{"id":"W4410741742","doi":"10.1016/j.ajhg.2025.05.002","title":"Toward whole-genome inference of polygenic scores with fast and memory-efficient algorithms","year":2025,"lang":"en","type":"article","venue":"The American Journal of Human Genetics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill Genome Centre; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Alliance de recherche numérique du Canada; Canada Research Chairs; Canada First Research Excellence Fund; Canada Foundation for Innovation; McGill University","keywords":"Computer science; Inference; Genome-wide association study; Linkage disequilibrium; Scalability; Data mining; Imputation (statistics); Machine learning; Algorithm; Artificial intelligence; Biology; Single-nucleotide polymorphism; Genetics; Missing data","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":[0.0026626,0.001630342,0.001346057,0.001675817,0.0006496366,0.001981185,0.002945455,0.00117108,0.004255686],"category_scores_gemma":[0.01375162,0.001097616,0.001583558,0.002207983,0.0008633597,0.001843365,0.002393922,0.00262298,0.002165514],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001012134,"about_ca_system_score_gemma":0.002845206,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0180617,"about_ca_topic_score_gemma":0.02344877,"domain_scores_codex":[0.9987267,0.0004198278,0.00008113876,0.0003761174,0.0003154603,0.00008064842],"domain_scores_gemma":[0.9964289,0.002115119,0.0001863608,0.000692989,0.0004614753,0.0001151571],"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":[0.0003916731,0.0001675543,0.006663836,0.0002947316,0.0003628249,0.0002439097,0.0003296088,0.6248747,0.007887788,0.04084769,0.01661747,0.3013182],"study_design_scores_gemma":[0.00008527078,0.00001762169,0.0006162785,0.00001265663,0.00002230754,0.00003085094,0.00002522574,0.969455,0.001209486,0.02644735,0.002062357,0.00001555902],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01242463,0.0002990235,0.978674,0.0002823503,0.00005510051,0.00004821027,0.0005914851,0.006707484,0.0009176778],"genre_scores_gemma":[0.06906337,0.0001822991,0.92614,0.0002001156,0.00007755682,0.0001709577,0.002275932,0.0008029168,0.001086973],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0180617,"threshold_uncertainty_score":0.03591311,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0140474100275374,"score_gpt":0.2826539542890729,"score_spread":0.2686065442615355,"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."}}