Toxishield: Computational Analyser for Food Additives and their Health Implications

Toxishield: Computational Analyser for Food Additives and their Health Implications | 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 Toxishield: Computational Analyser for Food Additives and their Health Implications Priya Govindarajan, Anagha D, Shambhavi R, Sheril Jathanna N, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8963759/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 Background: The increasing use of food additives in food products highlights the need for scalable computational approaches for population-level health risk assessment. The study presents Toxishield, a proposed algorithm that models a hierarchical pathway linking food products to their constituent additives, additive-level risk rankings, disease associations, and categorical disease risk levels. Methods: Large-scale ingredient datasets were integrated with curated chemical–disease knowledge bases to construct a unified food–additive–disease association matrix, supported by standardized preprocessing to enable systematic additive extraction. Statistical association analysis was employed to identify meaningful computational risk signals, including strong positive additive–disease correlations quantified using the Pearson correlation coefficient (r ≥ 0.7). The Toxishield algorithm was then applied to model hierarchical relationships between food products, additives, and diseases, generating additive risk rankings, disease linkage scores, and category-level risk classifications through recurrence-based aggregation. Results: Based on this analysis, additives and associated disease outcomes were classified into four distinct risk categories: very low risk, low risk, moderate risk, and high risk. Toxishield achieved 98.42% accuracy, precision, and F1-score, with a 1.58% error rate, and consistently outperformed baseline models in mapping food products to additives and associated human health risks. Conclusion: Overall, Toxishield enables scalable and interpretable computational food safety surveillance aligned with Sustainable Development Goal 3: Good Health and Well-Being. Trial registration Not applicable. Food additives Food safety surveillance Disease risk levels Correlation analysis Toxishield Full Text Additional Declarations No competing interests reported. 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-8963759","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":619574618,"identity":"b8727237-bc6a-47e8-97d9-1f710dcd4c81","order_by":0,"name":"Priya Govindarajan","email":"data:image/png;base64,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","orcid":"","institution":"Amrita School of Computing Amrita Vishwa Vidyapeetham","correspondingAuthor":true,"prefix":"","firstName":"Priya","middleName":"","lastName":"Govindarajan","suffix":""},{"id":619574619,"identity":"11ed4302-a799-4642-abad-006686b34455","order_by":1,"name":"Anagha D","email":"","orcid":"","institution":"Amrita School of Computing Amrita Vishwa Vidyapeetham","correspondingAuthor":false,"prefix":"","firstName":"Anagha","middleName":"","lastName":"D","suffix":""},{"id":619574620,"identity":"d58e0095-3e6e-4035-9f25-6ead5bed3a0b","order_by":2,"name":"Shambhavi R","email":"","orcid":"","institution":"Amrita School of Computing Amrita Vishwa Vidyapeetham","correspondingAuthor":false,"prefix":"","firstName":"Shambhavi","middleName":"","lastName":"R","suffix":""},{"id":619574621,"identity":"75278b15-1094-4388-bcd7-dc8023bbb277","order_by":3,"name":"Sheril Jathanna N","email":"","orcid":"","institution":"Amrita School of Computing Amrita Vishwa Vidyapeetham","correspondingAuthor":false,"prefix":"","firstName":"Sheril","middleName":"Jathanna","lastName":"N","suffix":""},{"id":619574622,"identity":"77c3272a-8768-4495-be02-1bdfddeea76e","order_by":4,"name":"Thejashwini R","email":"","orcid":"","institution":"Amrita School of Computing Amrita Vishwa Vidyapeetham","correspondingAuthor":false,"prefix":"","firstName":"Thejashwini","middleName":"","lastName":"R","suffix":""},{"id":619574623,"identity":"cc64db70-9471-4ddf-853d-4ee126778e1a","order_by":5,"name":"M Batumalay","email":"","orcid":"","institution":"INTI International University","correspondingAuthor":false,"prefix":"","firstName":"M","middleName":"","lastName":"Batumalay","suffix":""}],"badges":[],"createdAt":"2026-02-25 06:11:00","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8963759/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8963759/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":108773955,"identity":"21a7257b-107e-49cb-bbc8-7b834354c5c4","added_by":"auto","created_at":"2026-05-08 08:57:48","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1209861,"visible":true,"origin":"","legend":"","description":"","filename":"Toxishieldmanuscript252267.45.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8963759/v1_covered_aed4db11-843c-4020-b6f1-3ff976bf195e.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Toxishield: Computational Analyser for Food Additives and their Health Implications","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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":"Food additives, Food safety surveillance, Disease risk levels, Correlation analysis, Toxishield","lastPublishedDoi":"10.21203/rs.3.rs-8963759/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8963759/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground:\u003c/h2\u003e \u003cp\u003eThe increasing use of food additives in food products highlights the need for scalable computational approaches for population-level health risk assessment. The study presents Toxishield, a proposed algorithm that models a hierarchical pathway linking food products to their constituent additives, additive-level risk rankings, disease associations, and categorical disease risk levels.\u003c/p\u003e\u003ch2\u003eMethods:\u003c/h2\u003e \u003cp\u003eLarge-scale ingredient datasets were integrated with curated chemical\u0026ndash;disease knowledge bases to construct a unified food\u0026ndash;additive\u0026ndash;disease association matrix, supported by standardized preprocessing to enable systematic additive extraction. Statistical association analysis was employed to identify meaningful computational risk signals, including strong positive additive\u0026ndash;disease correlations quantified using the Pearson correlation coefficient (r\u0026thinsp;\u0026ge;\u0026thinsp;0.7). The Toxishield algorithm was then applied to model hierarchical relationships between food products, additives, and diseases, generating additive risk rankings, disease linkage scores, and category-level risk classifications through recurrence-based aggregation.\u003c/p\u003e\u003ch2\u003eResults:\u003c/h2\u003e \u003cp\u003eBased on this analysis, additives and associated disease outcomes were classified into four distinct risk categories: very low risk, low risk, moderate risk, and high risk. Toxishield achieved 98.42% accuracy, precision, and F1-score, with a 1.58% error rate, and consistently outperformed baseline models in mapping food products to additives and associated human health risks.\u003c/p\u003e\u003ch2\u003eConclusion:\u003c/h2\u003e \u003cp\u003eOverall, Toxishield enables scalable and interpretable computational food safety surveillance aligned with Sustainable Development Goal 3: Good Health and Well-Being.\u003c/p\u003e\u003ch2\u003eTrial registration\u003c/h2\u003e \u003cp\u003eNot applicable.\u003c/p\u003e","manuscriptTitle":"Toxishield: Computational Analyser for Food Additives and their Health Implications","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-10 21:42:19","doi":"10.21203/rs.3.rs-8963759/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":"4a4d79ce-e9a7-401b-9ae1-98f71d1a75ff","owner":[],"postedDate":"April 10th, 2026","published":true,"recentEditorialEvents":[{"type":"decision","content":"Rejected","date":"2026-05-08T08:44:59+00:00","index":"","fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-05-08T08:57:01+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-10 21:42:19","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8963759","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8963759","identity":"rs-8963759","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}