UNICORN: Towards Universal Cellular Expression Prediction with an Explainable Multi-Task Learning Framework

UNICORN: Towards Universal Cellular Expression Prediction with an Explainable Multi-Task Learning Framework | 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 Article UNICORN: Towards Universal Cellular Expression Prediction with an Explainable Multi-Task Learning Framework Hongyu Zhao, Tianyu Liu, Tinglin Huang, Yingxin Lin, Rex Ying This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5754185/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 27 Oct, 2025 Read the published version in Nature Communications → Version 1 posted You are reading this latest preprint version Abstract Sequence-to-function analysis is a challenging task in human genetics, especially in predicting cell-type-specific multi-omic phenotypes from biological sequences such as individualized gene expression. Here, we present UNICORN, a new method with improved prediction performances than the existing methods. UNICORN takes the embeddings from biological sequences as well as external knowledge from pre-trained foundation models as inputs and optimizes the predictor with carefully-designed loss functions. We demonstrate that UNICORN outperforms the existing methods in both gene expression prediction and multi-omic phenotype prediction at the cellular level and the cell-type level, and it can also generate uncertainty scores of the predictions. Moreover, UNICORN is able to link personalized gene expression profiles with corresponding genome information. Finally, we show that UNICORN is capable of characterizing complex biological systems for different disease states or perturbations. Overall, embeddings from foundation models can facilitate the understanding of the role of biological sequences in the prediction task, and incorporating multi-omic information can enhance prediction performances. Biological sciences/Computational biology and bioinformatics/Sequence annotation Biological sciences/Computational biology and bioinformatics/Data mining DNA Sequence Model Large Language Model Single-Cell Sequencing Multi-Modal Machine Learning Multi-Task Machine Learning Full Text Additional Declarations There is NO Competing Interest. Cite Share Download PDF Status: Published Journal Publication published 27 Oct, 2025 Read the published version in Nature Communications → 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-5754185","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":402100351,"identity":"0bfbcd45-a486-4dae-b56f-57dc65ecb38b","order_by":0,"name":"Hongyu Zhao","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA5ElEQVRIiWNgGAWjYBACAyQG4wMGBgsUQYJamIFYgjQtbBJEaTFn7z38mreNwd6c/fCxap4aCTkG9uZtEvi0WPacS7MGamG27ElLu81zTMKYgedYGV4tBjdyzIyBWtgMDuSY3eZhk0hskMgxI0oLj8H5N2bFPP8k6hvk3xDUYvwYqEUCpJeZt00igUGCh4CWM2fMGOeckzAwuPEsWXJun4RhG09asQVeLcd7jD+8KbOxNziffPDDm2828vzshzfewKcFCNikeCDRwcDEA+ISUA4CzB9/QFmMP/AqHAWjYBSMgpEKAAR3QO4h1DXsAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0000-0003-1195-9607","institution":"Yale University","correspondingAuthor":true,"prefix":"","firstName":"Hongyu","middleName":"","lastName":"Zhao","suffix":""},{"id":402100352,"identity":"cdfde774-cec5-4783-bd3d-98277f4ffe2c","order_by":1,"name":"Tianyu Liu","email":"","orcid":"https://orcid.org/0000-0002-9412-6573","institution":"Yale University","correspondingAuthor":false,"prefix":"","firstName":"Tianyu","middleName":"","lastName":"Liu","suffix":""},{"id":402100353,"identity":"1de09753-a17a-4e5f-964b-d597eb859df6","order_by":2,"name":"Tinglin Huang","email":"","orcid":"","institution":"Yale University","correspondingAuthor":false,"prefix":"","firstName":"Tinglin","middleName":"","lastName":"Huang","suffix":""},{"id":402100354,"identity":"1babdb13-2e6a-425b-a1a1-62d4ae8ae71f","order_by":3,"name":"Yingxin Lin","email":"","orcid":"https://orcid.org/0000-0002-4299-7326","institution":"Yale School of Public Health","correspondingAuthor":false,"prefix":"","firstName":"Yingxin","middleName":"","lastName":"Lin","suffix":""},{"id":402100355,"identity":"027bef4c-9032-4923-af0a-97489d589569","order_by":4,"name":"Rex Ying","email":"","orcid":"","institution":"Yale University","correspondingAuthor":false,"prefix":"","firstName":"Rex","middleName":"","lastName":"Ying","suffix":""}],"badges":[],"createdAt":"2025-01-02 22:20:13","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5754185/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5754185/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41467-025-64506-8","type":"published","date":"2025-10-27T04:00:00+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":94583248,"identity":"15fcad80-6d74-485f-9082-af1186e74bec","added_by":"auto","created_at":"2025-10-28 18:13:56","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3156662,"visible":true,"origin":"","legend":"Article File","description":"","filename":"unicornsubmission.