Self-supervised Graph Contrastive Learning for scRNA-seq Clustering

Self-supervised Graph Contrastive Learning for scRNA-seq Clustering | 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Research Article Self-supervised Graph Contrastive Learning for scRNA-seq Clustering Tong Wu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8072547/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 5 You are reading this latest preprint version Abstract Single-cell RNA sequencing (scRNA-seq) technology has enabled us to characterize cellular heterogeneity, and analyzing scRNA-seq data can help enhance our understanding of complex diseases. Clustering of scRNA-seq data is a critical step in the analysis, as it assigns cells to subpopulations, facilitating a deeper understanding of cellular diversity. Although numerous scRNA-seq clustering algorithms have been proposed, they often fail to consider inherent cell type information and the intrinsic relationships between cells. As a result, the learned representations may be suboptimal for accurate cell type identification, limiting overall performance. To address these challenges, we propose a self-supervised graph learning (SSGL) method for scRNA-seq clustering. SSGL aims to enhance feature representation learning and achieve more stable clustering results by incorporating both inherent cell type information and cell relationships. Specifically, our method applies dual random masking to gene expression profiles, generating two augmented datasets. We assume that samples within the same cluster, along with their augmentations, should exhibit similarity. To enforce this assumption, we construct a graph that captures inherent cell relationships across the augmented datasets. Additionally, high-confidence cell type identifications are leveraged to guide representation learning and ensure consistency between the clustering results of the two augmented datasets. This approach strengthens feature representation robustness and improves clustering stability. Extensive experiments on multiple public datasets demonstrate that our method outperforms baseline algorithms in clustering accuracy and provides valuable biological insights into scRNA-seq data. scRNA-seq clustering Graph contrastive learning Self-supervised learning Full Text Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Major revision 28 Dec, 2025 Reviewers agreed at journal 07 Dec, 2025 Reviewers invited by journal 07 Dec, 2025 Editor assigned by journal 11 Nov, 2025 First submitted to journal 09 Nov, 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-8072547","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":556396428,"identity":"2d1574f7-3cbf-405c-9c09-67258af25b48","order_by":0,"name":"Tong Wu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAxklEQVRIiWNgGAWjYJCCAx///JMDMx4Qo5yHgYHx4cyGA8ZgLQlEamE25m04kNgA4hGlxV4ix0yad8ed9Plhhx8CbbGT020gZAtQi+TcM89yN95OMwBqSTY2O0BIi3SOmcQbNubcjbMTQFoOJG4jSgsPG3O64ez0D0RrMTbkbTucIC+dQ6wt958VPpxxJs1wg3ROwYEEAyL8wt5zeMOBDxU28vKz0zd/+FBhJ0dQCxwYgFUaEKscBOQbSFE9CkbBKBgFIwoAAM40SEmwJaLMAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0009-0007-9058-8854","institution":"The University of Melbourne Faculty of Science","correspondingAuthor":true,"prefix":"","firstName":"Tong","middleName":"","lastName":"Wu","suffix":""}],"badges":[],"createdAt":"2025-11-10 04:13:45","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8072547/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8072547/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":97996879,"identity":"bebf95e4-31c1-4437-be50-6bae808e6b27","added_by":"auto","created_at":"2025-12-11 15:29:28","extension":"xml","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5305,"visible":true,"origin":"","legend":"","description":"","filename":"jtrmJTRMD2519856.xml","url":"https://assets-eu.researchsquare.com/files/rs-8072547/v1/8d9809cba21874541006e7f8.xml"},{"id":98424637,"identity":"698c5f13-c79b-478f-a0c1-cc58d6348649","added_by":"auto","created_at":"2025-12-17 16:33:36","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":929,"visible":true,"origin":"","legend":"","description":"","filename":"JTRMD2519856154570.go.xml","url":"https://assets-eu.researchsquare.com/files/rs-8072547/v1/1809d3c15da13ac9929d9302.xml"},{"id":97996881,"identity":"fe0d85ed-c808-4d4c-b427-58c017f0c554","added_by":"auto","created_at":"2025-12-11 15:29:28","extension":"xml","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":791,"visible":true,"origin":"","legend":"","description":"","filename":"JTRMD2519856Import.xml","url":"https://assets-eu.researchsquare.com/files/rs-8072547/v1/8a303f8a46a233d1583e3963.xml"},{"id":98444119,"identity":"c8f5d214-223e-4481-adea-b8652556125e","added_by":"auto","created_at":"2025-12-17 