{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006341211,0.0001263047,0.0002980257,0.00004400411,0.00006282449,0.000006276811,0.0002045009,0.0003706759,0.00001928609],"category_scores_gemma":[0.0006397426,0.0001266333,0.00007202956,0.00006937713,0.0001921454,0.000001353578,0.0003074225,0.0001333449,0.000002165413],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003710086,"about_ca_system_score_gemma":0.000481631,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002462421,"about_ca_topic_score_gemma":0.0005183573,"domain_scores_codex":[0.9988523,0.0001005264,0.000410599,0.0003056281,0.00009593029,0.0002350525],"domain_scores_gemma":[0.9993067,0.0001178734,0.0001377205,0.0002736108,0.00004947634,0.0001145818],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004069127,0.0003486375,0.6454125,0.0008592817,0.0007327902,0.00001144801,0.0003845386,0.01095419,0.2498192,0.001298502,0.007486219,0.08228572],"study_design_scores_gemma":[0.005806569,0.0006727724,0.671194,0.0002390677,0.0003682049,0.0001172334,0.001270032,0.1879272,0.01127195,0.00571355,0.1140382,0.001381294],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9267558,0.00305123,0.06831739,0.0002832558,0.0002880332,0.000134311,0.00001814554,0.000006350888,0.001145455],"genre_scores_gemma":[0.969625,0.005872078,0.02262155,0.0008127526,0.00009577772,0.0000146966,0.00008892976,0.00001668568,0.0008525577],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2385473,"threshold_uncertainty_score":0.5163957,"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."}}