Enhancing Chemical Toxicity Predictions with Synthetic SMILES from a Fine-Tuned LLM-Based Chemical Synthesis Generative Model

Enhancing Chemical Toxicity Predictions with Synthetic SMILES from a Fine-Tuned LLM-Based Chemical Synthesis Generative Model | 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 Enhancing Chemical Toxicity Predictions with Synthetic SMILES from a Fine-Tuned LLM-Based Chemical Synthesis Generative Model Yong Oh Lee, Do Yeon Kim This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6432369/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 adoption of transformer-based models in toxicity prediction has significantly advanced the field, yet these models continue to struggle with data imbalances inherent in benchmark datasets such as Tox21, Clintox, HIV, and BBBP. This persistent challenge undermines their effectiveness, particularly in minority class predictions where data scarcity prevails. Recent advancements in large language models (LLMs) have demonstrated remarkable capabilities in generating synthetic Simplified Molecular Input Line Entry System (SMILES), providing a novel approach to address these imbalances. In this study, we explore the potential of LLM-generated synthetic SMILES to enhance the training datasets, focusing on the augmentation of minority classes. Our comprehensive experiments on multiple benchmark datasets show that this strategy effectively mitigates class imbalance issue but also substantially improves the minority class prediction accuracy without compromising the overall model performance. For instance, in the Tox21 dataset, we observed an increase in minority class prediction accuracy from 0.707 to 0.965. Similar improvements across other datasets further validate the efficacy of synthetic SMILES augmentation in enhancing both toxicity prediction and broader chemical property assessments. Applied Biochemistry toxicity prediction chemical property prediction data imbalance synthetic chemical generation large language models 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-6432369","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":441940725,"identity":"e52f9df1-2444-4c0b-8f37-04b312a2d929","order_by":0,"name":"Yong Oh Lee","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA/klEQVRIiWNgGAWjYLACxgYGGQYG5mMgNo8EWOgAYS08DAxsaSRr4TEDcwhqMTjee/jFxx0MPPzsPd8efNxRKyPZwPzwA8OZe7i1nDmXZjnzDAOPZM/Z7YYzzxznkWZgM5ZguFGMW8uNHDNj3jYGHoMbudukeduO8cgxMABd+CGBsBb7+2+eQbWwfyOkxfgx2BYJHjaglhqgw0DhcAO3FskzZ8wYZ7ZJ8EicSTOTnNl2gEeymadYIuEMbi18x3uMP3xss5Hjbz/8TOJjW529xPH2jR8+HMOtReEAA5sELDKA4DAwFQAp3BoYGOQbGJg/IPHr8KgdBaNgFIyCkQoAJZxQzlNCpC0AAAAASUVORK5CYII=","orcid":"","institution":"Hongik University","correspondingAuthor":true,"prefix":"","firstName":"Yong","middleName":"Oh","lastName":"Lee","suffix":""},{"id":441940726,"identity":"e2284f4f-143a-4ff2-a259-18e5c7c6835e","order_by":1,"name":"Do Yeon Kim","email":"","orcid":"","institution":"Hongik University","correspondingAuthor":false,"prefix":"","firstName":"Do","middleName":"Yeon","lastName":"Kim","suffix":""}],"badges":[],"createdAt":"2025-04-12 05:50:28","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-6432369/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6432369/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":80626858,"identity":"7b49e00b-730a-4895-b96e-9c30d6fb71ad","added_by":"auto","created_at":"2025-04-15 10:55:22","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":384255,"visible":true,"origin":"","legend":"","description":"","filename":"WileyJournalTemplatepreprint.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6432369/v1_covered_8432171a-3e6d-46c0-8f4b-7e46b22320bd.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eEnhancing Chemical Toxicity Predictions with Synthetic SMILES from a Fine-Tuned LLM-Based Chemical Synthesis Generative Model\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Hongik 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":"toxicity prediction, chemical property prediction, data imbalance, synthetic chemical generation, large language models","lastPublishedDoi":"10.21203/rs.3.rs-6432369/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6432369/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe adoption of transformer-based models in toxicity prediction has significantly advanced the field, yet these models continue to struggle with data imbalances inherent in benchmark datasets such as Tox21, Clintox, HIV, and BBBP. This persistent challenge undermines their effectiveness, particularly in minority class predictions where data scarcity prevails. Recent advancements in large language models (LLMs) have demonstrated remarkable capabilities in generating synthetic Simplified Molecular Input Line Entry System (SMILES), providing a novel approach to address these imbalances. In this study, we explore the potential of LLM-generated synthetic SMILES to enhance the training datasets, focusing on the augmentation of minority classes. Our comprehensive experiments on multiple benchmark datasets show that this strategy effectively mitigates class imbalance issue but also substantially improves the minority class prediction accuracy without compromising the overall model performance. For instance, in the Tox21 dataset, we observed an increase in minority class prediction accuracy from 0.707 to 0.965. Similar improvements across other datasets further validate the efficacy of synthetic SMILES augmentation in enhancing both toxicity prediction and broader chemical property assessments.\u003c/p\u003e","manuscriptTitle":"Enhancing Chemical Toxicity Predictions with Synthetic SMILES from a Fine-Tuned LLM-Based Chemical Synthesis Generative Model","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-04-15 10:47:15","doi":"10.21203/rs.3.rs-6432369/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":"64902a8a-b3bc-4dfc-9b69-4a5796feee67","owner":[],"postedDate":"April 15th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":47059306,"name":"Applied Biochemistry"}],"tags":[],"updatedAt":"2025-04-15T10:47:15+00:00","versionOfRecord":[],"versionCreatedAt":"2025-04-15 10:47:15","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6432369","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6432369","identity":"rs-6432369","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}