Deep Generative Optimization of mRNA Codon Sequences for Enhanced Protein Production and Therapeutic Efficacy

Deep Generative Optimization of mRNA Codon Sequences for Enhanced Protein Production and Therapeutic Efficacy | 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 Deep Generative Optimization of mRNA Codon Sequences for Enhanced Protein Production and Therapeutic Efficacy Zhi Xie, Yupeng Li, Fan Wang, Jiaqi Yang, Zirong Han, Linfeng Chen, and 8 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5040961/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 12 Nov, 2025 Read the published version in Nature Communications → Version 1 posted You are reading this latest preprint version Abstract Messenger RNA (mRNA) therapeutics show immense promise, but their efficacy is limited by suboptimal protein expression. Here, we present RiboCode, a deep learning framework that generates mRNA codon sequences for enhanced protein production. RiboCode introduces several advances, including direct learning from large-scale ribosome profiling data, context-aware mRNA optimization and generative exploration of a large sequence space. In silico analysis demonstrate RiboCode’s robust predictive accuracy for unseen genes and cellular environments. In vitro experiments show substantial improvements in protein expression, with up to a 72-fold increase, significantly outperforming past methods. In addition, RiboCode achieves cell-type specific expression and demonstrates robust performance across different mRNA formats, including m 1 Ψ-modified and circular mRNAs, an important feature for mRNA therapeutics. In vivo mouse studies show that optimized influenza hemagglutinin mRNAs induce ten times stronger neutralizing antibody responses against influenza virus compared to the unoptimized sequence. In an optic nerve crush model, optimized nerve growth factor mRNAs achieve equivalent neuroprotection of retinal ganglion cells at one-fifth the dose of the unoptimized sequence. Collectively, RiboCode represents a paradigm shift from rule-based to data-driven, context-sensitive approach for mRNA therapeutic applications, enabling the development of more potent and dose-efficient treatments. Biological sciences/Computational biology and bioinformatics/Machine learning Biological sciences/Biotechnology/Nucleic-acid therapeutics Full Text Additional Declarations There is NO Competing Interest. Supplementary Files Supplementaryfile1.xlsx Source of data for modeling Supplementaryfile2.csv Nucleotide position contribution score Supplementaryfile3.xlsx Codon sequences and UTR sequences nrreportingsummarydone.pdf nreditorialpolicychecklistdone.pdf editorial policy checklist Cite Share Download PDF Status: Published Journal Publication published 12 Nov, 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-5040961","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":367345841,"identity":"3c0b63aa-33d5-4201-8d84-5a16554f4b18","order_by":0,"name":"Zhi Xie","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAt0lEQVRIiWNgGAWjYDACZhAysAGyGBsPkKIlDaSlgUgtEF2HwQzitBgcZz78uaDgvN3a9sNAW2psoglqkWxmSzCeYXA7eduZRKCWY2m5DYS08DPzGCTzALWYHQBqYWw4TFgLGzP/h8M8BueSzc4/JFIL0BbGZh6DA3ZmN4i1BegXY5DbEsxuAG1JIMYvBucPP/7M88fO3ux8+sMHH2psCGuBgUSwygRilYOAPSmKR8EoGAWjYIQBAPdDQJLmgo3+AAAAAElFTkSuQmCC","orcid":"https://orcid.org/0000-0002-5589-4836","institution":"Sun Yat-Sen University","correspondingAuthor":true,"prefix":"","firstName":"Zhi","middleName":"","lastName":"Xie","suffix":""},{"id":367345842,"identity":"567aea08-569c-4a7f-a72c-6c20aceae86e","order_by":1,"name":"Yupeng Li","email":"","orcid":"","institution":"Sun Yat-Sen University","correspondingAuthor":false,"prefix":"","firstName":"Yupeng","middleName":"","lastName":"Li","suffix":""},{"id":367345843,"identity":"59f56912-4357-46f2-a7f6-5cba3336c6ed","order_by":2,"name":"Fan Wang","email":"","orcid":"","institution":"Sun Yat-Sen University","correspondingAuthor":false,"prefix":"","firstName":"Fan","middleName":"","lastName":"Wang","suffix":""},{"id":367345844,"identity":"61aabafc-c175-436d-9820-1865d5b66166","order_by":3,"name":"Jiaqi Yang","email":"","orcid":"","institution":"Sun Yat-Sen University","correspondingAuthor":false,"prefix":"","firstName":"Jiaqi","middleName":"","lastName":"Yang","suffix":""},{"id":367345845,"identity":"f1a769e6-c4e2-4823-bf9f-a36c93bef857","order_by":4,"name":"Zirong