{"id":"W4410401306","doi":"10.1186/s12920-025-02154-z","title":"Dynamic clustering of genomics cohorts beyond race, ethnicity—and ancestry","year":2025,"lang":"en","type":"article","venue":"BMC Medical Genomics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"National Cancer Institute; Breast Cancer Research Foundation","keywords":"Genomics; Cluster analysis; Biology; Trait; Race (biology); Computational biology; Genetics; Evolutionary biology; Computer science; Genome; Machine learning; Gene","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004392316,0.0003430381,0.0005353084,0.002608363,0.001064183,0.002130808,0.001045397,0.0005876385,0.001316406],"category_scores_gemma":[0.00958883,0.0002285867,0.001145439,0.002327516,0.001094609,0.0008723538,0.002326595,0.001064298,0.0003809313],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001102827,"about_ca_system_score_gemma":0.0011301,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00838605,"about_ca_topic_score_gemma":0.01133563,"domain_scores_codex":[0.9977703,0.000889648,0.000114463,0.0008752842,0.0001966241,0.0001537717],"domain_scores_gemma":[0.995277,0.001513984,0.0008823111,0.001473834,0.0005397192,0.0003131439],"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":[0.0004755159,0.0001232609,0.8001896,0.0003388676,0.00143144,0.000479731,0.003456548,0.03153341,0.01579662,0.02768719,0.008408143,0.1100798],"study_design_scores_gemma":[0.00005666907,0.0001611698,0.7496108,0.0002032516,0.0005096971,0.0007846968,0.002833855,0.1197239,0.004169937,0.09797303,0.02383882,0.0001341162],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7339308,0.001808544,0.2516717,0.001934791,0.000182228,0.000335605,0.004676243,0.0006369009,0.004823148],"genre_scores_gemma":[0.9411263,0.0003204906,0.05281557,0.0004370168,0.00006484008,0.0001891528,0.003896277,0.000147733,0.001002543],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00838605,"threshold_uncertainty_score":0.02322906,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01367139958859318,"score_gpt":0.2935983176937255,"score_spread":0.2799269181051323,"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."}}