bioLUCID: quantifying batch and biological effect in single-cell transcriptomics by hypothesis-driven variance decomposition

bioLUCID: quantifying batch and biological effect in single-cell transcriptomics by hypothesis-driven variance decomposition | 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 Brief Communication bioLUCID: quantifying batch and biological effect in single-cell transcriptomics by hypothesis-driven variance decomposition Jean Hausser, Chuhanwen Sun, Alper Eroglu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7290456/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Batch-correcting single-cell gene expression data enables multi-sample analyses but risks erasing sample-specific biology along with batch effects. To address this, we introduce a novel heuristic to decompose gene expression variation into biological and batch effects. This decomposition allows (i) integrating cell embeddings across samples without erasing sample-specific biology, and (ii) flagging samples with excessive batch effects, with benefits for multiple applications such as exploring transcriptional heterogeneity and multi-omics integration. Biological sciences/Computational biology and bioinformatics/Data integration Biological sciences/Biological techniques/Gene expression analysis Full Text Additional Declarations There is NO Competing Interest. Supplementary Files Supplementarymaterial4.pdf Supplementary information Cite Share Download PDF Status: Posted 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-7290456","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Brief Communication","associatedPublications":[],"authors":[{"id":495523316,"identity":"f8c65b38-d115-476f-8458-11fc0c1e206c","order_by":0,"name":"Jean Hausser","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA2ElEQVRIiWNgGAWjYBACxgYYAQIfDkiQqIVxBjFaEPqAgJnnABGqmdubnz1g3GGXOL//8LHPNmcsGOTbG/BrYew5Zm7AeCY5ccONtOTZOTckGAzOELCKcUaCmQRjG3PiBgkeY+acD0AtEgkEtMx//g2opR7osPOfmS2AWuTnPyBkCw/IlsOJDQdymJkZgA5juIFfB9AvOWUSiW3HjYF+MWbsOSPBY3CGgMMM249vk/jYVi0LDLHHDD+O1cnJtx8goKUBSCAby0PAWQwM8gRVjIJRMApGwSgAAM77Q+NzcPzPAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0000-0002-3321-7199","institution":"Karolinska Institute \u0026 SciLifeLab","correspondingAuthor":true,"prefix":"","firstName":"Jean","middleName":"","lastName":"Hausser","suffix":""},{"id":495523317,"identity":"f3bd18b7-b484-4a92-841a-9bfd0b7035fe","order_by":1,"name":"Chuhanwen Sun","email":"","orcid":"","institution":"Karolinska Institute \u0026 SciLifeLab","correspondingAuthor":false,"prefix":"","firstName":"Chuhanwen","middleName":"","lastName":"Sun","suffix":""},{"id":495523318,"identity":"eba7960f-3502-4d76-b987-c1fb7fd1264e","order_by":2,"name":"Alper Eroglu","email":"","orcid":"","institution":"Karolinska Institute \u0026 SciLifeLab","correspondingAuthor":false,"prefix":"","firstName":"Alper","middleName":"","lastName":"Eroglu","suffix":""}],"badges":[],"createdAt":"2025-08-04 11:11:33","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7290456/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7290456/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":88466974,"identity":"d5295201-20fd-4c53-8fea-36d6e69d478d","added_by":"auto","created_at":"2025-08-06 17:49:03","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":996163,"visible":true,"origin":"","legend":"Article File","description":"","filename":"bioLUCIDmanuscript3.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7290456/v1_covered_59fcf45f-2b1f-4c9f-b12e-4584f98571c6.pdf"},{"id":88327269,"identity":"a2c6e946-66a8-463c-89fe-94d089e20fd0","added_by":"auto","created_at":"2025-08-05 10:03:44","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":5132657,"visible":true,"origin":"","legend":"Supplementary information","description":"","filename":"Supplementarymaterial4.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7290456/v1/e145ae88ce9d88b4becc67a3.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"bioLUCID: quantifying batch and biological effect in single-cell transcriptomics by hypothesis-driven variance decomposition","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-7290456/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7290456/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Batch-correcting single-cell gene expression data enables multi-sample analyses but risks erasing sample-specific biology along with batch effects. To address this, we introduce a novel heuristic to decompose gene expression variation into biological and batch effects. This decomposition allows (i) integrating cell embeddings across samples without erasing sample-specific biology, and (ii) flagging samples with excessive batch effects, with benefits for multiple applications such as exploring transcriptional heterogeneity and multi-omics integration.","manuscriptTitle":"bioLUCID: quantifying batch and biological effect in single-cell transcriptomics by hypothesis-driven variance decomposition","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-05 10:03:39","doi":"10.21203/rs.3.rs-7290456/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"nature-methods","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"nmeth","sideBox":"Learn more about [Nature Methods](http://www.nature.com/nmeth)","snPcode":"","submissionUrl":"","title":"Nature Methods","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Research","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"14a595f3-7c69-4ba9-bf29-02c088b5750a","owner":[],"postedDate":"August 5th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":52625416,"name":"Biological sciences/Computational biology and bioinformatics/Data integration"},{"id":52625417,"name":"Biological sciences/Biological techniques/Gene expression analysis"}],"tags":[],"updatedAt":"2025-09-02T08:45:10+00:00","versionOfRecord":[],"versionCreatedAt":"2025-08-05 10:03:39","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7290456","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7290456","identity":"rs-7290456","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}