Transfer Learning for Mendelian Randomization with Pleiotropic and Correlated High-Dimensional Exposures and Its Application to Trans-ethnic Populations

Transfer Learning for Mendelian Randomization with Pleiotropic and Correlated High-Dimensional Exposures and Its Application to Trans-ethnic Populations | 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 Article Transfer Learning for Mendelian Randomization with Pleiotropic and Correlated High-Dimensional Exposures and Its Application to Trans-ethnic Populations Chen Hao, Hou Lei, Xiaohua Zhou, Fuzhong Xue This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7712945/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract The majority of large-scale GWAS cohorts are of European ancestry, making it critical to generalize findings from European populations to other ethnic groups with smaller sample sizes. Traditional multivariable Mendelian randomization (MR) methods often perform poorly in high-dimensional and correlated exposure settings, due to issues such as collinearity and unstable model fitting. To address these challenges, we propose a two-step statistical transfer learning method for high-dimensional MR, called TL-HDMR, which enhances the detection of causal exposures in target populations. To mitigate the impact of exposure correlations, we incorporate the Minimax Concave Penalty, enabling asymptotically unbiased estimation of causal effects. Furthermore, we introduce two pre-transfer procedures—HDMR.SCD, which identifies source datasets conducive to positive transfer, and HDMR.PRESSO, which filters out pleiotropic instruments—to optimize the performance of TL-HDMR. We evaluate our method through extensive simulations and compare it with three alternative penalization approaches in high-dimensional scenarios. TL-HDMR demonstrates the best performance for ROC curve and mean absolute error. To illustrate its practical utility, we applied TL-HDMR to accurately identify ethnic-specific and subtype-specific causal biomarkers for stroke among 899 blood metabolites in a multi-ancestry context (European, East Asian, South Asian and African). The results highlight the ability of TL-HDMR to provide equitable and generalizable causal inferences across diverse populations. This work represents a meaningful advance in addressing the dual challenges of high-dimensional correlated exposures and cross-population generalization, thereby enhancing the robustness and inclusivity of causal inference in human health research. Biological sciences/Genetics/Genetic association study/Genome-wide association studies Health sciences/Health care/Disease prevention/Preventive medicine Mendelian randomization Transfer learning High-dimensional exposures Correlated exposures Pleiotropy Trans-ancestry Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Figure 7 Full Text Additional Declarations There is NO Competing Interest. Supplementary Files SupplementaryData.xlsx Supplementary Data SupplementaryFile.pdf Supplementary File Cite Share Download PDF Status: Posted 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-7712945","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":520873911,"identity":"25da2fa6-a492-423e-9750-1ba8e3d34de5","order_by":0,"name":"Chen Hao","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAyklEQVRIiWNgGAWjYBACAxDB2MDAwA9hM5OgRbKBZC0GB4jVYs5++ADDzx02ecbnD2+TYKiwTmxgP3sArxbLnrQExt4zacVmN9LKJBjOpCc28OQl4HfYgRwDZsa2w4nbbvCYSYAYDRI8Bvi1nH8D0vI/cXP/GaCWf8RouQG25UDiBoYcoJYGorQ8SzjY25acOONGWrFFwrF04zaeHEIOSz744GebXWJ//+GNNz7UWMv2s5/BrwUEDsBZCUDMRlD9KBgFo2AUjAKCAACKjUZRQJnEuAAAAABJRU5ErkJggg==","orcid":"","institution":"Shandong university","correspondingAuthor":true,"prefix":"","firstName":"Chen","middleName":"","lastName":"Hao","suffix":""},{"id":520873912,"identity":"ab228b3b-cd4d-4324-b2da-822df600fbbf","order_by":1,"name":"Hou Lei","email":"","orcid":"","institution":"Shandong university","correspondingAuthor":false,"prefix":"","firstName":"Hou","middleName":"","lastName":"Lei","suffix":""},{"id":520873913,"identity":"bad12fe1-420c-4955-aa06-14545d7c4186","order_by":2,"name":"Xiaohua