DNA Methylation Biomarkers-based Pan-Cancer Classifier: Predictive Modeling for Cancer Classification

DNA Methylation Biomarkers-based Pan-Cancer Classifier: Predictive Modeling for Cancer Classification | 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 Research Article DNA Methylation Biomarkers-based Pan-Cancer Classifier: Predictive Modeling for Cancer Classification Jan Bińkowski, Tomasz K. Wojdacz This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7408332/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 13 You are reading this latest preprint version Abstract Background: Machine-learning (ML) driven molecular diagnostics based on omics data has a potential to revolutionize personalized medicine. However, implementation of ML into diagnostic protocols is hindered by methodological challenges which often lead to inflated performance assessment of models during development followed by poor performance of these models in implementation phase. Here, we aimed to develop and validate a pan-cancer classification framework based on DNA methylation data, that addresses methodological challenges of omics data powered ML. Methods: We curated a primary dataset of DNA methylation profiles for 10 756 samples, that included 54 healthy and cancer tissue types and validation dataset comprising data for 2 306 samples from 28 independent studies. The classification framework was build using custom biomarkers selection strategy based on effect size metric that considers variance and class imbalance. The ML models were trained, tuned and evaluated using nested cross-validation approach. Local Outlier Factor algorithm was built into the inference pipelines to identify and filter samples displaying technical or biological anomalies. Additionally, for methodological validation of our framework we used methylation profiles for 3 905 central nervous system (CNS) tumors. Results: We found that relatively simple ML models outperformed complex algorithms such as deep neural network. A logistic regression classifier achieved a balanced accuracy (BACC) of 0.90 to classify 54 cancer and healthy tissue types using methylation levels at 1208 CpG sites. Similarly, our CNS tumor classifier also based on logistic regression algorithm reached a BACC of 0.94 across 59 CNS tumor subtypes. The anomaly filtering improved performance across all categories of samples tested. We deployed our inference pipelines for public access via secure web platform - https://opp.pum.edu.pl/ . Conclusions: Our study demonstrates that DNA methylation profiling, when combined with carefully controlled ML practices allows for development of robust solutions that might substantially increase the efficacy of oncological diagnosis. DNA methylation machine-learning biomarkers cancer classification Full Text Additional Declarations No competing interests reported. Supplementary Files AdditionalTables.xlsx Additionalfile1.html Additionalfile2.html Additionalfile3.html Additionalfile4.html Additionalfile5.html Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 03 Nov, 2025 Reviews received at journal 12 Oct, 2025 Reviews received at journal 07 Oct, 2025 Reviewers agreed at journal 29 Sep, 2025 Reviewers agreed at journal 25 Sep, 2025 Reviews received at journal 22 Sep, 2025 Reviews received at journal 17 Sep, 2025 Reviewers agreed at journal 31 Aug, 2025 Reviewers agreed at journal 29 Aug, 2025 Reviewers invited by journal 26 Aug, 2025 Editor assigned by journal 26 Aug, 2025 Submission checks completed at journal 20 Aug, 2025 First submitted to journal 19 Aug, 2025 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-7408332","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":508142260,"identity":"343f89fb-75d8-4f7a-983c-2d54dd733e37","order_by":0,"name":"Jan Bińkowski","email":"","orcid":"","institution":"Pomeranian Medical University","correspondingAuthor":false,"prefix":"","firstName":"Jan","middleName":"","lastName":"Bińkowski","suffix":""},{"id":508142261,"identity":"16c75b1b-7b01-4d51-b45f-b04ad0bc963c","order_by":1,"name":"Tomasz K. Wojdacz","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABBElEQVRIiWNgGAWjYHCDAwZAwgbC5gFiPhzqeNC0pCGE2QhrYQBpOUxYiz17d+LHH38YEvsZD2/88OPP+TyDawcYH7xtY8jDaQvP2c3SPDwMiTMbjhVL9vDcLja4ncBsOLeNoRinFoncDdIMEgy5Gw6cMQAybiduuJ3AJs3bxpDYhlvL5p8/DMBajH8zGJwDaWH/TUDLNgmeBLAWM2mGhANgW5jxajlzdps1zwGJeqBfyix7DiQXS95ObJacc04Cp1/Y23s33/zxx8aYX+Lw5hs//tjl8d1OPvjhTZlNHj8OLVAgAUQHwKwEBgbGBpBIAn4dIMDfANPCgMoYBaNgFIyCEQ8Aa1pcC6K/cyUAAAAASUVORK5CYII=","orcid":"","institution":"Pomeranian