Predicting dynamic expression patterns in budding yeast with a fungal DNA language model

Predicting dynamic expression patterns in budding yeast with a fungal DNA language model | 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 Predicting dynamic expression patterns in budding yeast with a fungal DNA language model Kuan-Hao Chao, Majed Magzoub, Emily Stoops, Sean Hackett, Johannes Linder, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7681940/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 Predicting gene expression from DNA sequence remains challenging due to complex regulatory codes. We introduce a masked DNA language model pretrained on 165 fungal genomes closely related to budding yeast that captures conserved regulatory grammar. Fine-tuning the LM on yeast RNA-seq data—including high-resolution transcriptional regulator induction time courses generated in this study—yielded Shorkie, a model that substantially improves gene expression prediction compared to baselines trained without self-supervision. Shorkie identified canonical transcription factor (TF) binding motifs and tracked their usage across induction experiments. Furthermore, Shorkie accurately predicted variant effects, outperforming leading sequence-to-expression models in cis-eQTL classification and achieving high concordance with massively parallel reporter assays. Interpretability analyses revealed Shorkie's ability to resolve promoter dynamics, splicing signals, and temporal changes in regulatory motif usage. This framework demonstrates that evolutionary-scale pre-training combined with transfer learning substantially improves our ability to decode gene regulation from sequence, providing insights into noncoding variants and regulatory networks. Biological sciences/Computational biology and bioinformatics/Computational models Biological sciences/Computational biology and bioinformatics/Machine learning Biological sciences/Computational biology and bioinformatics/Genome informatics Full Text Additional Declarations There is NO Competing Interest. Supplementary Files shorkiesupplementaltables.pdf Supplemental table shorkiesupplementalfigures.pdf Supplemental figures 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-7681940","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":529164743,"identity":"ccc6d19b-cb12-4a86-8203-82102cb1abb8","order_by":0,"name":"Kuan-Hao Chao","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA6ElEQVRIiWNgGAWjYBACCSBmhrM+ADEbOylaGGeAtDCTooWZhwHOxQ0kZyQ/e1xQY8PAP7v54WObX9vk+ZgZGD98zMGtRVoizdx4xrE0Bok7x4yNc/tuG7YxMzBLztyGW4ucRIKZNA/bYQYDECO35zYjUAsbMy9eLenfpHn+gbQAGZY9t+0JapGWyDGT5m0DaQEyGH7cTiSoRbLnTZk0b18aj8SNnGLD3obbyW3MjM14/SJxPH2bNM83Gzn+GekbH/z4c9t2fnvzwQ8f8WiBAXCMMDC2gckGwuoR4A8pikfBKBgFo2CkAACYakXNeY6IGwAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0003-0099-0692","institution":"Johns Hopkins University","correspondingAuthor":true,"prefix":"","firstName":"Kuan-Hao","middleName":"","lastName":"Chao","suffix":""},{"id":529164744,"identity":"39d438b7-1fec-4fc4-9226-f7534fcc70e6","order_by":1,"name":"Majed Magzoub","email":"","orcid":"","institution":"Calico Life Sciences LLC","correspondingAuthor":false,"prefix":"","firstName":"Majed","middleName":"","lastName":"Magzoub","suffix":""},{"id":529164745,"identity":"f9c9de2f-06cf-4763-b9df-31ca9c537652","order_by":2,"name":"Emily Stoops","email":"","orcid":"https://orcid.org/0000-0002-8620-1916","institution":"Calico Life Sciences LLC","correspondingAuthor":false,"prefix":"","firstName":"Emily","middleName":"","lastName":"Stoops","suffix":""},{"id":529164746,"identity":"d185857e-d713-468b-8409-387dacb54d59","order_by":3,"name":"Sean Hackett","email":"","orcid":"https://orcid.org/0000-0002-9553-4341","institution":"Calico","correspondingAuthor":false,"prefix":"","firstName":"Sean","middleName":"","lastName":"Hackett","suffix":""},{"id":529164747,"identity":"b0ea9f61-2b9d-4b22-95da-9ac1b721b8f6","order_by":4,"name":"Johannes Linder","email":"","orcid":"","institution":"Calico Labs","correspondingAuthor":false,"prefix":"","firstName":"Johannes","middleName":"","lastName":"Linder","suffix":""},{"id":529164748,"identity":"d2cd8f87-7853-45c6-8e51-1de5bd112145","order_by":5,"name":"David Kelley","email":"","orcid":"https://orcid.org/0000-0001-7782-3548","institution":"Calico Life Sciences","correspondingAuthor":false,"prefix":"","firstName":"David","middleName":"","lastName":"Kelley","suffix":""}],"badges":[],"createdAt":"2025-09-22 17:05:34","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7681940/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7681940/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":93495822,"identity":"688611ff-20d0-4f1c-adb4-146ba75b61b6","added_by":"auto","created_at":"2025-10-14 13:04:00","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":31794388,"visible":true,"origin":"","legend":"Article File","description":"","filename":"shorkie.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7681940/v1_covered_32c50b37-ee7b-4ef0-b609-96d566bac638.pdf"},{"id":93493591,"identity":"4178e908-47aa-4378-b0b7-e141878aa107","added_by":"auto","created_at":"2025-10-14 12:39:16","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":88136,"visible":true,"origin":"","legend":"Supplemental table","description":"","filename":"shorkiesupplementaltables.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7681940/v1/91a23a421ae9641fc58b0b3a.pdf"},{"id":93493592,"identity":"1c72258a-d532-40b9-b3ba-e4a2c393bae6","added_by":"auto","created_at":"2025-10-14 12:39:17","extension":"pdf","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":69284631,"visible":true,"origin":"","legend":"Supplemental figures","description":"","filename":"shorkiesupplementalfigures.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7681940/v1/a5ae6c909df1cb991c1891ef.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Predicting dynamic expression patterns in budding yeast with a fungal DNA language model","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-7681940/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7681940/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Predicting gene expression from DNA sequence remains challenging due to complex regulatory codes. We introduce a masked DNA language model pretrained on 165 fungal genomes closely related to budding yeast that captures conserved regulatory grammar. Fine-tuning the LM on yeast RNA-seq data—including high-resolution transcriptional regulator induction time courses generated in this study—yielded Shorkie, a model that substantially improves gene expression prediction compared to baselines trained without self-supervision. Shorkie identified canonical transcription factor (TF) binding motifs and tracked their usage across induction experiments. Furthermore, Shorkie accurately predicted variant effects, outperforming leading sequence-to-expression models in cis-eQTL classification and achieving high concordance with massively parallel reporter assays. Interpretability analyses revealed Shorkie's ability to resolve promoter dynamics, splicing signals, and temporal changes in regulatory motif usage. This framework demonstrates that evolutionary-scale pre-training combined with transfer learning substantially improves our ability to decode gene regulation from sequence, providing insights into noncoding variants and regulatory networks.","manuscriptTitle":"Predicting dynamic expression patterns in budding yeast with a fungal DNA language model","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-14 12:39:10","doi":"10.21203/rs.3.rs-7681940/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":"0bb69703-f5a7-4847-814c-693192ec7ddd","owner":[],"postedDate":"October 14th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":56242443,"name":"Biological sciences/Computational biology and bioinformatics/Computational models"},{"id":56242444,"name":"Biological sciences/Computational biology and bioinformatics/Machine learning"},{"id":56242445,"name":"Biological sciences/Computational biology and bioinformatics/Genome informatics"}],"tags":[],"updatedAt":"2025-11-11T09:05:24+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-14 12:39:10","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7681940","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7681940","identity":"rs-7681940","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}