AlphaGenome Enhances Personal Gene Expression Prediction but Retains Key Limitations

AlphaGenome Enhances Personal Gene Expression Prediction but Retains Key Limitations | 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 AlphaGenome Enhances Personal Gene Expression Prediction but Retains Key Limitations Li Shen This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7520707/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 In recent years, numerous genome AI models have been developed to elucidate the relationship between DNA sequence and gene expression. However, these models have faced criticism for their limited accuracy in predicting individual-specific gene expression. AlphaGenome, the current state-of-the-art in genome AI, achieves exceptional performance across a range of sequence-based predictive tasks, but its utility for personal expression prediction has not yet been assessed. In this study, we evaluate AlphaGenome's ability to predict personal gene expression and find that it significantly outperforms its predecessor. Using GTEx data, AlphaGenome improves the prediction of expression direction over Enformer, achieving an odds ratio of 3.0. In some cases, it even reverses previously observed negative correlations into positive ones. Moreover, AlphaGenome demonstrates improved performance for genes with known nonlinear sequence-expression relationships, though it uncovers mechanisms distinct from those identified by tree-based models. gene expression deep learning genome AI model personalized prediction Full Text Additional Declarations No competing interests reported. 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-7520707","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Short Report","associatedPublications":[],"authors":[{"id":510971881,"identity":"b362d205-7f20-49a5-860b-35faceb4e346","order_by":0,"name":"Li Shen","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAsklEQVRIiWNgGAWjYBACPmYGBiBikIPymQlrYYNqMSZBC1RZYgPxWtgZmD8XVNxJX9t//OkGhgprmF68DmOTnnHmWe62GzlmNxjOpBOnhZm37TBQCw/bDca2w0RpYf7M++9wutn5489uMP4jTguDNG/D4QSzAwlmNxgbiNLC2CbNc+ywIdgvCcfSjQlq4ec/fPgzT81hebDDPtRYyxLUwsDAiKQmgbDyUTAKRsEoGAXEAABw4DpbY7CRowAAAABJRU5ErkJggg==","orcid":"","institution":"Icahn School of Medicine at Mount Sinai","correspondingAuthor":true,"prefix":"","firstName":"Li","middleName":"","lastName":"Shen","suffix":""}],"badges":[],"createdAt":"2025-09-02 19:38:12","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7520707/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7520707/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":90851162,"identity":"231f0c89-3f0e-4c7e-a506-5b65a57dc371","added_by":"auto","created_at":"2025-09-09 03:14:27","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1206411,"visible":true,"origin":"","legend":"","description":"","filename":"AlphaGenomeAssessment.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7520707/v1_covered_35fa1cce-8583-4227-8020-c7f3e404a4fd.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"AlphaGenome Enhances Personal Gene Expression Prediction but Retains Key Limitations","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":"gene expression, deep learning, genome AI model, personalized prediction","lastPublishedDoi":"10.21203/rs.3.rs-7520707/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7520707/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"In recent years, numerous genome AI models have been developed to elucidate the relationship between DNA sequence and gene expression. However, these models have faced criticism for their limited accuracy in predicting individual-specific gene expression. AlphaGenome, the current state-of-the-art in genome AI, achieves exceptional performance across a range of sequence-based predictive tasks, but its utility for personal expression prediction has not yet been assessed. In this study, we evaluate AlphaGenome's ability to predict personal gene expression and find that it significantly outperforms its predecessor. Using GTEx data, AlphaGenome improves the prediction of expression direction over Enformer, achieving an odds ratio of 3.0. In some cases, it even reverses previously observed negative correlations into positive ones. Moreover, AlphaGenome demonstrates improved performance for genes with known nonlinear sequence-expression relationships, though it uncovers mechanisms distinct from those identified by tree-based models.","manuscriptTitle":"AlphaGenome Enhances Personal Gene Expression Prediction but Retains Key Limitations","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-09 03:06:19","doi":"10.21203/rs.3.rs-7520707/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","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}}],"origin":"","ownerIdentity":"4a51fdbb-2236-4688-9d26-e10c86d89238","owner":[],"postedDate":"September 9th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-09-09T03:06:19+00:00","versionOfRecord":[],"versionCreatedAt":"2025-09-09 03:06:19","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7520707","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7520707","identity":"rs-7520707","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}