Han","email":"","orcid":"","institution":"Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Zirong","middleName":"","lastName":"Han","suffix":""},{"id":367345846,"identity":"cb075eae-96de-45e5-8df9-31030c1e7b3b","order_by":5,"name":"Linfeng Chen","email":"","orcid":"","institution":"Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Linfeng","middleName":"","lastName":"Chen","suffix":""},{"id":367345847,"identity":"6237b4fa-4821-4025-bf79-43640baf6444","order_by":6,"name":"Wenbing Jiang","email":"","orcid":"","institution":"Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Wenbing","middleName":"","lastName":"Jiang","suffix":""},{"id":367345848,"identity":"fc5ed2d6-15b4-436c-8ecf-0387ec871604","order_by":7,"name":"Hao Zhou","email":"","orcid":"","institution":"Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Hao","middleName":"","lastName":"Zhou","suffix":""},{"id":367345849,"identity":"70ef08c0-ce9a-45a8-961e-525649664868","order_by":8,"name":"Tong Li","email":"","orcid":"","institution":"Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Tong","middleName":"","lastName":"Li","suffix":""},{"id":367345850,"identity":"0928303e-b0fe-43ed-b80f-1d2bf5328e99","order_by":9,"name":"Zehua Tang","email":"","orcid":"","institution":"Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Zehua","middleName":"","lastName":"Tang","suffix":""},{"id":367345851,"identity":"5cf011d6-062a-4e0f-8b2a-14ea8b9b701b","order_by":10,"name":"Jianxiang Deng","email":"","orcid":"https://orcid.org/0000-0002-7363-2274","institution":"Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Jianxiang","middleName":"","lastName":"Deng","suffix":""},{"id":367345852,"identity":"c8fdbc3e-5192-4da4-80cd-789eb1881684","order_by":11,"name":"Xin He","email":"","orcid":"","institution":"Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Xin","middleName":"","lastName":"He","suffix":""},{"id":367345853,"identity":"0721b21e-38a2-4c5e-bc0b-8ae0f6ec72e7","order_by":12,"name":"Gaofeng Zha","email":"","orcid":"","institution":"Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Gaofeng","middleName":"","lastName":"Zha","suffix":""},{"id":367345854,"identity":"970bda04-cd6d-455f-8853-ed392c25875c","order_by":13,"name":"Yao He","email":"","orcid":"https://orcid.org/0000-0002-0324-0267","institution":"State Key Laboratory of Ophthalmology, Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science, Zhongshan Ophthalmic Center, Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Yao","middleName":"","lastName":"He","suffix":""}],"badges":[],"createdAt":"2024-09-06 02:10:13","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5040961/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5040961/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41467-025-64894-x","type":"published","date":"2025-11-12T05:00:00+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":95809785,"identity":"b8db83f8-8e8a-4474-b440-a279d156b470","added_by":"auto","created_at":"2025-11-13 08:50:48","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2643452,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscriptfull.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5040961/v1_covered_baf9bcd4-4dcc-4fd3-ab88-1c5e506e02b1.pdf"},{"id":68229959,"identity":"4614321b-09b6-499b-b83a-9eecfa7d91fd","added_by":"auto","created_at":"2024-11-05 05:30:05","extension":"xlsx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":205738,"visible":true,"origin":"","legend":"Source of data for modeling","description":"","filename":"Supplementaryfile1.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-5040961/v1/4c59e43d897ea14c01bd1863.xlsx"},{"id":68229009,"identity":"4507ee3b-d69d-488c-b844-775f84df6dc8","added_by":"auto","created_at":"2024-11-05 05:06:06","extension":"csv","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":28870974,"visible":true,"origin":"","legend":"Nucleotide position contribution score","description":"","filename":"Supplementaryfile2.csv","url":"https://assets-eu.researchsquare.com/files/rs-5040961/v1/7abd27c629e1ee279644b23b.csv"},{"id":68229005,"identity":"9db48a7d-ec89-4b98-b76e-7deffce75ff1","added_by":"auto","created_at":"2024-11-05 05:06:05","extension":"xlsx","order_by":3,"title":"","display":"","copyAsset":false,"role":"supplement","size":20921,"visible":true,"origin":"","legend":"Codon sequences and UTR sequences","description":"","filename":"Supplementaryfile3.