FedscGen: privacy-aware federated batch effect correction of single-cell RNA sequencing data

FedscGen: privacy-aware federated batch effect correction of single-cell RNA sequencing data | 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 FedscGen: privacy-aware federated batch effect correction of single-cell RNA sequencing data Mohammad Bakhtiari, Stefan Bonn, Fabian Theis, Olga Zolotareva, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4807285/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 22 Jul, 2025 Read the published version in Genome Biology → Version 1 posted 9 You are reading this latest preprint version Abstract scRNA-seq data from clinical samples are prone to batch effects, while hospitals are hesitant to share their data for centralized analysis, including batch effect correction, due to the privacy sensitivity of human genomic data. We present FedscGen, a novel privacy-aware federated method based on the generative integration approach scGen. FedscGen presents two federated workflows for training and correction of batch effects with inclusion of new studies. We benchmark FedscGen and scGen using eight datasets and nine metrics to demonstrate competitive results. On the Human Pancreas dataset, for instance, the performance difference of all models is zero for NMI, GC, ILF1, ASW_C, and kBET while FedscGen outperforms by 0.03 in EBM. FedscGen opens a privacy-preserving path for single-cell RNAseq batch effect correction in particular in clinical multi-center studies. FedscGen is published as a FeatureCloud app to be used in real world federated collaboration ( https://featurecloud.ai/app/fedscgen ). Full Text Additional Declarations No competing interests reported. Supplementary Files FedscGenSupplementary.pdf Cite Share Download PDF Status: Published Journal Publication published 22 Jul, 2025 Read the published version in Genome Biology → Version 1 posted Editorial decision: Revision requested 11 Mar, 2025 Reviews received at journal 10 Mar, 2025 Reviewers agreed at journal 09 Feb, 2025 Reviews received at journal 29 Aug, 2024 Reviewers agreed at journal 12 Aug, 2024 Reviewers invited by journal 12 Aug, 2024 Editor assigned by journal 05 Aug, 2024 Submission checks completed at journal 29 Jul, 2024 First submitted to journal 26 Jul, 2024 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-4807285","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":342179236,"identity":"008ca6b2-fe82-409e-8a87-cebf7bd1d42e","order_by":0,"name":"Mohammad Bakhtiari","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABRUlEQVRIie3Rv0rDQBzA8V8IZDrpeuUafAIh5SAqrfoqCYG6JKHSRRD0itAs1WxygugrVISstgTaJXW2ZBLBB1CQogG9RET6x0I3kXyHu3DHhx/hAPLy/mQoWyWGQZYBMIitC6CB8XO1kBgpUYylSHaipeuvZM076T2P7G2VkeNHujfeWF330Cup18EtnA37ZP8NVH+S6NGdRZzAoqzUpxY3cPkiXAkI16CBY7dWHJ4CPZ8co9/bmiCyybBBQ2RgicuCIO3DZLGtF5ttMDvdaULfneBIkN2XlOxwGT0JAubVN7mdIbqYEgpiU0sQUxAlI52UsLH4mP6XSK84wYC2SlGDohq2uKzQSkquY9fabDJM+dSUQZvGTnCg+sS7Iah6uMUL4UOMEjAvY6c3YklV9Wce5itl/rHUwvMvFpQsLfLy8vL+XZ9wxnMniFEZiQAAAABJRU5ErkJggg==","orcid":"","institution":"University of Hamburg","correspondingAuthor":true,"prefix":"","firstName":"Mohammad","middleName":"","lastName":"Bakhtiari","suffix":""},{"id":342179237,"identity":"def3adec-d5aa-47fb-bf25-e1221bac10eb","order_by":1,"name":"Stefan Bonn","email":"","orcid":"","institution":"University Medical Center Hamburg-Eppendorf","correspondingAuthor":false,"prefix":"","firstName":"Stefan","middleName":"","lastName":"Bonn","suffix":""},{"id":342179238,"identity":"2cf7c540-0b68-4624-87ff-a12af89d2bb8","order_by":2,"name":"Fabian Theis","email":"","orcid":"","institution":"Helmholtz Munich","correspondingAuthor":false,"prefix":"","firstName":"Fabian","middleName":"","lastName":"Theis","suffix":""},{"id":342179239,"identity":"185dc581-5b0b-4df3-a836-64fdb24f7acc","order_by":3,"name":"Olga Zolotareva","email":"","orcid":"","institution":"University of Hamburg","correspondingAuthor":false,"prefix":"","firstName":"Olga","middleName":"","lastName":"Zolotareva","suffix":""},{"id":342179240,"identity":"f16c62d1-0fd9-4edf-b653-9bc6d7cc4569","order_by":4,"name":"Jan Baumbach","email":"","orcid":"","institution":"University of Hamburg","correspondingAuthor":false,"prefix":"","firstName":"Jan","middleName":"","lastName":"Baumbach","suffix":""}],"badges":[],"createdAt":"2024-07-26 10:06:30","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4807285/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4807285/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1186/s13059-025-03684-6","type":"published","date":"2025-07-22T15:57:49+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":87756741,"identity":"f266ece0-ec9e-435e-b833-32a5bfb128c0","added_by":"auto","created_at":"2025-07-28 16:08:34","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1289948,"visible":true,"origin":"","legend":"","description":"","filename":"FedscGen.