AI-Orchestrated Active Learning for Insulin Delivery Material Discovery

AI-Orchestrated Active Learning for Insulin Delivery Material Discovery | 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Article AI-Orchestrated Active Learning for Insulin Delivery Material Discovery Martins Otun This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8353835/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 We present a comprehensive implementation of an AI-driven material discovery platform for insulin delivery patches, featuring LangChain-orchestrated active learning that integrates three core computational workflows: (1) Retrieval-Augmented Generation (RAG) powered literature mining using Semantic Scholar API with ChromaDB vector storage and OpenAI embeddings, (2) conversational memory-enhanced PSMILES (Polymer SMILES) generation using GPT-4o with chemical validation frameworks, and (3) OpenMM molecular dynamics simulations employing Langevin integrators with AMBER force fields for insulin-polymer systems. The platform implements a closed-loop active learning orchestrator that iteratively refines material discovery through intelligent feedback mechanisms. Our RAG system utilizes text-embedding-3-small (1536-dimensional) vectors with ChromaDB persistent storage, achieving semantic similarity search over scientific literature. The PSMILES generator employs conversation buffer memory with 10-exchange context windows and multi-stage validation pipelines. MD simulations use LangevinMiddleIntegrator with 2 fs timesteps at physiological temperature (310 K) under NPT ensemble conditions with MonteCarloBarostat pressure coupling. The complete system demonstrates the integration of large language models as orchestration agents for complex scientific workflows, providing a template for AI-accelerated materials discovery in biomedical applications. Drug Delivery Computational Chemistry computational material discovery computational drug delivery ai-driven drug discovery ai-driven polymer chemistry Full Text Additional Declarations The authors declare potential competing interests as follows: Ollama Team: For the local LLM infrastructure LangChain: For conversation memory and LLM integration Semantic Scholar: For academic literature access Meta FAIR: For the Universal Model for Atoms (UMA) force field Materials Science Community: For foundational research 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-8353835","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":559854311,"identity":"9a7436a3-09b6-4c56-919f-13a9c7d9829f","order_by":0,"name":"Martins Otun","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA20lEQVRIiWNgGAWjYDADNgYGxgdAWgbMJKQUBCSANLMBA4MBD/FaQEwJorTwy/eYPbpRc6+OT7r9WcXHtj88/OxtCQw/Krbh1CLZxmNunHOsWIJN5ozZzZltBjySPccOMPacuY1Ti8ExHjPpHLYECTaJHLbbvEAtBjfSG5gZ2whp+QfSkv6smHgtuW0gLQlmzBAtaQfwapFsSyuTzu1LkGyTyDGWnHHOGOSXhIP4/MLPfHibdM63BH75GekPP3wok5MDhpjhgx8VuLVgBwdIVD8KRsEoGAWjAA0AAGZgSTdLoM1WAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0009-0007-1805-0195","institution":"Obafemi Awolowo University","correspondingAuthor":true,"prefix":"","firstName":"Martins","middleName":"","lastName":"Otun","suffix":""}],"badges":[],"createdAt":"2025-12-13 15:52:40","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":true,"conflictsOfInterestStatement":true,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":true},"doi":"10.21203/rs.3.rs-8353835/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8353835/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":98273093,"identity":"61cc15d2-b2ce-452d-b61c-71a7de3d7abe","added_by":"auto","created_at":"2025-12-16 02:43:34","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":259234,"visible":true,"origin":"","legend":"","description":"","filename":"fridgefreeinsulin.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8353835/v1_covered_771b717d-27cf-48c6-b73c-111e83f986cb.pdf"}],"financialInterests":"The authors declare potential competing interests as follows: Ollama Team: For the local LLM infrastructure\nLangChain: For conversation memory and LLM integration\nSemantic Scholar: For academic literature access\nMeta FAIR: For the Universal Model for Atoms (UMA) force field\nMaterials Science Community: For foundational research","formattedTitle":"\u003cp\u003eAI-Orchestrated Active Learning for Insulin Delivery Material Discovery\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Obafemi Awolowo 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":"computational material discovery, computational drug delivery, ai-driven drug discovery, ai-driven polymer chemistry","lastPublishedDoi":"10.21203/rs.3.rs-8353835/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8353835/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eWe present a comprehensive implementation of an AI-driven material discovery platform for insulin delivery patches, featuring LangChain-orchestrated active learning that integrates three core computational workflows: (1) Retrieval-Augmented Generation (RAG) powered literature mining using Semantic Scholar API with ChromaDB vector storage and OpenAI embeddings, (2) conversational memory-enhanced PSMILES (Polymer SMILES) generation using GPT-4o with chemical validation frameworks, and (3) OpenMM molecular dynamics simulations employing Langevin integrators with AMBER force fields for insulin-polymer systems. The platform implements a closed-loop active learning orchestrator that iteratively refines material discovery through intelligent feedback mechanisms. Our RAG system utilizes text-embedding-3-small (1536-dimensional) vectors with ChromaDB persistent storage, achieving semantic similarity search over scientific literature. The PSMILES generator employs conversation buffer memory with 10-exchange context windows and multi-stage validation pipelines. MD simulations use LangevinMiddleIntegrator with 2 fs timesteps at physiological temperature (310 K) under NPT ensemble conditions with MonteCarloBarostat pressure coupling. The complete system demonstrates the integration of large language models as orchestration agents for complex scientific workflows, providing a template for AI-accelerated materials discovery in biomedical applications.\u003c/p\u003e","manuscriptTitle":"AI-Orchestrated Active Learning for Insulin Delivery Material Discovery","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-16 02:43:27","doi":"10.21203/rs.3.rs-8353835/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":"4eb84e1f-cf84-4e34-ab67-08c394caaeab","owner":[],"postedDate":"December 16th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":59605583,"name":"Drug Delivery"},{"id":59605584,"name":"Computational Chemistry"}],"tags":[],"updatedAt":"2025-12-16T02:43:27+00:00","versionOfRecord":[],"versionCreatedAt":"2025-12-16 02:43:27","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8353835","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8353835","identity":"rs-8353835","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}