scGALA: Graph Link Prediction Based Cell Alignment for Comprehensive Data Integration

scGALA: Graph Link Prediction Based Cell Alignment for Comprehensive Data Integration | 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 scGALA: Graph Link Prediction Based Cell Alignment for Comprehensive Data Integration Jun Ding, Guo Jiang, Kailu Song, Iain Clark This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6656477/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 26 Nov, 2025 Read the published version in Nature Communications → Version 1 posted You are reading this latest preprint version Abstract Single-cell technologies have transformed our understanding of cellular heterogeneity through multimodal data acquisition. However, robust cell alignment remains a major challenge for data integration and harmonization, including batch correction, label transfer, and multiomics integration. Many existing methods constrain alignment based on rigid feature-wise distance metrics, limiting their ability to capture accurate cell correspondence across diverse cell populations and conditions. We introduce scGALA, a graph-based learning framework that redefines cell alignment by combining graph attention networks with a score-driven, task-independent optimization strategy. scGALA constructs enriched graphs of cell–cell relationships by integrating gene expression profiles with auxiliary information such as spatial coordinates and iteratively refines alignment via self-supervised graph link prediction, where a deep neural network is trained to identify and reinforce high-confidence correspondences across datasets. In extensive benchmarks, scGALA identifies over 25 percent more high-confidence alignments without compromising accuracy. By improving the core step of cell alignment, scGALA serves as a versatile enhancer for a wide range of single-cell data integration tasks. Biological sciences/Computational biology and bioinformatics/Machine learning Biological sciences/Computational biology and bioinformatics/Data integration Biological sciences/Computational biology and bioinformatics/Software Cell Alignment Link Prediction Data Integration Deep Learning Graph Neural Network Single Cell multiomics Spatial Transcriptomics Full Text Additional Declarations There is NO Competing Interest. Supplementary Files EditorialPolicyChecklist.pdf Editorial Policy Checklist CodeandSoftwareSubmissionChecklist.pdf Code and Software Submission Checklist ReportingSummary.pdf Reporting Summary scGALASupplementaryFigures.pdf scGALA Supplementary Figures Cite Share Download PDF Status: Published Journal Publication published 26 Nov, 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-6656477","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":456997050,"identity":"020a7d2b-2a5d-4dfe-90e5-35542194cb53","order_by":0,"name":"Jun Ding","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA00lEQVRIiWNgGAWjYBACxgYgwWPAwMAP4iUUWJCgRRLESDCQINIqHiA2OABiEaOFeUbuAYY3BXfsNl87/PjFA6AW/vYDBBw2Iy+BcY7Bs+Rtt9PMLEAOkziTQEhLjgEzj8HhZLPbOWwGIC0GDMRqMZ4N08L/gDgtdgbSOcwPwFokCNnS88bg4ByDwwkSQL+AAplH4gYBWwzbcwwfvPlz2J5/dvLjjz8qbOT4+wnYYtjAwHAASCcCaTZQpPDgVw8E8lDaHoiZPxBUPgpGwSgYBSMSAACvBz9uU/isZwAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0001-5183-6885","institution":"McGill University","correspondingAuthor":true,"prefix":"","firstName":"Jun","middleName":"","lastName":"Ding","suffix":""},{"id":456997051,"identity":"652d24a9-a6ac-46de-865b-0966c177227b","order_by":1,"name":"Guo Jiang","email":"","orcid":"https://orcid.org/0000-0002-3405-1119","institution":"Mcgill University","correspondingAuthor":false,"prefix":"","firstName":"Guo","middleName":"","lastName":"Jiang","suffix":""},{"id":456997052,"identity":"91f5ff1e-b7dd-4abf-98be-bccdead6d55d","order_by":2,"name":"Kailu Song","email":"","orcid":"https://orcid.org/0009-0003-5326-7593","institution":"McGill University","correspondingAuthor":false,"prefix":"","firstName":"Kailu","middleName":"","lastName":"Song","suffix":""},{"id":456997053,"identity":"3185404f-21fa-46c3-8e3e-7af6a5aa7a05","order_by":3,"name":"Iain Clark","email":"","orcid":"https://orcid.org/0000-0001-9082-0253","institution":"University of California, Berkeley","correspondingAuthor":false,"prefix":"","firstName":"Iain","middleName":"","lastName":"Clark","suffix":""}],"badges":[],"createdAt":"2025-05-13 14:26:18","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6656477/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6656477/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41467-025-66644-5","type":"published","date":"2025-11-26T05:00:00+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":99211908,"identity":"40915447-27ff-4b9e-b5eb-f4d3209e7c08","added_by":"auto","created_at":"2025-12-30 08:19:05","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":8195431,"visible":true,"origin":"","legend":"Article File","description":"","filename":"scGALAManuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6656477/v1_covered_c5cc5c9f-3768-46cd-aa5a-0a144a855173.pdf"},{"id":83612852,"identity":"56943296-8eac-4d58-adda-aaaa6db81b5e","added_by":"auto","created_at":"2025-05-29 12:49:10","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":1666861,"visible":true,"origin":"","legend":"Editorial Policy Checklist","description":"","filename":"EditorialPolicyChecklist.