{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T19:27:16Z","timestamp":1764617236660,"version":"3.46.0"},"reference-count":29,"publisher":"Public Library of Science (PLoS)","issue":"12","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000051","name":"National Human Genome Research Institute","doi-asserted-by":"publisher","award":["R01HG010140"],"award-info":[{"award-number":["R01HG010140"]}],"id":[{"id":"10.13039\/100000051","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01MH124244"],"award-info":[{"award-number":["R01MH124244"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>\n                    Recent genome-wide association studies (GWAS) have uncovered the genetic basis of complex traits, but show an under-representation of non-European descent individuals, underscoring a critical gap in genetic research. Prediction models trained primarily on European ancestry often fail to generalize to diverse populations, leading to reduced accuracy and potential health disparities. Here, we assess whether incorporating interaction modeling and pretraining into disease prediction models can improve performance. We evaluated the performance of Group-LASSO INTERaction-NET (glinternet) and pretrained lasso in disease prediction focusing on diverse ancestries in the UK Biobank. Models were trained on multiomic data from White British and other ancestries and validated in a cohort of more than 96,000 individuals for 8 diseases. Of the 96 trained models, we report 16 with statistically significant incremental predictive performance in terms of ROC-AUC scores (\n                    <jats:inline-formula id=\"pone.0336861.e001\">\n                      <jats:alternatives>\n                        <jats:graphic xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" id=\"pone.0336861.e001g\" mimetype=\"image\" position=\"anchor\" xlink:href=\"info:doi\/10.1371\/journal.pone.0336861.e001\" xlink:type=\"simple\"\/>\n                        <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" display=\"inline\" id=\"M1\">\n                          <mml:mrow>\n                            <mml:mi>p<\/mml:mi>\n                            <mml:mtext>-value<\/mml:mtext>\n                            <mml:mo>&lt;<\/mml:mo>\n                            <mml:mn>0.05<\/mml:mn>\n                          <\/mml:mrow>\n                        <\/mml:math>\n                      <\/jats:alternatives>\n                    <\/jats:inline-formula>\n                    ), found for diabetes, arthritis, gall stones, cystitis, asthma, and osteoarthritis. Our findings suggest that interaction terms and pre-training can modestly improve prediction accuracy, but these effects are not consistent across all diseases. Our code is available at (\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/rivas-lab\/AncestryOmicsUKB\" xlink:type=\"simple\">https:\/\/github.com\/rivas-lab\/AncestryOmicsUKB<\/jats:ext-link>\n                    ).\n                  <\/jats:p>","DOI":"10.1371\/journal.pone.0336861","type":"journal-article","created":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T18:38:07Z","timestamp":1764614287000},"page":"e0336861","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Using pre-training and interaction modeling for ancestry-specific disease prediction using multiomics data from the UK Biobank"],"prefix":"10.1371","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-5901-6407","authenticated-orcid":true,"given":"Thomas","family":"Le Menestrel","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Erin","family":"Craig","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robert","family":"Tibshirani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Trevor","family":"Hastie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manuel","family":"Rivas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2025,12,1]]},"reference":[{"key":"pone.0336861.ref001","doi-asserted-by":"crossref","first-page":"505357","DOI":"10.3389\/fgene.2020.00424","article-title":"From GWAS to function: using functional genomics to identify the mechanisms underlying complex diseases","volume":"11","author":"E Cano-Gamez","year":"2020","journal-title":"Frontiers in genetics."