Unveiling genetic architecture of white matter microstructure through unsupervised deep representation learning of fractional anisotropy maps

Unveiling genetic architecture of white matter microstructure through unsupervised deep representation learning of fractional anisotropy maps | 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 Unveiling genetic architecture of white matter microstructure through unsupervised deep representation learning of fractional anisotropy maps Degui Zhi, Xingzhong Zhao, Ziqian Xie, Wei He, Hyun Yong Koh, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7411165/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 Fractional anisotropy (FA) derived from diffusion MRI is a widely used marker of white matter (WM) integrity. However, conventional FA-based genetic studies focus on phenotypes representing tract- or atlas-defined averages, which may oversimplify spatial patterns of WM integrity and thus limit the genetic discovery. Here, we proposed a deep learning–based framework, termed unsupervised deep representation of WM (UDR-WM), it adopted the voxel-wise FA maps as the input, and to extract brain-wide FA features—referred to as UDIP-FA—that capture distributed microstructural variation without prior anatomical assumptions. UDIP-FAs exhibit enhanced sensitivity to aging and substantially higher SNP-based heritability compared to traditional FA phenotypes ( P < 2.20×10 –16 , Mann–Whitney U test, mean = 50.81%). Through multivariate GWAS, we identified 939 significant lead SNPs in 586 loci, mapped to 3480 genes, dubbed UDIP-FA related genes (UFAGs). UFAGs are overexpressed in glial cells, particularly in astrocytes and oligodendrocytes ( P < 8.03× 10 − 8 , Wald Test), and show strong overlap with risk gene sets for schizophrenia and Parkinson’s disease (P < 1.10 × 10 − 4 , Fisher exact test). UDIP-FAs are genetically correlated with multiple brain disorders and cognitive traits, including fluid intelligence and reaction time, and are associated with polygenic risk for bone mineral density. Network analyses reveal that UFAGs form disease-enriched modules across protein–protein interaction and co-expression networks, implicating core pathways in myelination and axonal structure. Notably, several UFAGs, including ACHE and ALDH2 , are targets of existing neuropsychiatric drugs. Together, our findings establish UDIP-FA as a biologically and clinically informative brain phenotype, enabling high-resolution dissection of WM genetic architecture and its genetic links to complex brain traits. Health sciences/Biomarkers/Predictive markers Biological sciences/Computational biology and bioinformatics/Data integration Health sciences/Biomarkers/Prognostic markers Full Text Additional Declarations There is NO Competing Interest. Supplementary Files SupplementaryFigures.docx Supplementary Figures SupplementaryTables.xlsx Supplementary Tables 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-7411165","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":503870678,"identity":"01e09ad8-ade9-4af2-8b53-ab6a607a258d","order_by":0,"name":"Degui Zhi","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA6klEQVRIiWNgGAWjYDCCA0CcAERs7A0MzDBBCeK08BxgbGZgMCBSC1iXRAKRWviOt1+TeMBQl8cn+cb8cQHDn2j+BuaDt3nwaJE8c6ZMIoGBrZhNOseweQaDQe6MA2zJ1vi0GNzISQNq4UlsA2nhAWrZwMBjJo1Xy/03IC0SiW2SZ2Ba+L/h13KD/RhQi0FimwQP3BY2vFokz+QwWyQYJCS28aQVzuYxMM6dcZjN2HIOHi18x48/vPmjoi5xfvvhDZ95KuRy+9ubH954g0cLAwOPASw2GCAMZjyKIYD9AUElo2AUjIJRMMIBAMN0RbVSeZroAAAAAElFTkSuQmCC","orcid":"","institution":"The University of Texas Health Science Center at Houston","correspondingAuthor":true,"prefix":"","firstName":"Degui","middleName":"","lastName":"Zhi","suffix":""},{"id":503870679,"identity":"65cc28ee-485d-4679-9c64-55df80d58c64","order_by":1,"name":"Xingzhong Zhao","email":"","orcid":"","institution":"The University of Texas Health Science Center at Houston","correspondingAuthor":false,"prefix":"","firstName":"Xingzhong","middleName":"","lastName":"Zhao","suffix":""},{"id":503870680,"identity":"e187f61c-d6aa-42cf-a6dc-e860e801b4b9","order_by":2,"name":"Ziqian Xie","email":"","orcid":"","institution":"The University of Texas Health Science Center at Houston","correspondingAuthor":false,"prefix":"","firstName":"Ziqian","middleName":"","lastName":"Xie","suffix":""},{"id":503870681,"identity":"787a629d-586f-455a-bb78-99f96761d240","order_by":3,"name":"Wei He","email":"","orcid":"","institution":"The University of Texas Health Science Center at Houston","correspondingAuthor":false,"prefix":"","firstName":"Wei","middleName":"","lastName":"He","suffix":""},{"id":503870682,"identity":"ff73b2e7-c289-4c0c-be11-80dabbe29637","order_by":4,"name":"Hyun Yong Koh","email":"","orcid":"","institution":"The University of Texas Health Science Center at Houston","correspondingAuthor":false,"prefix":"","firstName":"Hyun","middleName":"Yong","lastName":"Koh","suffix":""},{"id":503870683,"identity":"31cac803-9d95-4115-99ed-31dc82f2f424","order_by":5,"name":"Myriam Fornage","email":"","orcid":"https://orcid.org/0000-0003-0677-8158","institution":"The University of Texas Health Science Center at