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-5040961/v1/a013445d39d09003745ca583.xlsx"},{"id":68229008,"identity":"57b764dc-88cb-41ca-a4f8-f6e6d005fba2","added_by":"auto","created_at":"2024-11-05 05:06:05","extension":"pdf","order_by":4,"title":"","display":"","copyAsset":false,"role":"supplement","size":1666153,"visible":true,"origin":"","legend":"","description":"","filename":"nrreportingsummarydone.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5040961/v1/d7207a4ce4cd927ed22bba79.pdf"},{"id":68229961,"identity":"ade9c859-51ba-4971-ac77-21dc71277de4","added_by":"auto","created_at":"2024-11-05 05:30:06","extension":"pdf","order_by":5,"title":"","display":"","copyAsset":false,"role":"supplement","size":1682388,"visible":true,"origin":"","legend":"\u003cp\u003eeditorial policy checklist\u003c/p\u003e","description":"","filename":"nreditorialpolicychecklistdone.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5040961/v1/63cf9216734535d79381cfc9.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Deep Generative Optimization of mRNA Codon Sequences for Enhanced Protein Production and Therapeutic Efficacy","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":"","lastPublishedDoi":"10.21203/rs.3.rs-5040961/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5040961/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eMessenger RNA (mRNA) therapeutics show immense promise, but their efficacy is limited by suboptimal protein expression. Here, we present RiboCode, a deep learning framework that generates mRNA codon sequences for enhanced protein production. RiboCode introduces several advances, including direct learning from large-scale ribosome profiling data, context-aware mRNA optimization and generative exploration of a large sequence space. \u003cem\u003eIn silico\u003c/em\u003e analysis demonstrate RiboCode\u0026rsquo;s robust predictive accuracy for unseen genes and cellular environments. \u003cem\u003eIn vitro\u003c/em\u003e experiments show substantial improvements in protein expression, with up to a 72-fold increase, significantly outperforming past methods. In addition, RiboCode achieves cell-type specific expression and demonstrates robust performance across different mRNA formats, including m\u003csup\u003e\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e\u003c/sup\u003eΨ-modified and circular mRNAs, an important feature for mRNA therapeutics. \u003cem\u003eIn vivo\u003c/em\u003e mouse studies show that optimized influenza hemagglutinin mRNAs induce ten times stronger neutralizing antibody responses against influenza virus compared to the unoptimized sequence. In an optic nerve crush model, optimized nerve growth factor mRNAs achieve equivalent neuroprotection of retinal ganglion cells at one-fifth the dose of the unoptimized sequence. Collectively, RiboCode represents a paradigm shift from rule-based to data-driven, context-sensitive approach for mRNA therapeutic applications, enabling the development of more potent and dose-efficient treatments.\u003c/p\u003e","manuscriptTitle":"Deep Generative Optimization of mRNA Codon Sequences for Enhanced Protein Production and Therapeutic Efficacy","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-11-05 05:06:00","doi":"10.21203/rs.3.rs-5040961/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":"0a3c6d57-1b17-4a51-9f9d-9260dc918b85","owner":[],"postedDate":"November 5th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":39089791,"name":"Biological sciences/Computational biology and bioinformatics/Machine learning"},{"id":39089792,"name":"Biological sciences/Biotechnology/Nucleic-acid therapeutics"}],"tags":[],"updatedAt":"2025-11-13T08:44:58+00:00","versionOfRecord":{"articleIdentity":"rs-5040961","link":"https://doi.org/10.1038/s41467-025-64894-x","journal":{"identity":"nature-communications","isVorOnly":false,"title":"Nature Communications"},"publishedOn":"2025-11-12 05:00:00","publishedOnDateReadable":"November 12th, 2025"},"versionCreatedAt":"2024-11-05 05:06:00","video":"","vorDoi":"10.1038/s41467-025-64894-x","vorDoiUrl":"https://doi.org/10.1038/s41467-025-64894-x","workflowStages":[]},"version":"v1","identity":"rs-5040961","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5040961","identity":"rs-5040961","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}