{"id":"W4393306343","doi":"10.1101/2024.03.26.586646","title":"ntRoot: Computational Inference of Human Ancestry at Scale from Genomic Data","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Forensic and Genetic Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"Canadian Institutes of Health Research; National Institutes of Health","keywords":"Inference; Scale (ratio); Data science; Computational biology; Computer science; Evolutionary biology; Biology; Artificial intelligence; Geography; Cartography","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":[0.004470287,0.001049429,0.001380649,0.00195721,0.000895899,0.002293454,0.002673754,0.001025754,0.008168941],"category_scores_gemma":[0.01999942,0.0009795116,0.001823735,0.001923432,0.001045534,0.002157767,0.002974853,0.002091062,0.002810128],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001035217,"about_ca_system_score_gemma":0.001990096,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009184004,"about_ca_topic_score_gemma":0.01627709,"domain_scores_codex":[0.9986166,0.0005022088,0.0000795802,0.0004267892,0.0003163205,0.00005856829],"domain_scores_gemma":[0.9933968,0.004886381,0.0003049715,0.000845699,0.0003493671,0.0002168716],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001592172,0.0002023361,0.03548362,0.001060966,0.001522764,0.0009787725,0.001010867,0.5694789,0.01001309,0.03508445,0.05421063,0.2893614],"study_design_scores_gemma":[0.00009806734,0.00003350514,0.001390061,0.0000386615,0.00005190659,0.0001079834,0.00008528741,0.968281,0.001439896,0.02375294,0.004693508,0.0000271778],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03819835,0.0004723661,0.9229226,0.0006926273,0.0001936761,0.0001509022,0.008201252,0.02698618,0.002181955],"genre_scores_gemma":[0.1658847,0.0003390393,0.8134509,0.000409499,0.0001376178,0.0003806308,0.01368904,0.003086642,0.002622061],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009184004,"threshold_uncertainty_score":0.02732784,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03681819833290514,"score_gpt":0.2997241585844774,"score_spread":0.2629059602515722,"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."}}