Zhou","email":"","orcid":"","institution":"Peking University","correspondingAuthor":false,"prefix":"","firstName":"Xiaohua","middleName":"","lastName":"Zhou","suffix":""},{"id":520873914,"identity":"2f932149-fcdc-4129-978f-9fdf9f9ef0e5","order_by":3,"name":"Fuzhong Xue","email":"","orcid":"https://orcid.org/0000-0003-0378-7956","institution":"School of Public Health, Shandong University","correspondingAuthor":false,"prefix":"","firstName":"Fuzhong","middleName":"","lastName":"Xue","suffix":""}],"badges":[],"createdAt":"2025-09-25 12:31:15","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7712945/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7712945/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":92586506,"identity":"11bc27a7-1561-4ff7-8610-54660506d717","added_by":"auto","created_at":"2025-10-01 10:43:01","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":1649113,"visible":true,"origin":"","legend":"\u003cp\u003eSee image above for figure legend\u0026nbsp;\u003c/p\u003e","description":"","filename":"1.png","url":"https://assets-eu.researchsquare.com/files/rs-7712945/v1/e1a2ada2a045bac4bd46df48.png"},{"id":92585533,"identity":"0f6c5695-319c-445d-8359-6e02c14ad76e","added_by":"auto","created_at":"2025-10-01 10:27:01","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":720164,"visible":true,"origin":"","legend":"\u003cp\u003eSee image above for figure legend\u0026nbsp;\u003c/p\u003e","description":"","filename":"2.png","url":"https://assets-eu.researchsquare.com/files/rs-7712945/v1/758a4805708a96ae39308ea9.png"},{"id":92585749,"identity":"8a999941-5143-4ef6-8e6b-e0a1317989cd","added_by":"auto","created_at":"2025-10-01 10:35:01","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":397621,"visible":true,"origin":"","legend":"\u003cp\u003eSee image above for figure legend\u0026nbsp;\u003c/p\u003e","description":"","filename":"3.png","url":"https://assets-eu.researchsquare.com/files/rs-7712945/v1/431bbde3178dc930a6d80bc1.png"},{"id":92585751,"identity":"9e244329-dd93-44d9-84b5-4e3b1cc09c58","added_by":"auto","created_at":"2025-10-01 10:35:01","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":744208,"visible":true,"origin":"","legend":"\u003cp\u003eSee image above for figure legend\u0026nbsp;\u003c/p\u003e","description":"","filename":"4.png","url":"https://assets-eu.researchsquare.com/files/rs-7712945/v1/144af7dde2daa7d7507b5ab8.png"},{"id":92585532,"identity":"e61399b3-f32c-40aa-88aa-bf137419770e","added_by":"auto","created_at":"2025-10-01 10:27:01","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":1482369,"visible":true,"origin":"","legend":"\u003cp\u003eSee image above for figure legend\u0026nbsp;\u003c/p\u003e","description":"","filename":"5.png","url":"https://assets-eu.researchsquare.com/files/rs-7712945/v1/2340f2d656219f8391fa5c81.png"},{"id":92585536,"identity":"30075fb4-2c87-484d-b630-089c44329805","added_by":"auto","created_at":"2025-10-01 10:27:01","extension":"png","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":1521060,"visible":true,"origin":"","legend":"\u003cp\u003eSee image above for figure legend\u0026nbsp;\u003c/p\u003e","description":"","filename":"6.png","url":"https://assets-eu.researchsquare.com/files/rs-7712945/v1/f7389f1584a946a342781605.png"},{"id":92585539,"identity":"d03c38b5-6ec9-48d7-8443-2af52e3ab5db","added_by":"auto","created_at":"2025-10-01 10:27:01","extension":"png","order_by":7,"title":"Figure 7","display":"","copyAsset":false,"role":"figure","size":1378427,"visible":true,"origin":"","legend":"\u003cp\u003eSee image above for figure legend\u0026nbsp;\u003c/p\u003e","description":"","filename":"7.png","url":"https://assets-eu.researchsquare.com/files/rs-7712945/v1/9bef78d310218e4b8d78ad63.png"},{"id":93174748,"identity":"4a96cf00-2ee0-43b9-8116-3e580083b552","added_by":"auto","created_at":"2025-10-09 20:38:58","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3631985,"visible":true,"origin":"","legend":"Article File","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7712945/v1_covered_7cf3cfd8-8549-4d77-b443-4c473fad7051.pdf"},{"id":92585537,"identity":"cbc88b70-4ae4-4e1a-b9fb-e20fd3fa673b","added_by":"auto","created_at":"2025-10-01 10:27:01","extension":"xlsx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":2875857,"visible":true,"origin":"","legend":"Supplementary Data","description":"","filename":"SupplementaryData.