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6656477/v1/7bc73186785db7f7c4afc267.pdf"},{"id":83612851,"identity":"34ae8bda-85d2-4a28-9bc3-a178eca37bd8","added_by":"auto","created_at":"2025-05-29 12:49:10","extension":"pdf","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":1317201,"visible":true,"origin":"","legend":"Code and Software Submission Checklist","description":"","filename":"CodeandSoftwareSubmissionChecklist.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6656477/v1/32a8fd94d35f4b0275d12462.pdf"},{"id":83612683,"identity":"01c0b0da-fcde-4a87-96c5-8e57f43c4203","added_by":"auto","created_at":"2025-05-29 12:41:09","extension":"pdf","order_by":3,"title":"","display":"","copyAsset":false,"role":"supplement","size":1665982,"visible":true,"origin":"","legend":"Reporting Summary","description":"","filename":"ReportingSummary.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6656477/v1/4679c050a23f7ecb4fca0f12.pdf"},{"id":83612689,"identity":"bce93232-368a-4b34-9853-13c997550b06","added_by":"auto","created_at":"2025-05-29 12:41:10","extension":"pdf","order_by":4,"title":"","display":"","copyAsset":false,"role":"supplement","size":32568318,"visible":true,"origin":"","legend":"scGALA Supplementary Figures","description":"","filename":"scGALASupplementaryFigures.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6656477/v1/3b401039455741311aa954c2.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"scGALA: Graph Link Prediction Based Cell Alignment for Comprehensive Data Integration","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":"Cell Alignment, Link Prediction, Data Integration, Deep Learning, Graph Neural Network, Single Cell, multiomics, Spatial Transcriptomics","lastPublishedDoi":"10.21203/rs.3.rs-6656477/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6656477/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Single-cell technologies have transformed our understanding of cellular heterogeneity through multimodal data acquisition. However, robust cell alignment remains a major challenge for data integration and harmonization, including batch correction, label transfer, and multiomics integration. Many existing methods constrain alignment based on rigid feature-wise distance metrics, limiting their ability to capture accurate cell correspondence across diverse cell populations and conditions. We introduce scGALA, a graph-based learning framework that redefines cell alignment by combining graph attention networks with a score-driven, task-independent optimization strategy. scGALA constructs enriched graphs of cell–cell relationships by integrating gene expression profiles with auxiliary information such as spatial coordinates and iteratively refines alignment via self-supervised graph link prediction, where a deep neural network is trained to identify and reinforce high-confidence correspondences across datasets. In extensive benchmarks, scGALA identifies over 25 percent more high-confidence alignments without compromising accuracy. By improving the core step of cell alignment, scGALA serves as a versatile enhancer for a wide range of single-cell data integration tasks.","manuscriptTitle":"scGALA: Graph Link Prediction Based Cell Alignment for Comprehensive Data Integration","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-05-29 12:41:05","doi":"10.21203/rs.3.rs-6656477/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":"ddf96e2d-0a71-4c7a-ba7e-b28cd8f6bf64","owner":[],"postedDate":"May 29th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":48570944,"name":"Biological sciences/Computational biology and bioinformatics/Machine learning"},{"id":48570945,"name":"Biological sciences/Computational biology and bioinformatics/Data integration"},{"id":48570946,"name":"Biological sciences/Computational biology and bioinformatics/Software"}],"tags":[],"updatedAt":"2025-12-30T08:18:54+00:00","versionOfRecord":{"articleIdentity":"rs-6656477","link":"https://doi.org/10.1038/s41467-025-66644-5","journal":{"identity":"nature-communications","isVorOnly":false,"title":"Nature Communications"},"publishedOn":"2025-11-26 05:00:00","publishedOnDateReadable":"November 26th, 2025"},"versionCreatedAt":"2025-05-29 12:41:05","video":"","vorDoi":"10.1038/s41467-025-66644-5","vorDoiUrl":"https://doi.org/10.1038/s41467-025-66644-5","workflowStages":[]},"version":"v1","identity":"rs-6656477","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6656477","identity":"rs-6656477","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}