Accurate Immune Protein Structure Prediction by Large Language Model and Transfer Learning

Accurate Immune Protein Structure Prediction by Large Language Model and Transfer Learning | 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 Accurate Immune Protein Structure Prediction by Large Language Model and Transfer Learning Haicang Zhang, Tian Zhu, Milong Ren, Zaikai He, Siyuan Tao, Ming Li, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7153530/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 Accurate prediction of immune protein structures is critical for advancing immunotherapy. However, deep learning-based methods like AlphaFold and RosettaFold struggle with immune proteins due to the limited number of solved immune protein structures and the absence of homologous sequences in hypervariable regions. To address these challenges, we introduce ImmuneFold, a transfer-learning framework that leverages a large language model and low-rank adaptation (LoRA) for memory-efficient fine-tuning. ImmuneFold outperforms existing methods, including MSA-based AlphaFold3, in predicting the structures of T-cell receptors, antibodies, and nanobodies. Additionally, we pair ImmuneFold’s predictions with Rosetta energy scoring to develop a zero-shot protocol for TCR–epitope binding prediction, effectively mitigating overfitting issues common in supervised approaches. Experimental evaluations also confirm ImmuneFold’s robustness and accuracy in binding prediction. Beyond immune proteins, ImmuneFold provides a scalable framework for adapting advanced models, such as ESMFold and AlphaFold, to other protein families, thereby democratizing access to cutting-edge structural tools for researchers, even those with limited computational resources. Biological sciences/Computational biology and bioinformatics/Protein folding Biological sciences/Computational biology and bioinformatics/High-throughput screening Full Text Additional Declarations There is NO Competing Interest. 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-7153530","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":493318451,"identity":"1d2afd86-7bc2-4535-8ad9-552d3f5557b1","order_by":0,"name":"Haicang Zhang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABEUlEQVRIiWNgGAWjYDACCSBmbGDgAXM+MLDBBYnTwjiDgU2CaC1gwMwDVY1Xi/zs5mcPv+6wk+FvP3v4tc0fvjqDA8wHb/Mw2OXh0sI455i5seyZZB6JM3lp1rltbBIGB9iSrXkYkotxaWGWSDCTlmxj5jFgyDEzzm0AaeExk+ZhOJDYgEMLm0T6N6CWeh4D/jdmxhZ/QFr4v+HVwiORYyb5se0wj4FEjvFjBjawLWx4tUhI5JRJM7Yd55G48caMsbeNTXLmYTZjyzkGyTi1yM9I3yb5s63anr8/x/jDjz/H+PmONz+88abCDqcWcBDwwPzFwHAMyAWxDfCoBwLGH1CtHxgYavArHQWjYBSMghEJAAbATXJubP2oAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0000-0001-6268-4258","institution":"Shanghai Jiao Tong University School of Medicine","correspondingAuthor":true,"prefix":"","firstName":"Haicang","middleName":"","lastName":"Zhang","suffix":""},{"id":493318452,"identity":"28a9b4e4-7843-4603-823c-567fbb911411","order_by":1,"name":"Tian Zhu","email":"","orcid":"","institution":"Institute of Computing Technology, Chinese of Academy of Sciences","correspondingAuthor":false,"prefix":"","firstName":"Tian","middleName":"","lastName":"Zhu","suffix":""},{"id":493318453,"identity":"766b88af-eac7-4c72-bc17-81fdfd1d8aef","order_by":2,"name":"Milong Ren","email":"","orcid":"","institution":"Institute of Computing Technology, Chinese of Academy of Sciences","correspondingAuthor":false,"prefix":"","firstName":"Milong","middleName":"","lastName":"Ren","suffix":""},{"id":493318454,"identity":"0f084b60-7f84-497d-8785-d1c5259c4901","order_by":3,"name":"Zaikai He","email":"","orcid":"","institution":"Institute of Computing Technology, Chinese of Academy of Sciences","correspondingAuthor":false,"prefix":"","firstName":"Zaikai","middleName":"","lastName":"He","suffix":""},{"id":493318455,"identity":"ae48596e-dec4-45a2-a8fa-a9bf90e5e745","order_by":4,"name":"Siyuan Tao","email":"","orcid":"","institution":"Institute of Computing Technology, Chinese of Academy of