Medical University","correspondingAuthor":true,"prefix":"","firstName":"Tomasz","middleName":"K.","lastName":"Wojdacz","suffix":""}],"badges":[],"createdAt":"2025-08-19 11:53:28","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7408332/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7408332/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":90578478,"identity":"5ea931ad-a78a-4ad6-8289-fb9048d64a76","added_by":"auto","created_at":"2025-09-04 09:45:44","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":988792,"visible":true,"origin":"","legend":"","description":"","filename":"Binkowski.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7408332/v1_covered_6d5a208f-3597-4679-93fb-815ace2cc504.pdf"},{"id":90576116,"identity":"da13b4f8-8345-4264-90a4-d781a00ffe89","added_by":"auto","created_at":"2025-09-04 09:21:42","extension":"xlsx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":173078,"visible":true,"origin":"","legend":"","description":"","filename":"AdditionalTables.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-7408332/v1/c0a0ca6051dca512e9922b6a.xlsx"},{"id":90575633,"identity":"85f629ec-dac1-45b3-9d4a-8ee8f3d9ba53","added_by":"auto","created_at":"2025-09-04 09:13:42","extension":"html","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":516733,"visible":true,"origin":"","legend":"","description":"","filename":"Additionalfile1.html","url":"https://assets-eu.researchsquare.com/files/rs-7408332/v1/8ee4bfaffc4949eb3b660b5a.html"},{"id":90575636,"identity":"67336b69-eb2d-49c1-bba7-8127747809df","added_by":"auto","created_at":"2025-09-04 09:13:42","extension":"html","order_by":3,"title":"","display":"","copyAsset":false,"role":"supplement","size":361093,"visible":true,"origin":"","legend":"","description":"","filename":"Additionalfile2.html","url":"https://assets-eu.researchsquare.com/files/rs-7408332/v1/6ecb7ebbf112f3022bad4c68.html"},{"id":90576117,"identity":"86230877-ed88-444b-b427-a6896ab01c00","added_by":"auto","created_at":"2025-09-04 09:21:42","extension":"html","order_by":4,"title":"","display":"","copyAsset":false,"role":"supplement","size":382979,"visible":true,"origin":"","legend":"","description":"","filename":"Additionalfile3.html","url":"https://assets-eu.researchsquare.com/files/rs-7408332/v1/65f09cdce03677b260c727ec.html"},{"id":90575644,"identity":"b715c461-9657-42de-ab26-c77671c6c1f1","added_by":"auto","created_at":"2025-09-04 09:13:42","extension":"html","order_by":5,"title":"","display":"","copyAsset":false,"role":"supplement","size":497261,"visible":true,"origin":"","legend":"","description":"","filename":"Additionalfile4.html","url":"https://assets-eu.researchsquare.com/files/rs-7408332/v1/c5c694160e3ee79f95362760.html"},{"id":90575639,"identity":"58a3aa43-9c7a-48cf-b222-abf7b921b371","added_by":"auto","created_at":"2025-09-04 09:13:42","extension":"html","order_by":6,"title":"","display":"","copyAsset":false,"role":"supplement","size":495665,"visible":true,"origin":"","legend":"","description":"","filename":"Additionalfile5.html","url":"https://assets-eu.researchsquare.com/files/rs-7408332/v1/e4b74a84f4b20fc65f222709.html"}],"financialInterests":"No competing interests reported.","formattedTitle":"DNA Methylation Biomarkers-based Pan-Cancer Classifier: Predictive Modeling for Cancer Classification","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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":"genome-medicine","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Genome Medicine](https://genomemedicine.biomedcentral.com/)","snPcode":"13073","submissionUrl":"https://submission.springernature.com/new-submission/13073/3","title":"Genome Medicine","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"DNA methylation, machine-learning, biomarkers, cancer, classification","lastPublishedDoi":"10.21203/rs.3.rs-7408332/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7408332/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground:\u003c/h2\u003e\u003cp\u003eMachine-learning (ML) driven molecular diagnostics based on omics data has a potential to revolutionize personalized medicine. However, implementation of ML into diagnostic protocols is hindered by methodological challenges which often lead to inflated performance assessment of models during development followed by poor performance of these models in implementation phase. Here, we aimed to develop and validate a pan-cancer classification framework based on DNA methylation data, that addresses methodological challenges of omics data powered ML.