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5754185/v1_covered_796b01fd-35ce-4a20-8ed1-cfcc961d1315.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"UNICORN: Towards Universal Cellular Expression Prediction with an Explainable Multi-Task Learning Framework","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"nature-portfolio","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"","title":"Nature Portfolio","twitterHandle":"","acdcEnabled":false,"dfaEnabled":false,"editorialSystem":"ejp","reportingPortfolio":"","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"DNA Sequence Model, Large Language Model, Single-Cell Sequencing, Multi-Modal Machine Learning, Multi-Task Machine Learning","lastPublishedDoi":"10.21203/rs.3.rs-5754185/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5754185/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Sequence-to-function analysis is a challenging task in human genetics, especially in predicting cell-type-specific multi-omic phenotypes from biological sequences such as individualized gene expression. Here, we present UNICORN, a new method with improved prediction performances than the existing methods. UNICORN takes the embeddings from biological sequences as well as external knowledge from pre-trained foundation models as inputs and optimizes the predictor with carefully-designed loss functions. We demonstrate that UNICORN outperforms the existing methods in both gene expression prediction and multi-omic phenotype prediction at the cellular level and the cell-type level, and it can also generate uncertainty scores of the predictions. Moreover, UNICORN is able to link personalized gene expression profiles with corresponding genome information. Finally, we show that UNICORN is capable of characterizing complex biological systems for different disease states or perturbations. Overall, embeddings from foundation models can facilitate the understanding of the role of biological sequences in the prediction task, and incorporating multi-omic information can enhance prediction performances.","manuscriptTitle":"UNICORN: Towards Universal Cellular Expression Prediction with an Explainable Multi-Task Learning Framework","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-01-24 03:44:56","doi":"10.21203/rs.3.rs-5754185/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"nature-communications","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"NCOMMS","sideBox":"Learn more about [Nature Communications](http://www.nature.com/ncomms/)","snPcode":"","submissionUrl":"https://mts-ncomms.nature.com/","title":"Nature Communications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Communications","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"1c447e0a-270e-461a-a008-85902551d43c","owner":[],"postedDate":"January 24th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":42857696,"name":"Biological sciences/Computational biology and bioinformatics/Sequence annotation"},{"id":42857697,"name":"Biological sciences/Computational biology and bioinformatics/Data mining"}],"tags":[],"updatedAt":"2025-10-28T17:30:50+00:00","versionOfRecord":{"articleIdentity":"rs-5754185","link":"https://doi.org/10.1038/s41467-025-64506-8","journal":{"identity":"nature-communications","isVorOnly":false,"title":"Nature Communications"},"publishedOn":"2025-10-27 04:00:00","publishedOnDateReadable":"October 27th, 2025"},"versionCreatedAt":"2025-01-24 03:44:56","video":"","vorDoi":"10.1038/s41467-025-64506-8","vorDoiUrl":"https://doi.org/10.1038/s41467-025-64506-8","workflowStages":[]},"version":"v1","identity":"rs-5754185","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5754185","identity":"rs-5754185","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}