{"id":"W4416098230","doi":"10.1093/bioadv/vbaf287","title":"ntRoot: computational inference of human ancestry at scale from genomic data","year":2024,"lang":"en","type":"article","venue":"Bioinformatics Advances","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Canada's Michael Smith Genome Sciences Centre","funders":"Canadian Institutes of Health Research","keywords":"Inference; Scale (ratio); Genomics; Big data; Genetic data; Computational model","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":[0.0001625088,0.0001041892,0.0001572941,0.00003235545,0.0000774977,0.00001952525,0.0003282185,0.00008841229,0.00003762092],"category_scores_gemma":[0.0000651446,0.00009378715,0.00004104762,0.00006120998,0.0001066572,0.00001832628,0.0003485577,0.00005288025,0.00003227568],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000189965,"about_ca_system_score_gemma":0.00008583754,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002369874,"about_ca_topic_score_gemma":0.0001056051,"domain_scores_codex":[0.9991472,0.00002146564,0.000390032,0.0001947377,0.00009870868,0.0001479068],"domain_scores_gemma":[0.9993313,0.00007095164,0.0001455337,0.0003657867,0.00004532472,0.00004112372],"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":[0.0001117242,0.0002636554,0.4946676,0.001092715,0.0009260578,0.000005642132,0.001667136,0.05994702,0.2493836,0.002886649,0.05227872,0.1367695],"study_design_scores_gemma":[0.001327688,0.000704509,0.2694463,0.0002546045,0.0001801611,0.00002206162,0.0009479243,0.3832493,0.01571884,0.01727034,0.3097022,0.001176141],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9649525,0.006882804,0.02504881,0.0001131275,0.0002553089,0.0001009742,0.001010159,0.0000181214,0.001618185],"genre_scores_gemma":[0.9515955,0.0006782787,0.04384879,0.00008450243,0.0001453197,0.000005368394,0.003485098,0.000008799008,0.0001483621],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3233022,"threshold_uncertainty_score":0.3824529,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03687343643295704,"score_gpt":0.3371535968671262,"score_spread":0.3002801604341692,"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."}}