QSAR-Guided Generative Framework for the Discovery of Synthetically Viable Odorants

QSAR-Guided Generative Framework for the Discovery of Synthetically Viable Odorants | 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 QSAR-Guided Generative Framework for the Discovery of Synthetically Viable Odorants Timothy Pearce, Ahmed Ibrahim This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9326584/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 5 You are reading this latest preprint version Abstract The discovery of novel odorant molecules is key for the fragrance and flavor industries, yet efficiently navigating the vast chemical space to identify structures with desirable olfactory properties remains a significant challenge. Generative artificial intelligence offers a promising approach for de novo molecular design but typically requires large sets of molecules to learn from. To address this problem, we present a framework combining a variational autoencoder (VAE) with a quantitative structure-activity relationship (QSAR) model to generate novel odorants from limited training sets of odor molecules. The self-supervised learning capabilities of the VAE allow it to learn SMILES grammar from ChemBL database, while its training objective is augmented with a loss term derived from an external QSAR model to structure the latent representation according to odor probability. While the VAE demonstrated high internal consistency in learning the QSAR supervision signal, validation against an external, unseen ground truth dataset (Unique Good Scents) confirms the model generates syntactically valid structures (100% validity achieved via rejection sampling) and 94.8% unique structures. The latent space is effectively structured by odor likelihood, evidenced by a Frechet ChemNet Distance (FCD) of ≈ 6.96 between generated molecules and known odorants, compared to ≈ 21.6 for the ChemBL baseline. Structural analysis via Bemis-Murcko scaffolds reveals that 74.4% of candidates possess novel core frameworks distinct from the training data, indicating the model performs extensive chemical space exploration beyond simple derivatization of known odorants. Generated candidates display physicochemical properties consistent with ground-truth odorants (mean MW ∼158 Da, LogP ∼1.67) and comparable predicted ADMET profiles. Furthermore, quantum mechanical calculations (GFN2-xTB) verify thermodynamic stability with energy distributions matching known volatiles, and automated retrosynthesis demonstrates practical viability, yielding valid synthesis routes for 100% of candidates, averaging 2.89 steps from commercially available precursors. This integrated approach provides a novel and systematic methodology for applying generative AI to explore chemical space specifically for the discovery of new candidate odorant molecules. Physical sciences/Chemistry Biological sciences/Computational biology and bioinformatics Biological sciences/Drug discovery Physical sciences/Mathematics and computing odorant molecules olfaction computational chemistry molecule design generative Al Full Text Additional Declarations No competing interests reported. Supplementary Files Supplementaryinformation.pdf Cite Share Download PDF Status: Under Review Version 1 posted Reviewers invited by journal 15 Apr, 2026 Editor invited by journal 14 Apr, 2026 Editor assigned by journal 09 Apr, 2026 Submission checks completed at journal 09 Apr, 2026 First submitted to journal 05 Apr, 2026 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-9326584","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":626354900,"identity":"8be94fb8-2ca6-4f70-9606-9933064e5c15","order_by":0,"name":"Timothy Pearce","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAzUlEQVRIiWNgGAWjYHAD5oMHIAw2/Op4EEy2BJK18BgQp8WegfkBc0GFXT5/e8+HAx8Y7OQZJNISCNjCZsA840yy5YwzZzccnMGQbNggkXaAgBYeBmbeNmYDA4ncDYeB7AQGifQGIrT8qzcwkH/z4PAfhnpitTQcBtrCw3CYgeEwUAshhx1mMzg849hxA4kzaQYHewyOG7bxPEvAq4W9vfnh44KaagP+9sMPH/yoqJbnZ08zwKuFgZkB5B4YMCAYK3Bdo2AUjIJRMArwAAC7pDqPo6iPawAAAABJRU5ErkJggg==","orcid":"","institution":"University of Leicester","correspondingAuthor":true,"prefix":"","firstName":"Timothy","middleName":"","lastName":"Pearce","suffix":""},{"id":626354901,"identity":"62623e7a-053f-4007-a8df-6e388ebbbd74","order_by":1,"name":"Ahmed Ibrahim","email":"","orcid":"","institution":"University of Cambridge","correspondingAuthor":false,"prefix":"","firstName":"Ahmed","middleName":"","lastName":"Ibrahim","suffix":""}],"badges":[],"createdAt":"2026-04-05 13:38:34","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9326584/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9326584/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":107420967,"identity":"06980d17-fbe7-4f49-906d-06364067f098","added_by":"auto","created_at":"2026-04-21 10:30:12","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":6248961,"visible":true,"origin":"","legend":"","description":"","filename":"main.