MethylBERT:‬ ‭A‬ ‭Transformer-based‬ ‭model‬ ‭for‬ ‭read-level‬ ‭DNA‬ ‭methylation‬ pattern‬ ‭identification‬ ‭and‬ ‭tumour‬ ‭deconvolution‬

MethylBERT:‬ ‭A‬ ‭Transformer-based‬ ‭model‬ ‭for‬ ‭read-level‬ ‭DNA‬ ‭methylation‬ pattern‬ ‭identification‬ ‭and‬ ‭tumour‬ ‭deconvolution‬ | 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 MethylBERT:‬ ‭A‬ ‭Transformer-based‬ ‭model‬ ‭for‬ ‭read-level‬ ‭DNA‬ ‭methylation‬ pattern‬ ‭identification‬ ‭and‬ ‭tumour‬ ‭deconvolution‬ Pavlo Lutsik, Yunhee Yeong, Karl Rohr This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3915137/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 17 Jan, 2025 Read the published version in Nature Communications → Version 1 posted You are reading this latest preprint version Abstract DNA methylation (DNAm) is a key epigenetic mark that shows profound alterations in cancer. Read-level methylomes enable more in-depth DNAm analysis due to the broad coverage and preservation of rare cell-type signals, compared to array-based data such as 450K/EPIC array. Here, we propose MethylBERT, a novel Transformer-based model for read-level methylation pattern classification. MethylBERT identifies tumour-derived sequence reads based on their methylation patterns and genomic sequence. Based on the calculated classification probability, the method estimates tumour cell fractions within bulk samples and provides an assessment of the model precision. In our evaluation, MethylBERT outperforms existing deconvolution methods and demonstrates high accuracy regardless of methylation pattern complexity, read length and read coverage. Moreover, we show its potential for accurate non-invasive early cancer diagnostics using liquid biopsy samples. MethylBERT represents a significant advancement in read-level methylome analysis. It will increase the accuracy of tumour deconvolution and enhance circulating tumour DNA studies. Biological sciences/Computational biology and bioinformatics/Machine learning Biological sciences/Molecular biology/Epigenetics Full Text Additional Declarations There is NO Competing Interest. Supplementary Files MethylBERTsupplementary.pdf Cite Share Download PDF Status: Published Journal Publication published 17 Jan, 2025 Read the published version in Nature Communications → 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-3915137","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":272865359,"identity":"295227d3-591a-460c-9e41-40186b696ead","order_by":0,"name":"Pavlo Lutsik","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA/UlEQVRIie3PMUsDMRTA8Xfc4PIga6Rav0KODG2x4FdpOLguGRy7acnQ5cA136Y5AnU5cM3QQTi4+cBFcPGpHQTJoZtD/kMCL/xIApBK/c8yBzD/2A0MDi5OUzdq6JQDEsmso/0PBPIcf0NmZ61wA3C1Z97IZeuRcV10t3Ccxsii1qKxRGquTKmDx3OrpbTQyxgRrlp5/CSZ8XrwKEJVTRC8uo+Rp/5EWGP8nMhNqNZvRO6iJJTuiwA9DOhhgpeHnMgq+hfbucYKLuugTFG3a+Rt5yco+iJ2y4yp7fOwWV7uHh47/nq4nrKd2r7g5ngV/f639ed8hKRSqVRqrHesAVqMCSTGLgAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0001-9383-8555","institution":"KU Leuven","correspondingAuthor":true,"prefix":"","firstName":"Pavlo","middleName":"","lastName":"Lutsik","suffix":""},{"id":272865360,"identity":"6e1a69c9-b4e5-4cd6-9052-1987328f9ccc","order_by":1,"name":"Yunhee Yeong","email":"","orcid":"https://orcid.org/0000-0002-1150-7734","institution":"German Cancer Research Center (DKFZ)","correspondingAuthor":false,"prefix":"","firstName":"Yunhee","middleName":"","lastName":"Yeong","suffix":""},{"id":272865361,"identity":"291b700d-68c9-4daf-ba8a-384185d63eb6","order_by":2,"name":"Karl Rohr","email":"","orcid":"","institution":"Heidelberg University","correspondingAuthor":false,"prefix":"","firstName":"Karl","middleName":"","lastName":"Rohr","suffix":""}],"badges":[],"createdAt":"2024-01-31 