0004878333,0.00009521749],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003246771,0.0001976444,0.02849413,0.0001075925,0.0004158099,0.0002315234,0.0002225268,0.102551,0.004154543,0.003745332,0.01431191,0.8452433],"study_design_scores_gemma":[0.00005840837,0.00005541016,0.003157735,0.00002856556,0.00004781586,0.0001367228,0.00005413526,0.9824906,0.001837501,0.007374756,0.004731692,0.00002654342],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03870263,0.0008443004,0.9547751,0.0004078065,0.0001976365,0.0001426678,0.0009217711,0.002870204,0.001137896],"genre_scores_gemma":[0.3563651,0.0003142773,0.6340738,0.0008701904,0.0002214173,0.000527986,0.004094493,0.0003135698,0.003219181],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004694877,"threshold_uncertainty_score":0.01920402,"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."}}