Inflammation-Linked Aging Signals in Frozen Single-Cell Foundation Models: Donor-Aware Detection and Robustness Testing

Inflammation-Linked Aging Signals in Frozen Single-Cell Foundation Models: Donor-Aware Detection and Robustness Testing | 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 Inflammation-Linked Aging Signals in Frozen Single-Cell Foundation Models: Donor-Aware Detection and Robustness Testing Ihor Kendiukhov This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9289672/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 13 You are reading this latest preprint version Abstract Single-cell foundation models offer a possible route to studying aging biology in latent space, but apparent age effects can be distorted by donor identity and cell-composition differences. We developed a donor-aware interpretability workflow to test whether frozen scGPT and Geneformer representations contain biologically coherent aging signals in age-labeled human single-cell datasets. The workflow combined donor-held-out age decoding, sparse autoencoder feature discovery, cross-model pathway matching, targeted latent-space interventions, donor-bootstrap confidence intervals, and progressively stricter confound controls. Across five datasets, frozen representations contained detectable age information, with best donor-aware balanced accuracy of 0.384. Sparse autoencoders identified 132 donor-aware robust features, and cross-model pathway matching produced 193 paired features, with the strongest convergence in inflammation and NF-kappaB-related programs. The clearest intervention signal was observed in a global Geneformer inflammatory branch, where old-versus-random and old-versus-young contrasts remained positive after split expansion and donor-threshold tightening up to 400 donors. In a monocyte-restricted analysis, both scGPT and Geneformer also showed positive old-versus-random responses in one cohort. The strongest global signal weakened under stricter controls. Fully composition-matched forward-pass reruns yielded 0 of 4 full strict replications. These results indicate that frozen single-cell foundation models do capture biologically plausible aging-related structure, especially around inflammatory programs, but also that donor-aware and composition-aware stress tests are necessary before interpreting such signals as robust mechanisms. aging inflammaging single-cell transcriptomics foundation models interpretabil- ity immune aging Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 02 May, 2026 Reviews received at journal 22 Apr, 2026 Reviews received at journal 15 Apr, 2026 Reviews received at journal 13 Apr, 2026 Reviewers agreed at journal 10 Apr, 2026 Reviews received at journal 10 Apr, 2026 Reviewers agreed at journal 08 Apr, 2026 Reviewers agreed at journal 05 Apr, 2026 Reviewers agreed at journal 05 Apr, 2026 Reviewers invited by journal 04 Apr, 2026 Editor assigned by journal 02 Apr, 2026 Submission checks completed at journal 01 Apr, 2026 First submitted to journal 01 Apr, 2026 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-9289672","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":621063557,"identity":"6da2f745-74f7-46da-b6ae-4a20c87af048","order_by":0,"name":"Ihor Kendiukhov","email":"data:image/png;base64,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","orcid":"","institution":"University of Tübingen","correspondingAuthor":true,"prefix":"","firstName":"Ihor","middleName":"","lastName":"Kendiukhov","suffix":""}],"badges":[],"createdAt":"2026-04-01 09:24:52","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9289672/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9289672/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":106959920,"identity":"66c33a58-ab7f-44cb-835f-316b7ccbca1a","added_by":"auto","created_at":"2026-04-15 09:17:04","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1414974,"visible":true,"origin":"","legend":"","description":"","filename":"biogerontologylatex.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9289672/v1_covered_3c83d261-4a48-45d7-a6d0-dc9c2e418b87.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Inflammation-Linked Aging Signals in Frozen Single-Cell Foundation Models: Donor-Aware Detection and Robustness Testing","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":"biogerontology","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Biogerontology](https://www.springer.com/journal/10522)","snPcode":"10522","submissionUrl":"https://submission.nature.com/new-submission/10522/3","title":"Biogerontology","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"aging, inflammaging, single-cell transcriptomics, foundation models, interpretabil- ity, immune aging","lastPublishedDoi":"10.21203/rs.3.rs-9289672/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9289672/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Single-cell foundation models offer a possible route to studying aging biology in latent space, but apparent age effects can be distorted by donor identity and cell-composition differences. We developed a donor-aware interpretability workflow to test whether frozen scGPT and Geneformer representations contain biologically coherent aging signals in age-labeled human single-cell datasets. The workflow combined donor-held-out age decoding, sparse autoencoder feature discovery, cross-model pathway matching, targeted latent-space interventions, donor-bootstrap confidence intervals, and progressively stricter confound controls.\nAcross five datasets, frozen representations contained detectable age information, with best donor-aware balanced accuracy of 0.384. Sparse autoencoders identified 132 donor-aware robust features, and cross-model pathway matching produced 193 paired features, with the strongest convergence in inflammation and NF-kappaB-related programs. The clearest intervention signal was observed in a global Geneformer inflammatory branch, where old-versus-random and old-versus-young contrasts remained positive after split expansion and donor-threshold tightening up to 400 donors. In a monocyte-restricted analysis, both scGPT and Geneformer also showed positive old-versus-random responses in one cohort.\nThe strongest global signal weakened under stricter controls. Fully composition-matched forward-pass reruns yielded 0 of 4 full strict replications. These results indicate that frozen single-cell foundation models do capture biologically plausible aging-related structure, especially around inflammatory programs, but also that donor-aware and composition-aware stress tests are necessary before interpreting such signals as robust mechanisms.","manuscriptTitle":"Inflammation-Linked Aging Signals in Frozen Single-Cell Foundation Models: Donor-Aware Detection and Robustness Testing","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-13 12:24:29","doi":"10.21203/rs.3.rs-9289672/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-05-02T07:39:13+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-22T17:55:24+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-15T08:10:19+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-13T11:27:30+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"324337825419144534907902438962775797715","date":"2026-04-10T14:58:42+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-10T09:14:52+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"73515493453392643731797241441790510587","date":"2026-04-08T09:19:31+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"80874231757741677550534875362617618073","date":"2026-04-05T20:09:01+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"254084625483927917929677950581549882956","date":"2026-04-05T10:20:53+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-05T03:46:45+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-04-02T08:31:41+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-04-01T17:24:30+00:00","index":"","fulltext":""},{"type":"submitted","content":"Biogerontology","date":"2026-04-01T09:09:51+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"biogerontology","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Biogerontology](https://www.springer.com/journal/10522)","snPcode":"10522","submissionUrl":"https://submission.nature.com/new-submission/10522/3","title":"Biogerontology","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"92d83e76-9f15-4e45-af4b-643986eb08ac","owner":[],"postedDate":"April 13th, 2026","published":true,"recentEditorialEvents":[{"type":"decision","content":"Revision requested","date":"2026-05-02T07:39:13+00:00","index":"","fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-05-16T02:53:35+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-13 12:24:29","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9289672","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9289672","identity":"rs-9289672","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}