A unified cross-attention model for predicting antigen binding specificity to both HLA and TCR molecules

A unified cross-attention model for predicting antigen binding specificity to both HLA and TCR molecules | 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 A unified cross-attention model for predicting antigen binding specificity to both HLA and TCR molecules Hui Liu, Chenpeng Yu, Xing Fang, Shiye Tian This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4321674/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 28 Jan, 2025 Read the published version in Nature Machine Intelligence → Version 1 posted You are reading this latest preprint version Abstract The immune checkpoint inhibitors have demonstrated promising clinical efficacy across various tumor types, yet the percentage of patients who benefit from them remains low. The bindings between tumor antigens and HLA-I/TCR molecules determine the antigen presentation and T-cell activation, thereby playing important role in the immunotherapy response. Some computational methods have been developed to predict peptide-HLA (pHLA) or peptide-TCR (pTCR) binding specificity, but they focus solely on one task at a time. In this paper, we propose UnifyImmun, a unified cross-attention transformer model designed to simultaneously predict the bindings of peptides to both receptors, thereby providing more comprehensive evaluation of antigen immunogenicity. We devise a two-phase progressive training strategy that enables these two tasks to mutually reinforce each other, by compelling the encoders to extract more expressive features. We also incorporate virtual adversarial training to enhance the model generalizability. Compared to over ten previously published methods for predicting pHLA and pTCR bindings, our method demonstrates better performance in both tasks on multiple independent and external test sets. Notably, on a large-scale COVID-19 pTCR binding test set, our method outperformed the current state-of-the-art methods by at least 9%. The validation experiments on three clinical cohorts confirm that our approach effectively predicts immunotherapy response and clinical outcomes. Furthermore, the cross-attention scores and integrated gradients reveal the amino-acid sites critical for peptide binding to receptors. In essence, our approach marks a significant step towards comprehensive evaluation of antigen immunogenicity. Biological sciences/Computational biology and bioinformatics/Machine learning Biological sciences/Computational biology and bioinformatics/Computational models Cross-attention mechanism neoantigen T-cell receptor Human leukocyte antigen Virtual adversarial training Integrated gradient Full Text Additional Declarations There is NO Competing Interest. Supplementary Files Supplementaryfile.pdf Supplementary file Cite Share Download PDF Status: Published Journal Publication published 28 Jan, 2025 Read the published version in Nature Machine Intelligence → 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-4321674","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":300702486,"identity":"10482c5f-df85-4b62-baa3-31157f21f11a","order_by":0,"name":"Hui Liu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAyklEQVRIiWNgGAWjYBACA3bGBoYPDGxAJg8QsxGjhZmxgXEGA5sEKVoYGJiBiknQYs7M3CZtu4Ovjp/97AGGD2WHGfhnN+DXYtnM2Cade4ZNQrInL4FxxrnDDBJ3DhBw2GGQljY2CYMbPAbMvG2HGQwkEojQYgnUYg/S8pdoLYwgWySAWhiJ1NJs2dvGJjnjTI7BwZ5z6TwSNwhpOd7+8MbPtmP8/O1nDB/8KLOW459BQAsUHAOTBxggsUMUqCFW4SgYBaNgFIxEAABdOTnzEQ66dAAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0001-7158-913X","institution":"Nanjing Tech University","correspondingAuthor":true,"prefix":"","firstName":"Hui","middleName":"","lastName":"Liu","suffix":""},{"id":300702487,"identity":"510226d8-aff3-4f24-9596-d42a3e1bd645","order_by":1,"name":"Chenpeng Yu","email":"","orcid":"","institution":"Nanjing Tech University","correspondingAuthor":false,"prefix":"","firstName":"Chenpeng","middleName":"","lastName":"Yu","suffix":""},{"id":300702488,"identity":"41254ea3-0916-4b9f-bf8a-fd1ce70644c5","order_by":2,"name":"Xing Fang","email":"","orcid":"","institution":"Nanjing Tech University","correspondingAuthor":false,"prefix":"","firstName":"Xing","middleName":"","lastName":"Fang","suffix":""},{"id":300702489,"identity":"5e4aa7b7-6de4-4163-9c3b-dd03f94e0140","order_by":3,"name":"Shiye Tian","email":"","orcid":"","institution":"Nanjing Tech University","correspondingAuthor":false,"prefix":"","firstName":"Shiye","middleName":"","lastName":"Tian","suffix":""}],"badges":[],"createdAt":"2024-04-25 05:20:23","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4321674/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4321674/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s42256-024-00973-w","type":"published","date":"2025-01-28T05:00:00+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":74993288,"identity":"46cbbf7d-1331-49d2-8fad-007f9cb16ad0","added_by":"auto","created_at":"2025-01-29 08:07:57","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":41977237,"visible":true,"origin":"","legend":"","description":"","filename":"main.