Rational Design of Safer Inorganic Nanoparticles via Mechanistic Modeling-informed Machine Learning

Rational Design of Safer Inorganic Nanoparticles via Mechanistic Modeling-informed Machine 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 Rational Design of Safer Inorganic Nanoparticles via Mechanistic Modeling-informed Machine Learning Prashant Dogra, Joseph Cave, Anne Christiono, Carmine Schiavone, and 8 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5960303/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 The safety of inorganic nanoparticles (NPs) remains a critical challenge for their clinical translation. To address this, we developed a machine-learning (ML) framework that predicts NP toxicity both in vitro and in vivo, leveraging physicochemical properties and experimental conditions. A curated in vitro cytotoxicity dataset was used to train and validate binary classification models, with top-performing models undergoing explainability analysis to identify key determinants of toxicity and establish structure-toxicity relationships. External testing with diverse mesoporous silica NPs validated the framework’s predictive accuracy for in vitro settings. To enable organ-specific toxicity predictions in vivo, we integrated a physiologically-based pharmacokinetic (PBPK) model into the ML pipeline to quantify NP exposure across organs. Retraining the ML models with PBPK-derived exposure metrics yielded robust predictions of organ-specific nanotoxicity, further validating the framework. This PBPK-informed ML approach can thus serve as a potential Novel Alternative Method (NAM) to streamline NP safety assessment, enabling the rational design of safer NPs and expediting their clinical translation. Biological sciences/Biotechnology/Nanobiotechnology/Nanoparticles Physical sciences/Engineering/Biomedical engineering Full Text Additional Declarations There is NO Competing Interest. Supplementary Files Caveetal.SIFinal.pdf Supplementary Information 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-5960303","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":417473116,"identity":"a6ca2c3d-c9d0-47e2-9d49-5e8d840b7b33","order_by":0,"name":"Prashant Dogra","email":"data:image/png;base64,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","orcid":"https://orcid.org/0000-0001-6722-7371","institution":"The Houston Methodist Research Institute","correspondingAuthor":true,"prefix":"","firstName":"Prashant","middleName":"","lastName":"Dogra","suffix":""},{"id":417473117,"identity":"4837195a-173a-41c4-83a4-90c67a696c35","order_by":1,"name":"Joseph Cave","email":"","orcid":"","institution":"The Houston Methodist Research Institute; Weill Cornell Medicine","correspondingAuthor":false,"prefix":"","firstName":"Joseph","middleName":"","lastName":"Cave","suffix":""},{"id":417473118,"identity":"d3db705e-ffae-4084-84db-2b737d361431","order_by":2,"name":"Anne Christiono","email":"","orcid":"","institution":"Massachusetts Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Anne","middleName":"","lastName":"Christiono","suffix":""},{"id":417473119,"identity":"20e48d62-0aaa-4998-930a-663ae6eb02be","order_by":3,"name":"Carmine Schiavone","email":"","orcid":"","institution":"The Houston Methodist Research Institute; University of Naples Federico II","correspondingAuthor":false,"prefix":"","firstName":"Carmine","middleName":"","lastName":"Schiavone","suffix":""},{"id":417473120,"identity":"8e5efa6f-7962-4bb3-a1dd-e9d9924cd416","order_by":4,"name":"Henry Pownall","email":"","orcid":"","institution":"The Houston Methodist Research Institute; Weill Cornell Medicine","correspondingAuthor":false,"prefix":"","firstName":"Henry","middleName":"","lastName":"Pownall","suffix":""},{"id":417473121,"identity":"e8652d5a-7a5c-4c59-a5d4-193c69e2f6c7","order_by":5,"name":"Vittorio Cristini","email":"","orcid":"","institution":"University of Texas M.D. Anderson Cancer Center","correspondingAuthor":false,"prefix":"","firstName":"Vittorio","middleName":"","lastName":"Cristini","suffix":""},{"id":417473122,"identity":"04d8ec1d-7eee-4633-9c29-b7c3b5efe6b9","order_by":6,"name":"Daniela I. Staquicini","email":"","orcid":"","institution":"Rutgers Cancer Institute of New Jersey; Rutgers New Jersey Medical School","correspondingAuthor":false,"prefix":"","firstName":"Daniela","middleName":"I.","lastName":"Staquicini","suffix":""},{"id":417473123,"identity":"05255c98-6ecd-446a-8734-47e6e701289f","order_by":7,"name":"C Brinker","email":"","orcid":"https://orcid.org/0000-0002-7145-9324","institution":"University of New