\u003c/p\u003e\u003ch2\u003eMethods:\u003c/h2\u003e\u003cp\u003eWe curated a primary dataset of DNA methylation profiles for 10 756 samples, that included 54 healthy and cancer tissue types and validation dataset comprising data for 2 306 samples from 28 independent studies. The classification framework was build using custom biomarkers selection strategy based on effect size metric that considers variance and class imbalance. The ML models were trained, tuned and evaluated using nested cross-validation approach. Local Outlier Factor algorithm was built into the inference pipelines to identify and filter samples displaying technical or biological anomalies. Additionally, for methodological validation of our framework we used methylation profiles for 3 905 central nervous system (CNS) tumors.\u003c/p\u003e\u003ch2\u003eResults:\u003c/h2\u003e\u003cp\u003eWe found that relatively simple ML models outperformed complex algorithms such as deep neural network. A logistic regression classifier achieved a balanced accuracy (BACC) of 0.90 to classify 54 cancer and healthy tissue types using methylation levels at 1208 CpG sites. Similarly, our CNS tumor classifier also based on logistic regression algorithm reached a BACC of 0.94 across 59 CNS tumor subtypes. The anomaly filtering improved performance across all categories of samples tested. We deployed our inference pipelines for public access via secure web platform - \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://opp.pum.edu.pl/\u003c/span\u003e\u003cspan address=\"https://opp.pum.edu.pl/\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/p\u003e\u003ch2\u003eConclusions:\u003c/h2\u003e\u003cp\u003eOur study demonstrates that DNA methylation profiling, when combined with carefully controlled ML practices allows for development of robust solutions that might substantially increase the efficacy of oncological diagnosis.\u003c/p\u003e","manuscriptTitle":"DNA Methylation Biomarkers-based Pan-Cancer Classifier: Predictive Modeling for Cancer Classification","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-04 09:13:37","doi":"10.21203/rs.3.rs-7408332/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-11-03T20:18:43+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-12T19:36:18+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-07T12:48:49+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"103367015683923306881181249342681892794","date":"2025-09-29T18:31:03+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"276606794614624897382574688511742817482","date":"2025-09-25T10:35:05+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-09-22T17:11:45+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-09-17T08:20:43+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"155132524886898094575058631839602586588","date":"2025-08-31T21:38:30+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"288333765833960389700248960267037902406","date":"2025-08-29T05:52:16+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-08-26T16:34:40+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-08-26T14:03:04+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-08-20T06:00:08+00:00","index":"","fulltext":""},{"type":"submitted","content":"Genome Medicine","date":"2025-08-19T11:49:40+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"genome-medicine","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Genome Medicine](https://genomemedicine.biomedcentral.com/)","snPcode":"13073","submissionUrl":"https://submission.springernature.com/new-submission/13073/3","title":"Genome Medicine","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"a7afcc18-6c65-4a0c-8a92-bdf37449571a","owner":[],"postedDate":"September 4th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-04-03T19:09:38+00:00","versionOfRecord":[],"versionCreatedAt":"2025-09-04 09:13:37","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7408332","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7408332","identity":"rs-7408332","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}