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4321674/v1_covered_3edec11d-7ada-4dbb-aa20-62607fcf9fa8.pdf"},{"id":56223146,"identity":"92708005-f7f8-45d1-9fe3-9cee9977d7af","added_by":"auto","created_at":"2024-05-10 05:14:38","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":2788691,"visible":true,"origin":"","legend":"\u003cp\u003eSupplementary file\u003c/p\u003e","description":"","filename":"Supplementaryfile.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4321674/v1/95ee9ae08cb311982bc861f9.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"A unified cross-attention model for predicting antigen binding specificity to both HLA and TCR molecules","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":"Cross-attention mechanism, neoantigen, T-cell receptor, Human leukocyte antigen, Virtual adversarial training, Integrated gradient","lastPublishedDoi":"10.21203/rs.3.rs-4321674/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4321674/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The immune checkpoint inhibitors have demonstrated promising clinical efficacy across various tumor types, yet the percentage of patients who benefit from them remains low. The bindings between tumor antigens and HLA-I/TCR molecules determine the antigen presentation and T-cell activation, thereby playing important role in the immunotherapy response. Some computational methods have been developed to predict peptide-HLA (pHLA) or peptide-TCR (pTCR) binding specificity, but they focus solely on one task at a time. In this paper, we propose UnifyImmun, a unified cross-attention transformer model designed to simultaneously predict the bindings of peptides to both receptors, thereby providing more comprehensive evaluation of antigen immunogenicity. We devise a two-phase progressive training strategy that enables these two tasks to mutually reinforce each other, by compelling the encoders to extract more expressive features. We also incorporate virtual adversarial training to enhance the model generalizability. Compared to over ten previously published methods for predicting pHLA and pTCR bindings, our method demonstrates better performance in both tasks on multiple independent and external test sets. Notably, on a large-scale COVID-19 pTCR binding test set, our method outperformed the current state-of-the-art methods by at least 9%. The validation experiments on three clinical cohorts confirm that our approach effectively predicts immunotherapy response and clinical outcomes. Furthermore, the cross-attention scores and integrated gradients reveal the amino-acid sites critical for peptide binding to receptors. In essence, our approach marks a significant step towards comprehensive evaluation of antigen immunogenicity.","manuscriptTitle":"A unified cross-attention model for predicting antigen binding specificity to both HLA and TCR molecules","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-05-10 05:14:34","doi":"10.21203/rs.3.rs-4321674/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"nature-machine-intelligence","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"natmachintell","sideBox":"Learn more about [Nature Machine Intelligence](http://www.nature.com/natmachintell/)","snPcode":"","submissionUrl":"","title":"Nature Machine Intelligence","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Research","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"fb8603c4-3829-47d7-a578-46a334e9a579","owner":[],"postedDate":"May 10th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":31729265,"name":"Biological sciences/Computational biology and bioinformatics/Machine learning"},{"id":31729266,"name":"Biological sciences/Computational biology and bioinformatics/Computational models"}],"tags":[],"updatedAt":"2025-01-29T08:06:37+00:00","versionOfRecord":{"articleIdentity":"rs-4321674","link":"https://doi.org/10.1038/s42256-024-00973-w","journal":{"identity":"nature-machine-intelligence","isVorOnly":false,"title":"Nature Machine Intelligence"},"publishedOn":"2025-01-28 05:00:00","publishedOnDateReadable":"January 28th, 2025"},"versionCreatedAt":"2024-05-10 05:14:34","video":"","vorDoi":"10.1038/s42256-024-00973-w","vorDoiUrl":"https://doi.org/10.1038/s42256-024-00973-w","workflowStages":[]},"version":"v1","identity":"rs-4321674","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4321674","identity":"rs-4321674","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}