AI CAR Loop 1.0: A Modular AI-Driven Platform for Accelerated CAR-T Therapy Development, Illustrated with CLDN18.2-Positive Gastric Cancer

AI CAR Loop 1.0: A Modular AI-Driven Platform for Accelerated CAR-T Therapy Development, Illustrated with CLDN18.2-Positive Gastric Cancer | 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 Method Article AI CAR Loop 1.0: A Modular AI-Driven Platform for Accelerated CAR-T Therapy Development, Illustrated with CLDN18.2-Positive Gastric Cancer XIAOQI HU This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7350290/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 AI CAR Loop 1.0 is a modular, AI-driven platform designed to accelerate Chimeric Antigen Receptor T-cell (CAR-T) therapy development for solid and hematological malignancies, with all demonstrations conducted through computational validation. The platform integrates five interoperable modules (M1–M5): multi-modal antigen discovery, AlphaFold2-based structural modeling and HADDOCK docking of antigen–scFv complexes, mRNA delivery optimization, in vivo feedback simulation, and reinforcement learning optimization. Leveraging Coscientist’s multi-agent framework (51-day optimization, 40% yield increase [3]), it enables rapid, cost-effective prototyping and supports integration of strategic modules like DrugDomain 2.0, AuroBind, REAP, and SMART. Illustrated with CLDN18.2-positive gastric cancer, in silico analyses with public datasets (TCGA, n=375; TCIA, n=200) demonstrate a 40–50% cost reduction, 80–85% target accuracy (±5%, vs. 60–70% traditional methods), and 18–24-month development cycles. All results are derived from computational simulations, with no wet-lab or clinical testing performed. Cross-validation and uncertainty quantification ensure robust metrics. Future work will pursue in vitro and in vivo validation to translate these computational insights into clinical applications. Immunology Artificial Intelligence and Machine Learning Cancer Biology Oncology Bioinformatics Computational Biology Molecular Biology CAR-T therapy artificial intelligence reinforcement learning mRNA delivery multimodal modeling Coscientist cost-effectiveness precision oncology platform scalability computational validation 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-7350290","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Method Article","associatedPublications":[],"authors":[{"id":499077020,"identity":"27cdf510-a5f9-4628-a4b2-472c39047c9b","order_by":0,"name":"XIAOQI HU","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA9UlEQVRIiWNgGAWjYJCCA4x/2OTs2/s/PvjZJmFvwMD88DEPQS0NfMYGPAeMDXvP2fAYMLAZG88hZA1jg1ziBokEM2nGf2lALTxi0n/wqJZv7z144OcOs8TtDAlp1YzbDoO0sEnn4NFicOZcwsHeM2nGOxsOHLtNnBaJHIMDPGzHZBsONrbdliVGi/yMHIODf9j+MzYcZmYr5m37D9GCN8Ru5Bgc5m1jU9xwjI2NmbftMMT7+LQYnDljcFjmDJuxZA8Ps2QvSAszMJDxaZFv7zH++KaCTY5f/g3jh59th+3t25sJRyUaYCZN+SgYBaNgFIwCLAAAmkdRCmCIaigAAAAASUVORK5CYII=","orcid":"https://orcid.org/0009-0009-9829-6404","institution":"Independent Researcher","correspondingAuthor":true,"prefix":"","firstName":"XIAOQI","middleName":"","lastName":"HU","suffix":""}],"badges":[],"createdAt":"2025-08-12 01:43:12","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-7350290/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7350290/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":88939745,"identity":"62537e90-e570-4d1f-85e2-5610dda43ff5","added_by":"auto","created_at":"2025-08-13 02:58:39","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":698888,"visible":true,"origin":"","legend":"","description":"","filename":"AICARLoop1.0FinalEnglish.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7350290/v1_covered_6ae47416-aa87-4df4-875f-401f7768b3d3.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eAI CAR Loop 1.0: A Modular AI-Driven Platform for Accelerated CAR-T Therapy Development, Illustrated with CLDN18.2-Positive Gastric Cancer\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Shanghai Normal University","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":"CAR-T therapy, artificial intelligence, reinforcement learning, mRNA delivery, multimodal modeling, Coscientist, cost-effectiveness, precision oncology, platform scalability, computational validation","lastPublishedDoi":"10.21203/rs.3.rs-7350290/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7350290/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAI CAR Loop 1.0 is a modular, AI-driven platform designed to accelerate Chimeric Antigen Receptor T-cell (CAR-T) therapy development for solid and hematological malignancies, with all demonstrations conducted through computational validation. The platform integrates five interoperable modules (M1–M5): multi-modal antigen discovery, AlphaFold2-based structural modeling and HADDOCK docking of antigen–scFv complexes, mRNA delivery optimization, in vivo feedback simulation, and reinforcement learning optimization. Leveraging Coscientist’s multi-agent framework (51-day optimization, 40% yield increase [3]), it enables rapid, cost-effective prototyping and supports integration of strategic modules like DrugDomain 2.0, AuroBind, REAP, and SMART. Illustrated with CLDN18.2-positive gastric cancer, in silico analyses with public datasets (TCGA, n=375; TCIA, n=200) demonstrate a 40–50% cost reduction, 80–85% target accuracy (±5%, vs. 60–70% traditional methods), and 18–24-month development cycles. All results are derived from computational simulations, with no wet-lab or clinical testing performed. Cross-validation and uncertainty quantification ensure robust metrics. Future work will pursue in vitro and in vivo validation to translate these computational insights into clinical applications.\u003c/p\u003e","manuscriptTitle":"AI CAR Loop 1.0: A Modular AI-Driven Platform for Accelerated CAR-T Therapy Development, Illustrated with CLDN18.2-Positive Gastric Cancer","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-13 02:50:32","doi":"10.21203/rs.3.rs-7350290/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":"4b070e46-80c9-4d9f-a993-e43cfdb56da2","owner":[],"postedDate":"August 13th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":53008226,"name":"Immunology"},{"id":53008227,"name":"Artificial Intelligence and Machine Learning"},{"id":53008228,"name":"Cancer Biology"},{"id":53008229,"name":"Oncology"},{"id":53008230,"name":"Bioinformatics"},{"id":53008231,"name":"Computational Biology"},{"id":53008232,"name":"Molecular Biology"}],"tags":[],"updatedAt":"2025-08-13T02:50:32+00:00","versionOfRecord":[],"versionCreatedAt":"2025-08-13 02:50:32","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7350290","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7350290","identity":"rs-7350290","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}