{"id":"W4416094924","doi":"10.21203/rs.3.rs-7889315/v1","title":"Advancing Human Population Genomics with DNA Foundation Models","year":2025,"lang":"","type":"preprint","venue":"Research Square","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"SickKids Foundation; Hospital for Sick Children","funders":"National Heart, Lung, and Blood Institute; Canadian Institutes of Health Research; Hospital for Sick Children; National Human Genome Research Institute; University of Toronto; Yale University","keywords":"Genomics; Human genetic variation; Population; Haplotype; Human genome; Functional genomics; Locus (genetics); Human genetics","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":[0.005930993,0.0008364262,0.001413609,0.001661058,0.0008145238,0.002004011,0.001730344,0.001688894,0.008067782],"category_scores_gemma":[0.04152736,0.000924187,0.001374275,0.002251587,0.001491776,0.003682917,0.002483861,0.003450461,0.001001782],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001426151,"about_ca_system_score_gemma":0.00196312,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008019524,"about_ca_topic_score_gemma":0.007254132,"domain_scores_codex":[0.9973291,0.002119937,0.00003450607,0.0002196989,0.0002155026,0.00008119748],"domain_scores_gemma":[0.9769976,0.01985769,0.0005551919,0.001506888,0.0005978599,0.0004847672],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002765954,0.00003750057,0.002399303,0.00007614209,0.0001302413,0.0001060278,0.0001507409,0.08813117,0.00009623088,0.8878099,0.004235498,0.0167996],"study_design_scores_gemma":[0.00001661698,0.000004185026,0.0002386417,0.00001736386,0.00001871132,0.00002108605,0.00002155591,0.1349721,0.00003411697,0.8622869,0.002363018,0.000005660958],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01276563,0.0008453031,0.9714551,0.004953241,0.0001964702,0.00002323102,0.0006373898,0.000237735,0.008885968],"genre_scores_gemma":[0.4785715,0.004043081,0.4963571,0.002315318,0.001257425,0.0004215244,0.001658326,0.0005053735,0.01487034],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008067782,"threshold_uncertainty_score":0.03136647,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04909327892281476,"score_gpt":0.3977744391025554,"score_spread":0.3486811601797406,"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."}}