Mexico","correspondingAuthor":false,"prefix":"","firstName":"C","middleName":"","lastName":"Brinker","suffix":""},{"id":417473124,"identity":"91af1a9e-96f4-430a-9bd2-e523b8041d83","order_by":8,"name":"Matthew Campen","email":"","orcid":"","institution":"University of New Mexico","correspondingAuthor":false,"prefix":"","firstName":"Matthew","middleName":"","lastName":"Campen","suffix":""},{"id":417473125,"identity":"470840a3-1d70-46e4-a561-6dbc03a697fa","order_by":9,"name":"Zhihui Wang","email":"","orcid":"","institution":"Weill Cornell Medical College","correspondingAuthor":false,"prefix":"","firstName":"Zhihui","middleName":"","lastName":"Wang","suffix":""},{"id":417473126,"identity":"7006e855-d624-466c-8008-3c265b943a8d","order_by":10,"name":"Hien Van Nguyen","email":"","orcid":"","institution":"University of Houston","correspondingAuthor":false,"prefix":"","firstName":"Hien","middleName":"Van","lastName":"Nguyen","suffix":""},{"id":417473127,"identity":"fe93e023-dea3-4e19-a5f0-d29e68150711","order_by":11,"name":"Achraf Noureddine","email":"","orcid":"https://orcid.org/0000-0001-9530-5963","institution":"University of New Mexico","correspondingAuthor":false,"prefix":"","firstName":"Achraf","middleName":"","lastName":"Noureddine","suffix":""}],"badges":[],"createdAt":"2025-02-04 18:26:01","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5960303/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5960303/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":77723696,"identity":"bee08617-a29e-4fe6-b4aa-34600b37d86d","added_by":"auto","created_at":"2025-03-04 17:19:30","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1577898,"visible":true,"origin":"","legend":"Article File","description":"","filename":"Caveetal.MainFinal.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5960303/v1_covered_1bf0486f-d109-4e92-b746-6e218912342a.pdf"},{"id":76592939,"identity":"245c8217-b760-4f4f-999a-a7457a72b8ee","added_by":"auto","created_at":"2025-02-18 17:27:02","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":5562222,"visible":true,"origin":"","legend":"Supplementary Information","description":"","filename":"Caveetal.SIFinal.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5960303/v1/f082cd940a58288f5867e1d0.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Rational Design of Safer Inorganic Nanoparticles via Mechanistic Modeling-informed Machine 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-5960303/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5960303/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The safety of inorganic nanoparticles (NPs) remains a critical challenge for their clinical translation. To address this, we developed a machine-learning (ML) framework that predicts NP toxicity both in vitro and in vivo, leveraging physicochemical properties and experimental conditions. A curated in vitro cytotoxicity dataset was used to train and validate binary classification models, with top-performing models undergoing explainability analysis to identify key determinants of toxicity and establish structure-toxicity relationships. External testing with diverse mesoporous silica NPs validated the framework’s predictive accuracy for in vitro settings. To enable organ-specific toxicity predictions in vivo, we integrated a physiologically-based pharmacokinetic (PBPK) model into the ML pipeline to quantify NP exposure across organs. Retraining the ML models with PBPK-derived exposure metrics yielded robust predictions of organ-specific nanotoxicity, further validating the framework. This PBPK-informed ML approach can thus serve as a potential Novel Alternative Method (NAM) to streamline NP safety assessment, enabling the rational design of safer NPs and expediting their clinical translation.","manuscriptTitle":"Rational Design of Safer Inorganic Nanoparticles via Mechanistic Modeling-informed Machine Learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-02-18 17:26:58","doi":"10.21203/rs.3.rs-5960303/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":"7e4b7e3c-4a9d-4026-80e0-afe8802d7a7c","owner":[],"postedDate":"February 18th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":44508037,"name":"Biological sciences/Biotechnology/Nanobiotechnology/Nanoparticles"},{"id":44508038,"name":"Physical sciences/Engineering/Biomedical engineering"}],"tags":[],"updatedAt":"2025-02-18T17:27:00+00:00","versionOfRecord":[],"versionCreatedAt":"2025-02-18 17:26:58","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5960303","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5960303","identity":"rs-5960303","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}