},{"key":"pone.0336861.ref002","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-62703-447-0","volume-title":"Genome-wide association studies and genomic prediction","author":"C Gondro","year":"2013"},{"issue":"7624","key":"pone.0336861.ref003","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1038\/538161a","article-title":"Genomics is failing on diversity","volume":"538","author":"AB Popejoy","year":"2016","journal-title":"Nature."},{"issue":"3","key":"pone.0336861.ref004","doi-asserted-by":"crossref","first-page":"589","DOI":"10.1016\/j.cell.2019.08.051","article-title":"Genome-wide association studies in ancestrally diverse populations: opportunities, methods, pitfalls, and recommendations","volume":"179","author":"RE Peterson","year":"2019","journal-title":"Cell."},{"key":"pone.0336861.ref005","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1146\/annurev.genom.4.070802.110356","article-title":"Race, ancestry, and genes: implications for defining disease risk","volume":"4","author":"RA Kittles","year":"2003","journal-title":"Annu Rev Genomics Hum Genet."},{"issue":"7726","key":"pone.0336861.ref006","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1038\/s41586-018-0579-z","article-title":"The UK Biobank resource with deep phenotyping and genomic data","volume":"562","author":"C Bycroft","year":"2018","journal-title":"Nature."},{"issue":"3","key":"pone.0336861.ref007","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pgen.1010105","article-title":"Significant sparse polygenic risk scores across 813 traits in UK Biobank","volume":"18","author":"Y Tanigawa","year":"2022","journal-title":"PLoS Genet."},{"issue":"2","key":"pone.0336861.ref008","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1038\/s41588-020-00757-z","article-title":"Genetics of 35 blood and urine biomarkers in the UK Biobank","volume":"53","author":"N Sinnott-Armstrong","year":"2021","journal-title":"Nat Genet."},{"issue":"6","key":"pone.0336861.ref009","doi-asserted-by":"crossref","first-page":"715","DOI":"10.1016\/j.jacc.2020.06.028","article-title":"Polygenic Risk Scores for Diverse Ancestries","volume":"76","author":"IJ Kullo","year":"2020","journal-title":"Journal of the American College of Cardiology."},{"issue":"1","key":"pone.0336861.ref010","doi-asserted-by":"crossref","first-page":"4023","DOI":"10.1038\/s41467-023-38930-7","article-title":"Optimal strategies for learning multi-ancestry polygenic scores vary across traits","volume":"14","author":"B Lehmann","year":"2023","journal-title":"Nat Commun."},{"issue":"1","key":"pone.0336861.ref011","doi-asserted-by":"crossref","first-page":"964","DOI":"10.1038\/s42003-023-05352-6","article-title":"Improving genetic risk prediction across diverse population by disentangling ancestry representations","volume":"6","author":"PK Gyawali","year":"2023","journal-title":"Commun Biol."},{"issue":"1","key":"pone.0336861.ref012","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1002\/bimj.200900028","article-title":"L1 penalized estimation in the Cox proportional hazards model","volume":"52","author":"JJ Goeman","year":"2010","journal-title":"Biom J."},{"issue":"2","key":"pone.0336861.ref013","doi-asserted-by":"crossref","first-page":"522","DOI":"10.1093\/biostatistics\/kxaa038","article-title":"Fast Lasso method for large-scale and ultrahigh-dimensional Cox model with applications to UK Biobank","volume":"23","author":"R Li","year":"2022","journal-title":"Biostatistics."},{"issue":"2","key":"pone.0336861.ref014","doi-asserted-by":"crossref","first-page":"222","DOI":"10.1016\/j.ajhg.2020.06.003","article-title":"A fast and accurate method for genome-wide time-to-event data analysis and its application to UK Biobank","volume":"107","author":"W Bi","year":"2020","journal-title":"Am J Hum Genet."},{"issue":"7","key":"pone.0336861.ref015","doi-asserted-by":"crossref","first-page":"991","DOI":"10.3390\/genes12070991","article-title":"Machine learning prediction of biomarkers from SNPs and of disease risk from biomarkers in the UK Biobank","volume":"12","author":"E Widen","year":"2021","journal-title":"Genes (Basel)."