Transformer-Genetic Algorithm Co-Optimization for Neoantigen Prediction in Cancer Immunotherapy

Transformer-Genetic Algorithm Co-Optimization for Neoantigen Prediction in Cancer Immunotherapy | 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 Transformer-Genetic Algorithm Co-Optimization for Neoantigen Prediction in Cancer Immunotherapy Akshay Balaji, Poornima Jogi, Vishal Kumar This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8222565/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 Personalized neoantigen vaccine development requires accurate predictions of binding affinity, immunogenicity, and peptide stability across diverse HLA profiles. This paper presents a novel multi-task learning transformer architecture augmented with evolutionary optimization for comprehensive neoantigen prioritization. The proposed framework integrates enhanced positional encoding and biological attention mechanism targeting peptide anchor residues. We trained and validated our model on 30,450 neoantigen candidates from 50 melanoma patients, incorporating multi-omics data including somatic mutations, gene expression, copy number variations, and methylation profiles. The transformer architecture simultaneously predicts three critical neoantigen properties while a genetic algorithm optimizes vaccine candidate selection for population coverage and clinical outcomes. Experimental results demonstrate state-of-the-art performance with ROC AUC scores of 0.983, 0.980, and 0.962 for binding affinity, immunogenicity, and stability prediction, respectively, achieving an overall mean AUC of 0.975. Clinical validation shows significant survival correlation (r = 0.316, p = 0.028) and optimized vaccine candidates achieve $90$ HLA population coverage with genetic algorithm scores reaching 0.940. The proposed framework establishes a new benchmark for AI-driven neoantigen vaccine design with immediate translational applications in precision oncology. Bioinformatics Cancer Biology Neoantigen Prediction Personalized Cancer Immunotherapy HLA Binding Affinity Transformer based Models Evolutionary Algorithms T-cell Immunogenicity Computational Oncology Precision Immunotherapy Full Text Additional Declarations The authors declare no competing interests. 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-8222565","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":551787233,"identity":"f44f4fad-467b-4110-bd53-dd2a1495f2fb","order_by":0,"name":"Akshay Balaji","email":"data:image/png;base64,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","orcid":"","institution":"","correspondingAuthor":true,"prefix":"","firstName":"Akshay","middleName":"","lastName":"Balaji","suffix":""},{"id":551787234,"identity":"b843c60f-3067-4f42-b28d-87a5e1a6ab14","order_by":1,"name":"Poornima Jogi","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Poornima","middleName":"","lastName":"Jogi","suffix":""},{"id":551787235,"identity":"07be939e-f6b6-4bd4-b4de-2c148d4d756a","order_by":2,"name":"Vishal Kumar","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA40lEQVRIiWNgGAWjYDACZgY2BoYCGxCDgSGBeC0GaaRoYQBrOUyCuwyOsz978MPgfOL2dvaHHx5U3JHnZ2B++OgGPi2HecwNewxuJ845zGMskXDmmeHMBjZj4xw8WiSbedgkeIBaZjDzsDEkth1OMDjAwyaNXwv7M8k/BueAWtifMST+O5xgT0gLPzODmTSPwQGgFgYzhsQGoC0MBLXwmEnLGCQbAx0G9Muxw4YzDhPwCxv/8WeSbyrsZGfwH3/48UfNYXn+9uaHj/FpgQHHBjiTmQjlIGBPpLpRMApGwSgYiQAAxNJDFmwpWP8AAAAASUVORK5CYII=","orcid":"","institution":"","correspondingAuthor":true,"prefix":"","firstName":"Vishal","middleName":"","lastName":"Kumar","suffix":""}],"badges":[],"createdAt":"2025-11-27 13:56:08","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-8222565/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8222565/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":97249658,"identity":"7720a185-8107-4586-81d1-2c48399cb23e","added_by":"auto","created_at":"2025-12-02 13:13:11","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1169102,"visible":true,"origin":"","legend":"","description":"","filename":"Akshay4.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8222565/v1_covered_dbfea97a-e457-40f2-816b-90b2b4d9efd0.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eTransformer-Genetic Algorithm Co-Optimization for Neoantigen Prediction in Cancer Immunotherapy\u003c/p\u003e","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":"Neoantigen Prediction, Personalized Cancer Immunotherapy, HLA Binding Affinity, Transformer based Models, Evolutionary Algorithms, T-cell Immunogenicity, Computational Oncology, Precision Immunotherapy","lastPublishedDoi":"10.21203/rs.3.rs-8222565/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8222565/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003ePersonalized neoantigen vaccine development requires accurate predictions of binding affinity, immunogenicity, and peptide stability across diverse HLA profiles. This paper presents a novel multi-task learning transformer architecture augmented with evolutionary optimization for comprehensive neoantigen prioritization. The proposed framework integrates enhanced positional encoding and biological attention mechanism targeting peptide anchor residues. We trained and validated our model on 30,450 neoantigen candidates from 50 melanoma patients, incorporating multi-omics data including somatic mutations, gene expression, copy number variations, and methylation profiles. The transformer architecture simultaneously predicts three critical neoantigen properties while a genetic algorithm optimizes vaccine candidate selection for population coverage and clinical outcomes. Experimental results demonstrate state-of-the-art performance with ROC AUC scores of 0.983, 0.980, and 0.962 for binding affinity, immunogenicity, and stability prediction, respectively, achieving an overall mean AUC of 0.975. Clinical validation shows significant survival correlation (r = 0.316, p = 0.028) and optimized vaccine candidates achieve $90$ HLA population coverage with genetic algorithm scores reaching 0.940. The proposed framework establishes a new benchmark for AI-driven neoantigen vaccine design with immediate translational applications in precision oncology.\u003c/p\u003e","manuscriptTitle":"Transformer-Genetic Algorithm Co-Optimization for Neoantigen Prediction in Cancer Immunotherapy","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-02 03:21:44","doi":"10.21203/rs.3.rs-8222565/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":"92b11b21-58b0-4cbf-98e4-01853587156d","owner":[],"postedDate":"December 2nd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":58719121,"name":"Bioinformatics"},{"id":58719122,"name":"Cancer Biology"}],"tags":[],"updatedAt":"2025-12-02T03:21:44+00:00","versionOfRecord":[],"versionCreatedAt":"2025-12-02 03:21:44","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8222565","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8222565","identity":"rs-8222565","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}