LLM-based cell type annotation harmonization across single-cell studies using GCTHarmony

LLM-based cell type annotation harmonization across single-cell studies using GCTHarmony | 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 Short Report LLM-based cell type annotation harmonization across single-cell studies using GCTHarmony Xingyuan Zhang, Zhicheng Ji This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7151095/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 10 You are reading this latest preprint version Abstract A major challenge in integrating previously analyzed single-cell RNA-seq studies is the inconsistency of cell type annotations. To address this, we developed GCTHarmony, an LLM-based method for harmonizing cell type annotations across single-cell studies. Utilizing OpenAI's text embedding model, GCTHarmony accurately maps arbitrary cell type annotations to standardized cell ontology terms and reconciles discrepancies in annotation hierarchies across studies. In a real data example, we show that GCTHarmony substantially improves the consistency of cell type annotations across single-cell studies. Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 13 Nov, 2025 Reviews received at journal 09 Oct, 2025 Reviews received at journal 25 Sep, 2025 Reviewers agreed at journal 21 Sep, 2025 Reviewers agreed at journal 16 Sep, 2025 Reviewers agreed at journal 13 Aug, 2025 Reviewers invited by journal 05 Aug, 2025 Editor assigned by journal 21 Jul, 2025 Submission checks completed at journal 18 Jul, 2025 First submitted to journal 17 Jul, 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-7151095","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Short Report","associatedPublications":[],"authors":[{"id":495821829,"identity":"cab64ff8-b3b8-407e-90ff-0b636ba36ef7","order_by":0,"name":"Xingyuan Zhang","email":"","orcid":"","institution":"Duke University","correspondingAuthor":false,"prefix":"","firstName":"Xingyuan","middleName":"","lastName":"Zhang","suffix":""},{"id":495821830,"identity":"2133b0f8-a421-42e4-b59c-bb3c99b9bbc0","order_by":1,"name":"Zhicheng Ji","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA6UlEQVRIiWNgGAWjYDACCcYGZgjrYOMDHoYEEMuAaC3NBkRqYWCAamFgkyBKi/zs5sbPBRV37BoYD7dVvG1Lk2Ngb94mgU8L45yDzdIzzjxLbmA42HZzbluOMQPPsTK8WpglEtuYedsOJwP90nabt60isUEixwyvFjawln8QLcVALfUN8m/wa+EBa2k4bAfSArQuJ4FBgge/FgmJxGZpnmOHE9iAgSw551yaYRtPWrEFPi3yM9IffuapOWzPL3H84Yc3Zcny/OyHN97ApwUGEtskDkB9R4xyELBn4G8gVu0oGAWjYBSMNAAAdmdHdVZcH5gAAAAASUVORK5CYII=","orcid":"","institution":"Duke University","correspondingAuthor":true,"prefix":"","firstName":"Zhicheng","middleName":"","lastName":"Ji","suffix":""}],"badges":[],"createdAt":"2025-07-17 16:38:22","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7151095/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7151095/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":88864085,"identity":"13a6e46f-a2ac-4b93-bb34-36d32fb23078","added_by":"auto","created_at":"2025-08-12 08:06:30","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1340745,"visible":true,"origin":"","legend":"","description":"","filename":"paper.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7151095/v1_covered_f52827b2-9ede-41f9-84f8-98fd4f569be0.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"LLM-based cell type annotation harmonization across single-cell studies using GCTHarmony","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":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-7151095/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7151095/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"A major challenge in integrating previously analyzed single-cell RNA-seq studies is the inconsistency of cell type annotations. To address this, we developed GCTHarmony, an LLM-based method for harmonizing cell type annotations across single-cell studies. Utilizing OpenAI's text embedding model, GCTHarmony accurately maps arbitrary cell type annotations to standardized cell ontology terms and reconciles discrepancies in annotation hierarchies across studies. In a real data example, we show that GCTHarmony substantially improves the consistency of cell type annotations across single-cell studies.","manuscriptTitle":"LLM-based cell type annotation harmonization across single-cell studies using GCTHarmony","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-12 07:58:21","doi":"10.21203/rs.3.rs-7151095/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-11-13T13:35:08+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-09T19:29:36+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-09-25T12:43:40+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"98585934764208263671786289329533170300","date":"2025-09-21T22:51:30+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"261812299275992252579335565991235939207","date":"2025-09-16T08:52:14+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"155918127728566752237355720487006031791","date":"2025-08-13T13:45:28+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-08-05T07:06:11+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-07-21T10:48:39+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-07-18T05:16:11+00:00","index":"","fulltext":""},{"type":"submitted","content":"Genome Biology","date":"2025-07-17T16:30:07+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":"afe1f5a7-9cdf-48ae-ad96-d9e18912bfcc","owner":[],"postedDate":"August 12th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-01-28T06:08:54+00:00","versionOfRecord":[],"versionCreatedAt":"2025-08-12 07:58:21","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7151095","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7151095","identity":"rs-7151095","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}