Advancing Human Population Genomics with DNA Foundation Models

Advancing Human Population Genomics with DNA Foundation Models | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Biological Sciences - Article Advancing Human Population Genomics with DNA Foundation Models Lucila Ohno-Machado, Rui Zhu, Xiaopu Zhou, Marla Mendes, Worrawat Engchuan, and 6 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7889315/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted You are reading this latest preprint version Abstract DNA foundation models offer a new approach to interpret genetic variation, but their potential in population-scale genomics remains untapped. We introduce a novel analytical framework that integrates a genomic foundation model with human population genomics studies. We employed the Evo2 DNA foundation model to systematically score the functional impact of a variant and haplotype across diverse cohorts including people with Alzheimer's Disease Neuroimaging Initiative (ADNI), the Human Pangenome Project, and the UK Biobank. As proof-of-concept, the analysis of the APOE locus confirmed the approach’s validity, with model-derived scores can help to prioritize putatively functional variants and quantify effects of both variants and haplotype onto Alzheimer's Disease susceptibility or associated endophenotypes, including cognitive performance, brain structural change and amyloid load. Specifically, scoring multi-ancestry assembly sequences from the Human Pangenome Project revealed, for the first time, that genetic variation could nicely explain ancestry-specific differences in APOE expression and the impact of APOE -ε4 on Alzheimer’s disease risk. Overall, this study provides a scalable framework for mapping functional genetic variation, complementing conventional population-genomics approaches, enabling better interpretation of genetic effects in complex genomic regions at population scale. Biological sciences/Genetics/Population genetics Health sciences/Risk factors Biological sciences/Computational biology and bioinformatics/Machine learning Full Text Additional Declarations Yes there is potential Competing Interest. At the time of this study and its publication, S.W.S. served on the scientific advisory committee of Population Bio. Intellectual property from aspects of his research held at The Hospital for Sick Children are licensed to Athena Diagnostics and Population Bio. These relationships did not influence data interpretation or presentation during this study but are disclosed for potential future considerations. J.H. has served as a consultant for Eli Lilly and Eisai. Supplementary Files ZhuSupplementrayINFOfinal.docx SUPPLEMENTARY INFORMATION Cite Share Download PDF Status: Under Review Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-7889315","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Biological Sciences - Article","associatedPublications":[],"authors":[{"id":535830106,"identity":"f8fe75ac-78fe-4b27-889e-1bc5a809f361","order_by":0,"name":"Lucila Ohno-Machado","email":"data:image/png;base64,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","orcid":"","institution":"Yale University","correspondingAuthor":true,"prefix":"","firstName":"Lucila","middleName":"","lastName":"Ohno-Machado","suffix":""},{"id":535830107,"identity":"7e87a5d4-c501-46cb-8ed4-dadd63ab3356","order_by":1,"name":"Rui Zhu","email":"","orcid":"","institution":"Yale University","correspondingAuthor":false,"prefix":"","firstName":"Rui","middleName":"","lastName":"Zhu","suffix":""},{"id":535830108,"identity":"15b9f98a-8de8-4f97-994e-64c45335b770","order_by":2,"name":"Xiaopu Zhou","email":"","orcid":"https://orcid.org/0000-0001-5307-5805","institution":"The Hospital for Sick Children","correspondingAuthor":false,"prefix":"","firstName":"Xiaopu","middleName":"","lastName":"Zhou","suffix":""},{"id":535830109,"identity":"8663af5a-5d2f-4a63-b709-2e3183b903af","order_by":3,"name":"Marla Mendes","email":"","orcid":"","institution":"The Hospital for Sick Children","correspondingAuthor":false,"prefix":"","firstName":"Marla","middleName":"","lastName":"Mendes","suffix":""},{"id":535830110,"identity":"467605e8-6e6e-4783-85a6-9003305f414c","order_by":4,"name":"Worrawat Engchuan","email":"","orcid":"https://orcid.org/0000-0001-6138-1925","institution":"The Centre for Applied Genomics, The Hospital for Sick Children, Toronto, Ontario, Canada","correspondingAuthor":false,"prefix":"","firstName":"Worrawat","middleName":"","lastName":"Engchuan","suffix":""},{"id":535830111,"identity":"72918c41-7a29-4784-9ea7-83f389171b96","order_by":5,"name":"Hang Zhou","email":"","orcid":"https://orcid.org/0000-0002-7694-6391","institution":"Division of Human genetics, Yale School of Medicine; Veterans Affairs Connecticut Healthcare System","correspondingAuthor":false,"prefix":"","firstName":"Hang","middleName":"","lastName":"Zhou","suffix":""},{"id":535830112,"identity":"5b19816e-a787-4bd0-bb67-3379e3cc5a11","order_by":6,"name":"Haoyu Cheng","email":"","orcid":"https://orcid.org/0000-0002-9209-5793","institution":"a","correspondingAuthor":false,"prefix":"","firstName":"Haoyu","middleName":"","lastName":"Cheng","suffix":""},{"id":535830113,"identity":"3585d074-5d78-4791-af3f-6eb484975358","order_by":7,"name":"the Alzheimer’s Disease Neuroimaging Initiative (ADNI)","email":"","orcid":"","institution":"adni.loni.usc.edu","correspondingAuthor":false,"prefix":"","firstName":"the","middleName":"Alzheimer’s Disease Neuroimaging Initiative","lastName":"(ADNI)","suffix":""},{"id":535830114,"identity":"534945c2-b162-4f77-b21d-424b0ebec3cd","order_by":8,"name":"John