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9326584/v1_covered_e38f77a3-3816-4354-be7f-0d4460a4e69d.pdf"},{"id":107420966,"identity":"81cf9243-3e46-4ba8-8b84-df35c3b86c1f","added_by":"auto","created_at":"2026-04-21 10:29:59","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":6382186,"visible":true,"origin":"","legend":"","description":"","filename":"Supplementaryinformation.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9326584/v1/7ab4c58b01d6f749fe9e882c.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"QSAR-Guided Generative Framework for the Discovery of Synthetically Viable Odorants","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"odorant molecules, olfaction, computational chemistry, molecule design, generative Al","lastPublishedDoi":"10.21203/rs.3.rs-9326584/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9326584/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe discovery of novel odorant molecules is key for the fragrance and flavor industries, yet efficiently navigating the vast chemical space to identify structures with desirable olfactory properties remains a significant challenge. Generative artificial intelligence offers a promising approach for de novo molecular design but typically requires large sets of molecules to learn from. To address this problem, we present a framework combining a variational autoencoder (VAE) with a quantitative structure-activity relationship (QSAR) model to generate novel odorants from limited training sets of odor molecules. The self-supervised learning capabilities of the VAE allow it to learn SMILES grammar from ChemBL database, while its training objective is augmented with a loss term derived from an external QSAR model to structure the latent representation according to odor probability. While the VAE demonstrated high internal consistency in learning the QSAR supervision signal, validation against an external, unseen ground truth dataset (Unique Good Scents) confirms the model generates syntactically valid structures (100% validity achieved via rejection sampling) and 94.8% unique structures. The latent space is effectively structured by odor likelihood, evidenced by a Frechet ChemNet Distance (FCD) of ≈ 6.96 between generated molecules and known odorants, compared to ≈ 21.6 for the ChemBL baseline. Structural analysis via Bemis-Murcko scaffolds reveals that 74.4% of candidates possess novel core frameworks distinct from the training data, indicating the model performs extensive chemical space exploration beyond simple derivatization of known odorants. Generated candidates display physicochemical properties consistent with ground-truth odorants (mean MW ∼158 Da, LogP ∼1.67) and comparable predicted ADMET profiles. Furthermore, quantum mechanical calculations (GFN2-xTB) verify thermodynamic stability with energy distributions matching known volatiles, and automated retrosynthesis demonstrates practical viability, yielding valid synthesis routes for 100% of candidates, averaging 2.89 steps from commercially available precursors. This integrated approach provides a novel and systematic methodology for applying generative AI to explore chemical space specifically for the discovery of new candidate odorant molecules.\u003c/p\u003e","manuscriptTitle":"QSAR-Guided Generative Framework for the Discovery of Synthetically Viable Odorants","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-21 10:29:44","doi":"10.21203/rs.3.rs-9326584/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewersInvited","content":"","date":"2026-04-15T06:09:23+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-04-14T04:34:49+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-04-09T09:00:34+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-04-09T09:00:25+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2026-04-05T13:34:08+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"87dc8004-a18f-42d4-bfe4-d83565fcef70","owner":[],"postedDate":"April 21st, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":66724152,"name":"Physical sciences/Chemistry"},{"id":66724153,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":66724154,"name":"Biological sciences/Drug discovery"},{"id":66724155,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2026-04-21T10:29:44+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-21 10:29:44","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9326584","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9326584","identity":"rs-9326584","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}