Sciences","correspondingAuthor":false,"prefix":"","firstName":"Siyuan","middleName":"","lastName":"Tao","suffix":""},{"id":493318456,"identity":"0486cf12-2f8b-4732-9212-f53ca2f1bd05","order_by":5,"name":"Ming Li","email":"","orcid":"","institution":"University of Waterloo","correspondingAuthor":false,"prefix":"","firstName":"Ming","middleName":"","lastName":"Li","suffix":""},{"id":493318457,"identity":"b099c3f5-f41c-4b12-9a8e-994f1f245aea","order_by":6,"name":"Jian Zhang","email":"","orcid":"https://orcid.org/0000-0002-6558-791X","institution":"Shanghai Jiao Tong University School of Medicine","correspondingAuthor":false,"prefix":"","firstName":"Jian","middleName":"","lastName":"Zhang","suffix":""},{"id":493318458,"identity":"90551fd6-95d2-4965-8be6-971550d8b6d7","order_by":7,"name":"Dongbo Bu","email":"","orcid":"","institution":"Institute of Computing Technology, Chinese of Academy of Sciences","correspondingAuthor":false,"prefix":"","firstName":"Dongbo","middleName":"","lastName":"Bu","suffix":""}],"badges":[],"createdAt":"2025-07-18 03:50:38","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7153530/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7153530/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":91695703,"identity":"cd20a95a-98e1-49ad-9d32-b73885cc5791","added_by":"auto","created_at":"2025-09-19 09:33:35","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":9906770,"visible":true,"origin":"","legend":"Article File","description":"","filename":"ImmuneFold.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7153530/v1_covered_87add0a4-ef05-4f8a-ae87-b1956dda7b0e.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Accurate Immune Protein Structure Prediction by Large Language Model and Transfer Learning","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-7153530/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7153530/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Accurate prediction of immune protein structures is critical for advancing immunotherapy. However, deep learning-based methods like AlphaFold and RosettaFold struggle with immune proteins due to the limited number of solved immune protein structures and the absence of homologous sequences in hypervariable regions. To address these challenges, we introduce ImmuneFold, a transfer-learning framework that leverages a large language model and low-rank adaptation (LoRA) for memory-efficient fine-tuning. ImmuneFold outperforms existing methods, including MSA-based AlphaFold3, in predicting the structures of T-cell receptors, antibodies, and nanobodies. Additionally, we pair ImmuneFold’s predictions with Rosetta energy scoring to develop a zero-shot protocol for TCR–epitope binding prediction, effectively mitigating overfitting issues common in supervised approaches. Experimental evaluations also confirm ImmuneFold’s robustness and accuracy in binding prediction. Beyond immune proteins, ImmuneFold provides a scalable framework for adapting advanced models, such as ESMFold and AlphaFold, to other protein families, thereby democratizing access to cutting-edge structural tools for researchers, even those with limited computational resources.","manuscriptTitle":"Accurate Immune Protein Structure Prediction by Large Language Model and Transfer Learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-07-31 03:36:18","doi":"10.21203/rs.3.rs-7153530/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":"f30d09ba-30dc-4ad8-b6f7-6638da3834a7","owner":[],"postedDate":"July 31st, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":52388858,"name":"Biological sciences/Computational biology and bioinformatics/Protein folding"},{"id":52388859,"name":"Biological sciences/Computational biology and bioinformatics/High-throughput screening"}],"tags":[],"updatedAt":"2025-09-19T09:25:18+00:00","versionOfRecord":[],"versionCreatedAt":"2025-07-31 03:36:18","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7153530","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7153530","identity":"rs-7153530","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}