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-7712945/v1/f7ddba15d72b816cdcdc5ef3.xlsx"},{"id":92585540,"identity":"26fceaa5-b965-43ae-aacc-cc94be182688","added_by":"auto","created_at":"2025-10-01 10:27:02","extension":"pdf","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":22140637,"visible":true,"origin":"","legend":"Supplementary File","description":"","filename":"SupplementaryFile.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7712945/v1/a9f90f7cdac0ca7ed5c33849.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Transfer Learning for Mendelian Randomization with Pleiotropic and Correlated High-Dimensional Exposures and Its Application to Trans-ethnic Populations","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"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":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Mendelian randomization, Transfer learning, High-dimensional exposures, Correlated exposures, Pleiotropy, Trans-ancestry","lastPublishedDoi":"10.21203/rs.3.rs-7712945/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7712945/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The majority of large-scale GWAS cohorts are of European ancestry, making it critical to generalize findings from European populations to other ethnic groups with smaller sample sizes. Traditional multivariable Mendelian randomization (MR) methods often perform poorly in high-dimensional and correlated exposure settings, due to issues such as collinearity and unstable model fitting. To address these challenges, we propose a two-step statistical transfer learning method for high-dimensional MR, called TL-HDMR, which enhances the detection of causal exposures in target populations. To mitigate the impact of exposure correlations, we incorporate the Minimax Concave Penalty, enabling asymptotically unbiased estimation of causal effects. Furthermore, we introduce two pre-transfer procedures—HDMR.SCD, which identifies source datasets conducive to positive transfer, and HDMR.PRESSO, which filters out pleiotropic instruments—to optimize the performance of TL-HDMR. We evaluate our method through extensive simulations and compare it with three alternative penalization approaches in high-dimensional scenarios. TL-HDMR demonstrates the best performance for ROC curve and mean absolute error. To illustrate its practical utility, we applied TL-HDMR to accurately identify ethnic-specific and subtype-specific causal biomarkers for stroke among 899 blood metabolites in a multi-ancestry context (European, East Asian, South Asian and African). The results highlight the ability of TL-HDMR to provide equitable and generalizable causal inferences across diverse populations. This work represents a meaningful advance in addressing the dual challenges of high-dimensional correlated exposures and cross-population generalization, thereby enhancing the robustness and inclusivity of causal inference in human health research.","manuscriptTitle":"Transfer Learning for Mendelian Randomization with Pleiotropic and Correlated High-Dimensional Exposures and Its Application to Trans-ethnic Populations","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-01 10:26:56","doi":"10.21203/rs.3.rs-7712945/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"fbd88647-bd77-4e9a-b400-439cb72b3c28","owner":[],"postedDate":"October 1st, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":55367992,"name":"Biological sciences/Genetics/Genetic association study/Genome-wide association studies"},{"id":55367993,"name":"Health sciences/Health care/Disease prevention/Preventive medicine"}],"tags":[],"updatedAt":"2025-10-10T03:20:27+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-01 10:26:56","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7712945","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7712945","identity":"rs-7712945","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}