Houston","correspondingAuthor":false,"prefix":"","firstName":"Myriam","middleName":"","lastName":"Fornage","suffix":""}],"badges":[],"createdAt":"2025-08-19 18:35:19","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7411165/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7411165/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":91556390,"identity":"647ad99d-c83c-4958-9372-c391a796df54","added_by":"auto","created_at":"2025-09-17 17:32:03","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1038644,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7411165/v1_covered_b6259d13-73a8-459b-8ac1-662d35e2d2ea.pdf"},{"id":91556138,"identity":"8f732519-8d98-4aad-8df0-bbed3e6476c0","added_by":"auto","created_at":"2025-09-17 17:24:01","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":4156900,"visible":true,"origin":"","legend":"Supplementary Figures","description":"","filename":"SupplementaryFigures.docx","url":"https://assets-eu.researchsquare.com/files/rs-7411165/v1/6fed5d3291482653b58c510c.docx"},{"id":91556139,"identity":"a9a5cc93-6efe-481d-bbe4-1c2187a8dfb4","added_by":"auto","created_at":"2025-09-17 17:24:01","extension":"xlsx","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":12074355,"visible":true,"origin":"","legend":"Supplementary Tables","description":"","filename":"SupplementaryTables.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-7411165/v1/5289918a3017d62f45ab1954.xlsx"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Unveiling genetic architecture of white matter microstructure through unsupervised deep representation learning of fractional anisotropy maps","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-7411165/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7411165/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eFractional anisotropy (FA) derived from diffusion MRI is a widely used marker of white matter (WM) integrity. However, conventional FA-based genetic studies focus on phenotypes representing tract- or atlas-defined averages, which may oversimplify spatial patterns of WM integrity and thus limit the genetic discovery. Here, we proposed a deep learning\u0026ndash;based framework, termed unsupervised deep representation of WM (UDR-WM), it adopted the voxel-wise FA maps as the input, and to extract brain-wide FA features\u0026mdash;referred to as UDIP-FA\u0026mdash;that capture distributed microstructural variation without prior anatomical assumptions. UDIP-FAs exhibit enhanced sensitivity to aging and substantially higher SNP-based heritability compared to traditional FA phenotypes (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;2.20\u0026times;10\u003csup\u003e\u0026ndash;16\u003c/sup\u003e, Mann\u0026ndash;Whitney U test, mean\u0026thinsp;=\u0026thinsp;50.81%). Through multivariate GWAS, we identified 939 significant lead SNPs in 586 loci, mapped to 3480 genes, dubbed UDIP-FA related genes (UFAGs). UFAGs are overexpressed in glial cells, particularly in astrocytes and oligodendrocytes (\u003cem\u003eP\u0026thinsp;\u0026lt;\u003c/em\u003e\u0026thinsp;8.03\u0026times; 10\u003csup\u003e\u0026minus;\u0026thinsp;8\u003c/sup\u003e, Wald Test), and show strong overlap with risk gene sets for schizophrenia and Parkinson\u0026rsquo;s disease (P\u0026thinsp;\u0026lt;\u0026thinsp;1.10 \u0026times; 10\u003csup\u003e\u0026minus;\u0026thinsp;4\u003c/sup\u003e, Fisher exact test). UDIP-FAs are genetically correlated with multiple brain disorders and cognitive traits, including fluid intelligence and reaction time, and are associated with polygenic risk for bone mineral density. Network analyses reveal that UFAGs form disease-enriched modules across protein\u0026ndash;protein interaction and co-expression networks, implicating core pathways in myelination and axonal structure. Notably, several UFAGs, including \u003cem\u003eACHE\u003c/em\u003e and \u003cem\u003eALDH2\u003c/em\u003e, are targets of existing neuropsychiatric drugs. Together, our findings establish UDIP-FA as a biologically and clinically informative brain phenotype, enabling high-resolution dissection of WM genetic architecture and its genetic links to complex brain traits.\u003c/p\u003e","manuscriptTitle":"Unveiling genetic architecture of white matter microstructure through unsupervised deep representation learning of fractional anisotropy maps","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-17 17:23:56","doi":"10.21203/rs.3.rs-7411165/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":"e87993a6-8055-4783-9341-62c36713b0c9","owner":[],"postedDate":"September 17th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":53533794,"name":"Health sciences/Biomarkers/Predictive markers"},{"id":53533795,"name":"Biological sciences/Computational biology and bioinformatics/Data integration"},{"id":53533796,"name":"Health sciences/Biomarkers/Prognostic markers"}],"tags":[],"updatedAt":"2025-09-17T17:23:56+00:00","versionOfRecord":[],"versionCreatedAt":"2025-09-17 17:23:56","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7411165","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7411165","identity":"rs-7411165","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}