Hardy","email":"","orcid":"","institution":"University College London","correspondingAuthor":false,"prefix":"","firstName":"John","middleName":"","lastName":"Hardy","suffix":""},{"id":535830115,"identity":"3f816607-2de8-4d6a-b47c-04baf9717b3f","order_by":9,"name":"Haixu Tang","email":"","orcid":"","institution":"Indiana University","correspondingAuthor":false,"prefix":"","firstName":"Haixu","middleName":"","lastName":"Tang","suffix":""},{"id":535830116,"identity":"deccdc06-e3ea-4fed-bd98-c81beaf160fa","order_by":10,"name":"Stephen Scherer","email":"","orcid":"https://orcid.org/0000-0002-8326-1999","institution":"Hospital for Sick Children","correspondingAuthor":false,"prefix":"","firstName":"Stephen","middleName":"","lastName":"Scherer","suffix":""}],"badges":[],"createdAt":"2025-10-17 19:15:31","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7889315/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7889315/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":95529216,"identity":"4fceab9d-130d-4fb6-aa53-59de02e8ea85","added_by":"auto","created_at":"2025-11-10 10:16:54","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1274158,"visible":true,"origin":"","legend":"","description":"","filename":"ZhuMainTextfinal.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7889315/v1_covered_88832dba-a70d-41a6-b6bc-435eb56fee87.pdf"},{"id":95514174,"identity":"5a42fe32-1312-4219-95c2-f8d2daa422bf","added_by":"auto","created_at":"2025-11-10 08:07:17","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":1472312,"visible":true,"origin":"","legend":"SUPPLEMENTARY INFORMATION","description":"","filename":"ZhuSupplementrayINFOfinal.docx","url":"https://assets-eu.researchsquare.com/files/rs-7889315/v1/bb115f81c33e0bad37c0e473.docx"}],"financialInterests":"\u003cb\u003eYes\u003c/b\u003e there is potential Competing Interest.\nAt the time of this study and its publication, S.W.S. served on the scientific advisory committee of Population Bio. Intellectual property from aspects of his research held at The Hospital for Sick Children are licensed to Athena Diagnostics and Population Bio. These relationships did not influence data interpretation or presentation during this study but are disclosed for potential future considerations. J.H. has served as a consultant for Eli Lilly and Eisai.","formattedTitle":"Advancing Human Population Genomics with DNA Foundation Models","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"nature-portfolio","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"","title":"Nature Portfolio","twitterHandle":"","acdcEnabled":false,"dfaEnabled":false,"editorialSystem":"ejp","reportingPortfolio":"","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-7889315/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7889315/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eDNA foundation models offer a new approach to interpret genetic variation, but their potential in population-scale genomics remains untapped. We introduce a novel analytical framework that integrates a genomic foundation model with human population genomics studies. We employed the Evo2 DNA foundation model to systematically score the functional impact of a variant and haplotype across diverse cohorts including people with Alzheimer's Disease Neuroimaging Initiative (ADNI), the Human Pangenome Project, and the UK Biobank. As proof-of-concept, the analysis of the \u003cem\u003eAPOE\u003c/em\u003e locus confirmed the approach\u0026rsquo;s validity, with model-derived scores can help to prioritize putatively functional variants and quantify effects of both variants and haplotype onto Alzheimer's Disease susceptibility or associated endophenotypes, including cognitive performance, brain structural change and amyloid load. Specifically, scoring multi-ancestry assembly sequences from the Human Pangenome Project revealed, for the first time, that genetic variation could nicely explain ancestry-specific differences in APOE expression and the impact of \u003cem\u003eAPOE\u003c/em\u003e-ε4 on Alzheimer\u0026rsquo;s disease risk. Overall, this study provides a scalable framework for mapping functional genetic variation, complementing conventional population-genomics approaches, enabling better interpretation of genetic effects in complex genomic regions at population scale.\u003c/p\u003e","manuscriptTitle":"Advancing Human Population Genomics with DNA Foundation Models","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-10 08:07:12","doi":"10.21203/rs.3.rs-7889315/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"nature-communications","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"NCOMMS","sideBox":"Learn more about [Nature Communications](http://www.nature.com/ncomms/)","snPcode":"","submissionUrl":"https://mts-ncomms.nature.com/","title":"Nature Communications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Communications","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"823a168d-e62a-49cd-ab3b-9a93206d5ec7","owner":[],"postedDate":"November 10th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":56971628,"name":"Biological sciences/Genetics/Population genetics"},{"id":56971629,"name":"Health sciences/Risk factors"},{"id":56971630,"name":"Biological sciences/Computational biology and bioinformatics/Machine learning"}],"tags":[],"updatedAt":"2025-11-10T08:07:12+00:00","versionOfRecord":[],"versionCreatedAt":"2025-11-10 08:07:12","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7889315","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7889315","identity":"rs-7889315","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}