{"id":"W4391913886","doi":"10.1101/2024.02.14.580313","title":"Multi-ancestry polygenic risk scores using phylogenetic regularization","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Polygene; Phylogenetic tree; Polygenic risk score; Machine learning; Quantitative trait locus; Population; Biology; Expression quantitative trait loci; Artificial intelligence; Computer science; Set (abstract data type); Epistasis; Computational biology; Evolutionary biology; Genetics; Genotype; Gene; Single-nucleotide polymorphism","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":[0.007514411,0.0009372423,0.001112027,0.001259865,0.0007091782,0.001191501,0.00205875,0.001942376,0.00204257],"category_scores_gemma":[0.01797871,0.0007038151,0.001347612,0.001309554,0.001235673,0.001428959,0.001845832,0.002758892,0.0005614967],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00108104,"about_ca_system_score_gemma":0.001518133,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0069162,"about_ca_topic_score_gemma":0.008437808,"domain_scores_codex":[0.9981005,0.001167955,0.00006896327,0.0003619409,0.0002010281,0.00009961735],"domain_scores_gemma":[0.9922219,0.005719081,0.0005568108,0.0008626579,0.0004202088,0.0002193599],"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":[0.0001468267,0.00009354458,0.01382564,0.00008476595,0.0002735031,0.0002419771,0.0001620975,0.8511218,0.002241247,0.05764057,0.004267962,0.0699001],"study_design_scores_gemma":[0.00001215315,0.000009529957,0.0005613468,0.00001071943,0.00001022136,0.00003072892,0.000006308867,0.9736154,0.0001859405,0.0250375,0.0005104552,0.000009660573],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03182768,0.0001585722,0.9659066,0.0005635729,0.00001916279,0.00003131249,0.0002287148,0.0005684299,0.0006959963],"genre_scores_gemma":[0.5601955,0.000282704,0.4316296,0.0007082681,0.0001230441,0.0002852481,0.001446931,0.0005115712,0.004817013],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007514411,"threshold_uncertainty_score":0.0397405,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02176510471882714,"score_gpt":0.2594049330447823,"score_spread":0.2376398283259552,"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."}}