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4807285/v1_covered_29f260f9-61ed-4dfd-9876-313912361386.pdf"},{"id":63062017,"identity":"a6794d35-527b-4a9b-bc10-fc2ce4b7a097","added_by":"auto","created_at":"2024-08-22 16:27:02","extension":"pdf","order_by":5,"title":"","display":"","copyAsset":false,"role":"supplement","size":4448410,"visible":true,"origin":"","legend":"","description":"","filename":"FedscGenSupplementary.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4807285/v1/b32adb29060a31aba5200931.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"FedscGen: privacy-aware federated batch effect correction of single-cell RNA sequencing data","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-biology","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"gbio","sideBox":"Learn more about [Genome Biology](https://genomebiology.biomedcentral.com/)","snPcode":"13059","submissionUrl":"https://submission.springernature.com/new-submission/13059/3","title":"Genome Biology","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-4807285/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4807285/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003escRNA-seq data from clinical samples are prone to batch effects, while hospitals are hesitant to share their data for centralized analysis, including batch effect correction, due to the privacy sensitivity of human genomic data. We present FedscGen, a novel privacy-aware federated method based on the generative integration approach scGen. FedscGen presents two federated workflows for training and correction of batch effects with inclusion of new studies. We benchmark FedscGen and scGen using eight datasets and nine metrics to demonstrate competitive results. On the Human Pancreas dataset, for instance, the performance difference of all models is zero for NMI, GC, ILF1, ASW_C, and kBET while FedscGen outperforms by 0.03 in EBM. FedscGen opens a privacy-preserving path for single-cell RNAseq batch effect correction in particular in clinical multi-center studies. FedscGen is published as a FeatureCloud app to be used in real world federated collaboration (\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://featurecloud.ai/app/fedscgen\u003c/span\u003e\u003cspan address=\"https://featurecloud.ai/app/fedscgen\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003cspan type=\"Underline\" class=\"Underline\" name=\"Emphasis\"\u003e).\u003c/span\u003e\u003c/p\u003e","manuscriptTitle":"FedscGen: privacy-aware federated batch effect correction of single-cell RNA sequencing data","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-08-22 16:26:57","doi":"10.21203/rs.3.rs-4807285/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-03-11T09:53:32+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-03-10T19:11:02+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"70087219500595645575145849972288210414","date":"2025-02-09T23:34:17+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-08-29T13:45:58+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"306121337895752244582508589556343586720","date":"2024-08-12T13:55:36+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-08-12T10:26:12+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-08-05T13:38:48+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-07-29T08:47:43+00:00","index":"","fulltext":""},{"type":"submitted","content":"Genome Biology","date":"2024-07-26T10:04:01+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"genome-biology","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"gbio","sideBox":"Learn more about [Genome Biology](https://genomebiology.biomedcentral.com/)","snPcode":"13059","submissionUrl":"https://submission.springernature.com/new-submission/13059/3","title":"Genome Biology","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"bdc4d5a5-620a-4ba0-9cb9-30ede92854fb","owner":[],"postedDate":"August 22nd, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-07-28T16:02:24+00:00","versionOfRecord":{"articleIdentity":"rs-4807285","link":"https://doi.org/10.1186/s13059-025-03684-6","journal":{"identity":"genome-biology","isVorOnly":false,"title":"Genome Biology"},"publishedOn":"2025-07-22 15:57:49","publishedOnDateReadable":"July 22nd, 2025"},"versionCreatedAt":"2024-08-22 16:26:57","video":"","vorDoi":"10.1186/s13059-025-03684-6","vorDoiUrl":"https://doi.org/10.1186/s13059-025-03684-6","workflowStages":[]},"version":"v1","identity":"rs-4807285","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4807285","identity":"rs-4807285","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}