},{"key":"pone.0336861.ref016","doi-asserted-by":"crossref","unstructured":"Carrasco-Zanini J, Pietzner M, Davitte J, Surendran P, Croteau-Chonka DC, Robins C, et al. Proteomic prediction of common and rare diseases. Cold Spring Harbor Laboratory. 2023. https:\/\/doi.org\/10.1101\/2023.07.18.23292811","DOI":"10.1101\/2023.07.18.23292811"},{"key":"pone.0336861.ref017","doi-asserted-by":"crossref","unstructured":"Gadd DA, Hillary RF, Kuncheva Z, Mangelis T, Cheng Y, Dissanayake M, et al. Blood protein levels predict leading incident diseases and mortality in UK Biobank. Cold Spring Harbor Laboratory. 2023. https:\/\/doi.org\/10.1101\/2023.05.01.23288879","DOI":"10.1101\/2023.05.01.23288879"},{"key":"pone.0336861.ref018","doi-asserted-by":"crossref","unstructured":"Barrett JC, Esko T, Fischer K, Jostins-Dean L, Jousilahti P, Julkunen H, et al. Metabolomic and genomic prediction of common diseases in 477,706 participants in three national biobanks. Cold Spring Harbor Laboratory. 2023. https:\/\/doi.org\/10.1101\/2023.06.09.23291213","DOI":"10.1101\/2023.06.09.23291213"},{"issue":"3","key":"pone.0336861.ref019","doi-asserted-by":"crossref","first-page":"627","DOI":"10.1080\/10618600.2014.938812","article-title":"Learning interactions via hierarchical group-lasso regularization","volume":"24","author":"M Lim","year":"2015","journal-title":"J Comput Graph Stat."},{"key":"pone.0336861.ref020","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1201\/9780203738535-6","volume-title":"Statistical models in S","author":"TJ Hastie","year":"2017"},{"issue":"2","key":"pone.0336861.ref021","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1109\/JSTSP.2010.2042413","article-title":"Iterative Reweighted \u21131 and \u21132 methods for finding sparse solutions","volume":"4","author":"D Wipf","year":"2010","journal-title":"IEEE J Sel Top Signal Process."},{"issue":"1","key":"pone.0336861.ref022","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","article-title":"Regression shrinkage and selection via the Lasso","volume":"58","author":"R Tibshirani","year":"1996","journal-title":"Journal of the Royal Statistical Society Series B: Statistical Methodology."},{"key":"pone.0336861.ref023","unstructured":"Friedman J, Hastie T, Tibshirani R, Narasimhan B, Tay K, Simon N. glmnet: lasso and elastic-net regularized generalized linear models. 2023."},{"key":"pone.0336861.ref024","unstructured":"R Core Team. R: a language and environment for statistical computing. 2021."},{"issue":"3","key":"pone.0336861.ref025","doi-asserted-by":"crossref","first-page":"627","DOI":"10.1080\/10618600.2014.938812","article-title":"Learning interactions via hierarchical group-lasso regularization","volume":"24","author":"M Lim","year":"2015","journal-title":"J Comput Graph Stat."},{"key":"pone.0336861.ref026","article-title":"Pretraining and the lasso","author":"E Craig","year":"2024","journal-title":"arXiv preprint"},{"issue":"2","key":"pone.0336861.ref027","first-page":"627","article-title":"Receiver Operating Characteristic (ROC) curve analysis for medical diagnostic test evaluation","volume":"4","author":"K Hajian-Tilaki","year":"2013","journal-title":"Caspian J Intern Med."},{"issue":"3","key":"pone.0336861.ref028","doi-asserted-by":"crossref","first-page":"837","DOI":"10.2307\/2531595","article-title":"Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach","volume":"44","author":"ER DeLong","year":"1988","journal-title":"Biometrics."},{"key":"pone.0336861.ref029","article-title":"Genotyping and quality control of UK Biobank, a large-scale, extensively phenotyped prospective resource","year":"2015","journal-title":"arXiv preprint"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0336861","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T18:38:12Z","timestamp":1764614292000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0336861"}},"subtitle":[],"editor":[{"given":"Xiang","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2025,12,1]]},"references-count":29,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2025,12,1]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0336861","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,1]]}}}