{"id":"W4416386037","doi":"10.1101/2025.11.17.688763","title":"10,239 whole genomes with multiomic and clinical health information as the Korean Multiomics Reference dataset","year":2025,"lang":"","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute of Aging","funders":"Ministry of SMEs and Startups; Ministry of Trade, Industry and Energy","keywords":"Genome; Inference; Genomics; Genomic information; Imputation (statistics); Genetic genealogy","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":[0.00181732,0.001446271,0.001307072,0.002391717,0.0006185999,0.001461201,0.00216336,0.001389985,0.009515166],"category_scores_gemma":[0.004121239,0.0007004153,0.001575086,0.006039885,0.0003392482,0.0006921316,0.00234312,0.001530953,0.007977018],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006127552,"about_ca_system_score_gemma":0.002186547,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01590228,"about_ca_topic_score_gemma":0.02205989,"domain_scores_codex":[0.9985706,0.0002676149,0.0001825713,0.0006413795,0.0001615691,0.0001762728],"domain_scores_gemma":[0.9981536,0.0002534408,0.0002246432,0.0007846743,0.0003446516,0.0002389641],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.004303784,0.0006728421,0.1480628,0.005984279,0.004727081,0.002515003,0.0004901778,0.01315133,0.04269445,0.005313513,0.6648988,0.107186],"study_design_scores_gemma":[0.001866595,0.0003635906,0.2546992,0.001029567,0.001877438,0.002904568,0.0006432429,0.007228737,0.01286356,0.005817602,0.7104278,0.0002781497],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.0217695,0.0007811543,0.002459685,0.0002017025,0.00006667509,0.00006259233,0.9733309,0.0005134473,0.0008144167],"genre_scores_gemma":[0.008436102,0.0001393111,0.002639499,0.00008726733,0.000008227107,0.00008006566,0.9882954,0.00005961408,0.0002544692],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01590228,"threshold_uncertainty_score":0.03183138,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01996843736115997,"score_gpt":0.2849430506182223,"score_spread":0.2649746132570623,"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."}}