21:20:14","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3915137/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3915137/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41467-025-55920-z","type":"published","date":"2025-01-17T05:00:00+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":74127753,"identity":"3de458ea-0c36-4113-8802-1d96c6158630","added_by":"auto","created_at":"2025-01-18 08:08:08","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1244342,"visible":true,"origin":"","legend":"","description":"","filename":"MethylBERTmanuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3915137/v1_covered_766c0821-7b38-42f1-8de2-c50ad5b70ec8.pdf"},{"id":56633859,"identity":"b9136d34-9a55-4eac-a7c0-7531affccea5","added_by":"auto","created_at":"2024-05-17 02:52:08","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":2547933,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cbr\u003e\u003c/p\u003e","description":"","filename":"MethylBERTsupplementary.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3915137/v1/e1e5b8b8d25867406a2eba30.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"MethylBERT:‬ ‭A‬ ‭Transformer-based‬ ‭model‬ ‭for‬ ‭read-level‬ ‭DNA‬ ‭methylation‬ pattern‬ ‭identification‬ ‭and‬ ‭tumour‬ ‭deconvolution‬","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"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-3915137/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3915137/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"DNA methylation (DNAm) is a key epigenetic mark that shows profound alterations in cancer. Read-level methylomes enable more in-depth DNAm analysis due to the broad coverage and preservation of rare cell-type signals, compared to array-based data such as 450K/EPIC array. Here, we propose MethylBERT, a novel Transformer-based model for read-level methylation pattern classification. MethylBERT identifies tumour-derived sequence reads based on their methylation patterns and genomic sequence. Based on the calculated classification probability, the method estimates tumour cell fractions within bulk samples and provides an assessment of the model precision. In our evaluation, MethylBERT outperforms existing deconvolution methods and demonstrates high accuracy regardless of methylation pattern complexity, read length and read coverage. Moreover, we show its potential for accurate non-invasive early cancer diagnostics using liquid biopsy samples. MethylBERT represents a significant advancement in read-level methylome analysis. It will increase the accuracy of tumour deconvolution and enhance circulating tumour DNA studies.","manuscriptTitle":"MethylBERT:‬ ‭A‬ ‭Transformer-based‬ ‭model‬ ‭for‬ ‭read-level‬ ‭DNA‬ ‭methylation‬ pattern‬ ‭identification‬ ‭and‬ ‭tumour‬ ‭deconvolution‬","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-05-17 02:52:04","doi":"10.21203/rs.3.rs-3915137/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":"4c7afb8f-9b61-4e4d-baad-7ba93cb5844d","owner":[],"postedDate":"May 17th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":28763030,"name":"Biological sciences/Computational biology and bioinformatics/Machine learning"},{"id":28763031,"name":"Biological sciences/Molecular biology/Epigenetics"}],"tags":[],"updatedAt":"2025-01-18T08:07:59+00:00","versionOfRecord":{"articleIdentity":"rs-3915137","link":"https://doi.org/10.1038/s41467-025-55920-z","journal":{"identity":"nature-communications","isVorOnly":false,"title":"Nature Communications"},"publishedOn":"2025-01-17 05:00:00","publishedOnDateReadable":"January 17th, 2025"},"versionCreatedAt":"2024-05-17 02:52:04","video":"","vorDoi":"10.1038/s41467-025-55920-z","vorDoiUrl":"https://doi.org/10.1038/s41467-025-55920-z","workflowStages":[]},"version":"v1","identity":"rs-3915137","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3915137","identity":"rs-3915137","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}