17:15:05","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":4003688,"visible":true,"origin":"","legend":"","description":"","filename":"snarticle1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8072547/v1_covered_7a31ebd5-5143-45aa-ad92-9c5fb35b3524.pdf"}],"financialInterests":"","formattedTitle":"Self-supervised Graph Contrastive Learning for scRNA-seq Clustering","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":true,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"journal-of-translational-medicine","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jtrm","sideBox":"Learn more about [Journal of Translational Medicine](http://translational-medicine.biomedcentral.com)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/jtrm/default.aspx","title":"Journal of Translational Medicine","twitterHandle":"@BioMedCentral","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"scRNA-seq clustering, Graph contrastive learning, Self-supervised learning","lastPublishedDoi":"10.21203/rs.3.rs-8072547/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8072547/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Single-cell RNA sequencing (scRNA-seq) technology has enabled us to characterize cellular heterogeneity, and analyzing scRNA-seq data can help enhance our understanding of complex diseases. Clustering of scRNA-seq data is a critical step in the analysis, as it assigns cells to subpopulations, facilitating a deeper understanding of cellular diversity. Although numerous scRNA-seq clustering algorithms have been proposed, they often fail to consider inherent cell type information and the intrinsic relationships between cells. As a result, the learned representations may be suboptimal for accurate cell type identification, limiting overall performance. To address these challenges, we propose a self-supervised graph learning (SSGL) method for scRNA-seq clustering. SSGL aims to enhance feature representation learning and achieve more stable clustering results by incorporating both inherent cell type information and cell relationships. Specifically, our method applies dual random masking to gene expression profiles, generating two augmented datasets. We assume that samples within the same cluster, along with their augmentations, should exhibit similarity. To enforce this assumption, we construct a graph that captures inherent cell relationships across the augmented datasets. Additionally, high-confidence cell type identifications are leveraged to guide representation learning and ensure consistency between the clustering results of the two augmented datasets. This approach strengthens feature representation robustness and improves clustering stability. Extensive experiments on multiple public datasets demonstrate that our method outperforms baseline algorithms in clustering accuracy and provides valuable biological insights into scRNA-seq data.","manuscriptTitle":"Self-supervised Graph Contrastive Learning for scRNA-seq Clustering","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-11 15:29:21","doi":"10.21203/rs.3.rs-8072547/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Major revision","date":"2025-12-28T07:41:43+00:00","index":"","fulltext":""},{"type":"reviewerAgreed","content":"","date":"2025-12-07T07:01:15+00:00","index":0,"fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-12-07T06:31:54+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-11-11T16:20:18+00:00","index":"","fulltext":""},{"type":"submitted","content":"Journal of Translational Medicine","date":"2025-11-09T23:12:51+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"journal-of-translational-medicine","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jtrm","sideBox":"Learn more about [Journal of Translational Medicine](http://translational-medicine.biomedcentral.com)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/jtrm/default.aspx","title":"Journal of Translational Medicine","twitterHandle":"@BioMedCentral","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"ef2d8ef8-eced-4511-abf5-848074f632a4","owner":[],"postedDate":"December 11th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-05-10T17:15:09+00:00","versionOfRecord":[],"versionCreatedAt":"2025-12-11 15:29:21","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8072547","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8072547","identity":"rs-8072547","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}